Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 15 appraisals
Journal of chemical information and modeling
Functionally Guided Graph Learning for Robust Cross-Patient Cell-Type Annotation in Single-Cell RNA Sequencing
Cross-patient cell-type annotation in single-cell RNA sequencing (scRNA-seq) remains challenging due to pronounced interpatient heterogeneity and distribution shifts across patient-specific cellular contexts. Conventional annotation approaches often rely on proximity-driven graph construction or expression similarity, which may introduce spurious cell-cell connections and lead to unstable knowledge transfer across patients. To address this limitation, we propose PathoGraph, a functionally guided graph learning framework for robust cross-patient cell-type annotation. The proposed method integrates KEGG-7-based biosemantic graph structure learning with cross-patient representation adaptation. Specifically, pathway-derived functional semantic profiles are incorporated to refine patient-specific cell graphs, encouraging biologically coherent neighborhoods and suppressing noise introduced by purely expression-based similarity. Based on the refined graphs, a cross-patient representation adaptation mechanism further aligns embeddings between labeled reference patients and unlabeled query patients to facilitate reliable annotation transfer. Experiments on three cross-patient scRNA-seq data sets, including leukemia, breast invasive carcinoma, and colorectal cancer data sets, demonstrate that PathoGraph achieves stable annotation performance across 32 directed reference-to-query transfer tasks. Across all tasks, PathoGraph obtained an average ACC of 84.28% and an F1-score of 84.08%, showing competitive and stable performance compared with representative marker-based, correlation-based, and model-based annotation methods. Ablation studies further show that removing the biosemantic graph learning module reduces the average accuracy to 83.48%, highlighting the importance of functional-guided graph refinement. In addition, post hoc functional relevance analyses in immune-cell and cancer-associated contexts suggest that the learned cell-cell graphs capture biologically relevant neighborhood structures beyond expression-driven proximity. The source code and processed data are publicly available at: https://github.com/LiYuechao1998/PathoGraph.
29 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 →Cell
Deep learning of functional perturbations from condensate morphology
Biomolecular condensates compartmentalize the interior of cells to organize complex functions, yet linking molecular interactions within condensates to their mesoscale organization remains a major challenge. To bridge this gap, we developed a neural-network-based framework-Deep-Phase (deep learning of phase-separated condensates)-that uses microscopy images to directly measure condensate morphology changes resulting from pharmacological alterations in associated biochemical processes. We use Deep-Phase to precisely quantify time- and concentration-dependent structural perturbations to the multiphase nucleolus and show that they are tightly coupled to potencies of drugs inhibiting ribosomal RNA (rRNA) transcription and processing. Applying Deep-Phase in a chemical screen, we identify a unique nucleolar morphology and discover a role for a DNA topoisomerase in rRNA processing. Mechanistic studies of this morphology provide insights into how the interfaces between nucleolar sub-compartments are maintained. We demonstrate Deep-Phase's adaptability to diverse cell lines, labeling techniques, and condensates, offering a powerful