Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 144 appraisals
The American journal of pathology
An Integrated Machine Learning and Genomic Framework for Precise Detection of Gastric Cancer
This study presents a novel integrative approach for the analysis of high-dimensional gene expression data, leveraging the complementary strengths of unsupervised clustering and supervised classification. Using K-means clustering, the data set is stratified into three distinct clusters, revealing intrinsic biological patterns and relationships. The resulting cluster assignments are subsequently used as pseudolabels to train machine learning models, including support vector machines, random forest, and a stacking ensemble classifier. To validate and enhance the robustness of clustering, complementary methods, such as hierarchical clustering and density-based spatial clustering of applications with noise (DBSCAN), are used, with results visualized through principal component analysis-driven dimensionality reduction. The high predictive accuracy achieved by the classifiers underlines the separability and reliability of the identified clusters. Furthermore, feature importance analysis highlighted key genetic determinants within each cluster, offering actionable insights into potential biomarkers and critical genomic features. This framework bridges the gap between exploratory unsupervised learning and predictive supervised modeling, providing a scalable and interpretable method for analyzing complex genomic data sets. Its applicability extends to biomarker discovery, patient stratification, and other precision medicine applications, emphasizing its utility in advancing genomic research and clinical practice.
3 Aug 2026
Read appraisal →The Journal of rheumatology
Examining the Role of Wearables in Inflammatory Arthritis Care: A Narrative Literature Review
Rheumatoid arthritis, psoriatic arthritis, and axial spondyloarthritis are types of inflammatory arthritis (IA) characterized by joint pain and stiffness that, despite therapeutic advances, remain difficult to treat. Changes in physical activity (PA) and sleep patterns may provide insights into IA disease course and activity. Wearable accelerometers have been validated as reliable, objective measures of PA and have provided insight into IA disease activity and progression through both PA and sleep metrics. Further, the granular nature of accelerometry data may provide the opportunity to identify early signals of treatment response or disease flares, leading to more effective and personalized therapeutic regimens in patients with IA. In this review, we summarize the current state of wearable technology in IA and explore the potential of wearables to bridge gaps in care.
3 Aug 2026
Read appraisal →Rheumatic diseases clinics of North America
Machine Learning-Enhanced Autoantibody Discovery and Diagnostics in Systemic Autoimmune Rheumatic Diseases
The growing implementation of machine learning (ML) has extended into autoantibody research for the study of systemic autoimmune rheumatic diseases (SARDs). ML methods offer a promising approach for efficiently handling and identifying important signals within the big data generated by modern autoantibody technologies. The novel biomarkers identified through advanced ML techniques show promise in outperforming current clinical tools, bringing us closer to the goal of precision medicine. In this article, we will provide an overview of ML approaches and how they have been applied in autoantibody research to improve the diagnosis and characterization of SARDs.
2 Aug 2026
Read appraisal →Journal of chemical information and modeling
Protein Language Model-Based Fitness Estimates Facilitate Resistance Mutation Identification
Drug resistance is a major challenge in cancer therapy. Cancer cells with pre-existing or acquired mutations that confer resistance to a given drug treatment outgrow the susceptible cell population and cause cancer recurrence after an initial successful treatment response. Knowledge about resistance mutations before they occur in the clinic could prevent unnecessary patient treatment with ineffective drugs, in clinical trials as well as clinical practice, or potentially speed up the development of follow-up compounds. Here, we focused on on-target amino acid mutations that confer resistance to an inhibitor compound with a known binding mode. We evaluated whether a combination of physics-based free energy perturbation (FEP) affinity estimates and protein language model-based protein fitness estimates could improve the in silico identification of resistance mutations. Validation was done with data from deep mutational scanning (DMS) experiments that tested for resistance to single amino acid mutations. A public data set testing ERK2 resistance against the inhibitor SCH772984 and an internal data set testing resistance of an EGFR_exon20 mutant against a Bayer small molecule inhibitor were used. Our results show that protein fitness estimates can facilitate the identification of resistance mutations by filtering mutations with a low estimated fitness. Even though FEP has flagged such mutations as affinity-decreasing and thus potentially resistant, they were not resistant according to the DMS experiment and therefore correctly filtered out. This indicates that protein language model-based protein fitness estimates could be a computationally efficient method to filter mutations without having to model the negative impact of mutations on native function or protein stability, which is error-prone and computationally expensive.
28 July 2026
Read appraisal →Journal of chemical information and modeling
ProphDR: An Interpretable Deep Learning Model for Predicting Cancer Drug Response via Multi-Omics and Cross-Attention Mechanisms
Predicting cancer drug responses (CDRs) accurately remains a significant challenge due to the complexity of tumor biology and the limitations of existing "black-box" machine learning models. To address this, we propose ProphDR, an interpretable deep learning framework that integrates multiomics data and drug structural information using a hierarchical attention mechanism. ProphDR incorporates a Criss-Cross Gene-level Multiomics Integration (CGMI) module to capture gene-level features and a cross-attention (CA) module to model drug-gene interactions. Evaluated on datasets from GDSC and CCLE, ProphDR achieves state-of-the-art performance in predicting ln(IC50) values (PCC = 0.938, RMSE = 0.978) and classifying drug sensitivity (AUC = 0.981). It also demonstrates strong generalizability in cold-start scenarios involving unseen drugs or cell lines. Crucially, ProphDR generates biologically interpretable attention maps that highlight key pharmacophores and resistance-related genes such as ERBB2 (HER2), consistent with established mechanisms in NSCLC and BRCA. These insights bridge genomic features with phenotypic outcomes, offering valuable guidance for target prioritization and drug repurposing. ProphDR represents a robust and explainable AI tool for advancing precision oncology.
28 July 2026
Read appraisal →Science advances
Interpretable dynamic quantitative vascular morphometry features using SHAP for anti-angiogenic therapy response prediction
Anti-angiogenic therapy benefits vary, with response rates of 40 to 70%, highlighting the need for early biomarkers to identify responders. We developed an automated machine learning framework that uses delta quantitative vascular morphometry features from standard contrast-enhanced CT to evaluate treatment response. This workflow combines automated tumor and vessel segmentation with feature extraction from routine scans for clinical use. Shapley additive explanations (SHAP)-based attributions identify key vascular and clinical features, providing meaningful, imaging-visible evidence aligned with therapy targets beyond traditional radiomics. Using baseline and follow-up CTs from 163 patients with lung cancer, we built three models using fivefold cross-validation, with the delta-merge model achieving high accuracy (area under the receiver operating characteristic curve = 0.842 internally, 0.806 externally). SHAP analysis uncovered an "arterial-dominant, venous-adaptive" pattern, where arterial involvement and venous recovery distinguish responders. This automated workflow and visualization support early, imaging-based response assessment and personalized treatment.
27 July 2026
Read appraisal →New biotechnology
Harnessing AI to decode protein kinases: Structural, functional, and therapeutic design perspectives.
Recent advances in Artificial Intelligence (AI) are reshaping kinase research by uncovering complex regulatory mechanisms and accelerating drug discovery. These advances have enabled the capture of elusive allosteric transitions and transient cryptic pockets by exploring dynamic conformational landscapes, revealing features critical for understanding ligand interactions and enzymatic regulation. AI-driven structure prediction tools, such as AlphaFold (AF)-based models, offer high-resolution insights into kinase conformations and complex assembly, thereby clarifying receptor activation in signaling pathways. Moreover, cutting-edge AI frameworks provide fresh perspectives on substrate prediction, cofactor mapping, and mutation-induced structural changes. Integrative strategies that combine Machine Learning (ML), molecular docking, Molecular Dynamics (MD) simulation, and experimental validation have further streamlined the discovery of novel kinase inhibitors and related studies. Collectively, these AI-enhanced approaches deepen our understanding of kinase-mediated signaling-from developmental processes to oncogenic transformation-and highlight the powerful synergy between computational and experimental research in advancing therapeutic innovations.
25 July 2026
Read appraisal →Molecular genetics and genomics : MGG
The use of artificial intelligence in advancing molecular biology in Africa: a narrative review
Artificial intelligence (AI) is rapidly becoming a core methodological pillar of molecular biology and precision medicine, and Africa is a uniquely consequential setting for this transition because the continent combines the world's greatest human genomic diversity with the most severe underrepresentation of that diversity in the datasets and reference resources on which AI models are built and benchmarked. This narrative review examines, for a genetics and genomics readership, where AI-driven methods are already strengthening African molecular biology, where the supporting evidence remains preliminary, and what is required to translate technical capability into scientifically robust and equitable benefit. The central argument is that AI is especially consequential in African molecular biology, not simply because it automates analysis, but because it can help unlock insight from African genomic diversity, pathogen biology, and clinically relevant multi-omics data that remain underrepresented in global models. Across core molecular domains, AI is accelerating protein structure prediction, high-throughput variant calling and pan-genomic reference construction, genome-wide association analysis, transcriptomic interpretation, drug discovery, and CRISPR guide design. African initiatives such as H3Africa, the African Genome Variation Project, H3ABioNet, and the H3D Centre show that locally generated datasets and African-led computational pipelines can already support meaningful discovery, from improved variant interpretation to structure-guided therapeutic prioritization. At the same time, persistent barriers remain, including underrepresentation of African genomes in training data and reference genomes, uneven computational infrastructure, limited interdisciplinary training, fragmented governance, and the risk that AI-derived benefits will remain inaccessible to the populations whose data enable them. We conclude that the future impact of AI in African molecular biology will depend less on adopting global tools in the abstract and more on building African-led datasets, validation pipelines, governance frameworks, and translational pathways that make molecular discovery both scientifically robust and equitably useful. Looking ahead, the central perspective offered by this review is that Africa's exceptional genomic diversity should be treated as a scientific asset rather than an analytical liability: realising this will require population-representative pan-genome references, sustained computational capacity, and governance structures that ensure African populations are not only the source of the underlying data but also the principal beneficiaries of the discoveries it enables.
23 July 2026
Read appraisal →Cell reports methods
Data modeling the interplay between single-cell shape, single-cell protein expression, and tissue state.
While cell shape fundamentally governs tissue function, the underlying links between single-cell shape and protein expression have been difficult to resolve due to limitations in imaging multiplexing and population averaging. Here, we use multiplexed imaging and machine learning to investigate the coupling of cell shape and protein expression in heterogeneous human tissues. Our analysis establishes a universal, bi-directional link between a cell's shape and its protein expression across cell types, diseases, and disease states, amplified for cell state markers. Machine learning interpretability shows that shape features can potentially generate hypotheses of protein functions. Screening all protein-cell type pairs identified a subpopulation of large, p53-positive tumor cells across two cancers. Shape properties further enhanced graph neural network disease state prediction. Our results open the door to unraveling the intricate connections between protein expression, cell shape, tissue organization, and tissue state in a physiological context.
23 July 2026
Read appraisal →mSystems
MeLSI: Metric Learning for Statistical Inference in microbiome community composition analysis
Microbiome beta diversity analysis relies on distance-based methods, including permutational multivariate analysis of variance (PERMANOVA) combined with fixed ecological distance metrics (Bray-Curtis, Euclidean, Jaccard, and UniFrac), which treat all microbial taxa uniformly, regardless of their biological relevance to community differences. This "one-size-fits-all" approach may miss subtle but biologically meaningful patterns in complex microbiome data. We present Metric Learning for Statistical Inference (MeLSI), a novel machine learning framework that learns data-adaptive distance metrics optimized for detecting community composition differences in multivariate microbiome analyses. MeLSI employs an ensemble of weak learners using bootstrap sampling, feature subsampling, and gradient-based optimization to learn optimal feature weights, combined with rigorous permutation testing for statistical inference. The learned metrics can be used with PERMANOVA for hypothesis testing and with principal coordinates analysis for ordination visualization. Comprehensive validation on synthetic benchmarks and real data sets shows that MeLSI maintains proper type I error control while delivering competitive or superior statistical power for detecting subtle community shifts and, crucially, supplies interpretable feature-weight profiles that clarify which taxa drive group separation. On the DietSwap data set, MeLSI was the only method to achieve significance at α = 0.05, demonstrating that adaptive weighting can detect diet-induced community shifts that fixed metrics miss. Across all data sets, the learned feature weights identified biologically relevant taxa while providing actionable insight that no fixed distance metric can supply. MeLSI therefore offers a statistically rigorous tool that augments beta diversity analysis with transparent, data-driven interpretability.IMPORTANCEUnderstanding which microbes differ between groups of interest could reveal therapeutic targets and diagnostic biomarkers. However, current analysis methods treat all microbes equally (similar to using the same ruler to measure everything, regardless of what matters most). This means subtle but biologically important differences may go undetected, especially when only a few key species drive disease states while hundreds of "bystander" species add noise. Metric Learning for Statistical Inference (MeLSI) solves this by learning which microbes matter most for each specific comparison. In comparing male and female gut microbiomes, MeLSI identified specific bacterial families driving the differences, providing actionable biological insights that standard methods miss. This capability is particularly crucial for detecting early disease biomarkers, where differences are subtle and masked by biological variability. By telling researchers not just whether groups differ, but which specific microbes drive those differences, MeLSI accelerates the path from microbiome data to testable biological hypotheses and clinical applications.
22 July 2026
Read appraisal →JMIR mental health
Optimizing Treatment Strategies in the Bipolar Disorder Spectrum With Classical AI Approaches: Systematic Review of Performance, Bias, and Clinical Applicability
BACKGROUND: Bipolar disorder (BD) is a complex and heterogeneous psychiatric condition, characterized by fluctuating clinical courses that affect approximately 1%-2% of the global population in their lifetime. Despite pharmacological advances, treatment response varies significantly among patients, making the identification of individualized treatment strategies a major challenge. Artificial Intelligence (AI), through its classical approaches, has emerged as a powerful tool in precision psychiatry to identify subtle patterns in complex data and inform personalized clinical decisions. OBJECTIVE: The present systematic review aimed to examine the current evidence on classical AI-supported treatment optimization in the BD spectrum. METHODS: The review was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 guidelines. Four databases (PubMed, Web of Science, Scopus, and Embase) were searched for original studies published after 2015 on the application of classical AI in the treatment of BD in adult patients. Publication bias was evaluated by visual inspection of a funnel plot. The methodological quality, risk of bias, and clinical applicability of the predictive models were assessed using the Prediction Model Risk Of Bias Assessment Tool for prediction models using regression or AI methods (PROBAST+AI; PROBAST+AI Working Group) tool. RESULTS: A total of 35 studies were included and classified into 5 outcome-based categories, including acute symptomatic response, long-term maintenance response, relapse and readmission risk, safety and dose optimization, and brain aging and phenotyping. Acute symptomatic response models performed modestly (pooled area under the curve [AUC] 0.68), while imaging improved accuracy (74%-77%). Long-term maintenance response models showed moderate-to-high performance (pooled AUC 0.80), with biomarker- and cellular-based models reaching 96%-99% accuracy. Relapse and readmission prediction achieved a pooled AUC of 0.71, with digital phenotyping and rule-based methods performing best (AUC 0.85-0.88). Safety and dose optimization models achieved 85%-97% accuracy. Brain aging and phenotyping studies highlighted accelerated brain aging in BD, partially mitigated by lithium, and revealed novel data-driven subgroups. However, 3 studies were considered at high risk of bias due to small sample sizes associated with disproportionately high-performance estimates. An additional study was identified as potentially biased because it lay markedly distant from the funnel plot's confidence line. Finally, the PROBAST+AI assessment revealed a high risk of bias in most studies, primarily due to data analysis limitations, small sample sizes, and lack of external validation. CONCLUSIONS: The adoption of classical AI tools in BD serves as a driver for therapeutic optimization, although current AI tools in BD should still be considered exploratory rather than ready for clinical use. Effective implementation in real-world clinical scenarios requires more robust, transparent, and externally validated models to ensure reliability and generalizability.
22 July 2026
Read appraisal →Molecular biology reports
Metabolic signatures of triple-negative breast cancer
Triple-negative breast cancer (TNBC), being one of the most aggressive subtypes of breast malignancies, is characterized by poor prognosis and limited treatment options. As a leading cause of cancer-related mortality among women, TNBC poses unique clinical challenges due to the absence of effective targeted therapies. Conventional treatment strategies, including chemotherapy, often suffer from significant drawbacks such as drug resistance and intolerable side effects, underscoring an urgent need for innovative approaches to improve therapeutic outcomes. A defining hallmark of TNBC is its markedly altered cellular metabolism, which not only supports tumor growth and survival but also contributes to therapy resistance. Elucidating these metabolic alterations could provide critical insights into potential vulnerabilities that may be exploited for therapeutic intervention. This review provides a comprehensive overview of the major metabolic pathways that are dysregulated in TNBC and their relevance to disease progression and therapeutic intervention. Finally, we explore recent advances in metabolomics-driven precision medicine, highlighting the integration of artificial intelligence and machine learning approaches, covering aspects such as data processing, feature selection, and model construction that can accelerate the advancement of personalized treatment strategies for TNBC.
18 July 2026
Read appraisal →Cancer cell
OpenIO: An open framework for AI-native immunotherapy
We propose Open Immune Oncology (OpenIO), a framework integrating generative AI and omics to advance precision oncology. By leveraging biological scaling laws and foundation models, we aim to transition immunotherapy from empirical screening to rational, AI-native engineering of therapeutic interventions.
15 July 2026
Read appraisal →Nucleic acids research
ChIP-Atlas 2025 update: 10-year anniversary of a data-mining platform for exploring epigenomic landscape
ChIP-Atlas (https://chip-atlas.org/) is a data-mining platform that systematically processes and integrates public epigenomic profiling data, including ChIP-seq, ATAC-seq, DNase-seq, and Bisulfite-seq, together with curated sample metadata, currently encompassing >460 000 experiments across multiple model organisms. In this 2025 update, an experiment-level quality control framework was embedded in every experiment page, enabling intuitive assessment of data reliability and representativeness. In addition, a parametric analysis of gene set enrichment-based module was implemented, allowing enrichment analysis directly from continuous RNA-seq count tables without relying on threshold-defined, discrete gene lists, thereby helping elucidate underlying gene regulatory mechanisms. Combined with sustained data expansion, these updates advance ChIP-Atlas into a more quantitative and flexible platform for exploring the epigenomic landscape in multicellular organisms, marking its 10th anniversary.
13 July 2026
Read appraisal →Nucleic acids research
DeepKinomeWeb: a quantitative, panel-level platform for kinase inhibitor screening and selectivity profiling
Protein kinases are central targets in drug discovery, yet early-stage development of potent and selective inhibitors remains challenging due to high experimental costs and limited interpretability of large-scale screening data. Here, we present DeepKinomeWeb, an integrated web-based platform that transforms competition-based high-throughput screening data into actionable insights for kinase inhibitor prioritization. Built upon our previously validated deep learning regression model, DeepKinome, the platform enables quantitative prediction of kinase-inhibitor binding affinities and provides panel-level visualization of selectivity landscapes, selectivity metric calculations, and integrated structural and physicochemical analyses. Through its user-friendly interface, DeepKinomeWeb supports rational, data-driven decision-making for biologists and medicinal chemists, lowering the barrier to systematic selectivity assessment in kinase inhibitor discovery. DeepKinomeWeb is freely available to all users without any login requirement at https://str.kribb.re.kr/deepkinome.
13 July 2026
Read appraisal →Journal of gastrointestinal cancer
Radiomics Models as Tools for Predicting Genetic Mutations in Colorectal Cancer: A Systematic Review and Meta-Analysis
BACKGROUND: The evaluation of genetic mutations is crucial for personalized therapy in colorectal cancer (CRC), but the invasive tissue biopsy is subject to sampling bias and other complications. Radiomics has emerged as a non-invasive tool to predict these mutations from standard medical images. In this systematic review and meta-analysis, we aimed to evaluate the diagnostic accuracy and methodological quality of radiomics models for predicting key genetic mutations in CRC. METHODS: A comprehensive search of PubMed, Scopus, Web of Science, and Embase was conducted in accordance with PRISMA guidelines. Studies evaluating radiomics models for predicting genetic mutations in CRC patients using pre-operative CT, MRI, or PET/CT were included. A meta-analysis of diagnostic accuracy was performed to calculate the pooled sensitivity, specificity. Methodological quality was assessed using the Radiomics Quality Score (RQS) and QUADAS-2 tools. RESULTS: Sixteen studies were included in the quantitative analysis. The pooled sensitivity and specificity were 0.75 (95% CI, 0.67-0.81) and 0.78 (95% CI, 0.70-0.85), respectively, with an overall AUC of 0.79. Subgroup analyses revealed that radio-clinical models integrating both clinical and radiomics features achieved superior sensitivity compared to models with only radiological input. However, the overall methodological quality of the included studies was low, with a mean RQS of 45%. CONCLUSION: Conventional radiomics models demonstrate promising results for the non-invasive prediction of genetic mutations in CRC, with sensitivity enhanced by the integration of clinical data. Despite this potential, significant methodological shortcomings and heterogeneity across studies highlight the need for standardized protocols and large-scale, prospective validation before these models can be translated into routine clinical practice.
10 July 2026
Read appraisal →Gut
Digital twins in IBD-bridging data, biology and trial innovation
Clinical trials in IBD face difficulties of escalating complexity, high costs and challenges in recruitment. Digital twins are virtual, data-driven replicas of individual patients that model disease trajectories and treatment responses, which offer a potential innovative change in the conduct of clinical trials in IBD. Built from multimodal datasets integrating clinical, molecular, imaging and real-world data, digital twins can generate synthetic control arms, enable adaptive randomisation and predict disease relapse or treatment response. Early studies across oncology, cardiology and endocrinology demonstrate their feasibility and potential to improve statistical power while reducing patient burden. However, the integration of digital twins into clinical trials in IBD will require rigorous validation frameworks, transparent data governance and attention to algorithmic bias and consent. In this review, we explore how digital twins may transform IBD research-from in silico simulation to adaptive, patient-centred trial design-and outline the regulatory, ethical and logistical challenges to be considered in order to successfully integrate them into future trials.
10 July 2026
Read appraisal →Food & function
Application of artificial intelligence in synbiotic and functional food development for precision nutrition
Synbiotic and functional food formulations modulate gut microbiota, SCFA production, immune signalling and metabolic pathways, yet current development pipelines remain largely empirical and constrained by nonlinear trade-offs among probiotic viability, prebiotic functionality and sensory acceptance. Artificial Intelligence (AI) and machine learning (ML) approaches offer data-driven strategies to support formulation, multi-objective optimization and functional assessment. This review systematically identified and critically synthesized literature published between 2020 and 2025 across five thematic domains: (i) formulation and ingredient selection; (ii) viability and shelf-life modelling; (iii) functional and antioxidant bioactivity assessment; (iv) sensory and consumer prediction; and (v) personalization and precision nutrition. Studies were identified through database searches and screened for relevance to synbiotics, functional foods, microbiome modulation and nutrition outcomes, following PRISMA 2020 guidelines. Current evidence indicates that AI can assist ingredient pairing, viability forecasting, sensory modelling and functional property prediction, often complementing conventional statistical tools such as Response Surface Methodology in multivariate design spaces. However, most implementations remain computational or pilot-scale, with minimal integration of microbiome-informed personalization, clinical endpoints or adherence outcomes. Major translational gaps include data heterogeneity, model interpretability, regulatory substantiation and scarcity of longitudinal evidence. AI should therefore be considered a complementary decision-support tool that can accelerate hypothesis generation and formulation refinement rather than substitute mechanistic validation or human trials. Bridging computational modelling with microbiome science and nutritional evidence may enable precision synbiotic strategies and next-generation functional food innovation.
6 July 2026
Read appraisal →Briefings in bioinformatics
Bridging local-global transmembrane protein contexts with contrastive pretraining for alignment-free pathogenicity prediction.
Predicting the pathogenic consequences of protein mutations is a cornerstone of precision medicine, yet it remains a formidable challenge for transmembrane proteins (TMPs), a clinically vital class of drug targets. Existing computational methods are often hampered by their reliance on evolutionary data and fail to model TMP-specific biophysical constraints. Here, we introduce Memo-Patho, a deep learning framework for robust, alignment-free pathogenicity prediction of TMP variants. The core innovation is a within-protein, label-informed supervised contrastive pretraining strategy that learns sequence-encoded biophysical signatures distinguishing pathogenic and benign variants by directly comparing them within the same protein context. By fusing sequence-level representations from protein language models with local structural proxies derived from sequence, Memo-Patho achieves accurate predictions without multiple sequence alignments or experimental structures. Across diverse TMP benchmarks and under protein-level group splits, Memo-Patho consistently outperforms leading predictors, achieving up to 0.93 accuracy, and it transfers to an independent KCNQ1 ion-channel cohort without re-training. Its resource-efficient, alignment-free design enables routine large-scale screening when evolutionary or structural data are sparse. Conceptually, Memo-Patho addresses a key gap by directly learning discriminative, sequence-anchored signatures pertinent to TMP-specific constraints, offering a principled and generalizable foundation for research-use clinical variant triage and proteome-wide mutation-effect modeling.
6 July 2026
Read appraisal →Journal of hematology & oncology
Emerging artificial intelligence advances in oncology: latest updates from the 2026 AACR annual meeting.
Advances presented at the 2026 American Association for Cancer Research (AACR) Annual Meeting highlight a shift from standalone artificial intelligence (AI) models to integrated, agentic systems across oncology. Platforms such as Synapse enable large-scale data coordination, supporting interoperable and reproducible research. Building on this foundation, conversational and multi-agent AI tools (e.g., DrBioRight, GP CoPilot, Isabl AI Agent) allow natural language interaction with multimodal cancer data, lowering technical barriers. Agentic frameworks for real-world data (RWD) transformation, including clinical document abstraction, cohort extraction, and social determinants of health (SDOH) analysis, demonstrate high accuracy and scalability, while self-critical systems improve reliability. Clinically, AI shows growing impact through validated imaging biomarkers, enhanced trial matching, and scalable cohort identification. In parallel, multi-agent systems are accelerating therapeutic discovery, including CAR-T development and immunotherapy target identification. Collectively, these advances position AI as an active, collaborative partner in cancer research and precision oncology.
5 July 2026
Read appraisal →Nature communications
A deep learning framework for efficient pathology image analysis
Artificial intelligence has transformed digital pathology by enabling biomarker prediction from high-resolution whole-slide images. However, current methods are computationally inefficient, processing thousands of redundant tiles per slide and requiring complex aggregation models. We introduce EAGLE (Efficient Approach for Guided Local Examination), a deep learning framework that emulates pathologists by selectively analyzing informative regions. EAGLE combines task-agnostic tile selection with detailed feature extraction and is benchmarked against leading slide- and tile-level foundation models across 43 tasks from nine cancer types spanning morphology, biomarker prediction, treatment response and prognosis. EAGLE outperforms patch aggregation methods by up to 23% and achieves the highest overall classification performance. It processes one slide in 2.27 s, reducing computational time by more than 99% compared with existing models. This efficiency supports rapid and auditable workflows by enabling review of the exact tiles used for each prediction and reducing dependence on high-performance computing. By reliably identifying informative regions and minimizing artifacts, EAGLE provides robust and auditable outputs, supported by systematic negative controls and attention concentration analyses. Its unified embedding enables rapid slide search, integration into multi-omics pipelines and emerging clinical foundation models.
2 July 2026
Read appraisal →The American journal of pathology
Deep Learning-Enhanced Biomarker Interpretation on Cytology Cell Blocks: Foundations and Emerging Opportunities in Spatial Pathobiology
Cytology cell block specimens are essential for diagnosing patients with advanced-stage malignancy and often represents the only available strategy for therapeutic biomarker evaluation. The use of cell blocks preserves tumor cells, captures high-grade or metastatic populations, and retains meaningful microenvironmental context, making them well suited for IHC analysis. With the rapid expansion of computational pathology, deep learning-assisted biomarker interpretation in cell blocks is emerging as a promising frontier for improving reproducibility, reducing interobserver variability, and enabling quantitative assessment of spatial tumor-immune interactions. Because many treatment-defining biomarkers are routinely assessed on cytology cell blocks, this mini-review highlights artificial intelligence-based applications for PD-L1, HER2, ER/PR, Ki-67, ALK/ROS1, BRAF V600E, and p16 markers that directly inform decisions about immunotherapy, targeted therapy, and hormone therapy. Also reviewed are emerging predictive models that convey biomarker status directly from morphology, extending the utility of artificial intelligence beyond conventional IHC interpretation. Finally, spatial pathobiology-related opportunities afforded by cell block preparations are discussed, and future directions for integrating artificial intelligence-enabled analysis into cytology workflows are outlined. Together, these advances position cytology cell blocks as an important platform for computational biomarker interpretation and morphology-driven precision oncology.
2 July 2026
Read appraisal →Open biology
Deep learning in tumour genomics: from multi-omics integration to precision oncology
Cancer remains a leading cause of death globally, with nearly 10 million deaths in 2020. Advances in genomic technologies have revolutionized cancer research, shifting focus towards precision medicine based on comprehensive tumour genomic profiling. Concurrently, deep learning (DL) has emerged as a powerful paradigm for complex biological data. This review critically assesses recent advances in DL applications for tumour genomics, emphasizing four key domains: DNA sequencing analysis for mutation detection, gene expression profiling for cancer subtype classification, methylation function prediction for epigenetic characterization and integrative multi-omics approaches for comprehensive tumour profiling. We systematically analyse how different DL architectures-including convolutional neural networks, recurrent neural networks, graph neural networks, autoencoders and transformers-address specific challenges in cancer genomics. Our review highlights how these approaches significantly enhance detection sensitivity for genomic alterations, improve cancer subtype stratification, identify novel biomarkers and optimize therapeutic target selection. We examine technical challenges in DL implementation, including model interpretability, data scarcity, computational requirements and integration issues, alongside emerging solutions such as explainable AI, federated learning, and multi-modal frameworks. By synthesizing methodological innovations and identifying research directions, this review provides bioinformaticians and cancer researchers with a roadmap for leveraging DL to advance precision oncology.
2 July 2026
Read appraisal →Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association
Clinical applications of artificial intelligence in autosomal dominant polycystic kidney disease
Autosomal dominant polycystic kidney disease (ADPKD) is the most common genetic kidney disorder leading to kidney failure. Recent advancements in artificial intelligence (AI) are transforming the diagnosis, risk stratification, management and prognostication in ADPKD by enabling more accurate assessments and individualized care. AI-powered imaging tools enhance the measurement of total kidney volume (TKV), improving the precision and efficiency of monitoring disease progression and more reliable assessment of therapeutic response. Machine learning algorithms can integrate genetic, imaging and clinical data to predict kidney function decline, facilitating personalized treatment strategies. In addition, AI is being used to identify genetic variants and to refine genotype-phenotype relationships, offering deeper insights into disease variability. AI-enabled monitoring technologies can support longitudinal tracking of TKV measurements obtained through magnetic resonance imaging or computed tomography, thereby improving clinical decision-making and management. Furthermore, AI can optimize clinical trial design by improving patient selection, prediction of treatment responses and safety monitoring. Despite these promising developments, integrating AI into the clinical practice remains controversial and may pose several challenges. This review highlights the emerging clinical applications of AI in ADPKD, emphasizing its potential to advance precision medicine and improve patient outcomes.
1 July 2026
Read appraisal →Medicine
Molecular profiling of coronary stent restenosis: A systematic review and functional analysis of implicated genes
BACKGROUND: Coronary stent restenosis occurs in approximately 5% of patients treated with drug-eluting stents (DES) and is associated with adverse clinical outcomes. Elucidating the genetic mechanisms underlying restenosis may support precision medicine approaches to improve patient management.This systematic review aimed to synthesize evidence on genes and biological pathways associated with DES-related restenosis and to perform functional analysis of the implicated genes using bioinformatics tools. METHODS: The review was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews guidelines. A systematic search of PubMed, Scopus, and Web of Science was performed for human studies investigating genetic or genomic factors in coronary restenosis, with the last search conducted in March 2024. Eligibility criteria included original studies reporting genetic associations with DES restenosis. Screening and data extraction were performed by a single reviewer. Identified genes underwent gene set enrichment analysis using Enrichr (Ma'ayan Laboratory, Computational Systems Biology) and ClueGo extension on Cytoscape (National Resource for Network Biology). RESULTS: Seventeen studies met the inclusion criteria. The studies highlighted multiple genes involved in extracellular matrix remodeling, inflammatory signaling, and the renin-angiotensin system. Gene enrichment analysis confirmed the overrepresentation of these biological pathways in DES-associated restenosis. CONCLUSIONS: This systematic review synthesizes the genetic and molecular contributors to DES-associated restenosis and identifies potential targets for future research and personalized therapies. No external funding was received, and the protocol was not registered.
28 June 2026
Read appraisal →Journal of chemical information and modeling
GraFSyn: An Interpretable Deep Learning Framework for Anticancer Drug Synergy via Graphlet Fingerprints
Predicting drug synergy is important for accelerating the discovery of effective anticancer combination therapies. Synergy intrinsically depends on the precise interactions of key chemical substructures within specific cellular environments. However, current molecular graph-based computational methods typically rely on implicit atom-level feature aggregation, which may obscure the topological representation of critical chemical substructures and limit structural traceability. Therefore, we present Graphlet Fingerprint-based Synergy prediction (GraFSyn), a deep learning framework for anticancer drug synergy prediction that uses graphlet fingerprints to encode drugs as explicit connected substructure units, preserving predefined chemical substructures and their topological identity. We further introduce a Dynamic Multi-Scale Convolution (DMSC) module to learn informative representations from high-dimensional and sparse graphlet features. The framework also includes an interaction module to capture context-dependent interactions between drug substructures and cell line gene expression. On the Merck and AstraZeneca benchmark data sets, GraFSyn achieved ROC-AUC/PR-AUC values of 0.972/0.912 and 0.823/0.906, respectively, outperforming representative baseline methods. In addition, attributed signals can be mapped back to specific pharmacophoric regions, supporting substructure-level analysis of synergistic interactions. In general, GraFSyn provides an accurate and structurally traceable approach for anticancer drug combination screening.
23 June 2026
Read appraisal →European radiology experimental
Digital twin technologies in prostate cancer as a frontier for precision medicine
Prostate cancer (PCa) is the most frequently diagnosed malignancy among men and presents major clinical and socioeconomic challenges worldwide. Despite advances in early detection, imaging, and therapy, managing PCa remains complex due to disease heterogeneity, risks of overdiagnosis, and overtreatment. Digital twin (DT) technologies might represent an emerging conceptual framework aimed at supporting dynamic, patient-specific virtual modeling for personalized clinical decision-making. By integrating multimodal clinical, imaging, molecular, and physiological data, DTs can simulate disease progression, predict treatment responses, and support proactive, adaptive care. This perspective explores the conceptual framework for DT ecosystems in PCa, highlighting potential clinical impacts, infrastructural requirements, and barriers to implementation. Harnessing DTs could impact PCa management into a truly predictive, personalized, and participatory approach, improving outcomes and optimizing healthcare resource utilization globally. RELEVANCE STATEMENT: DT technologies may enable personalized, predictive PCa management by integrating multimodal patient data to guide diagnosis, treatment selection, and monitoring, with the potential to improve outcomes, reduce overtreatment, and optimize healthcare resource utilization KEY POINTS: DTs create virtual patient models to personalize PCa care. They integrate imaging, clinical, and molecular data into one system. This approach may reduce overdiagnosis and unnecessary treatments.
20 June 2026
Read appraisal →Cell systems
Fusing imaging and metabolic modeling via multimodal deep learning in ovarian cancer
Integrating genotype (e.g., transcriptomics), phenotype (e.g., imaging), and tumor microenvironment (e.g., metabolomics) is crucial to elucidating the molecular basis of ovarian cancer. However, there is a lack of robust multimodal integration methods when only a limited number of common samples is available. Here, we generate patient-specific metabolic models starting from transcriptomics data and integrate them with imaging data. We show that this multimodal integration-never attempted before-improves survival estimation and enables a mechanistic interpretation of the predictions. We assess the robustness of our approach with different combinations of transcriptomics, fluxomics, and 3D computerized tomography (CT) imaging data, correctly stratifying patients based on risk. Fusing metabolic modeling with imaging and transcriptomics significantly improves model accuracy compared with widely used transcriptomics-imaging approaches and elucidates critical metabolic reactions. Our approach is general and can be applied to other cancer types where coupled imaging-transcriptomics data are available. A record of this paper's transparent peer review process is included in the supplemental information.
19 June 2026
Read appraisal →Analytica chimica acta
Rapid detection of drug-resistant leukemia cell using an optofluidic chip and machine learning
BACKGROUND: Rapid detection of drug-resistant leukemia played a crucial role in formulating appropriate treatment plans for patients and improving their prognosis. In this research, an integrated optofluidic platform was developed to detect and analyze leukemia and drug-resistant leukemia cell. The detection technique was designed by embedding optical fibers coupled with photosensors and a laser source into optofluidic chip. The scattered light signals were detected when the cells pass through the detecting area. RESULTS: The platform was first validated by classifying 1 μm polystyrene microparticles and 1 μm polystyrene microparticles coated with spherical 10 nm Fe3O4 nanoparticles. After validation, the method was applied to classify leukemia and drug-resistant leukemia cells by injecting the testing sample and obtaining. The SVM classifier demonstrated the highest classification accuracy of 91.1% compared with LR, RF, and KNN classifiers for analyzing leukemia cells and drug-resistant leukemia cells. The proposed method can perform detection within 10 min with a total experimental timeframe of 20 min. SIGNIFICANCE: The presented results demonstrate the feasibility of applying microfluidics and machine learning approaches to detect and classify biological entities with slight variations based on scattered light signals. This platform holds significant potential for clinical diagnostics, offering a rapid, cost-effective, and efficient method for detecting drug-resistant leukemia cells, potentially aiding in personalized treatment strategies.
16 June 2026
Read appraisal →Mammalian genome : official journal of the International Mammalian Genome Society
A novel biological function-based method for mining core genes in rare disease with limited cases
Conventional high - throughput sequencing data analysis methods, relying on large cohorts, are unsuitable for rare diseases with few cases and poor at explaining gene biological functions. This study proposes a biological-function-based method for mining core genes under limited-sample conditions. Using colorectal cancer (CRC) and its rare subtype signet-ring cell carcinoma (SRCC) as examples, differential expression analysis was performed separately for each SRCC sample against CRC samples. Shared genes obtained through progressive intersections were defined as the initial core gene set (List 1). Non-core genes were subjected to functional enrichment analysis, and pathway-associated genes were integrated to construct the non-core gene set. Two independent SRCC samples were subsequently used for secondary mining to obtain the final biologically significant core gene set (List 2). In addition, RankProd (RP), Robust Rank Aggregation (RRA), and an external mucinous adenocarcinoma dataset (GSE281917) were used for validation. First-round mining identified 246 core genes in SRCC, while secondary mining generated 66 and 65 biologically significant core genes from two validation samples with a high degree of overlap. RP identified 1,850 candidate genes and RRA identified 601 candidate genes, among which 64 genes overlapped with the 65 genes identified by this method. In the external mucinous adenocarcinoma dataset, first-round mining identified 144 core genes, while secondary mining generated 122 and 119 core genes with high overlap between validation samples. This method enables the identification of biologically significant core genes in rare diseases under limited-sample conditions, improves the biological interpretability of gene-mining results, demonstrates stable performance in both SRCC and external mucinous adenocarcinoma datasets, and provides a reliable experimental basis for the advancement of precision medicine in rare disease research.
15 June 2026
Read appraisal →Science advances
PathTIGR: A pathway topology-informed graph representation learning framework for immunotherapy response prediction
Immunotherapy has revolutionized cancer treatment, yet substantial inter-patient response heterogeneity limits therapeutic benefit to specific patient subsets. Here, we present PathTIGR, a pathway topology-informed graph representation learning framework that systematically integrates biological pathway network topology knowledge with genome variation information for immunotherapy response prediction. PathTIGR uses a three-component design: (i) pathway graph encoder with multihead attention embeding pathway topology knowledge and cancer genomic variants to pathway representation, (ii) transformer module capturing pathway regulatory dependencies, and (iii) multilayer perceptron synthesizing pathway-level representations to predict immunotherapy response. This architecture enables PathTIGR to capture complex molecular interactions underlying immunotherapy response. Comprehensive validation across multiple independent immunotherapy cohorts demonstrates that PathTIGR achieves superior predictive performance compared to established biomarkers and state-of-the-art deep learning approaches while maintaining biological interpretability through identification of key signatures underlying response heterogeneity. PathTIGR represents an interpretable graph-based learning framework that enhances immunotherapy response prediction and elucidates molecular determinants of therapeutic efficacy, thereby facilitating the advancement of precision cancer immunotherapy.
14 June 2026
Read appraisal →The pharmacogenomics journal
Development and validation of an open data model for pharmacogenetics to enable semantic interoperability in clinical practice
Pharmacogenetics uses genetic testing to improve the safety and effectiveness of prescribed medicines, yet implementation at scale remains limited due to the absence of interoperable health IT solutions that integrate results into prescribing workflows. This study aimed to develop and validate open data standards for pharmacogenetic results to enable interoperability across healthcare systems. A baseline data model was constructed using the open standard openEHR by synthesising literature, genomic sequencing outputs, and international data specifications, and refined through iterative workshops with the Global Alliance for Genomics and Health. The model underwent two rounds of structured peer review involving 24 experts from 10 countries. Mapping to HL7 FHIR was evaluated using both manual and automated approaches, including the FHIR-Connect tool. The resulting standardised pharmacogenetic data model separates test results from therapeutic implications and incorporates recognised terminologies such as SNOMED CT and HGNC. It achieved international consensus and is published on the openEHR Clinical Knowledge Manager platform. Mapping to HL7 FHIR demonstrated bidirectional information flow within healthcare systems, with automated mapping enabling scalable and reusable transformations. This work provides a framework for storing and exchanging pharmacogenetic test results, supporting semantic harmonisation, interoperability, and integration with clinical decision support systems. Open data standards for pharmacogenetic test results therefore offer a foundation for scalable implementation of pharmacogenetics in routine clinical practice.
14 June 2026
Read appraisal →Journal of ovarian research
Deep learning-based prediction of gene expression from histopathology identifies NR5A1 as a candidate biomarker and druggable target in high-grade serous ovarian carcinoma
BACKGROUND: High-grade serous ovarian cancer (HGSOC) is the most lethal ovarian cancer subtype, responsible for ~ 70% of ovarian cancer-related deaths and marked by late-stage diagnosis and frequent platinum resistance. Although transcriptomic profiling enables molecular stratification and prediction of therapeutic response; routine clinical use of this approach is limited by cost and logistical constraints. Computational pathology analysis offers a scalable alternative by inferring transcriptional states directly from routine hematoxylin and eosin (H&E) whole-slide images (WSIs). METHODS: Paired H&E WSIs and RNA-sequencing data from the TCGA-OV cohort, including 1,371 diagnostic H&E WSIs retrieved for preprocessing and quality control, were used to develop a self-supervised virtual-transcriptomics framework based on Momentum Contrast v2 (MoCo v2) and multi-output Random Forest regression. Model performance was assessed using patient-level five-fold cross-validation. Candidate genes were evaluated by reverse transcription quantitative polymerase chain reaction (RT-qPCR) in an independent cohort of 10 HGSOC tumors, including 4 platinum responders and 6 non-responders. RESULTS: The model predicted expression of approximately 6,400 protein-coding genes, achieving a genome-wide mean Pearson correlation of r = 0.36, with more than 300 genes showing stronger image-expression coupling (r > 0.44). RT-qPCR analysis of 18 candidate genes revealed substantial inter-patient heterogeneity. NR5A1 exhibited the highest expression variability (coefficient of variation [CV] = 1.486) and significantly higher expression in platinum-responsive tumors than in non-responders (mean 2⁻ΔCt = 0.263 vs. 0.013; p < 0.05). Exploratory in silico docking and molecular dynamics (MD) analyses suggested structurally stable binding interactions between Steroidogenic Factor-1 (SF-1/NR5A1) and the natural plant compound cubebin. CONCLUSION: This study demonstrates that histological architecture contains measurable transcriptomic information that can support scalable biomarker prioritization from routine diagnostic histology in HGSOC. NR5A1 represents a hypothesis-generating candidate biomarker and structurally tractable target for future experimental studies. Future validation in larger, multi-center cohorts will be essential to confirm model robustness, biological relevance, and potential clinical utility.
14 June 2026
Read appraisal →Journal of clinical oncology : official journal of the American Society of Clinical Oncology
HER2CLIMB-05: A Phase III Study of Tucatinib Versus Placebo in Combination With Trastuzumab and Pertuzumab as First-Line Maintenance Therapy for HER2+ Metastatic Breast Cancer
PURPOSE: The HER2CLIMB-05 study (ClinicalTrials.gov identifier: NCT05132582) is investigating the efficacy and safety of adding tucatinib to trastuzumab and pertuzumab as first-line (1L) maintenance therapy in patients with human epidermal growth factor receptor 2-positive (HER2+) metastatic breast cancer (MBC). METHODS: Patients with centrally confirmed HER2+ MBC without evidence of progression post induction therapy and no or asymptomatic brain metastases (BM) were enrolled. Patients were randomly assigned 1:1 to tucatinib (300 mg) or placebo twice a day combined with trastuzumab/pertuzumab. The primary end point is investigator-assessed progression-free survival (PFS); secondary end points include overall survival (OS), PFS per blinded independent central review, CNS-PFS, and safety. RESULTS: Between March 2022 and July 2024, 654 patients were randomly assigned to tucatinib (n = 326) and placebo (n = 328) arms. All patients were female (median age, 54 years), 69.3% had de novo MBC, 52.6% were hormone receptor-positive, and 12.4% had presence/history of baseline BM. In this primary analysis, PFS was statistically significantly improved with addition of tucatinib versus placebo (hazard ratio, 0.641 [95% CI, 0.514 to 0.799]; P < .0001; median PFS: 24.9 v 16.3 months); a PFS benefit was seen regardless of the presence/absence of BM or hormone receptor status. OS data remain immature. The most common treatment-emergent adverse events (TEAEs) in the tucatinib arm were diarrhea (72.7%), nausea (33.1%), and elevated liver enzymes (ALT: 28.2%; AST: 25.8%), of which 6.1%, 0.9%, 13.5%, and 7.1%, respectively, were grade ≥3. In the tucatinib arm, 13.5% discontinued tucatinib because of TEAEs. CONCLUSION: Tucatinib addition to trastuzumab and pertuzumab demonstrated improvement in PFS with no new safety signals identified and may be an option for 1L maintenance therapy in patients with HER2+ MBC.
12 June 2026
Read appraisal →Biochemical and biophysical research communications
Efferocytosis-related biomarkers and immune infiltration in pancreatic ductal adenocarcinoma based on single-cell sequencing and machine learning: a comprehensive bioinformatics analysis and experimental validation
BACKGROUND: Pancreatic ductal adenocarcinoma (PDAC) is a highly invasive and lethal malignancy, with its complex tumor microenvironment (TME) severely limiting therapeutic efficacy. Efferocytosis, a key process by which macrophages clear apoptotic cells, has been demonstrated to influence tumor initiation and progression by modulating immune responses, promoting M2 polarization, and facilitating immune evasion. Yet, the function and predictive significance of genes linked to efferocytosis in PDAC are still not fully understood. METHODS: This study integrated TCGA-PDAC, GTEx, and GEO datasets with single-cell transcriptomics to screen and analyze expression patterns and functions of efferocytosis-related genes (ERGs) in PDAC. Differential analysis, single-cell clustering, cell communication, and pseudo-time analysis revealed heterogeneity in macrophage efferocytosis. Subsequently, a six-gene prognostic model (CD36, ITGAV, PANX1, PPARG, S100A4, THBS1) was constructed and validated using Cox and LASSO regression. Concurrently, GSEA pathway analysis, immune infiltration assessment, and immunotherapy response prediction were conducted. Key gene functions were validated through molecular docking, RT-qPCR, western blotting, and functional experiments. RESULTS: Single-cell analysis revealed that macrophages exhibit the highest efferocytic activity within the PDAC microenvironment, demonstrating significant subpopulation heterogeneity. Differential analysis identified 23 key intersecting genes, ultimately yielding a risk model comprising six core genes. The model exhibited strong predictive accuracy in both the training and validation groups (notable AUC). Additional examination showed that patients at high risk showed a heightened presence of pathways linked to the reprogramming of energy metabolism and inflammatory reactions, along with heightened genomic instability and immunosuppressive TME traits, suggesting a grim prognosis. Experimental validation confirmed that knockdown of THBS1 significantly inhibited the proliferation, migration, and invasion of PDAC cells. CONCLUSION: The research clarifies the diverse nature of macrophage efferocytosis in PDAC and its crucial function in the restructuring of TME. It establishes and validates a six-gene risk prediction model, clarifying the functional significance of core genes, including THBS1. These findings provide novel molecular tools for PDAC prognosis assessment and identify potential targets for immunotherapy and personalized treatment strategies.
11 June 2026
Read appraisal →Journal of theoretical biology
Subtypes estimation in single-cell multi-omics data via S-multi-SNE
Single-cell RNA sequencing (scRNA-seq) has rapidly become an essential method in modern biology, as it allows global characterisation of transcriptomics in individual cells from different tissues, or organisms. scRNA-seq data are collected from a single individual organism and they are composed as mRNA count matrices with rows representing the cells and columns the genes. New technologies further allow multi-omics data to be obtained on the same set of single cells. In this paper, multi-SNE and S-multi-SNE, two multi-view dimensionality reduction approaches, are adapted for visualization and classification of cellular subtypes, two important challenges in the analysis of scRNA-seq data. S-multi-SNE has been adapted for cell subtype estimation of scRNA-seq data. In a series of experiments we illustrate that it is possible to identify cell subtypes by leveraging information from individuals from the same species, from different species, and when data are generated by different sequencing technologies. In the conducted analyses, we show that S-multi-SNE consistently outperformed several other machine learning techniques and, in most comparisons, surpassed existing reference-based single-cell classification algorithms. We further illustrate how two single-cell multi-omics datasets, scATAC-seq and scRNA-seq, can be integrated together through S-multi-SNE for improved cell subtype identification.
7 June 2026
Read appraisal →PLoS computational biology
A prototype-augmented graph representation learning framework for identifying brain disorder-associated genes and facilitating drug repurposing
Many genetic loci were identified as associated with neuropsychiatric disorders and neurodegenerative disorders by Genome-wide association studies (GWAS). How these loci impact these diseases is unclear. Advances in deep-learning approaches and multi-omics data have the potential to link GWAS findings with disease mechanisms. Here, we proposed the Multi-omics Graph Transformer Network (MOGT), a semi-supervised graph neural network that leverages graph representation learning to model biological networks derived from multi-omics data to predict disease-associated genes. MOGT outperforms the current approaches in disease gene prediction for two psychiatric disorders and three neurodegenerative/neurological diseases. High-risk genes (HRGs) for Parkinson's disease (PD) predicted by MOGT were used to drug discovery by integrating with the CMAP database. Finally, 10 drugs were identified as potential candidates. Among them, the effect of drug UK-356618 was experimentally verified in a primary neuron model, showing that UK-356618 reversed the abnormal expression of PD-associated genes and improved the cell-level phenotypes of PD. Together, these results indicate that MOGT can be used to identify HRGs for brain disorders, and these predicted HRGs provide high-level insights into the mechanisms and treatments of brain disorders.
1 June 2026
Read appraisal →Purinergic signalling
Turning failure into success: how artificial intelligence can help personalize therapies and re-use patient data.
Despite robust preclinical evidence, many clinical trials, including several that targeted the purinergic system, fail to demonstrate efficacy in humans. Failure may stem from inability to accurately identify patient subgroups responding similarly to treatments. Here, we explore the potential of artificial intelligence to revolutionize how we group and classify patients in clinical studies. We introduce a new framework using Large Language Models-generated embeddings of detailed patient data, to create a semantic-aware latent space, enabling us to identify truly meaningful patients' clusters. Large Language Models can provide explainable groupings, giving clear reasons why certain patients respond similarly to treatments. We present an example of successful application of this approach through the re-analysis of the AMARANTH clinical trial (NCT02245737, involving ~ 2200 patients and completed in 2018) testing Lanabecestat, a BACE1 inhibitor decreasing β-amyloid production in Alzheimer's disease, for which traditional analysis reported no efficacy. As in the original trial, our simulation showed no overall benefit. However, re-analysis per patients' clusters and subjects' re-stratification by semantic similarities (shared symptom profiles, progression patterns) identified a patients' subgroup in one of the clusters showing Lanabecestat-associated slower disease worsening, thus succeeding where the full trial had failed. By making a new therapy available to at least a subset of patients with a defined disease, this new approach may help maximize the return on drug development and reduce the burden on healthcare. Moreover, it will significantly improve the precision, efficiency and interpretability of clinical trials, paving the way for a new era of personalized medical treatments.
31 May 2026
Read appraisal →Journal of the Egyptian National Cancer Institute
Artificial intelligence in cancer immunotherapy: current trends in predicting response and personalizing treatment
Artificial intelligence (AI) can transform cancer immunotherapy by enabling more accurate prediction of treatment responses, the discovery of specific biomarkers, and the development of personalised treatment plans. Traditional single-marker biomarkers (PD-L1, TMB, MSI) lack consistency across tumour types and cannot be used to assess tumour heterogeneity or the dynamic tumour microenvironment (TME). This review synthesises developments in multimodal AI models that combine genomics, transcriptomics, radiomics, digital pathology (pathomics), circulating biomarkers, and clinical evidence to create composite predictive signatures with significantly better discriminatory value. AUCs over 0.8 have been seen in a few retrospective studies with deep learning and ensemble models on whole-slide images, CT/MRI/PET radiomics, spatial and single-cell omics, and multi-omics fusion models, but prospective and multicentre validation is scarce, and external validation often shows deterioration in performance. AI is also used to enhance the translational pipelines of adoptive cell therapies (e.g., CAR-T) by improving patient selection, manufacturing (e.g., digital twins), and early toxicity prediction (e.g., CRS, ICANS). Nevertheless, clinical implementation remains hindered by data heterogeneity, bias, poor longitudinal validation, limited reproducibility, and a lack of transparency in most models, even though prospective, multicenter validation and explainable AI are crucial for clinician trust and regulatory acceptance. New systems such as federated learning, foundation models, spatial omics, digital twins, and wearable monitoring represent paths to generalizable, privacy-preserving, and actionable systems in clinical practice. To achieve the potential of AI, the generation of data will need to be standardized, reporting must be transparent, interdisciplinary, and regulatory frameworks must be strengthened focusing on the practical use of AI and patient safety. By taking these steps, AI could be shifted to prospective clinical decision support, which uses AI to meaningfully enhance personalization and outcomes in cancer immunotherapy based on a retrospective research tool.
30 May 2026
Read appraisal →European respiratory review : an official journal of the European Respiratory Society
The evolution of scientific knowledge in childhood asthma over time
Paediatric asthma management has undergone a significant transformation from rudimentary assessments in the early 20th century to sophisticated diagnostic and therapeutic approaches today. Early clinical observations lacked paediatric specificity, but mid-20th-century studies introduced functional assessments, spirometry and recognition of asthma as a chronic inflammatory condition. The introduction of inhaled corticosteroids transformed long-term management, offering targeted control with reduced systemic risks. Advances in noninvasive diagnostics, such as fractional exhaled nitric oxide, induced sputum analysis, exhaled breath condensate and electronic nose technology, have improved inflammation monitoring, phenotype classification and therapeutic responsiveness. The integration of omics technologies, i.e. genomics, proteomics and metabolomics, has enabled deeper insights into disease mechanisms and facilitated early, individualised interventions. Concurrently, artificial intelligence (AI) and machine learning are emerging as tools for predicting exacerbations, identifying clinical subtypes and enhancing decision-making through large-scale data integration. Despite these advancements, challenges remain around standardisation, data quality and ensuring equitable access. This narrative review synthesises decades of progress in paediatric asthma care, emphasising the transition from empirical treatment to personalised, biomarker-driven strategies. It highlights current gaps, particularly in algorithm transparency, paediatric-specific validation and holistic care integration. As asthma management enters an era of digital health and AI-assisted precision medicine, future success will depend on interdisciplinary collaboration, real-world validation and policies that close care disparities.
29 May 2026
Read appraisal →Cell reports
Artificial intelligence-driven donor-recipient gut microbiome matching for optimized fecal microbiota transplantation
Fecal microbiota transplantation (FMT) has emerged as a promising therapy for gastrointestinal diseases, yet its clinical efficacy remains individually variable. Here, we analyze multi-kingdom and functional profiles in pre- and post-FMT metagenomes from 515 FMTs across 30 cohorts and 12 diseases, in which 94 metagenomes from 44 FMTs are newly collected. We reveal a robust association between clinical efficacy and post-FMT microbiome convergence of recipients toward donors, across diseases. To predict post-FMT microbial convergence, we develop MOZAIC (Microbiome Matching Optimization via Artificial Intelligence), a framework that integrates multi-dimensional donor-recipient microbiota features. MOZAIC achieves an average area under the curve (AUC) of 0.88 and accuracy/recall >0.80 in forecasting microbiome convergence, with 78.7% accuracy in predicting clinical outcomes, and retrospectively simulates a 1.44-fold improvement (from 49.4% to 71.0%) in clinical response rates over baseline. This study establishes microbiome convergence as a key mediator of FMT and provides a scalable tool for precision matching in microbiota-based therapies.
28 May 2026
Read appraisal →Chembiochem : a European journal of chemical biology
Mutant-Initiated Structure-Guided Refinement Enables Second-Generation Compact IscB Genome Editors
Compact RNA-guided nucleases such as IscB represent an attractive foundation for next-generation genome editors, yet their application in mammalian cells has been constrained by suboptimal activity. Here, instead of re-engineering enzymes, we establish a mutant-initiated, structure-guided optimization strategy to generate second-generation high-activity IscB editors. Using AlphaFold3 to model the engineered IscB*-ωRNA-DNA complex, we reveal remodeling of the nucleic-acid-binding interface induced by activity-enhancing substitutions. Guided by this predicted structure, we perform a focused mutational scan and identify V367 as an activity hotspot. Saturation mutagenesis at this position yields a single substitution, V367Y (IscB*-Act), which increases mean editing efficiency by 34% and achieves up to 2.1-fold improvement across endogenous targets in mammalian cells. Importantly, the V367Y substitution is transferable to an IscB-based adenine base editor, elevating A-to-G conversion by 68% on average and up to 4.46-fold at individual loci without altering the intrinsic editing window. Targeted off-target profiling at loci suggests that V367Y does not substantially increase off-target indels or A-to-G conversion. Together, our work demonstrates a practical framework for second-generation refinement of compact genome editors, bridging deep-learning-enabled structural prediction with interpretable protein engineering, and expands the functional potential of miniature IscB systems for both nuclease and base editing applications.
27 May 2026
Read appraisal →Journal of chemical theory and computation
MolSculptor: An Adaptive Diffusion-Evolution Framework Enabling Generative Drug Design for Multitarget Affinity and Selectivity
The rational design of molecules with tailored activity/selectivity across multiple protein targets is crucial for developing therapies for complex diseases like cancer, yet it remains a formidable challenge. While deep generative models show immense promise, their application to these tasks faces fundamental challenges, as they struggle to incorporate the structural information on multiple distinct protein pockets and require vast multitarget data sets or specialized expert knowledge that are rarely available. Here we introduce MolSculptor, an adaptive diffusion-evolution framework designed to generate inhibitors for any combination of on- and off-targets, circumventing the need for target-specific training data or prior expert knowledge. MolSculptor unifies both de novo design and lead optimization, provides a versatile workflow applicable to different stages of drug discovery, and allows for direct conditioning on key drug-like properties. It integrates a 3D-aware surrogate model to enable flexible guidance for any set of specified on- and off-targets. Furthermore, MolSculptor employs an active learning protocol to adaptively refine this guidance, ensuring high performance even in data-scarce scenarios. We demonstrate MolSculptor on a series of challenging multitarget and selective inhibitor design tasks, where it significantly outperforms state-of-the-art methods in generating high-quality candidates that satisfy all complex constraints. Notably, many of the generated molecules exhibit predicted affinity profiles superior to those of experimentally validated references. Using MolSculptor, we successfully designed and synthesized a novel and potent dual-target inhibitor for castration-resistant prostate cancer (CRPC), whose inhibitory activity was confirmed through wet-lab validation. MolSculptor provides a powerful and generalizable paradigm for designing ligands with complex, multitarget activity profiles, paving the way for data-efficient solutions to complex therapeutic problems.
27 May 2026
Read appraisal →Blood advances
Phase 1b study of ABBV-744, a novel, selective BET inhibitor, as monotherapy for patients with myelofibrosis
Janus kinase inhibitors (JAKi) are standard of care for patients with myelofibrosis (MF) but can be associated with treatment-limiting cytopenias and do not modify underlying disease. Novel treatments targeting other clinically relevant pathways are needed. Inhibitors of bromodomain (BD) and extraterminal domain (BET) proteins are a promising class of drugs that have demonstrated the ability to modulate key pathways involved in inflammation, fibrosis, and apoptosis. ABBV-744 is a novel small molecule that targets the BDII of BET proteins and has previously been shown to be well tolerated when administered daily at doses of 120 and 180 mg to patients with acute myeloid leukemia. We report the outcomes of a multicenter, open-label phase 1b study of ABBV-744 in patients with MF who received ≥1 previous lines of therapy, including a JAKi. The primary objective was safety, including dose-limiting toxicities (DLTs). Secondary end points included a reduction in spleen volume of ≥35% (SVR35), ≥50% reduction in total symptom score (TSS50), objective response rate, and pharmacokinetics. All 21 patients experienced at least 1 treatment-emergent adverse event, and 11 patients experienced a DLT. The most common events leading to DLTs were thrombocytopenia (33%) and anemia (24%). SVR35 was attained in 24% of patients at week 12 and 33% at week 24. TSS50 was reported for 29% of patients at 12 weeks and 19% at week 24. These outcomes are noteworthy in this heavily pretreated population considering the advanced disease state and limited treatment options for this patient population. This trial was registered at www.clinicaltrials.gov as NCT04454658.
27 May 2026
Read appraisal →Journal of gastrointestinal cancer
Optimal First-line Immune-related Therapy Selection for Advanced Gastric Cancer: A Systematic Review and Network Meta-analysis
PURPOSE: Although immune checkpoint inhibitors combined with chemotherapy improve survival in advanced gastric cancer (AGC), comparative evidence across first-line regimens remains insufficient. This study aimed to systematically evaluate their relative efficacy and safety. METHODS: PubMed, Embase, the Cochrane Library, Web of Science, and major conferences were searched up to February 28, 2025. Eligible RCTs comparing ICI-related regimens as first-line AGC treatment were included. Primary outcomes were overall survival (OS) and progression-free survival (PFS). RESULTS: Eleven RCTs involving 8,999 patients, six integrated strategies, and twelve specific regimens were included. Dual-target ICI-chemo and single ICI-chemo showed significant survival benefits over chemotherapy, whereas dual ICIs±chemo and single ICI alone did not. Dual-target ICI-chemo was associated with significantly better survival than both dual ICIs±chemo and single ICI±chemo. Among the specific regimens, cadon-chemo achieved the most favorable OS and PFS. No significant OS differences were observed among the single ICI-chemo regimens. In PD-L1-positive subgroups, both dual-target ICI-chemo and single ICI-chemo significantly improved survival compared with chemotherapy, with cadon-chemo being most effective in CPS ≥ 10 and CPS ≥ 1, and SHR1701-chemo in CPS ≥ 5. In the CPS < 5 subgroup, dual-target ICI-chemo significantly improved OS, while single ICI-chemo showed a trend toward benefit. However, no ICI-based strategy demonstrated benefit in CPS < 1. CONCLUSIONS: Dual-target ICI-chemo appears to be the most effective first-line strategy for AGC based on current indirect evidence, surpassing single ICI-chemo and dual ICI-based regimens. These findings support personalized therapy selection but await confirmation by head‑to‑head trials. Future studies should address CPS < 1 and explore optimized combinations to enhance outcomes.
25 May 2026
Read appraisal →Medicine
Survival prediction of colorectal cancer using 101 machine learning methods based on immune-related genes: A machine learning study
Colorectal cancer (CRC) is characterized by high incidence and mortality rates. Early identification of high-risk CRC patients and timely intervention are crucial for reducing mortality rates. This study aims to develop a prognostic model incorporating immune-related genes using 101 machine learning algorithms. We utilized data from 630 CRC patients in The Cancer Genome Atlas Program database and the Gene Expression Omnibus database as a validation set. We identified immune-related genes from the ImmPort repository and conducted differential gene expression analysis. We developed 101 machine learning models, including random survival forest, elastic net, LASSO, Ridge regression, stepwise Cox, Coxboost, partial least squares regression for Cox, supervised principal component analysis, generalized boosted modeling, and survival support vector machines. The model with the highest mean concordance index was selected as the optimal prognostic model. The Ridge regression model demonstrated the most robust performance with a mean concordance index of 0.67. Patients with higher immune-related gene risk score (IRGRS) had significantly lower survival rates (log-rank test, P < .001). Univariate and multivariate Cox regression analyses confirmed IRGRS as an independent prognostic factor. Nomograms successfully predicted overall survival at 1, 2, and 3 years. IRGRS correlated with immune cell infiltration levels and stromal activity in the tumor microenvironment. High IRGRS scores were associated with higher tumor immune dysfunction and exclusion scores, suggesting potential differences in response to immune checkpoint inhibitors. In addition, high IRGRS patients exhibited greater sensitivity to certain chemotherapy drugs. The IRGRS score is a potent predictor of survival in CRC patients. This study offers a new perspective for CRC prognosis and supports the development of personalized treatment strategies.
24 May 2026
Read appraisal →BMC cancer
Efficacy and risk analysis of monotherapy and dual immunotherapy in dMMR/MSI-H metastatic colorectal cancer: a meta-analysis based on randomized controlled trials
BACKGROUND: Immune checkpoint inhibitors (ICIs) have transformed the treatment landscape for metastatic colorectal cancer (mCRC) exhibiting DNA mismatch repair deficiency (dMMR) or microsatellite instability-high (MSI-H). However, the comparative efficacy and safety of monotherapy versus dual immunotherapy remain inadequately quantified. This meta-analysis aims to evaluate the benefits and risks of these strategies by quantitatively synthesizing data from randomized controlled trials (RCTs) to inform clinical decision-making. DESIGN: We systematically searched major databases (PubMed, Web of Science, Cochrane, Embase) from inception to September 2025 for relevant RCTs. Outcomes included objective response rate (ORR), progression-free survival (PFS), overall survival (OS), duration of response (DOR), and adverse events. Statistical analyses were performed using RevMan 5.3 and Stata 18.0. RESULTS: Six RCTs (1,460 patients) were included. Pooled analysis showed that PD-1/PD-L1 monotherapy significantly improved ORR compared with chemotherapy (OR = 1.52, 95% CI: 1.02-2.27, P = 0.04), based on two RCTs (n = 429), and demonstrated a significantly lower incidence of grade ≥ 3 adverse events (OR = 0.14, 95% CI: 0.08-0.23, P < 0.00001; 2 studies). Dual immunotherapy with nivolumab plus ipilimumab significantly improved ORR versus monotherapy (OR = 1.77, 95% CI: 1.25-2.49, P = 0.001), based on one RCT (n = 582), with a significantly increased toxicity risk (OR = 1.73, 95% CI: 1.22-2.44, P = 0.002). For PFS, KEYNOTE-177 (HR = 0.59, 95% CI: 0.45-0.79) and CheckMate 8HW (HR = 0.62, 95% CI: 0.48-0.81) showed significant benefits, while SAMCO-PRODIGE 54 and CheckMate 9 × 8 did not demonstrate statistically significant PFS improvement. OS hazard ratios across four studies ranged from 0.74 to 1.03, with all 95% confidence intervals crossing 1.0, indicating no statistically significant survival benefit in any individual study. DOR was consistently longer with immunotherapy, with median not reached for pembrolizumab versus 10.6 months for chemotherapy in KEYNOTE-177. CONCLUSIONS: Effect estimates for PFS, OS, and DOR generally favored immunotherapy; however, confidence intervals were wide and statistical significance was not consistently observed across trials. PD-1/PD-L1 monotherapy demonstrated a favorable safety profile and a statistically significant improvement in ORR compared with chemotherapy (OR = 1.52, 95% CI: 1.02-2.27, P = 0.04). Dual immunotherapy significantly improved ORR compared with monotherapy (OR = 1.77, 95% CI: 1.25-2.49, P = 0.001), but this benefit was accompanied by significantly increased toxicity (OR = 1.73, 95% CI: 1.22-2.44, P = 0.002) and did not consistently translate into statistically significant PFS or OS benefits across trials. These findings highlight the need for personalized risk-benefit assessment. Future research should focus on biomarker-driven patient selection and strategies to overcome resistance.
23 May 2026
Read appraisal →Molecular cell
Rapid customization of base editors via machine learning-powered combinatorial mutagenesis
Being able to control the complementarity and hindrance between target DNA and base editor proteins enables precise, bystander-free editing. Here, we combined combinatorial mutagenesis with machine learning to analyze and engineer these interactions at scale. By profiling DNA motif preferences across 160,000 evoAPOBEC1 and 64 million TadA variants in human cells, we used as little as 0.004% of the mutational landscape to make predictions. This identified variants with motif-specific activity and eliminated residual adenine editing in cytosine base editors. In correcting >800 disease-associated mutations, our variants outperformed previous versions in precluding unintended edits at purine motifs, achieving undetectable bystander edits in 50% of cases. Additionally, a pre-trained, structure-based deep learning model predicted functional TadA variants with 63% success across 2026 variants spanning 26 amino acid sites, without experimental data and in a single prediction round. These approaches streamline the re-engineering of base editors for enhanced precision tailored to specific targets.
23 May 2026
Read appraisal →Cell systems
GFETM: Genome foundation-based embedded topic model for scATAC-seq modeling
Single-cell assay for transposase-accessible chromatin with sequencing (scATAC-seq) enables investigation of open chromatin landscapes at single-cell resolution. However, analyzing scATAC-seq data remains challenging due to inherent sparsity and noise. Genome foundation models (GFMs), pre-trained on extensive DNA sequence datasets, have demonstrated effectiveness in genome analysis. Because open chromatin regions (OCRs) harbor salient sequence features, we hypothesized that leveraging GFMs' sequence embeddings could enhance scATAC-seq modeling accuracy and generalizability. We introduce the genome foundation embedded topic model (GFETM), an interpretable deep learning framework combining GFMs with the embedded topic model (ETM) for scATAC-seq analysis. By integrating DNA sequence embeddings extracted by a GFM from OCRs, GFETM demonstrates superior accuracy and generalizability and captures cell-state-specific transcription factor (TF) activity with both zero-shot inference and attention-mechanism analysis. Finally, the topic mixtures inferred by GFETM reveal biologically meaningful epigenomic signatures of kidney diabetes. A record of this paper's transparent peer review process is included in the supplemental information.
22 May 2026
Read appraisal →Cell systems
Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease states
Single-cell RNA sequencing (scRNA-seq) is a prominent tool for studying human disease biology. The availability of massive scRNA-seq datasets and advanced machine learning has driven the development of single-cell foundation models that provide versatile cell representations based on expression. To understand disease states, we need to account for entire tissue ecosystems, simultaneously considering many different interacting cells. Here, we tackle this challenge by generating patient-level representations derived from multi-cellular expression contexts measured with scRNA-seq of tissues. We develop PaSCient, a machine learning model that employs a multi-level representation learning paradigm and provides importance scores at the cell and gene levels for fine-grained analysis of disease characteristics. We apply PaSCient to a large-scale scRNA-seq atlas of 12.5 million cells from over 2,700 patients. Comprehensive benchmarking demonstrates the superiority of PaSCient in disease classification and multiple downstream applications, including dimensionality reduction, feature prioritization, and patient subgroup discovery.
22 May 2026
Read appraisal →Postgraduate medical journal
Next-generation cancer therapies: translating experimental advances into clinical practice
Recent advancements in cancer therapy have led to the emergence of innovative approaches that offer new hope to patients. This review provides a comprehensive overview of the latest cutting-edge technologies and strategies in cancer treatment, including clinically approved therapies and experimental modalities in preclinical or early clinical development, with a focus on their potential to improve patient outcomes. We examined next-generation therapies, including personalized immunotherapies, targeted molecular treatments, gene editing approaches, and artificial intelligence-driven strategies. By evaluating the current landscape of these therapies, we highlighted their benefits, limitations, and future directions. The integration of these advanced modalities into clinical practice holds promise for enhancing their efficacy, reducing side effects, and ultimately transforming cancer care.
22 May 2026
Read appraisal →European radiology experimental
Predicting resistance to neoadjuvant chemotherapy in osteosarcoma using machine learning with clinical data and T2-weighted MRI radiomics
OBJECTIVES: Identifying patients at risk of chemoresistant osteosarcoma enables risk-adapted management. This study aimed to predict chemoresistant osteosarcoma using baseline clinical and magnetic resonance (MRI)-derived radiomics features, with histological response as the reference standard and external validation included. MATERIALS AND METHODS: This retrospective single-center study included 115 patients with osteosarcoma from an institutional registry as the internal cohort, divided into training and test sets, and 49 patients from another institution as an external validation cohort. Tumor and peritumoral regions were manually segmented on baseline fat-suppressed T2-weighted MRI. Radiomics features were extracted using PyRadiomics, followed by two feature selection methods to identify potential predictors. Six machine learning models with varying feature combinations were trained to classify histologic chemoresistance in the internal training set. Model performance was assessed in the internal test set, and the best model was externally validated. RESULTS: The support vector machine model combining eight tumor radiomics features and four clinical-imaging parameters (presence of tumor necrosis > 50% on contrast-enhanced MRI, age, body mass index, and presence of metastasis at presentation) demonstrated the best performance. In the internal test set, it achieved a sensitivity of 83.3%, a specificity of 72.7%, an area under the receiver operating characteristic curve (AUROC) of 0.84, and a positive likelihood ratio of 3.06. External validation yielded a sensitivity of 88.5%, a specificity of 47.8%, and an AUROC of 0.77. CONCLUSION: A model combining tumor radiomics and clinical parameters at diagnosis showed strong performance in predicting chemoresistant osteosarcoma, with results confirmed by external validation. This approach may support personalized treatment strategies in high-grade osteosarcoma. RELEVANCE STATEMENT: The validated model may support early, individualized osteosarcoma management. KEY POINTS: Baseline T2-weighted MRI radiomics and clinical data can predict chemoresistant osteosarcoma. Tumor radiomics combined with clinical features achieved strong predictive accuracy. The support vector machine model reached an AUROC of 0.84 for the internal testing and of 0.77 for the external validation. The validated model may support early, individualized osteosarcoma management.
21 May 2026
Read appraisal →Journal of clinical oncology : official journal of the American Society of Clinical Oncology
Tissue-Free Circulating Tumor DNA Assay and Patient Outcome in a Phase III Trial of FOLFOX-Based Adjuvant Chemotherapy (Alliance N0147)
PURPOSE: Detection of molecular residual disease using circulating tumor DNA (ctDNA) may enable postoperative risk stratification and guide adjuvant therapy. We evaluated the prognostic value of a tissue-free, epigenomic ctDNA assay in patients with stage III colon cancer (CC) enrolled in a phase III adjuvant chemotherapy trial. METHODS: Plasma samples were collected after surgery and before adjuvant infusional fluorouracil, leucovorin, and oxaliplatin alone or combined with cetuximab. ctDNA was analyzed using a tissue-free assay; in ctDNA-positive patients, tumor fraction (TF) was quantified and genotyping was performed with a 739-gene panel. Associations with disease-free survival (DFS), time to recurrence (TTR), and overall survival (OS) were assessed using multivariable Cox models adjusted for covariates. RESULTS: Among 2,260 evaluable patients, 461 (20.4%) were ctDNA-positive with significantly higher detection in advanced T-/N-stage, high-grade, obstruction/perforation, and BRAFV600E tumors. At a median follow-up of 6.1 years, ctDNA positivity was independently associated with shorter TTR (hazard ratio [HR], 5.96 [95% CI, 5.11 to 6.96]), DFS (HR, 5.03 [95% CI, 4.36 to 5.81]), and OS (HR, 4.45 [95% CI, 3.76 to 5.27]; all P < .0001). The 5-year DFS was 27.7% (95% CI, 23.8 to 32.2) v 77.1% (95% CI, 75.1 to 79.1) in ctDNA-positive versus ctDNA-negative patients, and adverse prognostic impact was greater in lower T/N stage, low-risk, and dMMR subsets (interaction P = .0012-.041). Among ctDNA-positive patients, TF was nearly double in those who recurred or died (P = .0002) and stratified patients for TTR, DFS, and OS (all adjusted P < .002). Genotyping identified mutations in FLT1 (OR, 8.99) and PREX2 (OR, 7.73) genes that were most strongly associated with recurrence (P < .03). CONCLUSION: Evaluation of ctDNA in resected stage III CC using a tissue-free assay provided robust and independent prognostic value. Higher ctDNA burden, dMMR, and specific mutations defined poor prognostic groups among ctDNA-positive patients.
20 May 2026
Read appraisal →Cell reports methods
A network-based deep learning model integrating subclonal architecture for therapy response prediction in cancer
Predicting treatment response remains challenging in oncology, particularly given the growing diversity of therapeutic options. Despite efforts using gene expression signatures, or integrative multi-omics frameworks, robust and interpretable biomarkers remain limited. We present SubNetDL, a deep learning framework that integrates subclonal mutation profiles and protein-protein interaction networks via network propagation. Unlike condition-specific approaches, SubNetDL leverages somatic mutations alone and is applicable across diverse cancer types and treatment modalities. Applied to 10 TCGA cancer-drug combinations, SubNetDL achieved consistently strong performance (median area under the receiver operating characteristic curve [AUROC] = 0.74) and successfully generalized to two independent immunotherapy datasets (median AUROC = 0.77). Importantly, it identified candidate biomarker genes with treatment-specific relevance. SubNetDL prioritized genes that were not central in the network, highlighting its ability to capture context-specific patterns beyond traditional metrics. In conclusion, our approach offers a robust and interpretable framework for identifying predictive biomarkers and stratifying patients based on mutation profiles and network context.
20 May 2026
Read appraisal →Journal for immunotherapy of cancer
Clinical outcomes and spatial transcriptomic profiles of CD19/20 CAR-T therapy in relapsed or refractory B-cell non-Hodgkin's lymphoma
BACKGROUND: Relapsed or refractory (R/R) B-cell non-Hodgkin's lymphoma (B-NHL) remains a major therapeutic challenge despite CD19-directed chimeric antigen receptor (CAR) T-cell therapies, with treatment failure often driven by antigen escape and limited CAR-T persistence. Dual targeting of CD19 and CD20 may mitigate antigen loss. We conducted an expanded phase I/II study of bispecific CD19/20 CAR-T cells and incorporated spatially resolved single-cell transcriptomics to evaluate tumor-intrinsic and microenvironmental factors of clinical response. METHODS: Patients with R/R B-NHL received CD19/20 CAR-T cells following lymphodepletion. Efficacy, safety, CAR-T expansion/persistence, and B-cell reconstitution were assessed. Pretreatment tumor biopsies from five patients with divergent outcomes underwent spatial single-cell transcriptomic profiling. RESULTS: 32 patients were treated, including 24 with diffuse large B-cell lymphoma. Among 31 evaluable patients, the best overall response rate was 74%, including 58% achieving complete remission. Median progression-free and overall survival were 6.8 and 22.1 months, respectively. Response rates were higher in patients with normal lactate dehydrogenase. CAR-T expansion peaked on days 7-17, and persistence exceeded 500 days in long-term responders. Cytokine release syndrome occurred in 53% (12% grade ≥3) and immune effector cell-associated neurotoxicity syndrome in 9% (all grade 3), with no lasting deficits. Spatial profiling identified two dominant tumor architectures: (1) a B-cell-dominant phenotype, in which durable remission was associated with heightened apoptotic competence in malignant B cells, and (2) a fibroblast-enriched and monocyte/macrophage-enriched phenotype, in which response correlated with a chemokine-rich, T-cell-permissive microenvironment. CONCLUSIONS: Bispecific CD19/20 CAR-T therapy produced durable clinical activity with manageable toxicity. Spatial single-cell analysis reveals distinct tumor-intrinsic and microenvironmental features associated with CAR-T responsiveness, providing a spatially informed framework for understanding heterogeneous therapeutic outcomes. TRIAL REGISTRATION NUMBER: NCT04723914.
18 May 2026
Read appraisal →Biological psychiatry
Overview of Challenges in Brain-Based Predictive Modeling: Toward Meaningful Predictive Insights
Predictive analytics based on machine learning (ML) and artificial intelligence is a powerful tool enabling precision psychiatry and providing insights into brain-behavior relationships. However, given the mixed results observed in the field so far, making meaningful progress requires careful consideration of several key challenges to ensure the validity of models and findings, including overfitting, confounding biases, site effect harmonization, and interpretability, among others. First, we highlight limitations of cross-validation, a ubiquitous ML strategy used to prevent overfitting and obtain generalization estimates, emphasizing the risk of performance inflation and the need for independent validation. Next, we introduce different types of so-called third variables that can influence the examination of a brain-behavioral relationship of interest in different ways, using causal inference principles. We emphasize the biasing impact of confounding variables on ML models and summarize common mitigation strategies. We then discuss site-specific effects in multisite datasets, reviewing different harmonization strategies to reduce unwanted variability and site-specific noise. Finally, we explore post hoc model interpretation methods to enhance model transparency while cautioning against misinterpretation. By integrating rigorous result validation, confounder control, and interpretability techniques, researchers can ensure that ML models produce more reliable and generalizable findings and avoid spurious associations.
18 May 2026
Read appraisal →Journal of neuro-oncology
Should checkpoint inhibitors be reserved for biomarker-selected pediatric brain tumors?
PURPOSE: Pediatric brain tumors, including high-grade gliomas (HHG), medulloblastomas (MB), and ependymomas (EPN), are a leading cause of death in children. They are often immunologically "cold" with low tumor mutational burden (TMB) and very few tumor-infiltrating lymphocytes (TILs), which may limit the role of immune checkpoint inhibitors (ICI). METHODS: We performed a PRISMA‑guided systematic review of PubMed/MEDLINE, Embase, and Scopus from inception to September 17, 2025, for English-language studies of patients ≤ 21 years with primary CNS tumors treated with PD‑1/PD‑L1 or CTLA‑4 inhibitors. Eligible reports included prospective trials, retrospective series, and observational/case reports with extractable data on efficacy and/or toxicity. Of 479 records identified, 386 unique citations were screened, 127 underwent full‑text review, and 40 met inclusion criteria for qualitative synthesis. RESULTS: Prospective and institutional studies in biomarker-unselected diffuse midline glioma, high-grade glioma, medulloblastoma, and ependymoma showed low objective response rates (generally ≤ 6%), short median progression-free survival (1-3 months), and overall survival similar to historical controls, despite acceptable safety (grade ≥ 3 treatment-related adverse events ~ 15-25% with anti-PD-1 ± anti-CTLA-4). In contrast, across germline MMR-deficient and broader RRD/hypermutant cohorts, PD-1 blockade produced clinically meaningful and sometimes durable responses, including complete remissions in malignant glioma and approximate 2-year overall survival near 50%, often with delayed responses and pseudoprogression. Histology-specific profiling highlighted marked variation in immune contexture: pediatric gliomas segregate into immune "hot," "altered," and "cold" subtypes; medulloblastoma is largely PD-L1-low with prominent B7-H3 and myeloid programs; checkpoint expression is also observed in germ cell and selected sellar tumors. Evidence quality is limited by small, heterogeneous, predominantly non-comparative designs. CONCLUSION: ICIs show manageable safety but limited efficacy in unselected pediatric CNS tumors. Durable benefit is most evident in RRD/hypermutant biology and possibly PD-L1-high niches (e.g., some low-grade gliomas and CNS-GCT). Future trials should be biomarker-driven and pair ICIs with priming combinations (e.g., radiation, epigenetic modulators, metronomic chemotherapy) to convert "cold" tumors into responders.
18 May 2026
Read appraisal →Computers in biology and medicine
Generative deep learning-driven de novo design of targeted MAP4K6 inhibitors
The discovery of selective small-molecule inhibitors for pharmacologically underexplored kinases remains a critical barrier to precision drug development, particularly under data-sparse conditions, where ligand annotations are scarce. Here, we present MolEvoRNN, a generative deep learning (GDL) model that enables the de novo design of chemically valid, structurally diverse, and target-adapted compounds in low-data regimes. Through transfer learning and temperature-controlled sampling, MolEvoRNN efficiently navigates the kinase-relevant chemical space while preserving scaffold novelty, drug-likeness, and synthetic tractability. Applied to MAP4K6, a poorly characterized serine/threonine kinase implicated in hepatocellular carcinoma (HCC), MolEvoRNN generated >49,000 chemically valid molecules with >80% novel Bemis-Murcko scaffolds. MolEvoRNN outperformed the baseline GDL models across key generative metrics, including diversity (1.00), uniqueness (1.00), novelty (1.00), and internal diversity (0.869), demonstrating broad chemical exploration with minimal redundancy. A multilayered virtual screening cascade combining QSAR modeling, pharmacophore mapping, molecular docking, MM-GBSA binding energy estimation, and 1000 ns molecular dynamics simulations identified three lead candidates MINK-5730, MINK-13510, and MINK-16516 with high predicted affinity, favorable ADMET properties, and robust dynamic stability. Unlike end-to-end optimization pipelines, MolEvoRNN decouples generation from evaluation, promoting methodological transparency and rigorous post-hoc triaging. This study establishes a scalable, generalizable paradigm for rational small-molecule design in underexplored target spaces, bridging generative deep learning with structural pharmacology to accelerate early-phase therapeutic discovery.
17 May 2026
Read appraisal →International immunopharmacology
NY-ESO-1 in Triple-Negative Breast Cancer: Systematic Review, Meta-Analysis, and Immunotherapeutic Implications
Breast cancer remains one of the most common types of cancer, including the subtype triple-negative breast cancer (TNBC) which is challenging to treat due to its aggressiveness. Cancer-testis antigens (CTAs), especially New York Esophageal Squamous Cell Carcinoma 1 (NY-ESO-1), have become promising immunotherapeutic targets attributable to their restricted expression profile in normal tissues but overexpressed in TNBC, leading to immunogenicity. This review provides comprehensive discussion of NY-ESO-1 including its structural basis of NY-ESO-1 recognition by T cell receptors (TCRs) and antibodies, epigenetic regulation via DNA methylation or histone modifications, and expression patterns or clinical relevance in TNBC. A systematic meta-analysis of 12 studies comprising 1,545 TNBC patients showed a pooled NY-ESO-1 expression prevalence of 16.1% (95% CI: 11.4-22.2%), with heterogeneity (I2=83.7%) attributable to antibody clone used for NY-ESO-1 detection (E978: 15.1% vs. D8.38: 32.6%, p<0.0001) and scoring methods (composite scoring: 15.9% vs. dual scoring: 16.9% vs. H-score: 10.1% vs. simple threshold: 32.6%, p<0.001). Structural analyses reveal NY-ESO-1157-165 recognition by TCRs, antibodies, and engineered binding scaffolds. We examine preclinical and clinical evidence for NY-ESO-1-targeted therapies, including adoptive cell therapy and peptide vaccines, which show manageable safety profiles and induce immunological responses. Epigenetic regulation is a therapeutic avenue, whereby hypomethylating agents and histone deacetylase inhibitors can upregulate NY-ESO-1 expressions that promote tumor immunogenicity. Nonetheless, challenges persist such as NY-ESO-1 expression heterogeneity, lack of TNBC-specific clinical trials, and inadequate immunogenicity. Future research should standardize NY-ESO-1 detection protocols to identify TNBC patients for NY-ESO-1-targeted immunotherapy, prioritize TNBC-specific trials and combinations with epigenetic priming agents.
16 May 2026
Read appraisal →Blood
Evolution of tumor subclones and T-cell dynamics underlie variable ibrutinib responses in Waldenström macroglobulinemia
To elucidate the molecular basis underlying differential responses and resistance to ibrutinib in Waldenström macroglobulinemia (WM), we conducted a prospective phase 2 trial of ibrutinib monotherapy in treatment-naïve patients. A total of 74 sequential bone marrow (BM) aspirates from 17 patients, collected from baseline through 48 treatment cycles, were profiled using single-cell multiomics. BM cells were segregated primarily into B-cell/plasma cell and T-cell compartments. Longitudinal clonal tracking of malignant B cells/plasma cells identified 3 distinct evolutionary patterns: evolution (early clone contraction with late clone expansion and increasing genomic complexity), devolution (early clone expansion with late clone contraction and genomic simplification), and no evolution (stable clonal architecture). The evolution pattern was strongly associated with disease progression, whereas devolution correlated with durable clinical response. Transcriptomic profiling of resistant clones enabled development and validation of the Waldenström ibrutinib prediction (WIP) score, which predicted treatment response at baseline. Within the WIP signature, LYN emerged as a key regulator; LYN knockdown or inhibition significantly increased WM cell sensitivity to ibrutinib, suggesting a rational combination strategy. In parallel, GZMB+ CD8+ effector-memory T cells expanded after treatment in patients with progressive disease and coexisted with tumor evolution. These cells exhibited persistently impaired cytotoxic programs (eg, GNLY), a dedifferentiated memory-like state, elevated PDCD1 expression, and reduced T-cell receptor diversity. Together, this study provides, to our knowledge, the first single-cell framework of tumor clonal evolution and T-cell dysfunction under ibrutinib in WM, introduces the WIP score as a predictive biomarker for treatment response, and identifies actionable tumor-intrinsic and immune mechanisms driving resistance. This trial was registered at www.ClinicalTrials.gov as NCT02604511.
16 May 2026
Read appraisal →Computer methods and programs in biomedicine
Explainable machine learning framework for the molecular classification of triple negative breast cancer
BACKGROUND AND OBJECTIVE: The difference in molecular characteristics of Triple negative breast cancer (TNBC) aids in distinguishing between its four prominent subtypes- basal-like 1, basal-like 2, mesenchymal, and luminal androgen receptor. This study presents the first integrative framework that combines explainable AI with machine learning approaches to classify TNBC subtypes. Unlike conventional models, our approach offers interpretability while enabling biomarker prioritization by identifying key hub genes that drive subtype-specific predictions. METHODS: In the experiment 783 cases (BL1 (160), BL2 (75), M (151), LAR (106), non-TNBC (291) reported in Gene Expression Omnibus (GEO) and Genomic Data Commons (GDC) data portal were used for the analysis. The proposed framework comprises modules for the identification of gene signatures for the four-subtype followed by the classification model based on eight different machine learning algorithms. Random Forest classifier was found to be best model with 96 % testing accuracy, which was elected for Explainable framework using Shapley Additive Explanations. RESULTS: Explainable biomarker module could provide a set of 47 biomarkers which is relevant in distinguishing the four types on triple negative breast cancer. The biomarkers could have the potential to be considered for TNBC prognosis in clinical setting. CONCLUSION: Key findings highlight the hub genes CDC20, CDCA2, PIMREG, KIF2C, and CENPW, implicating pathways such as ubiquitin-proteasome signaling and microtubule dynamics. These insights pave the way for biomarker-driven therapies and precision medicine in triple negative breast cancer.
16 May 2026
Read appraisal →European journal of cancer (Oxford, England : 1990)
Integrating liquid biopsies and artificial intelligence for early cancer detection: A systematic review and meta-analysis
INTRODUCTION: The latest generation of liquid biopsies incorporates multi-omic features, including genomics, methylomics, and fragmentomics. Machine learning (ML) approaches have been proposed to synthesize these complex biological data for the development of diagnostic classifiers. This study aims to evaluate the integration of ML with circulating cell-free DNA (cfDNA) analysis for early cancer detection. METHODS: Medline, Embase, Cochrane, and Web of Science were searched in July 2025. Eligible studies combined ML and cfDNA features to distinguish cancer patients (stages I-III) from non-cancer controls. Summary diagnostic performance metrics and their 95% confidence intervals (CI) were calculated. RESULTS: The study included 109 articles permitting analyses for lung (n = 34), liver (n = 29), colorectal (n = 28), pancreatic (n = 16), breast (n = 17), esophageal (n = 12), ovarian (n = 13), gastric (n = 9), head and neck (n = 4), and mixed (n = 27) cancer types. Specificity was consistently high across all tumor types and stages (94%-99%). Sensitivity ranged from 72% to 92% for stage I-III, 44-91% for stage I, 71-98% for stage II and 83-99% for stage III. In the pooled study population, neural networks (90%, 95% CI: 81%-95%), random forest (86%, 95% CI: 77%-92%) and heterogeneous ensemble learning (85%, 95% CI: 79%-89%) demonstrated the highest sensitivity. The stratified analysis by classifier feature revealed 86% (95% CI: 80%-90%) sensitivity for fragmentation and 81% (95% CI: 76%-85%) for methylation, with 92%-96% specificity. CONCLUSION: ML and cfDNA profiling show potential for early cancer detection, with ensemble methods, neural networks and random forests achieving the best overall performance. Fragmentomic features provide the highest sensitivity.
16 May 2026
Read appraisal →Computers in biology and medicine
Imaging and machine learning reveal pigment ring spatial characteristics in vitiligo progression
BACKGROUND: Vitiligo is a chronic autoimmune disorder causing skin depigmentation due to melanocyte loss, with pigment ring dynamics being key to understanding and managing the disease. METHODS: Data from 105 vitiligo patients were collected using reflectance confocal microscopy (RCM) imaging to analyze pigment ring patterns across progressive and stable stages. A multi-task self-supervised learning framework was used to identify and classify pigment ring types (complete, depressed, incomplete, and absent). Graph-based structural analysis was applied to characterize the spatial and network dynamics of pigment rings, incorporating metrics such as clustering coefficients, centrality measures, and Ripley's statistics. RESULTS: Progressive-stage patients exhibited denser clustering and spatial propagation of absent and depressed pigment rings, which played dominant roles in the network. Stable-stage patients showed higher clustering coefficients for complete rings, indicating restored structural stability. The learning framework demonstrated high accuracy in identifying pigment ring types, with an AUC of 0.99 and PR score of 0.95. Ripley's K-function analysis highlighted significant clustering of absent and depressed rings in the progression stage, correlating with active disease. CONCLUSION: Integrating imaging, machine learning, and graph-based analysis offers key insights into vitiligo progression, enabling better staging and personalized treatments, with future research needed for broader validation and model refinement.
16 May 2026
Read appraisal →PloS one
Analyzing the performance of deep learning splice prediction algorithms
SpliceAI is the leading tool for predicting splice-altering variants, but restrictive licensing limits clinical adoption. While open-source implementations have been published with author-reported comparisons, independent benchmarking across diverse datasets is needed to establish equivalence. We compared the original SpliceAI with two open-source implementations (OpenSpliceAI and CI-SpliceAI) and a legacy ensemble baseline across six datasets: a curated set of 1,316 validated variants, 213 variants with splice-assay data, 99,601 variants from the SPiP splicing prediction study, 242 manually curated deep intronic pathogenic variants, and two ClinVar-derived datasets comprising 53,600 intronic variants and 58,064 variants spanning all genomic contexts. The deep learning models were also evaluated against an ensemble of four legacy splice-prediction tools. Across all datasets, the deep learning algorithms outperformed the legacy ensemble. All three deep learning algorithms showed similar performance on the larger datasets dominated by canonical splice site variants (balanced accuracies 0.889-0.977). On the deep intronic benchmark, the original SpliceAI achieved the highest balanced accuracy (0.940), outperforming both CI-SpliceAI (0.890) and OpenSpliceAI (0.841). Critically, optimal thresholds for deep intronic variants were an order of magnitude lower than standard recommendations, indicating that default thresholds would miss the majority of pathogenic deep intronic variants. A correlation analysis showed that CI-SpliceAI maintained balanced concordance across event types, whereas OpenSpliceAI showed stronger correlation for loss events than gain events. Both implementations showed high positional agreement with SpliceAI, with exact splice-site match rates exceeding 90% across event types. Together, these results demonstrate that both open-source reimplementations of SpliceAI successfully reproduce the predictive behavior of the original algorithm across multiple evaluation contexts, while consistently outperforming traditional splice prediction methods. However, performance diverges on deeply intronic variants, and standard score thresholds are poorly calibrated for this variant class regardless of algorithm choice.
15 May 2026
Read appraisal →JMIR mental health
Machine Learning for Comparative Antidepressant Selection in Major Depressive Disorder: Systematic Review
BACKGROUND: Major depressive disorder (MDD) affects approximately 1 in 6 adults during their lifetime, yet antidepressant selection relies predominantly on trial-and-error, with response rates of only 42% to 53%. While machine learning (ML) models have shown promise in predicting treatment outcomes, most focus on single treatments rather than comparative selection across therapeutic alternatives, limiting their clinical utility for the medication choice decisions that clinicians face in practice. OBJECTIVE: This systematic review evaluates ML approaches that examine 2 or more pharmacological interventions for predicting treatment outcomes in MDD, with a focus on their capacity to facilitate comparative treatment selection between medications or medication classes for individual patients. METHODS: Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, we searched PubMed, Scopus, and Web of Science for studies published from 2015 to 2025. We included studies involving adults with MDD that used ML models to predict treatment outcomes across 2 or more pharmacological treatments and reported medication-specific prediction outcomes. Risk of bias was assessed using PROBAST-AI (Prediction Model Risk of Bias Assessment Tool for Artificial Intelligence). We conducted a narrative synthesis organized by modeling strategies, data integration approaches, validation methodologies, and performance patterns. RESULTS: From 5370 initial records, 19 studies met the inclusion criteria, with dataset sample sizes ranging from 49 to 77,226 participants. Studies employed 3 distinct modeling strategies: drug-specific supervised models trained independently for each medication, subtype- or trajectory-based approaches using clustering methods to identify differential response patterns, and a unified differential prediction framework generating calibrated cross-treatment predictions. Performance varied substantially, with area under the curve values ranging from 0.59 to 0.95 and classification accuracies between 62% and 95.4%, though high performance was concentrated in studies with small samples, high-dimensional neurobiological features, and internal-only validation. Only 7 studies conducted external validation, which generally yielded more conservative performance estimates. Feature informativeness was more consistently associated with performance variation than algorithm complexity. Most studies did not formally distinguish between prognostic features predicting general outcomes and predictive features identifying differential medication responses, and none applied formal explainability techniques. CONCLUSIONS: ML for comparative antidepressant selection remains in an early stage of development. Only 1 study implemented a unified framework directly supporting patient-level treatment ranking. Key barriers to clinical translation include insufficient distinction between prognostic and predictive markers, limited cross-trial validation, near-absent calibration reporting, and absent explainability. Future research should prioritize unified comparative frameworks with calibrated predictions, rigorous external validation on diverse cohorts, explicit modeling of heterogeneous treatment effects, and integration of explainability into model development.
14 May 2026
Read appraisal →Heart (British Cardiac Society)
Individual hearts: computational models for improved management of cardiovascular disease
Cardiovascular disease remains a leading cause of morbidity and mortality worldwide, with conventional management often applying standardised approaches that struggle to address individual variability in increasingly complex patient populations. Computational models, both knowledge-driven and data-driven, have the potential to reshape cardiovascular medicine by offering innovative tools that integrate patient-specific information with physiological understanding or statistical inference to generate insights beyond conventional diagnostics. This review traces how computational modelling has evolved from theoretical research tools into clinical decision support systems that enable personalised cardiovascular care. We examine this evolution across three key domains: enhancing diagnostic accuracy through improved measurement techniques, deepening mechanistic insights into cardiovascular pathophysiology and enabling precision medicine through patient-specific simulations. The review covers the complementary strengths of data-driven approaches, which identify patterns in large clinical datasets, and knowledge-driven models, which simulate cardiovascular processes based on established biophysical principles. Applications range from artificial intelligence-guided measurements and model-informed diagnostics to digital twins that enable in silico testing of therapeutic interventions in the digital replicas of individual hearts. This review outlines the main types of cardiovascular modelling, highlighting their strengths, limitations and complementary potential through current clinical and research applications. We also discuss future directions, emphasising the need for interdisciplinary collaboration, pragmatic model design and integration of hybrid approaches. While progress is promising, challenges remain in validation, regulatory approval and clinical workflow integration. With continued development and thoughtful implementation, computational models hold the potential to enable more informed decision-making and advance truly personalised cardiovascular care.
14 May 2026
Read appraisal →Journal of chemical information and modeling
HLABrew for Human Leukocyte Antigen Class I-Presented Epitope Recognition and Mimotope Discovery
Accurate identification of human leukocyte antigen (HLA) class I-presented epitopes is essential for developing personalized vaccines and immunotherapies. Here, we present HLABrew, a unified deep learning framework for HLA class I epitope prediction and allele-specific mimotope design. By integrating the Transformer, variational autoencoder, and dual cross-attention, HLABrew achieves state-of-the-art performance with hierarchical and allele-aware representations. HLABrew accurately deconvolves multiallelic immunopeptidomics data to recover allele-specific binding motifs and expand epitope coverage. Leveraging its generative capacity, HLABrew further designs mimotopes guided by learned peptide-HLA binding preferences, with the potential to enhance antigen presentation and provide candidates for downstream immunogenicity evaluation.
13 May 2026
Read appraisal →Journal of chemical information and modeling
mDADGAN: Predicting miRNA-Drug Response Associations Using lncRNAs and a Diffusion-Based Generative Adversarial Network
MicroRNAs (miRNAs) are key regulators of anticancer drug response, including sensitivity and resistance. Accurate prediction of miRNA-drug response associations is important for understanding response mechanisms and guiding targeted therapy. Existing prediction methods are difficult to fully capture complex high-order biological interactions and are sensitive to data sparsity and class imbalance. In this paper, we present an miRNA-drug response association prediction method called mDADGAN by constructing a diffusion-based generative adversarial network. First, we curated a large-scale and biologically informative data set from four public data resources by aggregating functional associations to facilitate model training. Second, we built a miRNA-lncRNA-drug interaction network by integrating lncRNA into the miRNA-drug network to address data sparsity and employed heterogeneous graph convolution to extract latent features from the interactions among miRNAs, lncRNAs, and drugs. Third, we applied diffusion-based perturbation to denoise and enhance the robustness of feature representations. Finally, we performed cost-sensitive learning to optimize the objective function in an adversarial training process to address class imbalance. The experimental results on four data sets demonstrated that, compared with the existing six methods, mDADGAN achieved higher values for AUC, AUPR, ACC, Recall, and F1-score. The case study demonstrates that integrating lncRNA information effectively enhances miRNA-drug response association prediction. mDADGAN can not only accurately identify known associations in the data sets but also predict previously unreported candidate associations supported by published evidence. Overall, our method mDADGAN has the ability to identify potential miRNA-drug response associations and can provide guidance for future biological experiments to enhance experimental efficiency and reduce experimental costs.
13 May 2026
Read appraisal →Journal of chemical information and modeling
scFNSA: A Factorized Node-Set Attentive Framework for Single-Cell Multi-Omics Integration
Single-cell multi-omics technologies enable simultaneous interrogation of transcriptional and epigenomic states at single-cell resolution, providing powerful means to dissect cellular heterogeneity and regulatory mechanisms. However, effective integration of single-cell multi-omics data remains challenging due to extreme sparsity, high dimensionality, and cross-modal heterogeneity, which often lead to distorted similarity structures, information loss, and limited biological interpretability in existing methods. Here, we propose scFNSA, a factorized node-set attentive framework for integrative analysis of single-cell multi-omics data that explicitly decouples modality-specific feature learning from graph-based relational modeling. scFNSA first learns aligned low-dimensional representations for individual modalities through multi-view variational inference and subsequently models complex cellular dependencies via attention-guided graph learning with structured node masking. This design enables robust cross-modal structural alignment while effectively mitigating noise propagation and oversmoothing commonly encountered in deep graph neural networks. Across multiple single-cell multi-omics datasets, scFNSA consistently improves integrative representation quality and cell type resolution compared with state-of-the-art approaches. By decoupling feature extraction from relational inference, scFNSA provides a robust and interpretable framework for single-cell multi-omics integration, facilitating more accurate characterization of cellular states and underlying regulatory landscapes.
13 May 2026
Read appraisal →Journal of clinical oncology : official journal of the American Society of Clinical Oncology
Phase I Study of Mosperafenib, a Novel Paradox Breaker B-Raf Proto-Oncogene Serine/Threonine Kinase (BRAF) Inhibitor, in Patients With BRAF V600-Mutant Solid Tumors
PURPOSE: BRAF V600 mutations are tumor-agnostic oncogenic drivers whose targeted inhibition is challenged by therapeutic resistance. Mosperafenib is a novel paradox breaker and brain-penetrant BRAF inhibitor (BRAFi), tested in this study for safety, maximum tolerated dose (MTD), pharmacokinetics (PK), and preliminary clinical activity. PATIENTS AND METHODS: This phase Ia/b study was conducted in patients with advanced solid tumors harboring a BRAF V600 mutation (ISRCTN13713551). The modified continuous reassessment method guided dose escalation of mosperafenib, which was given orally up to 3,600 mg once daily in 28-day cycles. The primary objective was to estimate the MTD and/or recommended phase II dose(s). RESULTS: Eighty patients (60% BRAFi-exposed)-63 with colorectal cancer (CRC), 13 with melanoma, and 4 with other solid tumors-received ≥1 dose of mosperafenib as a single agent for a median of 3.7 months (range, 0.2-28.6). Two dose-limiting grade 3 toxicities of rash and rash maculopapular were reported. MTD was not reached. Grade 3 to 4 treatment-related adverse events (TRAEs) occurred in 13 patients (16.3%); no grade 5 TRAEs events were reported. Two patients (2.5%) discontinued study treatment due to TRAEs. There were no reports of palmar-plantar erythrodysesthesia or keratoacanthoma. Linear and time-independent PK was demonstrated across the tested dose range, achieving exposure levels with sustained PK-derived pERK inhibition ≥90%. An exposure-response relationship was observed. Overall response rate was 24.2%, including two complete responses and 14 partial responses. Median progression-free survival was 6.4 months in patients with CRC (200 mg once daily-1200 mg three times a day) and 3.5 months in patients with melanoma (200 mg once daily-800 mg twice a day). CONCLUSION: Mosperafenib demonstrated a favorable safety profile, sustained target inhibition, and early signs of clinically meaningful single-agent activity in BRAFi-naïve and BRAFi-exposed patients.
13 May 2026
Read appraisal →Physics in medicine and biology
A delta-based multi-omics model to predict adaptive radiotherapy benefit in patients with non-small cell lung cancer during carbon-ion radiotherapy
Objective.Patients with non-small cell lung cancer (NSCLC) treated with carbon-ion radiotherapy (CIRT) are potential candidates for adaptive radiotherapy (ART). However, ART is time- and resource-intensive. This study aimed to develop a decision-support tool to estimate ART demand before treatment.Approach.This retrospective study included 69 patients with NSCLC treated with CIRT. Baseline clinical characteristics, dose-volume histogram (DVH) parameters, and radiomic and dosiomic features from the plan-computed tomography (CT) (1-2 weeks before treatment) and confirm-CT (1-2 d before treatment) were collected, and relative change rates in features (ΔDVH, Δradiomics, and Δdosiomics) were calculated. Feature selection involved univariable testing, correlation analysis, least absolute shrinkage and selection operator regression, and stepwise regression with 1000 bootstrap resamples. A multivariable logistic regression model was constructed and validated using 200 iterations of five-fold cross-validation.Main results.ART was triggered in 32 (46.4%) patients. A five-feature delta-omic model (one ΔDVH, two Δradiomic, and two Δdosiomic features) achieved a validated median area under the curve of 0.897 (interquartile range, 0.833-0.950) with good calibration. At a high-sensitivity threshold (0.11), the model identified all ART candidates while potentially reducing the frequency of weekly-CT evaluations in 21.4% of patients; at the maximum-Youden threshold (0.41), the median accuracy reached 78.6%, with up to 50.0% classified as low ART demand.Significance.A delta-omic model predicting ART demand in patients with NSCLC receiving CIRT was developed. The model may help optimize resource allocation and streamline ART workflows, although prospective validation in larger cohorts is warranted before widespread clinical adoption.
13 May 2026
Read appraisal →The oncologist
Characterization and clinical management of adverse events following treatment with repotrectinib: a TRIDENT-1 analysis
BACKGROUND: Repotrectinib, a next-generation ROS1/TRK tyrosine kinase inhibitor, is approved for ROS1 fusion-positive non-small cell lung cancer and NTRK fusion-positive solid tumors. Its side effects and safety management strategies require further characterization. PATIENTS AND METHODS: The safety profile of repotrectinib (treatment-emergent/related adverse events [TEAEs/TRAEs]) was established in patients who initiated treatment at the recommended dose (160 mg daily [QD] for 14 days, then 160 mg twice daily [BID]) across all cohorts of the global, multicenter phase 1/2 TRIDENT-1 study. AE management strategies were outlined. RESULTS: In 472 patients, the most common TRAEs (dizziness [58%] and dysgeusia [50%]) were likely TRK inhibition-related. Median relative dose intensity was 90%; 14% (n = 66/472) of patients did not increase their initial QD dose to BID (mostly due to CNS AEs). Rates of dizziness (median onset, 7 days) were similar in patients with/without baseline brain metastases. Dose modifications downgraded severity or resolved dizziness in 78% of patients; 58% of patients had pharmacologic intervention without dose modification. Dizziness was downgraded/resolved in 62% (n = 120/195) of patients who did not receive dose modification or pharmacologic intervention. Treatment-related cognitive impairment and weight gain occurred in 19% and 12% of patients, respectively. Treatment-emergent withdrawal pain occurred in 14% of patients (median resolution time, 2.1 weeks). Dose interruption and reduction from TRAEs occurred in 39% and 38% of patients, respectively; 10% reported later re-escalation back to 160 mg BID. CONCLUSION: Many repotrectinib AEs, including neurological AEs secondary to TRK inhibition, were mitigated with appropriate management, including dose modification and/or pharmacologic intervention.
12 May 2026
Read appraisal →PloS one
DeepDRP: Dose-response predictions of drug pairs using deep learning based on data-driven feature representation and dose-response curve characteristics
Combination therapies have become a cornerstone of modern medicine, offering improved treatment outcomes and reduced side effects compared to monotherapies. However, the efficacy and safety of drug combinations depend heavily on the specific doses of each component, making the optimization of dosing regimens a crucial yet challenging task. Despite the importance of dose optimization, few computational methods address this challenge. Here, we propose DeepDRP, a novel approach that integrates two complementary models: the global model, which is trained using all available combinations, and the local model, which utilizes only samples with similar information to queries. The DeepDRP architecture comprises three main modules: the first module has three embedding networks to extract features from drugs, doses, and cell lines, and then predicts synergy using the fused knowledge. The second module constructs a graph using the input query and the set of similar retrieved training samples fed into a semi-supervised graph convolutional network to predict the synergy value. Finally, these two models are aggregated to have the final predicted value. To evaluate the proposed approach, it is applied to the NCI-ALMANAC dataset and O'Neil dataset. The obtained results denote that the proposed method achieves superior performance with respect to the other approaches.
11 May 2026
Read appraisal →Genome research
Incorporating valuable prior knowledge to improve deep learning prediction of genetic perturbation responses
Genetic perturbation response prediction plays a critical role in virtual cell research, yet the performance of current deep learning models still leaves room for improvement. In this study, we present a prior-guided response inference model (PRIM) that leverages a valuable priori knowledge of gene expression in control cells to model the effects of perturbations at the cellular level. This allows PRIM to predict the amount of change in gene expression after perturbation to better approximate the real situation. Compared with existing deep learning approaches, PRIM achieves superior performance across multiple data sets and notable advantages in predicting combinatorial perturbation responses. Moreover, it is more lightweight than current deep learning models and enables faster forward inference. Importantly, PRIM effectively captures nonadditive genetic interactions and shows the potential to uncover associations between combinatorial perturbations and new biologically meaningful phenotypes. These findings provide new insights into the application of deep learning for predicting cellular responses to genetic perturbations.
11 May 2026
Read appraisal →Analytical chemistry
FiLM-Enhanced Biologically Informed Neural Networks for Multiclass Omics Analysis and Biomarker Discovery
High-throughput proteomics enables detailed molecular phenotyping but poses challenges for predictive modeling and interpretation due to high dimensionality, sparsity, and nonlinear interactions. Biologically informed neural networks (BINNs) address these challenges by embedding pathway knowledge into network architectures, providing interpretable models of complex omics data. We present BINN-FiLM, which extends conventional BINNs by integrating feature-wise linear modulation, enabling task-specific scaling and shifting of pathway-level activations while preserving a fixed Reactome-based hierarchy. Unlike BINNs that share all pathway parameters across classes, BINN-FiLM captures class-dependent biological rewiring, making it particularly effective for multiclass classification tasks. Multiclass problems are reformulated as multitask binary learning, allowing pathway activations to adapt to disease-specific contexts. We evaluated BINN-FiLM on three multiclass proteomic data sets, and BINN-FiLM consistently outperformed conventional BINNs and standard machine learning models. FiLM modulation parameters revealed task-specific pathway activity, and SHAP-based interpretation identified key proteins and pathways driving disease discrimination.
11 May 2026
Read appraisal →Journal of medical Internet research
Rheumatic Digital Twin: Proposed Machine Learning-Based Multimodal Framework to Inform Clinical Decision-Making
Rheumatic diseases are chronic, immune-mediated conditions characterized by significant heterogeneity in presentation and disease course. However, current clinical approaches often rely on snapshot-based assessments that fail to capture the complex longitudinal evolution of these conditions. To address these limitations and support the implementation of precision medicine, we present the design for the Rheumatic Digital Twin, a novel, modular conceptual framework intended to integrate heterogeneous multimodal data, ranging from electronic health records and clinical notes to imaging and omics, into a dynamic, computational representation of the patient journey. Our theoretical architecture addresses challenges related to data silos and variable availability of data modalities through a multistage approach that envisions the use of domain-specific foundation models to independently process distinct data modalities. To effectively model the temporal progression inherent in chronic diseases, the proposed design utilizes Transformer architectures, leveraging self-attention mechanisms to treat patient events, such as lab results or medication changes, as sequential data tokens. We describe how these unimodal representations would subsequently be fused via joint embedding techniques to construct a shared, multimodal representational space. Envisioned to function analogously to a recommender system, the Rheumatic Digital Twin framework is modeled to map patients into a latent space where proximity reflects clinical and biological similarity. By identifying "nearest neighbors," historical patients with comparable trajectories, the system aims to enable in silico cohorting, theoretically allowing clinicians to forecast key clinical events, predict treatment responses, and identify likely disease courses based on the outcomes of similar peers.
11 May 2026
Read appraisal →Journal for immunotherapy of cancer
Phase II trial of combination radiation, hormone, and immunotherapy in grade group 5 prostate cancer
BACKGROUND: Grade group 5 (GG5) prostate cancer (PCa) carries a less favorable prognosis after standard-of-care (SOC) therapy, necessitating novel therapeutic approaches. High-dose rate brachytherapy (HDRBT) and androgen deprivation therapy (ADT) may modulate immune response in GG5 PCa, particularly in tumors with increased immune content. This study evaluated whether the addition of nivolumab to SOC was associated with improved disease control in patients with high-volume GG5 PCa, including those with oligometastatic disease. METHODS: In this non-randomized phase II trial, 31 patients with localized or oligometastatic GG5 PCa and >30% positive biopsy cores were evaluated between September 2018 and April 2021. Patients received four doses of nivolumab (240 mg every 2 weeks) beginning 4 weeks prior to HDRBT, alongside ADT, HDRBT, and external beam radiation. The primary endpoint was to evaluate whether the 2-year freedom from biochemical recurrence (FFBR) rate would exceed a prespecified historical control rate of 75%. RESULTS: Among the 31 patients, the median follow-up was 38.8 months (IQR 31.0-46.5 months). The addition of nivolumab to SOC RT with ADT was associated with a 2-year FFBR rate of 90.3% (95% CI 74.3% to 98.0%) (median FFBR not reached), exceeding the prespecified historical control rate of 75% (one-sided p value from binomial test=0.024). Definitive and probable nivolumab-related toxicity included 6.3% acute grade 2 and 6.3% acute grade 3 adverse events (AEs), with no grade 4+ AEs observed. A higher Decipher immunosuppression score at diagnosis correlated with early pathologic response (p=0.005) and was independently associated with time to metastatic failure (p=0.044). CONCLUSIONS: Nivolumab combined with SOC was associated with encouraging FFBR in this high-risk GG5 PCa population and may represent a promising therapeutic intensification strategy. The Decipher immunosuppression score may serve as a predictive biomarker for response. These findings warrant further investigation in randomized trials.
11 May 2026
Read appraisal →European journal of medicinal chemistry
AI-driven identification of a selective dual function inhibitor blocking HK2 activity and HK2-VDAC1 interaction displaying enhanced anticancer efficacy under hypoxia
Selective inhibition of hexokinase 2 (HK2) represents a promising therapeutic strategy due to the pivotal role of HK2 in the Warburg effect, enhancement of glycolysis and anti-apoptosis via HK2-Voltage-Dependent Anion Channel 1 (VDAC1) protein-protein interaction. Moreover, HK2 initiates glycolysis to generate lactate, hence this central enzyme can be pharmacologically targeted to enhance therapy outcomes. Currently, no HK2 inhibitors (HK2is) exist in the clinic. Herein, we employed GCVec, an artificial intelligence (AI)-based compound-protein interaction (CPI) prediction tool, along with molecular docking, to identify the HK2i, 106. This compound exhibited an IC50 of 0.79 ± 0.07 μM and a consistent Kd of 0.41 ± 0.03 μM against HK2 enzyme. It also apparently blocked HK2-VDAC1 interaction as indicated by the disrupted colocalization of HK2-GFP and VDAC1-mCherry. Furthermore, 106 demonstrated enhanced anticancer efficacy under hypoxia in tumor cells with elevated HIF-1α/HK2 and VDAC1 levels. Compound 106 selectively targeted SW480 colorectal cancer cells with high HK2 expression, achieving a growth inhibition IC50 value of 5.00 ± 0.94 μM. Consistently, knockout of HK2 in these tumor cells significantly rescued the IC50 values and eliminated the glycolytic inhibition induced by 106. We further showed that 106 reduced lactate and ATP levels and induced markers of apoptosis, including increased p-AMPK/AMPK ratio and increased Bax levels, as well as decreased Bcl2 levels. Collectively, our findings highlight the potential of GCVec in identifying 106, a first in class dual-function HK2i which emerges as a promising lead compound for further development into a possible anticancer therapeutic agent.
11 May 2026
Read appraisal →Briefings in bioinformatics
Comprehensive evaluation of artificial intelligence-empowered approaches for protein-aptamer complex prediction
Drug discovery is a time-consuming, expensive, and high-risk process. Recent advances in artificial intelligence (AI) have enabled major breakthroughs in small-molecule and protein therapeutics. However, AI-driven design of aptamer drugs remains largely unexplored. Aptamers are short (15-100 nt) single-stranded DNAs or RNAs that exhibit high binding affinity, high specificity, and low immunogenicity, making them promising candidates for disease (such as cancer) therapeutics. Compared with protein-ligand or protein-protein systems, protein-aptamer complexes are under-represented in public structural databases, and aptamers themselves are highly flexible and relatively large molecules. These characteristics present distinct challenges for AI-based structural modeling. Here, we systematically evaluate recent AI frameworks, including AlphaFold3, Chai-1, Boltz-2, and RoseTTAFold2NA, along with a template-based approach, in predicting protein-aptamer complex structures and estimating binding free energies. We establish an independent benchmark to assess their performance in structural accuracy, stability, and energetic consistency. This study provides a foundation for the application of AI in aptamer drug design and offers a reference framework for future research in nucleic-acid therapeutics and biomolecular modeling.
10 May 2026
Read appraisal →Briefings in bioinformatics
MLN2SVG: domain-aware spatially variable gene detection using contrastive variational autoencoder and multi-level neighbor search
Spatial transcriptomics (ST) technologies have transformed our ability to examine gene expression within intact tissues, yet accurately identifying spatially variable genes (SVGs) remains challenging due to spatial heterogeneity, data sparsity, and incomplete modeling of domain-level dependencies. To address these limitations, we propose MLN2SVG, a domain-aware framework that integrates contrastive variational autoencoding with a multi-level neighbor (MLN) search algorithm to jointly learn tissue domains and SVGs. MLN2SVG constructs a weighted spatial graph to capture both local and long-range spatial relationships, employing a deep contrastive variational autoencoder to align augmented and original data representations while preserving biological diversity. The MLN algorithm dynamically expands neighborhood connectivity to mitigate sparsity and enhance domain coherence. Across multiple human and mouse ST datasets, including dorsolateral prefrontal cortex, breast cancer, and brain tissues, MLN2SVG consistently outperformed existing methods in clustering accuracy, robustness, and biological interpretability. Notably, in breast cancer tissues, MLN2SVG uncovers fine-grained spatial organization of tertiary lymphoid structures, delineating region-specific immune architectures spanning intratumoral, tumor-edge, and extratumoral compartments. Through the integration of spatial domain discovery and SVG detection, MLN2SVG delivers a robust and biologically interpretable framework for uncovering the molecular and structural complexity of tissue organization.
10 May 2026
Read appraisal →European journal of cancer (Oxford, England : 1990)
MuTriM: A multiscale deep learning model integrating longitudinal radiomics and pathomic features for predicting recurrence and adjuvant radiation benefit in breast cancer.
PURPOSE: We present MuTriM, a multimodal deep learning model integrating DCE-MRI and whole-slide pathology to predict survival and radiation benefit in breast cancer. PATIENTS AND METHODS: MuTriM employs an attention-based cross-modal and cross-temporal fusion framework that concurrently integrates DCE-MRI radiomic features with pathomic features of cellular morphology on WSI. MuTriM was trained on the Fudan University Shanghai Cancer Center (FUSCC) cohort (N = 335) and externally tested on the TCGA cohort (N = 126) using matched DCE-MRI and WSI. RESULTS: MuTriM was prognostic of recurrence-free survival (RFS) in a subtype-agnostic setting (HR = 5.26, 95% CI, 1.69-16.4, p = 0.004; C-index = 0.75), outperforming unimodal models based on DCE-MRI alone (C-index = 0.65) or WSI alone (C-index = 0.70). MuTriM was also prognostic among HER2 + (HR = 6.82, 95% CI, 1.08-43.2, p = 0.04) and ER+ populations (HR = 4.61, 95% CI, 1.25-17.1, p = 0.02). A high MuTriM score was associated with improved RFS (HR = 0.15, 95% CI 0.03-0.87; P = 0.03), whereas a low MuTriM score showed no significant benefit (HR = 4.06, 95% CI 0.05-31; P = 0.53) (interaction P = 0.04). Transcriptomic analyses revealed that high-risk tumors showed suppressed cytotoxic T-cell activity and enrichment of extracellular matrix remodeling, neutrophil degranulation, and neuronal signaling, consistent with immune evasion. Upregulation of NRXN1, GABRA3, KCNK3, and KLK12 was linked to worse survival, whereas SYNGR3 and CD207 were associated with favorable outcomes. CONCLUSION: By unifying radiology, pathology, and transcriptomics, MuTriM provides an interpretable multimodal framework for breast cancer prognosis and treatment guidance.
10 May 2026
Read appraisal →Pancreas
Whole Metagenomic Profiling Identifies a Gut Microbial Signature for Chronic Pancreatitis via Machine Learning
BACKGROUND: Pancreatitis significantly alters the microbial composition of the oral and intestinal compartments, causing dysbiosis that may contribute to disease mechanisms and potentially serve as a basis for diagnosis or treatment. OBJECTIVE: To determine whether the oral or gut microbial signature can classify chronic pancreatitis (CP). METHODS: Stool samples (n=707) were collected from participants in the Prospective Evaluation of Chronic Pancreatitis for Epidemiologic and Translational Studies (PROCEED). Samples were distributed among 200 healthy (HC), 310 CP, 49 acute pancreatitis (AP), and 148 recurrent acute pancreatitis (RAP). In addition, saliva samples were collected for a subset of participants (n=156). Whole genome sequencing was performed to assess microbiome composition. Machine learning algorithms were utilized to identify a signature with microbial features predictive of CP. RESULTS: Gut alpha diversity was significantly decreased in AP, RAP, and CP compared with HC, with CP exhibiting the lowest diversity. In contrast, oral microbial diversity showed no significant variation across groups. Beta diversity analysis revealed distinct gut microbiome compositions between HC and pancreatitis subtypes, with CP showing the most pronounced differences. Random forest models using gut microbial species demonstrated robust predictive performance for CP using a minimum of 10 species (Area under the curve-AUC: 0.834; accuracy: 0.774). Despite similarities in gut microbiome composition across pancreatitis subtypes, a unique gut microbial signature for CP was identified highlighting the microbiome's potential in CP diagnosis. CONCLUSION: Our study reveals a gut microbial signature predictive of CP using machine learning models in a large US multi-institutional cohort.
6 May 2026
Read appraisal →Cell
Deep-learning-based de novo discovery and design of therapeutics that reverse disease-associated transcriptional phenotypes
Identifying drugs that reverse disease-associated transcriptomic features has been widely explored for drug repurposing, but its potential for de novo drug discovery remains underexplored. Here, we present gene expression profile predictor on chemical structures (GPS), a deep-learning-based drug discovery platform, guided by transcriptomic features, that screens large compound libraries and optimizes lead molecules. We first develop a model that captures transcriptomic perturbation signatures solely from chemical structures and deploy it to library compounds. We refine scoring methods and employ a tree-search method for optimization. By incorporating structure-gene-activity relationships, we uncover drug mechanisms from transcriptomic data. We evaluate GPS across multiple diseases and conduct extensive validation in two cases. In hepatocellular carcinoma, we discover two unique compound series with favorable cellular selectivity and in vivo efficacy. In idiopathic pulmonary fibrosis, we identify one repurposing candidate and one novel anti-fibrotic compound by reversing gene expression of multiple distinct cell types derived from single-cell transcriptomics.
5 May 2026
Read appraisal →Cancer medicine
Predicting Prognosis for Gastric Cancer Patients Receiving Neoadjuvant Treatment With Body Composition-Based Deep Learning
BACKGROUND: This study sought to develop an innovative body composition (BC)-based deep learning (DL) model to precisely evaluate survival in gastric cancer (GC) patients undergoing neoadjuvant treatment (NT). MATERIALS AND METHODS: This retrospective study included GC patients undergoing NT from two centers. CT images both pre-NT and post-NT were preprocessed, focusing on the automatic segmentation of subcutaneous fat, visceral fat, and skeletal muscle regions using TotalSegmentator. Delta Radiomics features were extracted using Pyradiomics. After feature fusion and selection, the optimal model is Naive Bayes (Rad model). A hybrid DL model was developed by combining ResNet18 and Transformer networks for feature extraction. The Clinic_Rad_DL model was constructed by combining clinical features, radiomic signatures, and DL signatures. The ExtraTree classifier was used for the Clinic_Rad_DL model, while a separate Cox regression model was developed for survival analysis using the same features. RESULTS: A total of 356 patients (mean age, 59 ± 10 years; 264 males [74.2%]) were enrolled and divided into training, validation, and test sets in a 7:2:1 ratio. The DL model outperformed the Rad model. The Clinic_Rad_DL model outperformed both Rad model and DL model, with AUC of 0.915, 0.890, and 0.890 in training, validation, and test sets, respectively. The Cox proportional hazards model showed C-index of 0.806, 0.803, and 0.819, effectively stratifying patients into high- and low-risk groups with significant survival differences. CONCLUSION: The study developed and validated a BC-based DL model to predict survival in GC patients undergoing NT, offering potential for personalized treatment strategies in clinical practice.
5 May 2026
Read appraisal →Medical image analysis
PH2ST: Prompt-guided hypergraph learning for spatial transcriptomics prediction in whole slide images
Spatial Transcriptomics (ST) reveals the spatial distribution of gene expression in tissues, offering critical insights into biological processes and disease mechanisms. However, the high cost, limited coverage, and technical complexity of current ST technologies restrict their widespread use in clinical and research settings, making obtaining high-resolution transcriptomic profiles across large tissue areas challenging. Predicting ST from H&E-stained histology images has emerged as a promising alternative to address these limitations but remains challenging due to the heterogeneous relationship between histomorphology and gene expression, which is affected by substantial variability across patients and tissue sections. In response, we propose PH2ST, a prompt-guided hypergraph learning framework, which leverages limited ST signals to guide multi-scale histological representation learning for accurate and robust spatial gene expression prediction. Extensive evaluations on two public ST datasets and multiple prompt sampling strategies simulating real-world scenarios demonstrate that PH2ST not only outperforms existing state-of-the-art methods, but also shows strong potential for practical applications such as imputing missing spots, ST super-resolution, and local-to-global prediction, highlighting its value for scalable and cost-effective spatial gene expression mapping in biomedical contexts.
5 May 2026
Read appraisal →Journal of psychiatric research
Predicting treatment response in psychosis using fMRI: A comprehensive review
In recent years, the use of functional Magnetic Resonance Imaging (fMRI) methods to predict treatment response in schizophrenia (SCZ) through statistical and machine learning (ML) algorithms has increased. We conducted a comprehensive literature review to assess the role of various fMRI measures in predicting pharmacological treatment response in psychosis. Literature available on PubMed from January 1990 to December 2023 was reviewed, and 21 fMRI studies were included. The results suggest that many studies have employed ML techniques, which may enhance the accuracy of treatment outcome predictions. Additionally, several studies utilizing resting-state fMRI have identified potential associations of functional connectivity patterns across multiple large-scale networks, including the default mode network (DMN), the salience network (SN), the central executive network (CEN), and sensory-motor circuits. These findings suggest that altered connectivity within and between these networks may be relevant for personalized treatment strategies in patients with psychosis, although further investigation is needed to confirm their predictive value. Future research should focus on developing robust and generalizable models to more reliably optimize treatment outcomes in psychosis.
5 May 2026
Read appraisal →Annals of surgical oncology
Computed Tomography-Pathology Deep Learning Model for the Precise Prediction of Recurrence in Pathological Stage IA Lung Adenocarcinoma
BACKGROUND: The postoperative prognosis of pathological stage IA lung adenocarcinoma (LUAD) exhibits significant heterogeneity. While the tumor node metastasis (TNM) staging system offers limited recurrence prediction capability, this study aims to develop a precise deep learning model for prognostic stratification. PATIENTS AND METHODS: We retrospectively analyzed a consecutive cohort of patients with pathological stage IA LUAD who underwent surgical resection at Zhongshan Hospital Fudan University. Our novel ResNet 3D-Pathology Fusion (Res3D-PF) model-integrating a three-dimensional ResNet backbone with an image-pathology fusion module-was developed to predict recurrence-free survival (RFS) using preoperative computed tomography (CT) images and International Association for the Study of Lung Cancer (IASLC) grading. Model performance was evaluated through receiver operating characteristic curve analysis, with independent RFS predictors identified via multivariable Cox regression. RESULTS: Among 551 patients with stage IA LUAD (median age 61 years; 339 women) divided into training (n = 368) and validation (n = 183) sets, the CT-pathology fusion model achieved superior predictive performance. In the validation cohort, Res3D-PF significantly outperformed the 8th T-stage (AUC 0.837 vs. 0.660, p = 0.001) and IASLC grade (AUC 0.837 vs. 0.684, p = 0.015) for 5-year RFS prediction. Multivariable analysis confirmed Res3D-PF as an independent prognostic factor (HR 15.772, 95% CI 3.384-73.508; p < 0.001). Model-stratified high-risk patients demonstrated significantly reduced 5-year RFS (73.1% vs. low-risk 98.5%, p < 0.001) and shorter median RFS (74.4 vs. 96.2 months, p < 0.001). CONCLUSIONS: We developed and validated a CT-pathology deep learning model that outperforms conventional TNM staging and IASLC grading for predicting postoperative recurrence in stage IA LUAD. This approach enables individualized risk stratification to guide precision treatment strategies.
4 May 2026
Read appraisal →Radiology. Artificial intelligence
Radiopathomic Graph Deep Learning for Multiscale Spatial-Contextual Modeling of Intratumoral Heterogeneity to Predict Breast Cancer Response to Neoadjuvant Therapy
Purpose To develop an explainable radiopathomic graph deep learning (RPGDL) system for multiscale spatial-contextual modeling of intratumoral heterogeneity and evaluate its performance for the prediction of pathologic complete response (pCR) to neoadjuvant therapy in breast cancer. Materials and Methods The RPGDL system was developed from dual-center retrospective analysis of patients with biopsy-proven invasive breast cancer (May 2018-August 2024). For each tumor, individual radiomic and pathomic graphs were generated from pretherapeutic MRI and hematoxylin-eosin-stained biopsy slide images, respectively. These graphs were then processed by three distinct graph neural networks (GNNs): radiomic, pathomic, and radiopathomic. GNN performance was assessed with the area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), and integrated discrimination improvement (IDI). A multifaceted approach was used to explain the GNNs' predictions. Results The training set included 582 (mean age, 52 years ± 9 [SD]) patients and the external test set 468 (50 years ± 10) patients from centers 1 and 2, respectively. The radiomic GNN achieved AUCs of 0.89 (95% CI: 0.85, 0.93) in the training set and 0.84 (95% CI: 0.80, 0.89) in the external test set; the pathomic GNN achieved AUCs of 0.87 (95% CI: 0.83, 0.91) in the training set and 0.83 (95% CI: 0.78, 0.88) in the external test set, with no significant difference between them (P > .05). The radiopathomic GNN outperformed both single-modality GNNs (training set: AUC, 0.95 [95% CI: 0.92, 0.98]; external test set: AUC, 0.91 [95% CI: 0.87, 0.94]; P < .05; NRI and IDI confirmed). Pathomic graphs dominated probability increases for pCR predictions, while radiomic graphs drove probability decreases for non-pCR predictions. Multifaceted analyses verified GNNs' explainability. Conclusion The developed RPGDL system enabled multiscale spatial-contextual intratumoral heterogeneity modeling for high-performance, explainable prediction of pCR to neoadjuvant therapy in breast cancer. Keywords: Dynamic Contrast-enhanced MRI, Breast, Tumor Response, Radiology-Pathology Integration, Prognosis, Principal Component Analysis, Perception, Supervised Learning, Reconstruction Algorithm Supplemental material is available for this article. © RSNA, 2026.
4 May 2026
Read appraisal →Psychiatry research
A machine learning approach to predicting clinical trajectories in bipolar disorder
BACKGROUND: Bipolar disorder (BD) is characterized by significant heterogeneity in clinical presentation, age of onset, and diagnostic delays. Identifying clinical trajectories and subtypes is a central aim of precision psychiatry, with the goal of improving risk stratification and characterization of illness courses, enabling early recognition of high-risk patients and facilitating timely interventions that improve long-term outcomes. METHODS: This is a dual-site retrospective cross-sectional secondary analysis of 203 clinical datasets from BD patients to develop machine learning models: Random Forest, Weighted Logistic Regression (LR), and XGBoost, supplemented by statistical modelling, to predict age of onset timing (early/late onset) and illness severity. Survival analysis (Kaplan-Meier and Cox proportional hazards) investigated factors influencing diagnostic delay, while clustering identified patient subtypes. RESULTS: Single-split Weighted LR (AUC = 0.733) and nested cross-validation XGBoost (AUC = 0.729) achieved superior performance in predicting onset timing. Cluster analysis identified three distinct phenotypes: baseline low complexity, late-onset familial-severe, and an early-onset comorbid group. Survival analysis revealed that the time to diagnosis was independent of clinical risk profiles (Log-Rank p = 0.34), with the most severe cases experiencing significant diagnostic latency. CONCLUSIONS: Machine learning accurately predicts BD clinical trajectories using routinely collected data in an African cohort. Diagnostic delay did not differ significantly across clinical risk or severity strata, indicating that the measured variables did not explain variation in time to diagnosis.
4 May 2026
Read appraisal →Nano letters
Seeing and Feeling DNA Methylation: Single-Molecule Biophysics Meets Machine Learning
DNA methylation at 5-methylcytosine (5mC) is crucial for embryonic development and cellular function, while aberrant patterns strongly drive disease onset and progression. Its reversible nature offers substantial therapeutic potential, emphasizing the need for precise, context-specific genome wide 5mC mapping. Conventional techniques such as bisulfite sequencing and ensemble biosensor assays are hindered by DNA degradation, amplification bias, high cost, and inability to resolve single-molecule structural and mechanical effects of methylation. This review examines advances in single-molecule biophysical methods (nanopore sensing, smFRET, optical/magnetic tweezers, and AFM) that provide direct, label-free/minimally invasive 5mC detection, along with quantitative insights into DNA conformation, mechanics, and protein-DNA interactions. These techniques complement traditional methylome mapping by linking genomic localization to molecular mechanisms. Emerging machine-learning approaches are revolutionizing analysis, particularly in nanopore sensing, while promising applications in smFRET, tweezers, and AFM address throughput and reproducibility challenges. Their convergence promises scalable, high-resolution epigenetic profiling, advancing precision epigenomics toward clinical application.
4 May 2026
Read appraisal →European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology
Machine learning identifies a 10-gene signature predicting hepatocellular carcinoma recurrence and immune-metabolic reprogramming
BACKGROUND: Hepatocellular carcinoma (HCC) remains a major cause of cancer-related mortality, with frequent recurrence after curative treatment. Conventional clinicopathological prognostic systems fail to capture the molecular heterogeneity underlying recurrence, highlighting the need for biologically informed biomarkers. METHODS: We developed a transcriptome-based prognostic model for HCC recurrence using a machine learning-guided feature selection strategy designed to reduce survival-time bias. LASSO-based gene selection was integrated with multivariable Cox regression, and model performance was assessed through stratified cross-validation and independent external validation. RESULTS: Analysis of the TCGA-LIHC cohort (n = 344) identified a stable 38-gene recurrence-associated signature (AUC: 0.715-0.847), which was distilled into a reproducible 10-gene classifier combined with tumor stage. This integrated model effectively stratified patients into high- and low-risk groups (log-rank P < 0.0001) and was independently validated in the HCCDB25 cohort (n = 158; P = 0.031). High-risk tumors exhibited an immune-excluded phenotype with reduced cytotoxic immune infiltration. Gene set enrichment analyses revealed progressive activation of proliferative signaling, metabolic dysregulation, and immune evasion pathways. CONCLUSIONS: The integrated 10-gene-plus-stage classifier is a robust and generalizable predictor of HCC recurrence, providing mechanistic insights into immune-metabolic reprogramming and highlighting potential implications for risk-informed patient stratification in future studies.
4 May 2026
Read appraisal →Physics in medicine and biology
FLIP-HEDOS: a patient-specific blood dose quantification model during radiotherapy treatments
Objective.To introduce FLIP-HEDOS, a blood dose modeling framework that combines patient-specific and generic circulatory data to enable individualized blood dose estimation during radiotherapy (RT) treatments and to overcome limitations of non-personalized approaches.Approach.Patient-specific images of vasculature were obtained from patients with thorax-abdomen or head-neck tumors treated with proton or photon RT. Large vessels from the tumor location were segmented, and their blood flow velocities were extracted from phase-contrast MRI. Movement of blood particles (BPs) was simulated using a Lagrangian approach along patient-specific flowlines in these vessels, forming the FLIP method. This circulation was incorporated into a standardized model (HEDOS) to form a closed-loop whole-body model that computes the spatiotemporal BP distribution and associated blood dose accumulation, accounting for dose delivery dynamics, dose rate and beam-on/beam-off times. Cardiac output (CO) was individualized to match each patient blood flow characteristics. FLIP-HEDOS retains the modular HEDOS architecture, extending its large vessel compartments with the FLIP approach patient-specific vessels represented as new compartments. Remaining compartments were adapted to preserve the standardized connectivity of the circulatory network.Main Results.The study quantified mean blood dose values and tracked the number of times BPs entered patient-specific compartments during dose delivery. Simulations were performed across a range of inter-beam intervals, and the three models FLIP (patient-specific vessels), HEDOS (generic whole-body), and FLIP-HEDOS (integrated model) were compared with respect to their resulting blood dose values. The comparison shows that when patient-specific information is incorporated in blood dose assessment, BPs experience higher radiation doses.Significance.FLIP-HEDOS proves that standardized vascular data can be effectively combined with patient-specific parameters to achieve physiologically realistic modeling of circulating blood. By enabling individualized CO and blood flow dynamics, the framework adapts to the anatomical and hemodynamic characteristics of each patient.
3 May 2026
Read appraisal →Journal of chemical information and modeling
TriPDCL: A Tri-Pathway Prototype-Driven Contrastive Learning Framework for Cross-Modality Single-Cell Integration
The rapid development of single-cell sequencing technologies has laid a solid foundation for multiomics data integration. A central objective in multiomics integration is to attenuate cross-omic discrepancies stemming from technical batch effects and inherent biological variability, thereby facilitating a unified latent representation that supports robust downstream analyses. However, the intrinsic high sparsity of single-cell data and pronounced intercellular heterogeneity pose greater challenges for joint analysis. We foreground cellular heterogeneity and present TriPDCL, a prototype-based contrastive learning framework, which not only achieves effective transfer of heterogeneity information through an iterative prototype-learning update mechanism but also, by leveraging learnable prototype centers, enables precise construction of reliable positive-negative sample pairs. It tackles two principal challenges, the alignment of cross-modal heterogeneity and the robust learning, in multiomics analysis. Subsequently, comparative assessments conducted on five data sets in contrast to seven representative methods illustrate the superiority of the proposed approach.
2 May 2026
Read appraisal →ACS sensors
Nanobiosensors and Artificial Intelligence Strategies for Glycan Profiling in Cancer Progression: A Critical Review
Glycans are complex carbohydrates that are integral to cancer progression and tumor biology. Conventional methods face challenges due to the structural diversity and low abundance of glycans, limiting the detection of cancer-associated glycan signatures. This bottleneck hampers the accurate monitoring of cancer progression and the development of effective diagnostic tools. Nanobiosensor-enabled glycan profiling overcomes conventional limitations by providing highly sensitive detection of low-abundance glycans and precise discrimination of similar forms through nanoscale electrochemical or optical signal amplification and selective biorecognition. This review evaluates emerging nanobiosensors, including optical modalities such as surface plasmon resonance, localized surface plasmon resonance, surface-enhanced Raman scattering, fluorescence, and colorimetric nanobiosensors. It also covers electrochemical systems, including impedimetric, voltammetric, and amperometric sensors that use nanomaterials to enhance the sensitivity, specificity, and reliability of glycan detection. After a critical evaluation of nanobiosensors, this review highlights their applications for glycan analysis in cancer progression and potential of miniaturized point-of-care platforms. In parallel, this review highlights emerging artificial intelligence (AI) and machine learning (ML) approaches that are being explored to analyse complex biosensor outputs. By enabling multivariate pattern recognition, dimensionality reduction, and nonlinear modeling of biosensor responses, these computational frameworks may facilitate the extraction of diagnostically relevant signatures from high-dimensional optical and electrochemical datasets. The review identifies challenges in standardization and clinical scalability of nanobiosensors and explores future directions, including AI integration to advance early cancer detection and personalized patient management.
27 Apr 2026
Read appraisal →Lab on a chip
MaGIC-OT: an AI-guided optical tweezers platform for autonomous single-cell isolation in microfluidic devices
Automating the isolation of rare cells such as circulating tumour cells (CTCs) within crowded microfluidic environments remains a bottleneck in liquid biopsy workflows. Optical tweezers offer contact-free, selective manipulation but traditionally rely on expert operators. We present MaGIC-OT (machine-guided isolation of cells using optical tweezers), a platform that integrates classical path planning and deep reinforcement learning (DRL) to automate single-cell manipulation inside a microfluidic chip. We built a high-fidelity simulation to train and benchmark control policies and show that cooperative, human-in-the-loop training improves DRL performance. Trained agents outperform expert users in speed and isolation success in silico, and we demonstrate proof-of-concept isolation of a cancer cell from a spiked blood sample on-chip. MaGIC-OT provides a flexible framework for intelligent optical manipulation, aligning microfluidic device design with autonomous control strategies and offering a pathway toward high-purity, label-free single-cell workflows.
26 Apr 2026
Read appraisal →The pharmacogenomics journal
A randomized trial to evaluate attitudes regarding pharmacogenomics among pregnant and pediatric populations: design and baseline characteristics.
Pharmacogenomics (PGx) is a key component of precision medicine, yet most PGx studies exclude pregnant people and children. The VICE (Vanderbilt Integrated Center of Excellence)-MPRINT (Maternal and Pediatric Precision in Therapeutics): Maternal and Pediatric Pharmacogenetics Trial is a single-center, randomized control trial to assess how PGx testing and return of results influence patients' understanding and perceived utility of PGx testing in a pregnancy and pediatric cohort. Pregnant individuals and families or guardians of children with a chronic health condition aged 0-16 were recruited. We assessed participants' knowledge and attitudes regarding PGx testing at baseline and after receiving results with patient-friendly interpretations. Cases received an educational video about PGx testing with return of results. Controls received PGx test results alone. We aimed to determine perspectives regarding PGx in these understudied populations with the goal of promoting research and clinical implementation of PGx for pregnant women and children.
26 Apr 2026
Read appraisal →Cell reports methods
A high-speed attention network for MHC-bound peptide identification and 3D modeling
We developed SwiftMHC, an ultra-fast and accurate structure-based framework for peptide-MHC (pMHC) modeling and binding affinity prediction. Using task-specific deep learning trained on physics-derived synthetic data, SwiftMHC predicts pMHC binding affinities in 0.009 s per case on a single A100 GPU when running in batch mode, offering improved speed compared with leading sequence-based tools such as netMHCpan and MHCflurry while maintaining competitive accuracy. In addition, SwiftMHC generates all-atom 3D pMHC structures with a median Cα-RMSD of 1.32 Å against crystallographic benchmarks, matching or exceeding state-of-the-art methods such as AlphaFold2-finetune but at a lower computational cost. Optimized for HLA-A∗02:01 9-mer peptides but readily extensible to other alleles, SwiftMHC unites structural insight with high-throughput scalability to accelerate safe and effective epitope discovery in cancer immunotherapy.
24 Apr 2026
Read appraisal →Analytical chemistry
scAClc: A Multi-Objective Adaptive Clustering Framework for Single-Cell Transcriptomics via Contrastive and Resolution-Aware Representation Learning
Single-cell RNA sequencing (scRNA-seq) enables whole-transcriptomic profiling at single-cell resolution, facilitating the construction of virtual cell representations that capture the full spectrum of cellular identities. Realizing this goal hinges on accurate clustering, which remains challenging due to data sparsity, high dimensionality, noise, and the need to specify cluster numbers a priori. We propose scAClc, a novel clustering framework featuring multiobjective optimization and adaptive resolution discovery, designed to address these limitations through three key innovations. First, a Hierarchical Gene Relevance Module integrates global gene variability with local neighborhood-specific signals to eliminate redundancy while retaining biologically informative features. Second, an Anchor-Centered Contrastive Learning Module adaptively selects representative anchors to guide embedding learning, promoting compact intracluster structure and clear intercluster separation. Third, based on the robust low-dimensional embedding, we propose a Self-Adaptive Resolution Discovery Module to automatically infer the number of clusters by jointly modeling intra- and intercluster distances. Extensive experiments on 15 real scRNA-seq data sets demonstrate that scAClc consistently outperforms six state-of-the-art methods across multiple evaluation metrics. Ablation studies further confirmed the complementary contributions of each module. In addition, interpretability analysis effectively mitigates the "black box" nature of clustering models and sheds light on the biological mechanisms underlying cell clustering. The source code is publicly available at https://github.com/scAClc/scAClc.
23 Apr 2026
Read appraisal →PloS one
Identification and clinical implications of immune-related hub genes in psoriasis
BACKGROUND: Psoriasis, a chronic inflammatory skin disease affecting 2-3% of the global population, is driven by dysregulated immune responses. Despite advancements in biologic therapies, treatment challenges persist due to high recurrence rates. This study aimed to identify immune-related hub genes and elucidate their clinical implications in psoriasis pathogenesis and therapy. METHODS: Multiple microarray datasets from psoriasis patients (GSE30999, GSE106992, GSE14905, GSE78097, and GSE117468) were obtained to identify immune-key genes by differential gene analysis and Weighted Gene Co-expression Network Analysis (WGCNA). Subsequently, immune-related hub genes were identified using the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm and Protein-Protein Interaction (PPI) networks, with further validation through Gene Set Enrichment Analysis (GSEA) and Receiver Operating Characteristic (ROC) curves to assess exploratory within-sample discrimination. Pearson correlation analysis evaluated the relationship between hub genes, skin lesion severity, and treatment outcomes. The study also conducted immune infiltration by using the Cell-type Identification by Estimating Relative Subsets Of RNA Transcripts (CIBERSORT) algorithm and identified potential therapeutic targets by the Drug-Gene Interaction Database (DGIdb). RESULTS: Thirty-one immune-related key genes were identified, and six hub genes (CLEC7A, CXCL1, IRF1, S100A12, S100A8, S100A9) were validated as central players in immune signaling pathways. These genes exhibited within-sample discrimination (AUC > 0.9) and correlated with disease severity and biological therapy efficacy. Immune infiltration analysis revealed increased activated memory CD4+ T cells and M1 macrophages in lesional skin, which was strongly associated with hub gene expression. Additionally, drug-gene interaction analysis identified potential therapeutic agents targeting these genes. CONCLUSION: This study identified six immune-related hub genes that were closely linked to the severity of psoriasis, the effectiveness of biological treatments, and infiltrated activated memory CD4+ T cells and M1 macrophages. Our findings elucidate a novel immune-related hub gene network in psoriasis and provide potential targets for the development and application of biologics.
23 Apr 2026
Read appraisal →Journal of clinical oncology : official journal of the American Society of Clinical Oncology
CALYPSO: Final Results of Savolitinib and Durvalumab Combination in Metastatic Papillary Renal Cancer
PURPOSE: The CALYPSO study demonstrated activity of savolitinib and durvalumab in MET-driven papillary renal cancer (PRC). We report final efficacy outcomes and exploratory circulating tumor DNA (ctDNA) biomarker analysis. METHODS: This single-arm phase II study evaluated savolitinib and durvalumab in treatment-naïve or pretreated PRC. End points included overall response rate (ORR), progression-free survival (PFS), and overall survival (OS). FoundationOne CDx assessed DNA alterations and MET/PD-L1 or MET/tumor mutational burden (TMB) copositivity. ctDNA collected at baseline and on treatment was correlated with outcomes. RESULTS: At 41-months median follow-up, ORR was 34% (95% CI, 20.0 to 51.0) in the intention-to-treat (ITT) population (N = 41) and 53% (95% CI, 28.0 to 77.0) in MET-driven patients (n = 17). Median PFS was 6.5 (95% CI, 2.7 to 12.0) versus 13.9 months (95% CI, 2.9 to 23.8), and OS was 18.3 (95% CI, 7.3 to 30.7) versus 27.4 months (95% CI, 9.3 to 37.4), in the ITT population and the MET-driven population, respectively. PD-L1 (66% positive) and TMB (median 2.5 mut/Mb) status did not correlate with response. Baseline ctDNA positivity (10/21) correlated with shorter OS (median 7.3 v 33.3 months), while ctDNA clearance and mean variant allele frequency reduction correlated with improved OS (median 31.3 v 7.2 and 31.3 v 15.5 months, respectively). CONCLUSION: Savolitinib plus durvalumab shows OS in MET-driven PRC, supporting the ongoing SAMETA RIII trial (ClinicalTrials.gov identifier: NCT05043090). ctDNA may be a useful predictive biomarker.
21 Apr 2026
Read appraisal →Journal of clinical oncology : official journal of the American Society of Clinical Oncology
VIKTORIA-1 Trial of Gedatolisib Plus Fulvestrant With or Without Palbociclib in Hormone Receptor-Positive/HER2-/PIK3CA Wild-Type Advanced Breast Cancer
PURPOSE: Gedatolisib potently targets all four class I PI3K isoforms and mTORC1 and mTORC2 to comprehensively block the PI3K/AKT/mTOR pathway and has shown compelling activity in early clinical trials with palbociclib and fulvestrant. METHODS: This phase III randomized trial (VIKTORIA-1; ClinicalTrials.gov identifier: NCT05501886) evaluated the efficacy of gedatolisib-based therapy, comparing gedatolisib, palbociclib, and fulvestrant (gedatolisib triplet) and gedatolisib plus fulvestrant (gedatolisib doublet) with fulvestrant monotherapy in patients with hormone receptor-positive, human epidermal growth factor receptor 2-negative (HER2-), PIK3CA wild-type (WT) advanced breast cancer. Eligible patients had disease progression during or after CDK4/6 inhibitor and aromatase inhibitor treatment. Comparison of progression-free survival as assessed by blinded independent central review for gedatolisib triplet versus fulvestrant and gedatolisib doublet versus fulvestrant was the primary objective. RESULTS: A total of 392 patients were randomly assigned 1:1:1. The median study follow-up was 10.1 months. The median progression-free survival was 9.3 months in the gedatolisib-triplet group, 2.0 months in the fulvestrant group (hazard ratio [HR] for progression or death, 0.24 [95% CI, 0.17 to 0.35]; P < .001), and 7.4 months in the gedatolisib-doublet group (HR, 0.33 [95% CI, 0.24 to 0.48]; P < .001 v fulvestrant). Grade ≥3 treatment-related adverse events (TRAEs) reported in the gedatolisib-triplet and gedatolisib-doublet groups, respectively, included neutropenia (62.3%, 0.8%), stomatitis (19.2%, 12.3%), rash (4.6%, 5.4%), hyperglycemia (2.3%, 2.3%), and diarrhea (1.5%, 0.8%). Study treatment discontinuation because of TRAEs was reported in 2.3% (triplet) and 3.1% (doublet) of patients. CONCLUSION: The addition of gedatolisib to fulvestrant, with or without palbociclib, significantly reduced the risk of disease progression or death in patients with hormone receptor-positive/HER2-, PIK3CA WT advanced breast cancer.
21 Apr 2026
Read appraisal →JMIR formative research
Artificial Intelligence Design for Race-Based Prostate Cancer Stage Classification With Multilayer Perceptron: Feature Selection Optimization Approach
BACKGROUND: Prostate cancer progression exhibits significant variability influenced by biological and racial factors. DNA methylation profiling has shown potential in early cancer detection, but its integration with machine learning across racially diverse populations remains limited. OBJECTIVE: This study aimed to develop a prostate cancer stage classifier for the majority White cohort using DNA methylation data and a multilayer perceptron (MLP) model in order to classify prostate cancer stages into early (stages I-II) and late (stages III-IV) stages and assess its performance when applied to other racial groups to highlight the need for race-specific models. METHODS: Methylation and phenotype data from the TCGA-PRAD (The Cancer Genome Atlas Prostate Adenocarcinoma) dataset were processed using differentially methylated position (DMP) analysis to identify CpG sites correlated with cancer stages. These features were further refined through recursive feature elimination (RFE) and used to train MLP models. Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) were used to interpret the model and identify key DNA methylation features contributing to model predictions. RESULTS: The best-performing model achieved 95% accuracy and up to 99% area under the curve on the majority race (White) training data using 90 selected features. However, performance declined sharply in racial minority groups, revealing the effects of sample imbalance and race-specific methylation patterns. Feature importance examination indicated strong patterns within certain CpG sites driving model predictions. CONCLUSIONS: We propose a race-aware MLP model for prostate cancer stage classification using DNA methylation data, which has been optimized through DMP and RFE-based feature selection. SHAP and LIME confirmed the predictive relevance of selected CpG sites, supporting model transparency. The results highlight high performance within the White cohort but reveal poor generalization to racial minority groups, emphasizing the importance of race-specific modeling strategies.
17 Apr 2026
Read appraisal →Clinical cancer research : an official journal of the American Association for Cancer Research
Recurrent Resistance Mutations to Lirafugratinib Inform Treatment Sequencing in FGFR2-Driven Tumors
PURPOSE: The use of reversible fibroblast growth factor receptor 2 (FGFR) inhibitors leads to the emergence of "undruggable" FGFR2 kinase domain mutations, hampering sequential treatment strategies. Lirafugratinib and futibatinib are irreversible FGFR inhibitors with the most promising clinical activity against FGFR2-driven tumors. EXPERIMENTAL DESIGN: We characterized resistance to lirafugratinib with circulating tumor DNA, tissue whole-exome sequencing, and bulk RNA sequencing in 30 patients with FGFR2-driven cancers, treated in the phase I/II ReFocus trial (NCT04526106) and enrolled in the UNLOCK program at Gustave Roussy. RESULTS: Among the 30 patients included, 18 (60%) had intrahepatic cholangiocarcinoma and 12 (40%) had other tumor types. Twenty-two patients (73%) were FGFR inhibitor-naïve. Among those experiencing primary resistance to lirafugratinib, we identified potential resistance mechanisms in five of six pretreatment samples. Patients with acquired lirafugratinib resistance manifested an unprecedented emergence of FGFR2 mutations in the M538 and/or L618 residues of the kinase domain, documented in 11 of 16 cases (69%). Compared with futibatinib resistance, FGFR2 molecular brake (N550) and gatekeeper (V565) mutations were rare. Leveraging the spectrum of FGFR2 kinase domain mutations at resistance to lirafugratinib and futibatinib, respectively, we identified the complementarity of the two irreversible inhibitors. On the basis of viability assays in FGFR2::BICC1-dependent Ba/F3 models and in vivo studies on patient-derived xenografts, we propose treatment sequences with the two agents. After lirafugratinib progression, three patients received futibatinib and experienced prolonged disease response. CONCLUSIONS: The complementary activity of lirafugratinib and futibatinib against FGFR2 kinase domain mutations supports their sequential use when precise resistance mutations are detected in patients.
17 Apr 2026
Read appraisal →Physical chemistry chemical physics : PCCP
TransG4: an interpretable deep-learning approach for sequence-based G-quadruplex prediction
G-quadruplexes (G4) are non-canonical nucleic acid secondary structures formed in guanine-rich regions and have been shown to regulate diverse cellular processes such as gene expression, DNA replication, and telomere maintenance, with increasing evidence linking G4 to cancer and other human diseases. G4 predominantly emerge in guanine-rich regions and are implicated in a spectrum of molecular interactions and disease phenotypes, thus researchers are interested in the formation of G4. However, predicting the formation of G4 from nucleotide sequences is a persistent problem. Existing computational tools for G4 prediction are either rule-based on domain knowledge or rely on a single neural network model like a convolutional neural network (CNN), which lacks interpretability and struggles to capture long-range dependencies among bases. Here, we introduce TransG4, a novel neural network architecture that integrates a CNN, a transformer, and bidirectional gated recurrent units (BiGRUs) to identify potential G4 structures. TransG4 demonstrates strong predictive performance on both G4-seq and rG4-seq datasets, accurately predicting DNA mismatch scores and consistently outperforming existing methods in RNA RSR-ratio prediction. Attention-based interpretations further show that TransG4 captures biologically meaningful motifs consistent with canonical G4 structures, providing an interpretable and generalizable framework and representing a novel and impactful contribution to sequence-based G4 propensity prediction.
17 Apr 2026
Read appraisal →Signal transduction and targeted therapy
HDAC inhibitor tucidinostat and metronomic capecitabine plus endocrine therapy for patients with HR-positive HER2-negative advanced breast cancer after CDK4/6 inhibitors treatment: clinical findings and exploratory circulating tumor cell and ctDNA biomarker analyses of a multicenter, phase 2 study (SYSUCC-020 trial)
Treatment options for patients with hormone receptor (HR)-positive, human epidermal growth factor receptor 2 (HER2)-negative advanced breast cancer (ABC) that progresses after CDK4/6 inhibitor (CDK4/6i) continue to evolve, and no single regimen has been established as the preferred standard of care. We conducted a phase 2 trial (SYSUCC-020, NCT05411380) to investigate the efficacy and safety of a novel combination of tucidinostat and metronomic capecitabine (mCAP) with endocrine therapy (ET) in patients following progression on CDK4/6i. This trial adopted a Simon two-stage design: eligible patients received tucidinostat plus metronomic capecitabine together with either an aromatase inhibitor (Cohort 1) or fulvestrant (Cohort 2), selected according to prior ET. Seventy-two female patients were screened and sixty-six patients were included in the efficacy and safety analyses. The median follow-up was 13.88 months (Interquartile range, 8.67-20.67) and the objective response rate was 25.8%, with 17 partial responses. The median progression-free survival (PFS) was 5.39 months (95% CI, 4.07-7.69), namely 6.93 months (95% CI, 4.76-12.22) in Cohort 1 and 3.98 months (95% CI, 2.79-7.59) in Cohort 2. Most patients (93.9%) experienced at least one adverse event. In addition, exploratory analyses of biomarkers indicated that the baseline TP53 mutation status (Wild type vs. mutated, 7.64 months vs. 3.55 months) and circulating tumor cell (CTC) status (CTC-negative vs. CTC-positive, 7.59 months vs. 3.78 months) were associated with the median PFS. Our study demonstrated that tucidinostat combined with mCAP and ET is efficacious and well-tolerated in patients with HR-positive HER2-negative ABC previously treated with CDK4/6i.
17 Apr 2026
Read appraisal →Cancer research
Mutant and Wild-Type RAS Cross-talk and Stoichiometric Deficiencies Are Determinants of Sensitivity to Targeted Therapies in KRASG12R Pancreatic Ductal Adenocarcinoma
UNLABELLED: Therapies targeting the RAF-MEK-ERK pathway are generally considered to have limited efficacy in KRAS-mutant cancers. However, specific KRAS mutants exhibit distinct behaviors. Notably, KRASG12R pancreatic ductal adenocarcinoma (PDAC) tumors have shown sensitivity to MEK inhibitors (MEKi) in combination with autophagy inhibitors, but a better understanding of the underlying mechanisms is needed to optimize this treatment strategy. Using a systems-level approach, we uncovered a mechanistic explanation for this phenomenon. Due to distinct biophysical properties, KRASG12R had an impaired ability to activate wild-type HRAS and NRAS (WT-RAS) compared with other KRAS mutants, such as KRASG12D. This reduced activation stemmed from the weaker interaction between KRASG12R and guanine exchange factors (SOS), as well as the tumor suppressor neurofibromin (NF1), crucial in regulating WT-RAS activity. The impaired ability to activate WT-RAS led to weaker holistic MAPK signaling in KRASG12R-driven tumors, which conferred increased sensitivity to MEKi. To substantiate the preclinical findings, the utility of MEKi in combination with the autophagy inhibitor hydroxychloroquine was analyzed in patients with KRASG12R-mutated metastatic PDAC. Five of the eight (62.5%) patients treated in first- or second-line settings had a progression-free survival exceeding 6 months. Three patients had impressive disease control: two had stable disease of 11 and 22.7 months, and one achieved a partial response with an 83% decrease in tumor size that lasted for 8.9 months. Overall, this work highlights how systems-based approaches in precision medicine can uncover mechanistic insights to guide the identification of patients with PDAC most likely to benefit from tailored therapeutic strategies. SIGNIFICANCE: The unique sensitivity of KRASG12R-mutant cancers to MEK inhibitors offers a critical advancement in understanding MAPK signaling and paving the way for precision-targeted therapies in previously untreatable contexts. See related commentary by Tiriac and Engle, p. 1817 See related article by Burge et al., p. 1854 See related article by Burge et al., p. 1868.
17 Apr 2026
Read appraisal →Clinical cancer research : an official journal of the American Association for Cancer Research
Camonsertib, an ATRi, in Combination with Low-Dose Gemcitabine in Solid Tumors with DNA Damage Response Aberrations: Preclinical and Phase Ib Results.
PURPOSE: The utility of combination treatment with gemcitabine and camonsertib, an ataxia telangiectasia and Rad3-related kinase inhibitor, in mediating tumor cell death was assessed in preclinical models, prompting clinical investigation. The phase Ib TRESR study (NCT04497116) aimed to evaluate the safety, tolerability, and preliminary efficacy of the combination in patients with advanced solid tumors harboring DNA damage repair (DDR) gene alterations. PATIENTS AND METHODS: Cell lines and tumor xenografts were tested across a range of dose levels and schedules. Patients (N = 76) harboring tumors with DDR gene alterations received camonsertib (80-120 mg) and de-escalating gemcitabine (1,000-100 mg/m2) in 21- or 28-day cycles on an intermittent dosing regimen. Safety, tolerability, and preliminary efficacy were assessed to identify an optimal dosing regimen. RESULTS: In preclinical models, low-dose camonsertib (1/3 maximum tolerated dose) and gemcitabine led to tumor regression and was well tolerated with minimal body weight loss observed. In patients, synergistic toxicities were observed, primarily myelosuppression, resulting in gemcitabine de-escalation. The introduction of a 1 week on/1 week off schedule in combination with low-dose gemcitabine allowed for spontaneous neutrophil recovery, fewer dose modifications, and improved tolerability. Tumor responses were primarily observed in patients with gynecologic cancers, with tumor control maintained for greater than 1 year in some patients. CONCLUSIONS: Camonsertib and low-dose gemcitabine demonstrated preliminary clinical activity, but due to challenging tolerability, further evaluation is warranted to identify the optimal dosing regimen and subset of patients who may benefit most from this combination.
17 Apr 2026
Read appraisal →The Journal of clinical investigation
Carriage of rare APOB variants predisposes to severe steatotic liver disease and hepatocellular carcinoma
BACKGROUNDMetabolic dysfunction-associated steatotic liver disease (MASLD) has a substantial inherited component. Rare variants in apolipoprotein B gene (APOB) have been implicated in susceptibility to liver steatosis, but their role in disease progression and outcomes is unclear.METHODSWe investigated APOB rare variants in a case-control cohort of people with advanced MASLD versus healthy controls (n = 510 and 261, respectively), a family-based study (n = 43 and literature meta-analysis), the Million Veteran Program (MVP) cohort (n = 94,885), and the UK Biobank (UKBB) (n = 417,657).RESULTSIn the clinical cohort, APOB variants were enriched in people with advanced MASLD (OR 13.8, 95% CI: 2.7-70.7, P = 0.002) and associated with lower circulating lipids, but higher MASLD activity and fibrosis (P < 0.05). In the family study, APOB variants segregated with hepatic steatosis and fibrosis (P < 0.05). Cross-ancestry meta-analysis of the study cohorts yielded pooled ORs for cirrhosis and hepatocellular carcinoma (HCC) of 1.82, 95% CI: 1.33-2.49 and 3.53, 95% CI: 2.09-5.98, respectively. Variants affecting specifically ApoB100 had a 3-fold greater effect on hepatic lipid metabolism compared with those impairing also ApoB48 and were specifically protective against coronary artery disease (P < 0.05). The variants affected cirrhosis risk similarly, but ApoB48/100 had a larger effect on HCC (P < 0.05).CONCLUSIONSRare APOB variants predispose individuals to advanced MASLD and HCC, with distinct contributions from disrupted VLDL and chylomicrons secretion. These findings highlight the interplay between hepatic and intestinal lipid handling, suggesting that APOB genotyping may enhance MASLD risk stratification and patient identification.FUNDINGEuropean Union, Italian Ministry of Health, Swedish Research Council, Veterans Health Administration, NIH.
16 Apr 2026
Read appraisal →Computers in biology and medicine
Deep learning with limited data: a transfer learning approach for transcriptomic survival prediction
BACKGROUND: Deep neural networks (DNNs) are promising for analyzing high-dimensional transcriptomic data in cancer research but are limited by data scarcity and heterogeneity. Transfer learning (TL), which leverages large datasets to improve performance on smaller ones, has been widely applied in classification and clustering, yet its use in survival prediction remains underexplored. METHODS: We evaluated transfer learning for disease-free survival prediction using RNA-seq data from 7509 patients across 27 tumor types from The Cancer Genome Atlas. A pan-cancer DNN was optimized via random search across 750 configurations. Tumor-specific baseline models were trained independently, while transfer learning models were built with a leave-one-out pre-training strategy followed by fine-tuning on the target tumor. Performance was assessed with the concordance index. Biological relevance was evaluated through a LIME-like interpretability approach and gene-set enrichment analysis. RESULTS: Transfer learning outperformed tumor-specific baselines in 24 of 27 tumor types, with the greatest improvements in smaller cohorts. Fine-tuning consistently enhanced predictions by adapting pan-cancer features to tumor-specific data. Enrichment analysis confirmed that the models captured both general oncogenic mechanisms and tumor-specific pathways. CONCLUSIONS: Transfer learning improves survival prediction from transcriptomic data, especially in small cohorts, by exploiting molecular patterns shared across cancers. These findings support transfer learning as a robust strategy for survival modeling and a step toward foundation models in molecular oncology.
16 Apr 2026
Read appraisal →International immunopharmacology
CXCL9 as a key feature for deep learning-based immune subtyping and prediction of immune checkpoint blockade response in triple-negative breast cancer
BACKGROUND: Immune checkpoint blockade (ICB) therapy has provided a promising treatment option for patients with triple-negative breast cancer (TNBC). However, existing efficacy prediction strategies based on programmed death-ligand 1 (PD-L1) expression and Tumor Mutational Burden (TMB) have significant limitations, leading to inaccurate patient selection. METHODS: This study integrated multi-omics data obtained from GEO, TCGA, and GTEx datasets. Based on ComBat correction results, two deep learning-driven unsupervised clustering methods were constructed to identify potential immune subtypes. These identified TNBC subtypes were subjected to comprehensive bioinformatics analyses to investigate their differences in overall survival, immune cell infiltration, and functional enrichment analysis, which clarified the biological rationale of the proposed classification. Subsequently, differential expression analysis (DEA) and multiple machine learning algorithms were applied to identify subtype-specific features, with the expression and differentiation status of the key feature in immune cells further validated using single-cell sequencing (scRNA-seq). Finally, co-expression networks at multiple cellular levels were constructed to predict the co-expressed regulatory targets of the key feature, and the hypothesized regulatory mechanism was preliminarily validated in in vitro experiments (qRT-PCR, western blotting, immunofluorescence, and ELISA). RESULTS: After 5-fold cross-validation, the AE-K-means clustering method classified TNBC into three distinct latent subtypes. This algorithm exhibited superior classification efficacy compared with the other models (including NMF, ConsensusClusterPlus and VAE-GMM), as demonstrated by markedly elevated Silhouette Coefficients (training: 0.585 ± 0.030; test: 0.698 ± 0.103; validation: 0.611) and substantially reduced Davies-Bouldin Index values (training: 0.623 ± 0.032; test: 0.385 ± 0.218; validation: 0.558) at K = 3. These three identified TNBC subtypes displayed significant differences in overall survival and exhibited pronounced immune heterogeneity. Specifically, the K2 subtype was characterized by high PD-L1 expression and abundant M1 macrophage infiltration, while the K3 subtype displayed an opposing, immunosuppressive microenvironment. Feature selection results from multiple machine learning models were intersected to identify key features including CXCL9, and an RF model constructed based on these intersected genes showed high efficacy, particularly in distinguishing the K2 and K3 subtypes (AUC = 0.941). Further scRNA-seq analysis revealed that CXCL9 was specifically highly expressed in myeloid cells, and the proportion of CXCL9+ macrophages differed significantly between responders and non-responders. Given the strong positive correlation between CXCL9 and IDO1 expression, we subsequently treated macrophages with IDO1 inhibitors and observed a marked upregulation in both the expression and secretion of CXCL9, suggesting that IDO1 overexpression in macrophages may represent a potential mechanism underlying CXCL9 exhaustion in the tumor microenvironment. CONCLUSIONS: Our study developed a novel immune classification system for TNBC, identifying CXCL9 as a key biomarker positively correlated with ICB response and regulated by IDO1. These findings provide a basis for precision immunotherapy in TNBC and support the exploration of IDO1 inhibitors in combination with ICB.
15 Apr 2026
Read appraisal →Cancer
A phase 1 study of ASTX727 plus talazoparib in patients with triple-negative or hormone resistant/HER2-negative metastatic breast cancer
BACKGROUND: Poly(adenosine diphosphate ribose) polymerase (PARP) is recruited to DNA damage sites along with epigenetic factors such as DNA methyltransferase 1 (DNMT1). Inhibitors of DNMT modulate reactive oxygen species (ROS)-cyclic adenosine monophosphate (cAMP)/Protein Kinase A signaling and induce a "BRCAness phenotype" that further sensitizes cells to PARPi. In preclinical studies, combined DNMTi + PARPi therapy was effective in both triple-negative (TNBC) and hormone resistant (HRBC) models with intact BRCA. METHODS: The authors conducted a phase 1 study combining the oral DNMTi ASTX727 with the PARPi talazoparib in patients with previously treated TNBC or HRBC. Patients with deleterious mutations of BRCA were excluded. A classical 3+3 design guided dose escalation/de-escalation, and 28 days constituted each cycle. Serial peripheral blood mononuclear cells (PBMCs) were analyzed for changes in methylation using the Infinium Methylation EPIC BeadChip and LINE1 sequencing. RESULTS: Thirty-four evaluable patients were enrolled and treated in eight dose cohorts. Myelosuppression was common with grade >3 neutropenia in 42% and grade 3 anemia and thrombocytopenia in 13%. Dose-limiting toxicity was limited to neutropenia. Efficacy was assessed in 29 patients. There were no objective responses, six patients had stable disease persisting for >4 months in three patients. LINE1 demethylation ranged from ∼2%-10% and immune-specific CpGs (methylation in immune cells) changed 1%-5% at day 15. Methylation changes were not dose-dependent. CONCLUSIONS: ASTX727 plus talazoparib produces significant myelosuppression without other adverse events. Modest methylation changes in PBMCs were detected. There were no objective responses, but some heavily pretreated patients had stable disease for >4 months despite the attenuated doses.
15 Apr 2026
Read appraisal →International immunopharmacology
Machine learning derived proliferating T cell-related signature: a novel biomarker for prognosis and treatment efficacy in clear cell renal cell carcinoma
BACKGROUND: Clear cell renal cell carcinoma (ccRCC) exhibits profound molecular heterogeneity, and reliable biomarkers for predicting clinical outcomes are urgently needed. Proliferating T cells (Tprolif) are central to immune system activation but their related signatures in predicting prognosis and therapeutic effect of ccRCC patients remains unexplored. METHODS: We developed a Tprolif-related RCC score (TRRS) using an integrative machine learning framework. Transcriptomic data from the CheckMate025 trial formed the discovery cohort. The model was validated across multiple independent cohorts, including IMmotion151, JAVELIN Renal 101, TCGA-KIRC, and West China Hospital (WCH) cohort from our center. Multi-omics analyses, including spatial and single-cell transcriptomics, were employed to investigate the associated biology and identify key mediators. RESULTS: The final TRRS model, built from 7 genes, demonstrated robust performance in stratifying patients for overall survival (OS) and progression-free survival (PFS) in training and all validation sets. TRRS was a powerful predictor of improved outcomes not only for immune checkpoint inhibitor (ICI) monotherapy but also for ICI-based combination therapy and targeted therapies. Biologically, a high TRRS was associated with aggressive tumor hallmarks, a distinct metabolic profile favoring aerobic glycolysis and glutamine metabolism, and an immunosuppressive tumor microenvironment despite high immune cell infiltration based on WCH cohort transcriptome expression profile. Through multi-omics screening, we identified CST3 as a key target, with spatial and single-cell analyses confirming its role in promoting tumor malignancy and enhancing cell-cell communication among microenvironment components. CONCLUSION: The TRRS is a novel, validated biomarker that effectively predicts prognosis and therapeutic responses in advanced ccRCC. It reflects critical biological features of tumor aggressiveness and immune evasion, with CST3 emerging as a potential central mediator and therapeutic target.
15 Apr 2026
Read appraisal →ACS nano
Deep Learning Enables Pixel-Level Nanoparticle Distribution Mapping in Routine Histological Sections by Integrating Cancer Associated Fibroblasts Features
The efficient accumulation and uniform distribution of nanomedicine within tumors are critical for achieving therapeutic outcomes. However, conventional medical imaging technologies struggle to efficiently and accurately detect nanoparticles (NPs) distribution, especially in resolving their cellular-level spatial heterogeneity. Existing deep-learning-based predictive models focus on tumor cell density and vascular distribution but do not address the complex spatial relationship between cancer-associated fibroblasts (CAFs) and drug distribution. This study presents NanoNet, a deep-learning framework that leverages fibroblast activation protein (FAP) immunostaining to spatially characterize CAFs and predict NPs distribution at high resolution. NanoNet achieved high predictive accuracy (ICC = 0.963, R2 = 0.9849) by transforming tumor section images into pixel-level NPs distribution maps. The FAP channel contributed substantially to predictive accuracy, indicating its important role in guiding NPs behavior. This study provides a spatially resolved predictive framework that enables pixel-level predictions of NPs distribution from conventional histological sections, with potential applications for optimizing nanomedicine design and personalized nanomedicine.
15 Apr 2026
Read appraisal →Journal of chemical information and modeling
ncProFormer: A CNN-enhanced Transformer for ncRNA Coding-Potential Prediction
Recent studies have revealed that some noncoding RNAs (ncRNAs) bear translational potential, and their encoded micropeptides have essential functions in multiple biological processes. However, accurate identification of coding-capable ncRNAs remains challenging due to weak translation signals, low conservation, and heterogeneous data distributions. Herein, we propose ncProFormer, a deep learning framework tailored for ncRNA coding-potential prediction. ncProFormer integrates the nucleic-acid language model GENA-LM to obtain contextual sequence embeddings, adopts an all-token representation strategy, and employs a convolutional neural network (CNN)-enhanced transformer encoder to jointly capture local nucleotide patterns and long-range dependencies. ncProFormer consistently outperformed the existing methods across the in-house human data set, the external validation data set, the public CPPred benchmark data set. More importantly, this study presents the first cross-species evaluation in ncRNA coding-potential prediction. Without retraining, ncProFormer maintained its strong predictive performance on mouse and rat data sets, showing that the learned biological representations are transferable and it is robust under the distributional shift and cross-species conditions. Collectively, these findings establish ncProFormer as an effective and generalizable framework for uncovering the coding potential of ncRNAs, thus offering a promising computational tool for characterizing ncRNA functions across diverse transcriptomic contexts.
14 Apr 2026
Read appraisal →Medicine
Glioma biomarker analysis and drug targeting prediction based on ferroptosis-related genes
Glioma represents a significant challenge in neuro-oncology due to its highly invasive nature and poor prognosis. Recent studies indicate that ferroptosis, a form of regulated cell death, plays a crucial role in the pathogenesis of glioma. Modulating ferroptosis may offer a novel therapeutic approach for glioma treatment. This study aims to identify ferroptosis-related biomarkers and patterns of immune infiltration in glioma using bioinformatics techniques, and to predict potential therapeutic drugs targeting these biomarkers. Gene expression profiles (GSE16011, GSE50161) were retrieved from the GEO database, while ferroptosis-related genes were sourced from the FerrDb database. Intersection genes were identified using the CytoHubba algorithm and a consensus clustering method. Immune infiltration was assessed using the CIBERSORT algorithm. Functional enrichment analysis and gene set enrichment analysis were conducted with Gene Ontology and Kyoto Encyclopedia of Genes and Genomes databases. Drug targeting predictions were made based on identified hub genes. We identified 10 hub genes: TP53, RRM2, EZH2, CDKN1A, MYCN, KIF20A, BLM, GLS2, HMOX1, and GOT1. Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analyses revealed that ferroptosis is primarily associated with apoptosis, reactive oxygen metabolism, the p53 signaling pathway, and immune regulation. Immune infiltration analysis showed significant differences in the expression of plasma cells, CD8 T cells, follicular helper T cells, activated NK cells, and macrophages between groups. qRT-PCR validation in glioma cell lines confirmed the differential expression of key ferroptosis-related genes, supporting the robustness of our bioinformatic findings. Furthermore, molecular docking demonstrates excellent binding properties between the drug components and key targets, and these key targets were further validated by PCR analysis in vitro. In summary, this study highlights the potential of ferroptosis-related biomarkers in glioma and suggests novel drug targets, providing a foundation for future therapeutic strategies.
12 Apr 2026
Read appraisal →Proceedings of the National Academy of Sciences of the United States of America
Resistance to neoadjuvant talazoparib in triple-negative breast cancer by BRN2-induced ATR/STAT3 pathways or SHLD2 subclone expansion
Intrinsic and acquired resistance to poly(ADP-ribose) polymerase (PARP) inhibitors (PARPi) remains a major barrier in treating homologous recombination (HR) repair-deficient tumors, including those with germline or somatic BRCA1/2 mutations. Although PARPi are FDA approved for adjuvant treatment of locally advanced or metastatic breast cancer in patients with germline BRCA1/2 mutations, emerging data support their use as monotherapy in the neoadjuvant setting. Promising safety profiles of newer-generation PARPi further support this potential. However, resistance mechanisms specific to the neoadjuvant setting are poorly understood. To address this gap, we leveraged resources from a phase II neoadjuvant clinical trial (NCT03499353), analyzing tumors from patients with germline BRCA1/2 mutant breast tumors before and after six months of talazoparib monotherapy. Whole-transcriptome analyses were performed on these samples. Additionally, we established orthotopic patient-derived xenograft models from a subset of the patient tumors and conducted whole-exome and whole-transcriptome analysis. This integrative approach revealed both known and previously unknown PARPi resistance mechanisms. In one case, overexpression of BRN2, encoding a transcription factor that plays a critical role in neurogenesis, led to activation of ATR/RAD51 and STAT3 pathways, restoring HR repair. BRN2-driven resistance could be reversed with ATR and STAT3 inhibitors, resensitizing cells to talazoparib. In another, an HR repair proficient tumor subclone lacking Shieldin 2 expression expanded during treatment and accounted for intrinsic resistance. Our findings highlight the need to determine intrinsic and anticipate acquired resistance pathways in treatment-naïve tumors and support combining PARPi with targeted agents to improve outcomes in the neoadjuvant setting.
12 Apr 2026
Read appraisal →Journal for immunotherapy of cancer
Anti-TIM-3 antibody TQB2618 in combination with penpulimab in relapsed or refractory classic Hodgkin lymphoma previously treated with PD-1/PD-L1 therapy: a multicenter, open-label, single-arm, phase Ib clinical trial
BACKGROUND: Immune checkpoint inhibitors achieve high response rates in relapsed or refractory (r/r) classical Hodgkin lymphoma (cHL), but few treatment options are available for patients who experience failure after PD-1/PD-L1 blockade. T cell immunoglobulin and mucin-domain containing-3, a key mediator of immune escape from PD-1/PD-L1 inhibition, is targeted by TQB2618, a humanized IgG4 monoclonal antibody. This phase Ib study aimed to evaluate the safety and efficacy of TQB2618 in combination with the anti-PD-1 antibody penpulimab in patients with r/r cHL. METHODS: This multicenter phase 1b study was conducted from June 2022 to September 2024 at 12 sites in China (NCT05400876). The study included a dose-escalation phase in which patients with r/r lymphoma received TQB2618 (600 or 1200 mg, every 3 weeks, Q3W) plus penpulimab (200 mg, Q3W) to evaluate dose-limiting toxicities and determine the recommended phase II dose (RP2D). The subsequent dose-expansion phase enrolled patients with r/r cHL previously treated with PD-1/PD-L1 inhibitors to assess the objective response rate (ORR). RESULTS: 10 patients with r/r lymphoma were enrolled in the dose-escalation phase, and TQB2618 (600 mg, Q3W) plus penpulimab (200 mg, Q3W) was selected as the RP2D. In the dose-expansion phase, 18 additional patients with r/r cHL previously treated with PD-1/PD-L1 inhibitors were enrolled. Among the total 21 r/r cHL patients, the median age was 32 years (range, 22-65), and 12 (57%) were male. The ORR was 52%, including 1 complete response and 10 partial responses. Treatment-related adverse events (TRAEs) occurred in 18 patients (86%), with grade ≥3 TRAEs in 5 (24%). The most common TRAEs (≥20%) were platelet count decreased (24%), anemia (24%), and aspartate aminotransferase increased (24%). As of the data cut-off in December 2024, the median follow-up was 14.1 months, the median duration of response and the median overall survival had not yet been reached. CONCLUSIONS: TQB2618 in combination with penpulimab was well tolerated and demonstrated promising efficacy in patients with cHL who had failed prior anti-PD-1/PD-L1 therapy, supporting its potential as a therapeutic option for this difficult-to-treat population. TRIAL REGISTRATION NUMBER: NCT05400876.
12 Apr 2026
Read appraisal →Heart (British Cardiac Society)
Subphenogroups of acute heart failure with preserved ejection fraction: comprehensive proteomics and pathway analysis
BACKGROUND: Heterogeneity of heart failure with preserved ejection fraction (HFpEF) results in significant challenges for treatment development. Identifying and characterising distinct HFpEF phenogroups may aid in tailoring therapeutic strategies for these patients. The objective of this study was to assess proteomic patterns of HFpEF phenogroups identified through a machine-learning-based clustering model, with the aim of uncovering specific biological pathways associated with each phenogroup. METHODS: This study represents a post-hoc analysis of the ongoing Prospective mUlticenteR obServational stUdy of patIenTs with Heart Failure with preserved Ejection Fraction (PURSUIT-HFpEF) study, which is a multicentre prospective observational study of hospitalised patients with acute decompensated HFpEF. Of the overall cohort (N=1238), this study analysed 198 patients with HFpEF with available proteomics data. These patients were classified into four phenogroups using the machine-learning-based clustering model. The SomaScan assay V.4.1 was used to measure levels of >7000 plasma proteins, and subsequent pathway analysis was conducted to determine the biological differences among the phenogroups. RESULTS: We identified four distinct phenogroups: Phenogroup 1 ('rhythm trouble'), Phenogroup 2 ('ventricular-arterial uncoupling'), Phenogroup 3 ('low output and systemic congestion') and Phenogroup 4 ('systemic failure'). The proteomics revealed distinct protein expression profiles among the phenogroups, with ribonuclease 4, tax1-binding protein 1, regenerating islet-derived protein 3-gamma and alpha-1-antichymotrypsin being the most significant markers to specific identified phenogroups. Pathway analysis suggested differences in immune response, autonomic activation, cellular homeostasis and tissue repair mechanisms across the phenogroups. CONCLUSIONS: Using a comprehensive plasma proteomics approach, our study identified distinct proteomic profiles of HFpEF phenogroups, which in turn suggest specific underlying biological processes. These profiles suggest the involvement of inflammatory activation, tissue injury and regenerative responses, immune modulation and systemic stress signalling as key components of HFpEF pathophysiology. TRIAL REGISTRATION NUMBER: UMIN-CTR ID: UMIN000021831.
12 Apr 2026
Read appraisal →PLoS medicine
Spatial omics and AI for clinically actionable cancer biomarkers
Integrating spatial omics with artificial intelligence is likely to advance biomarker research and diagnostics, with the potential to pair mechanistic insight into spatial target biology. By developing scalable, reproducible quantification in routine pathology, it can help bridge discovery, validation, and real-world clinical implementation.
11 Apr 2026
Read appraisal →Human mutation
Use of Single-Cell Data and scPagwas Analysis to Identify T Cell Subsets and Construct a Prognostic Model for Clear Cell Renal Cell Carcinoma
BACKGROUND: Clear cell renal cell carcinoma (KIRC), the most prevalent pathological renal cell carcinoma (RCC) subtype, makes up approximately 75%-84% of total cases. KIRC is characterized by high heterogeneity, high metastasis rates, and a poor prognosis. Its incidence rate has continued to rise in recent years. We sought to construct new prognostic models to optimize treatment decisions, improve clinical benefits, and explore potential therapeutic targets. METHODS: This study integrated various omics data including single-cell RNA seq (GSE171306), TCGA-KIRC, GWAS, and validation datasets (GSE29609 and E-MTAB-1980). The scPagwas algorithm combines GWAS with scRNA-seq to identify immune subgroups with high feature correlation. Key genes are identified through the combination of weighted correlation network analysis (WGCNA) with differentially expressed genes (DEGs). We built a clinical prognostic model by using machine learning algorithms and validated it through survival rate and receiver operating characteristic (ROC) analysis. We used cancer drug sensitivity genomics data to analyze drug sensitivity and performed molecular docking to identify potential therapeutic drugs. RESULTS: Using single-cell RNA seq data, we identified T cell subsets as characteristic cell subsets in KIRC through scPagwas analysis. In single-cell analysis, key genes in T cell subsets and genes with PCC values > 0.05 were combined with the core genes in DEGs and WGCNA modules, thus yielding 86 intersecting genes. These genes were significantly enriched in immune-related pathways. We established a clinical prognostic model containing seven risk genes. Low-risk patients exhibited substantial survival advantages. Time-dependent ROC analysis indicated the prognostic model's excellent clinical predictive value. Functional enrichment, immune infiltration, and somatic mutation analyses highlighted different biological mechanisms among risk populations. The SHAP values of the XGBoost and LightGBM machine learning algorithms indicated DOCK8 as a potential biomarker. Drug prediction and molecular docking predicted five potential drugs targeting DOCK8 (finasteride, nocodazole, palonosetron, pifithrin alpha, and topiramate). CONCLUSION: Our systematic analysis of the immune microenvironment, key genes, and prognosis of KIRC highlighted the critical roles of T cell subsets. We additionally established an effective clinical prognostic model. Our findings provide new insights and potential targets for the precise diagnosis and targeted KIRC therapy.
11 Apr 2026
Read appraisal →Cell genomics
Variant-resolved prediction of context-specific isoform variation with a graph-based attention model
In eukaryotes, most genes produce multiple transcript isoforms that diversify the transcriptome and proteome, serving as a key mechanism of functional regulation. Genetic variation can disrupt the RNA processing signals that shape isoform structure and abundance, yet modeling these effects at full-length isoform resolution remains challenging due to the complexity of transcript regulation. Here, we introduce Otari, an attention-based graph neural network framework trained on the human genomic sequence and long-read transcriptomes across 30 tissue types and brain regions. Otari predicts tissue-specific differential isoform abundance by integrating sequence-derived epigenetic and post-transcriptional signals, enabling isoform-resolved variant effect interpretation. Applied to large-scale variant datasets, including an autism cohort, Otari uncovers patterns of isoform dysregulation undetectable at the gene level, such as variant-driven perturbations in isoform abundance and microexon usage implicated in autism pathophysiology. We provide Otari as a resource for powering isoform-level analyses across tissues at scale.
11 Apr 2026
Read appraisal →Journal of clinical oncology : official journal of the American Society of Clinical Oncology
Development of a Classifier for Metabolic Subtypes of Nasopharyngeal Carcinoma to Guide Personalized Immunotherapy Strategies: Biomarker Analysis of the Phase III CONTINUUM and DIPPER Trials
PURPOSE: Personalized immunotherapy strategies are urgently needed for patients with locoregionally advanced nasopharyngeal carcinoma (NPC). We aim to identify biomarkers predictive of immunotherapy benefits, using data from the phase III CONTINUUM (ClinicalTrials.gov identifier: NCT03700476) and DIPPER (ClinicalTrials.gov identifier: NCT03427827) randomized clinical trials. PATIENTS AND METHODS: Tumor samples from 407 patients in the CONTINUUM (discovery cohort) and DIPPER (validation cohort) trials were subjected to RNA sequencing. In the discovery cohort, metabolic gene-based consensus clustering was performed to determine subtypes. A machine learning-based classifier was subsequently developed in the discovery cohort and then applied to the validation cohort to assign metabolic subtypes. Gene set enrichment analyses were used to characterize the biological features of each metabolic subtype. The clinical end point was event-free survival (EFS). RESULTS: In the discovery cohort, three metabolic subtypes were identified with distinct tumor-intrinsic and immune features as well as differential EFS benefits from adding anti-PD-1 to chemoradiotherapy (CRT). Specifically, the MS1 subtype exhibited a significant improvement in 3-year EFS in the anti-PD-1 plus CRT arm compared with the CRT-alone arm (3-year EFS, 90.2% v 69.6%; hazard ratio, 0.27 [95% CI, 0.11 to 0.67]), whereas MS2 (3-year EFS, 94.1% v 93.8%) and MS3 subtypes (3-year EFS, 75.0% v 75.0%) derived no significant survival benefit. The subtype features were preserved in the validation cohort, with consistent prognostic and predictive value. A pooled analysis of both cohorts demonstrated the significant interaction between metabolic subtypes and the treatment effect (Pinteraction = 0.0074). CONCLUSION: In this biomarker study, we defined metabolic subtypes of NPC that predicted the EFS benefit from immunotherapy. This novel molecular classification provides a promising predictive biomarker for personalized treatment decision for patients with locoregionally advanced NPC.
11 Apr 2026
Read appraisal →Journal for immunotherapy of cancer
Deep learning-driven recognition of panoramic tumor microenvironment features in H&E sections and its application
The tumor microenvironment (TME), composed of tumor cells together with stromal cells, immune cells, vascular networks, and other components, constitutes a complex ecosystem that plays a decisive role in tumor initiation, progression, metastasis and therapeutic response. Traditional pathological diagnosis mainly relies on pathologists manually examining H&E-stained tissue sections under the microscope, a method that not only suffers from substantial interobserver variability but also has relatively low analytical efficiency. With the rapid development of computational pathology, the integration of whole-slide imaging technology and deep learning algorithms has provided powerful tools for characterizing tumor microenvironment. These techniques enable automated characterization of cellular, spatial and molecular heterogeneity within the tumor microenvironment, providing integrated insights that advance precision diagnostics and improve prediction of therapeutic response and patient outcomes. Based on a comprehensive review of existing research, this paper highlights recent advances in deep learning-driven recognition of panoramic TME features from H&E slides and their clinical applications and further discusses both the translational potential and current limitations of this technology in oncology research and clinical applications.
11 Apr 2026
Read appraisal →International journal of pharmaceutics
Beyond spectroscopy: Machine vision as the future of non-destructive testing in 3D-printed pharmaceuticals
3D Printing (3DP) has revolutionized personalized medicine by enabling the production of patient-specific dosage forms and adaptable drug delivery systems. However, despite these advances, 3DP presents significant challenges in quality control (QC), particularly as traditional methods may not be suitable for small-scale or on-demand manufacturing. To address these challenges, it is essential to develop flexible, precise, and efficient QC strategies that ensure product integrity. This review focuses on non-destructive spectroscopic- and imaging-based testing techniques that can bridge this gap. Techniques such as Near-Infrared Spectroscopy, Raman Spectroscopy, Terahertz Spectroscopy, Optical Coherence Tomography, and Hyperspectral Imaging provide robust alternatives to conventional QC approaches. Moreover, Machine Vision (MV) is emerging as a promising tool for real-time defect detection and visual inspection. When integrated with advanced algorithms and artificial intelligence, MV enables automated decision-making and defect identification in 3DP pharmaceuticals. Recent advancements in deep learning, especially through Convolutional Neural Networks (CNNs) and You Only Look Once (YOLO)-based models, have further enhanced the potential of MV in this domain, offering improved accuracy, speed, and adaptability under varying conditions. This review also includes a comparative evaluation of these techniques, highlighting the increasing importance of non-destructive tools, particularly MV, in supporting innovation and ensuring quality within an increasingly personalized pharmaceutical landscape. Furthermore, it also discusses existing gaps, regulatory challenges, and the need for standardization to ensure the safe and reliable integration of these technologies into pharmaceutical manufacturing workflows.
10 Apr 2026
Read appraisal →Analytical chemistry
SIBioX: A Matrix Based Bioinformatics Analysis Tool Based on Swarm Intelligence Algorithm
Biological matrix data are essential for computational analysis, providing a structured framework to identify patterns and relationships in biological systems. Many other biological data types, including sequences, networks, and images, can be transformed into matrix representations through feature extraction and encoding. However, their high dimensionality complicates analysis, leading to increased computational complexity and the risk of overfitting, known as the curse of dimensionality. To address these challenges, we developed SIBioX, a matrix-based bioinformatics tool powered by swarm intelligence algorithms. It integrates 54 swarm intelligence methods, 5 conventional feature selection techniques, and 17 machine learning models, enabling comprehensive analysis of biological matrix data. With a user-friendly graphical interface, it supports operations such as feature normalization, selection, classification, clustering, statistical analysis, and data visualization. Additionally, it converts nonmatrix biological data, like gene and protein sequences, into matrix formats for further study. Experimental results demonstrate that SIBioX not only attains high accuracy in feature selection but also effectively reduces dimensionality, thereby streamlining bioinformatics workflows and promoting greater efficiency in biomedical research.
10 Apr 2026
Read appraisal →Biochemical and biophysical research communications
Interpretable prognostic modeling of glioblastoma using cross-cohort transcriptome integration and machine learning approaches
Glioblastoma (GBM) is an aggressive brain tumor with highly variable patient outcomes due to pronounced molecular heterogeneity. Prognosis remains dismal (median survival ∼15 months) and current prognostic models often function as "black boxes," lacking interpretability and limiting clinical utility. There is an urgent need for interpretable prognostic tools to better stratify GBM patients. This study performed cross-cohort, cross-platform transcriptome data integration (TCGA RNA-seq and GEO microarrays) and incorporated inferred immunogenomic features to capture GBM's complexity. An automated machine learning (AutoML) pipeline tested over 100 algorithmic combinations to build an optimal survival prediction model. The final model is a 22-gene signature, and SHAP (SHapley Additive exPlanations) analysis was applied to explain each gene's contribution to risk. Key genes identified by the model (e.g. UBE2W, EID1, HS2ST1) were validated by qRT-PCR and Western blot, confirming their dysregulated expression in GBM cell lines. The 22-gene model achieved a concordance index of ∼0.72 and was validated on independent cohorts (TCGA training and GEO validation), demonstrating robust performance. It effectively stratified patients into high- and low-risk groups with significant survival differences. High-risk tumors were associated with an immune-cell-enriched yet immune-evasive microenvironment, showing greater infiltration of immunosuppressive cells and higher TIDE scores (indicating immune escape). In contrast, low-risk patients had a more favorable immune profile, and their tumors were predicted to be more sensitive to multiple chemotherapeutic agents. This interpretable transcriptome-based integrative prognostic model can serve as a valuable tool for GBM risk stratification and may guide therapeutic decision-making by highlighting potential targets. Not only does it improve outcome prediction, but it also identifies novel prognostic biomarkers, holding promise for personalized treatment and clinical translation in glioblastoma.
10 Apr 2026
Read appraisal →Proceedings of the National Academy of Sciences of the United States of America
Reconstruction of human metabolic models with large language models
Genome-scale metabolic models (GEMs) have become essential tools for understanding human metabolism. Here, we introduce Human2, a consensus human GEM with enhanced precision and biological relevance, which leverages large language models (LLMs) and GitHub Action checks to streamline automated, efficient, and collaborative curation. Human2 supports the reconstruction of tissue- and organ-specific models tailored to sex- and age-specific human groups. By integrating transcriptomic, proteomic, and kinetic data, we reveal distinct metabolic features across these groups, such as significant differences in arachidonic acid and leukotriene metabolism. The specific models were integrated into a dynamic whole-body framework, marking an enzyme-constrained dynamic model that simulates interorgan metabolite exchanges under varying nutritional states, from feeding to fasting. Our work highlights the transformative role of LLMs in GEM reconstruction and introduces a whole-body dynamic simulation that integrates kinetic data, offering a powerful resource for multiscale human metabolism modeling.
10 Apr 2026
Read appraisal →Lupus science & medicine
Unsupervised clustering of clinical and laboratory features of systemic lupus erythematosus: insights from a multicentre cohort
OBJECTIVE: This study explored the relationship between clinical phenotypes and immuno-molecular features of systemic lupus erythematosus (SLE) using unsupervised machine learning and multi-omics integration. METHODS: A multicentre cohort of 1065 SLE patients from five teaching hospitals was studied. Unsupervised clustering was performed using integrated clinical and laboratory data to identify distinct phenotypic clusters. Multi-omics profiling, including proteomics and transcriptomics, was conducted for each cluster, comparing with healthy controls. In addition, 899 patients were prospectively followed for over 1 year to assess therapeutic responses and remission outcomes. RESULTS: Unsupervised clustering identified five distinct clusters of SLE based on clinical phenotypes and immunological signatures, and an intrinsic association was found between each cluster and immune-inflammatory features. Cluster 1 (renal; 14.27%) had predominant renal involvement (87.5%) and high disease activity. Cluster 2 (mucocutaneous; 39.53%) exhibited mainly cutaneous manifestations (72.45%) with mild visceral involvement and the highest rates of achieving low disease activity state (46.42%). Cluster 3 (neuropsychiatric; 14.74%) had a high frequency of neuropsychiatric manifestations (96.18%) and anti-U1 ribonucleoprotein antibodies positivity (42.04%). Cluster 4 (haematologic; 22.63%) was characterised by haematologic involvement, predominantly cytopenia (95.85%), with frequent antiphospholipid antibody positivity and direct Coombs positivity (87.55%). Cluster 5 (cardiopulmonary; 8.83%) exhibited prominent cardiopulmonary involvement (97.87%) and serositis, with enrichment of inflammatory CD161+ regulatory T cells. Transcriptomic and proteomic analyses confirmed distinct molecular signatures and cluster-specific enrichment of biological pathways. Key molecule apolipoprotein A4 was validated using enzyme-linked immunosorbent assay. Regarding therapeutic outcomes at 1 year follow-up, Cluster 2 had the highest proportions achieving lupus low disease activity state (46.42%) and tapering glucocorticoids. Cyclophosphamide use was associated with greater clinical improvement (r=0.284; p=0.023) in Cluster 3, while in Cluster 5, rituximab use was associated with favourable responses (r=0.286; p=0.019). CONCLUSIONS: We identified five SLE clusters with distinct clinical, immunological features and treatment outcomes, demonstrating an intrinsic link between clinical involvement and immune-inflammatory alterations.
9 Apr 2026
Read appraisal →PloS one
Deep learning for adaptive chemotherapy: A DDPG-based approach to optimizing tumor-immune dynamics
In this article, we propose a deep reinforcement learning based chemotherapy regulation framework to realize personalized and dynamic optimization of cancer treatment. We use a nonlinear dynamic system to model the dynamic evolution of the tumor microenvironment including tumor cell, normal cell and immune cell interactions, with drug concentration serving as the control input variable. The Deep Deterministic Policy Gradient (DDPG) algorithm makes agents can study optimal dosing strategy in a continuous space of movement to inhibit tumor growth effectively and minimize damage to normal tissues. To make the strategy more stable, Gauss noise is added to the model to simulate physiological oscillations and uncertainties in the treatment reaction. Experimental results show that it can control the growth of tumor in various initial scenarios and the accumulation of the drug concentration with high flexibility and safety. Our technique provides a feasible technical way for precision, low toxicity adaptive chemotherapy.
9 Apr 2026
Read appraisal →The New England journal of medicine
Setidegrasib in Advanced Non-Small-Cell Lung Cancer and Pancreatic Cancer
BACKGROUND: The KRAS p.G12D variant occurs in 5% of patients with non-small-cell lung cancer (NSCLC) and is the most common substitution variant in pancreatic ductal adenocarcinoma, occurring in 40% of patients, but no targeted therapies directed against this variant are currently approved for clinical use. Setidegrasib (ASP3082) is a first-in-class KRAS G12D-targeted protein degrader. METHODS: We conducted this phase 1 study to evaluate the safety, pharmacokinetics, pharmacodynamics, and antitumor activity of setidegrasib in patients with previously treated advanced solid tumors harboring KRAS p.G12D variants. The primary objectives were to evaluate the safety profile, as indicated by dose-limiting toxic effects and adverse events (the primary end points), and to determine the phase 2 dose. Setidegrasib was administered intravenously once weekly at doses of 10 to 800 mg. RESULTS: Overall, 203 patients were enrolled. Among the 76 patients who received setidegrasib at a dose of 600 mg, which was ultimately selected as the phase 2 dose, adverse events occurred during treatment in all the patients, with events of grade 3 or higher in 42%. Treatment-related adverse events occurred in 93% of the patients; the most common were transient infusion-related reactions (in 80%) and nausea (in 30%). Adverse events led to discontinuation in 2 patients. Among the 45 patients with NSCLC who received the 600-mg dose, 36% (95% confidence interval [CI], 22 to 51) had a partial response, the median progression-free survival was 8.3 months (95% CI, 4.1 to could not be estimated), and the estimated 12-month overall survival was 59% (95% CI, 40 to 74). Among the 21 patients with metastatic pancreatic ductal adenocarcinoma who received the 600-mg dose as second- or third-line treatment (of whom 67% received setidegrasib as third-line treatment), 24% (95% CI, 8 to 47) had a response, the median progression-free survival was 3.0 months (95% CI, 1.4 to 6.9), and the median overall survival was 10.3 months (95% CI, 4.2 to 13.0). CONCLUSIONS: Setidegrasib was associated with antitumor activity and a low incidence of treatment discontinuation due to adverse events in patients with previously treated advanced KRAS p.G12D-mutated NSCLC or pancreatic ductal adenocarcinoma. (Funded by Astellas Pharma; ClinicalTrials.gov number, NCT05382559.).
9 Apr 2026
Read appraisal →Lifetime data analysis
Q-learning via deep learning-based Buckley-James method for non-linear censored data
In healthcare, personalized treatment strategies are vital for improving patient outcomes, especially under right-censored survival data. We propose Dynamic Deep Buckley-James Q-Learning, a novel counterfactual Q-learning algorithm that integrates deep learning with the Buckley-James method to simultaneously address censoring and nonlinear modeling challenges. By explicitly capturing complex, nonlinear interactions between covariates and treatment effects, the algorithm robustly estimates optimal dynamic treatment regimes. Leveraging a counterfactual framework, we define and estimate potential survival outcomes under hypothetical treatment sequences, enabling unbiased Q-function estimation even in the presence of time-dependent covariates and right censoring. The algorithm maximizes the expected imputed survival reward under these counterfactual scenarios. Simulation studies and real-world data analysis demonstrate its superior performance in predictive accuracy and treatment decision-making, offering a powerful framework for individualized care in complex clinical settings.
6 Apr 2026
Read appraisal →Genetics
Mondo: integrating disease terminology across communities
Precision medicine aims to enhance diagnosis, treatment, and prognosis by integrating multimodal data at the point of care. However, challenges arise due to the vast number of diseases, differing methods of classification, and conflicting terminological coding systems and practices used to represent molecular definitions of disease. This lack of interoperability artificially constrains the potential for diagnosis, clinical decision support, care outcome analysis, as well as data linkage across research domains to support the development or repurposing of therapeutics. There is a clear and pressing need for a unified system for managing disease entities-including identifiers, synonyms, and definitions. To address these issues, we created the Mondo disease ontology-a community-driven, open-source, unified disease classification system that harmonizes diverse terminologies into a consistent, computable framework. Mondo integrates key medical and biomedical terminologies, including Online Mendelian Inheritance in Man (OMIM), Orphanet, Medical Subject Headings (MeSH), National Cancer Institute Thesaurus (NCIt), and more, to provide a comprehensive and accurate representation of disease concepts with fully provenanced and attributed links back to the sources. Mondo can be used as the handle for curation of gene-disease associations utilized in diagnostic applications, research applications such as computational phenotyping, and in clinical coding systems in clinical decision support by pointing the clinician to the numerous knowledge resources linked to the Mondo identifier. Mondo's community-centric approach, stewarded by the Monarch Initiative's expertise in ontologies, ensures that the ontology remains adaptable to the evolving needs of biomedical research and clinical communities, as well as the knowledge providers.
5 Apr 2026
Read appraisal →Annals of surgical oncology
A Deep Learning-Based Multimodal Clinico-Histology-Genomic Prognostic Model in Prostate Cancer
BACKGROUND: Prostate cancer remains a leading cause of cancer mortality, yet current risk stratification systems inadequately integrate multidimensional tumor characteristics. This study aims to develop a deep learning-based multimodal prognostic model that combines genomic signatures, histomorphological features from whole-slide imaging (WSI), and clinical parameters to improve risk stratification and therapeutic decision-making. MATERIALS AND METHODS: We constructed a deep learning framework using two independent cohorts: The Cancer Genome Atlas (TCGA) for training and the Prostate, Lung, Colorectal and Ovarian (PLCO) trial for external validation. The model sequentially extracted 768-dimensional histopathological features from hematoxylin and eosin (H&E)-stained WSIs, predicted genomic scores, and histopathological scores, and integrated these with clinical variables via Cox regression to generate a multimodal prognostic score. Performance was evaluated through Kaplan-Meier analysis, Harrell's concordance index, and multivariate Cox regression. RESULTS: The prognostic score demonstrated superior prognostic accuracy (C-index: 0.774) compared with unimodal scores (genomic, histopathological, clinical) and NCCN risk stratification (C-index: 0.706-0.746, p < 0.05). High-risk patients identified by the multimodal model had significantly shorter progression-free intervals (HR = 9.088, 95% CI 6.033-13.691, p < 0.0001) and prostate cancer-specific mortality (HR = 8.787, 95% CI 3.238-23.847, p < 0.0001). Subgroup analysis within NCCN high-risk patients revealed distinct survival trajectories (p < 0.001). Gene set enrichment linked multimodal scores to tumor-relevant pathways. CONCLUSIONS: This integrative model eliminates reliance on genomic testing by computationally inferring genomic features from histopathology, while significantly enhancing prognostic precision. By stratifying heterogeneous patient populations and refining existing NCCN classifications, the prognostic score offers clinical potential for personalized risk assessment and optimized therapeutic strategies.
4 Apr 2026
Read appraisal →Critical reviews in oncology/hematology
Artificial intelligence and multi-omics convergence in breast cancer: Revolutionizing diagnosis, prognostication, and precision oncology
Breast cancer (BC) is a highly heterogeneous malignancy and remains a major cause of cancer-related mortality among women worldwide. Advances in multi-omics profiling spanning genomics, transcriptomics, epigenomics, proteomics, and metabolomics have enabled finer subtype stratification and more comprehensive characterisation of tumour biology, thereby accelerating the discovery of diagnostic and prognostic biomarkers and actionable therapeutic targets. Nonetheless, translating multi-layer molecular signals into clinically robust decision support remains challenging because of the high dimensionality and heterogeneity of omics data, cross-cohort and cross-platform variability, and the fragmentation inherent to single-modality analyses. This review summarises how multi-omics studies have refined BC subtype definitions and advanced biomarker and target identification, and then synthesises recent progress in artificial intelligence, particularly deep learning, for integrating multi-omics with imaging, pathology, and clinical variables to improve diagnosis, risk stratification, prognosis prediction, and treatment response assessment. We critically examine representative multimodal integration frameworks and emerging deep learning architectures that learn both shared and modality-specific representations, which in many settings enable more accurate patient-level prediction than unimodal baselines. We further delineate key barriers to clinical translation, including cross-centre heterogeneity and inconsistent endpoint definitions, structural missingness of modalities in real-world workflows, inadequate cross-platform normalisation, limited interpretability and auditability, and a lack of prospective validation. Finally, we propose realistic next steps, including standardised and auditable preprocessing pipelines, missingness-aware fusion strategies, explainable and uncertainty-aware modelling, privacy-preserving multi-centre learning, and prospective, workflow-based evaluation. Collectively, these perspectives provide a roadmap for advancing multimodal AI-multi-omics integration toward reliable clinical deployment in BC management.
4 Apr 2026
Read appraisal →The Lancet. Oncology
Deep learning on histopathological images to predict breast cancer recurrence risk and chemotherapy benefit: a multicentre, model development and validation study
BACKGROUND: Genomic assays such as Oncotype DX have transformed adjuvant treatment selection for hormone receptor-positive, HER2-negative, early breast cancer but remain inaccessible to many patients because of high cost and logistical barriers. We aimed to develop and validate an artificial intelligence (AI) model that estimates Oncotype DX 21-gene recurrence scores directly from routine histopathology slides and clinicopathological variables. METHODS: In this multicentre, model development and validation study, a multimodal deep-learning model was trained on digital whole-slide images and clinical features using a foundation model pre-trained on 171 189 histopathology slides for predicting Oncotype DX recurrence score. We included slides from patients with hormone receptor-positive, HER2-negative, invasive breast cancers and without scanning artifacts and with at least 100 tissue tiles (1·6 mm2). The model was fine-tuned and validated on the TAILORx randomised trial (8284 patients after quality control). Prognostic and predictive performance was assessed in the TAILORx-test set and externally validated in six independent cohorts (Carmel, Haemek, and Sheba medical centres [Israel], the University of Chicago Medical Center [USA], the Australian Breast Cancer Tissue Bank [Australia], and the Cancer Genome Atlas Breast Invasive Carcinoma project [USA]). FINDINGS: In the TAILORx-test set (n=2407), the AI model classified 1097 (45·6%) patients as low risk, 1021 (42·4%) as intermediate risk, and 289 (12·0%) as high risk. For identifying high genomic-risk disease (recurrence score ≥26), the area under the curve (AUC) was 0·898 (95% CI 0·879-0·913). AI-based risk stratification was prognostic for recurrence-free interval (hazard ratio 2·61 [95% CI 1·68-4·04]), distant recurrence-free interval (2·88 [1·73-4·79]), and disease-free survival (1·32 [0·92-1·89]). Chemotherapy benefit was evident in premenopausal patients classified by AI as being at high risk (0·63 [0·46-0·86]) but absent in postmenopausal patients classified by AI as being at low risk (0·94 [0·78-1·12]). 151 (31·3%) clinically high-risk postmenopausal women (by MINDACT criteria) were reclassified as low AI risk with no chemotherapy benefit. Analysis on external cohorts (5497 patients) showed that the model is transferable to new data with high generalisability (recurrence score ≥26 AUC ranging from 0·858 to 0·903). INTERPRETATION: These findings show that AI applied to routine histopathology can serve as a practical and scalable tool for guiding chemotherapy decisions in hormone receptor-positive, HER2-negative, early breast cancer. This approach has the potential to reduce unnecessary chemotherapy and broaden access to precision oncology, particularly in resource-limited settings where genomic testing remains unavailable or unaffordable. FUNDING: Israel Innovation Authority (Kamin), Zimin Institute for Artificial Intelligence Solutions in Healthcare, Israel Precision Medicine Partnership program, and Israel Cancer Research Fund.
4 Apr 2026
Read appraisal →Current opinion in genetics & development
Deep learning for psychiatric genomics: from tools to applications
The genetic architecture of psychiatric disorders is highly complex, with genome-wide association studies implicating thousands of risk loci. A central challenge is that most of these variants are located in noncoding regions, making it difficult to elucidate their regulatory consequences within the brain's intricate cellular landscape. The recent convergence of advanced artificial intelligence, particularly deep learning (DL), has catalyzed a paradigm shift by providing powerful tools to address this gap. This review traces the evolution of DL in genomics, beginning with task-specific models. We then examine the transformative impact of foundation models, pretrained neural networks that learn the 'language' of biology, including genomic language models, single-cell foundation models, and large language models originally trained on natural language. Finally, we survey applications to key problems in psychiatric genomics. We hope this review provides a comprehensive overview of recent advances in DL for genomics and serves as a bridge to help researchers in psychiatric genomics more effectively understand and apply these frontier methods to guide the development of novel therapeutic strategies for psychiatric disorders.
4 Apr 2026
Read appraisal →The Journal of investigative dermatology
A Metabolism-Driven Prognostic Model and PSMD14-SP1-GYS1 Axis Reveal Therapeutic Vulnerabilities in Melanoma
Melanoma is a highly aggressive cutaneous malignancy characterized by a strong propensity for metastasis and therapy resistance, with its progression being closely linked to metabolic reprogramming. This study integrated multiomics data (The Cancer Genome Atlas, Gene Expression Omnibus, European Nucleotide Archive) and advanced machine learning to develop prognostic and immunotherapy prediction models for melanoma, focusing on 114 metabolism-related pathways. Cox regression identified 70 genes linked to survival, with functional enrichment revealing key metabolic pathway alterations. A metabolism-related prognostic model (MRPM) was constructed using 101 combinations of machine learning algorithms, demonstrating superior predictive accuracy across 4 cohorts. High-risk patients showed worse survival and immunotherapy response in melanoma and other cancers. Tumor microenvironment analysis revealed MRPM's negative correlation with immune infiltration and positive association with tumor purity. Single-cell sequencing highlighted MRPM gene enrichment in melanocytes. Mechanistically, GYS1 (the key gene in MRPM) emerged as a pivotal prognostic gene that promotes melanoma proliferation and metastasis. Regulatory studies uncovered SP1's transcriptional control of GYS1- and PSMD14-mediated stabilization of SP1 through K48-linked ubiquitination removal. In vivo validation confirmed that PSMD14 knockdown suppressed tumor growth through SP1-GYS1 axis disruption. This work establishes MRPM as a robust predictive tool and elucidates the PSMD14-SP1-GYS1 regulatory network as a potential therapeutic target in melanoma metabolism.
4 Apr 2026
Read appraisal →Nature reviews. Clinical oncology
MicroRNAs in oncology: a translational perspective in the era of AI
Over the past three decades, knowledge of microRNA (miRNA) biology has advanced from the initial discovery of their regulatory functions to the finding of abnormal activity in leukaemias, and then to a comprehensive understanding of the roles of miRNAs in both normal physiology and most diseases, with cancer being extensively studied. miRNA dysregulation contributes to tumorigenesis, with certain miRNAs acting as either tumour suppressors or oncogenic factors in a context-dependent manner. A subset of miRNAs have shown promise as tumour biomarkers and therapeutic targets in preclinical studies, with several miRNA-based diagnostic tools and treatments progressing to clinical trials. Artificial intelligence (AI) and machine learning techniques began to be introduced into cancer research and oncology a decade ago and are now on the verge of revolutionizing biomarker identification and clinical trials. In this Review, we highlight important roles of miRNAs in cancer biology and their potential as diagnostic tools and therapeutic targets. In particular, we discuss emerging challenges and opportunities presented by AI-driven data analysis and combinatorial strategies, and how advances in these areas have addressed previous doubts on the clinical translation of miRNA-based biomarkers and therapeutics.
4 Apr 2026
Read appraisal →Cancer Cell
Precision treatment with artificial intelligence assisted subtyping enhances therapeutic efficacy in HR+/HER2- breast cancer: The LINUXtrial.
We report the results of LINUX (NCT05594095), a multicenter, randomized, controlled phase II platform trial aiming to identify effective precision treatments for hormone receptor-positive/human epidermal growth factor receptor 2-negative metastatic breast cancer after resistance to cyclin-dependent kinase 4/6 inhibitor. A total of 105 patients were categorized into four similarity network fusion (SNF) subtypes by artificial intelligence-assisted classification and randomly assigned to receive subtyping-based precision therapy (N = 70) or treatment of physician's choice (N = 35). Results demonstrate superior primary endpoint of objective response rates in the subtyping-based groups compared to controls: 10% versus 0% for SNF1, 65% versus 30% for SNF2, 40% versus 30% for SNF3, and 70% versus 20% for SNF4. Grade 3-4 treatment-related adverse events occurred in 37% of both groups. These findings highlight the clinical benefits of subtyping-based precision therapies, particularly for SNF2 and SNF4 subtypes, warranting further validation in phase III trials.
1 Feb 2026
Read appraisal →J Clin Oncol
Genomics Define Malignant Transformation in Myeloma Precursor Conditions
Multiple myeloma (MM) is consistently preceded by monoclonal gammopathy of undetermined significance (MGUS) and smoldering multiple myeloma (SMM). While these precursor conditions are asymptomatic, they are not entirely benign and carry a lifelong risk of progression to MM. Unlike other cancers defined by pathology, malignant transformation from MGUS or SMM to MM has so far relied on demonstration of clinical end-organ damage as morphology and cytogenetics cannot reliably distinguish them. In this study, using genomic data from 374 patients with MGUS or SMM (277 training, 97 validation), to our knowledge, we demonstrate for the first time the ability to identify malignant transformation in MGUS and SMM. We introduce the concept of genomic MM and genomic MGUS to differentiate the subsets of MGUS and SMM that are biologically malignant with genomic features indistinguishable from MM from the subset that is premalignant and unlikely to progress to malignancy. Importantly, we find that most SMM has biological features of malignant transformation indistinguishable from MM. As expected, this subset that we consider having genomic MM is associated with a high risk of progression to MM although some patients remained progression-free beyond 5 years. Conversely, 60% of MGUS and 10% of SMM have no evidence of malignant transformation (genomic MGUS), with no progression during follow-up. Integration of genomic features with the 2/20/20 International Myeloma Working Group model significantly improved the prediction of progression among genomic MM. These findings support the use of genomic criteria to refine the classification and the risk stratification in myeloma precursor conditions.
1 Jan 2026
Read appraisal →Ageing Res Rev
AI-driven aging digital twins: A roadmap for clinical translation in precision geriatrics
Aging and related diseases account for ⁓70 % of global mortality with declining physiological homeostasis and cognitive function increasing susceptibility to neurodegenerative disorders, cardiovascular diseases and cancer. Treatment is hampered by imprecise diagnostics and limited therapeutic options. Precision medicine involving artificial intelligence (AI)-powered Aging Digital Twin (ADT) technology which integrates multi-source heterogeneous data via advanced AI and deep learning has great potential. Virtual doppelgangers enable real-time health monitoring, predictive analytics and personalized interventions to facilitate early disease detection and optimize risk assessment and treatment strategies. Challenges remain and include age-stratified biases in training datasets and variations in data quality for older populations which may limit model generalizability. Critical concerns regarding data privacy, algorithmic transparency and clinical validation of ADT models remain unresolved. The current review examines the transformative potential of AI-enabled ADTs in precision medicine for aging and highlights technical and ethical limitations.
1 Jan 2026
Read appraisal →J Allergy Clin Immunol
Proteomic profiling and machine learning for endotype prediction in chronic rhinosinusitis
BACKGROUND: Chronic rhinosinusitis (CRS) is a common, heterogeneous upper airway inflammatory disorder, affecting approximately 12% of the general population. The disease is clinically stratified into CRS without nasal polyps and CRS with nasal polyps, including the most severe subtype of nonsteroidal anti-inflammatory drug (NSAID)-exacerbated respiratory disease (N-ERD). OBJECTIVE: To identify molecular signatures and biomarkers allowing for the distinction between different disease endotypes and controls, we used targeted proteomics combined with bioinformatics and machine learning analyses. METHODS: Nasal secretions and serum from 80 patients (20 each of CRS without nasal polyps, CRS with nasal polyps, N-ERD, and disease controls) were subjected to high-throughput targeted proteomics (Olink). The expression patterns of 161 and 2677 proteins, for nasal secretions and serum, respectively, were analyzed alongside clinical evaluations of nasal polyp and smell test scores. RESULTS: Two distinct expression patterns were identified in nasal secretions: proteins associated with macrophage recruitment and type 2 inflammation were increased in CRS with nasal polyps and N-ERD, whereas proteins associated with innate immunity, particularly Toll-like receptor 4 signaling, were gradually downregulated from disease control to N-ERD. Furthermore, using machine learning, we confirmed 2 potential biomarkers for nasal polyposis: the glial cell line-derived neurotrophic factor in nasal secretions and Charcot-Leyden crystal protein in serum. CONCLUSIONS: Our findings provide unique insights into CRS pathophysiology and highlight potential biomarkers for precision diagnosis and treatment, particularly in severe cases such as N-ERD.
1 Jan 2026
Read appraisal →Genes (Basel)
The Evolving Role of Artificial Intelligence in Medical Genetics: Advancing Healthcare, Research, and Biosafety Management
The integration of artificial intelligence (AI) with medical genetics is transforming healthcare by addressing the analytical challenges posed by the vast complexity of multi-omics data. This review explores the synergistic convergence of these fields, highlighting AI's transformative role in enhancing diagnostic precision, enabling non-invasive molecular profiling through imaging-genetics, and advancing predictive and personalized medicine via polygenic risk scores and pharmacogenomics. AI is also emerging as a powerful generative tool in therapeutic design, accelerating drug discovery, protein engineering, and precision gene editing. However, this powerful synergy introduces significant ethical, regulatory, and biosecurity challenges, including data privacy, algorithmic bias, and the dual-use risks of AI-enabled genetic engineering. The future envisions a responsible co-evolution, with multimodal AI and the concept of the Digital Twin driving precision medicine, underpinned by interdisciplinary collaboration to ensure fairness, transparency, and societal trust. This article charts the current landscape and proposes actionable directions, emphasizing the need for robust governance to harness AI's potential while mitigating its risks for the benefit of human health.
1 Dec 2025
Read appraisal →J Allergy Clin Immunol
Explainable artificial intelligence predicts inflammatory and spatial heterogeneity from nasal polyp histology
BACKGROUND: Chronic rhinosinusitis with nasal polyps is a heterogeneous disorder characterized by diverse inflammatory signatures and endotypes. OBJECTIVE: We sought to develop a histology-based deep learning network for predicting inflammatory gene signatures and spatial patterns in chronic rhinosinusitis with nasal polyps. METHODS: We developed HE2Signature, a deep learning model, using 70 hematoxylin and eosin-stained whole-slide images of nasal polyps paired with corresponding endotypic signature gene expression profiles derived from transcriptomic data. The model was validated in an internal cohort (n = 30) and tested in an independent external cohort (n = 224) from 4 medical centers. The performance was evaluated using correlation and confusion matrix analyses and receiver-operating characteristic curves. Spatial predictions were validated by immunohistochemistry. RESULTS: The HE2Signature demonstrated strong positive correlations between the predicted and actual expression levels of 28 of the 33 signature genes. The internal validation cohort was stratified into distinct endotypes on the basis of predicted signature gene expression, achieving area under the curve values of 0.833, 0.903, and 0.935 for the T1, T2, and T3 endotypes, respectively. In the external cohort, the combination of HE2Signature-predicted Fc epsilon receptor II and CST1 effectively identified the T2 endotype, with a receiver-operating characteristic value of 0.716. Histopathologic examination of high-prediction patches revealed characteristic features associated with signature gene expression. Heatmaps and immunohistochemistry confirmed the accuracy of the model in mapping spatial gene expression patterns. HE2Signature-predicted spatial expression of signature genes correlated with blood and tissue eosinophil counts, Lund-Kennedy score, and Sino-Nasal Outcome Test-22 score, particularly within subepithelial regions. CONCLUSIONS: Our study introduces the first histology-based, explainable deep learning model capable of predicting inflammatory gene signatures and spatial molecular heterogeneity. This proof-of-concept highlights that artificial intelligence-powered histopathologic analysis can generate digital biomarkers by linking tissue patterns with molecular profiles, providing a clinically applicable framework for endotype-guided precision medicine in chronic rhinosinusitis with nasal polyps.
1 Dec 2025
Read appraisal →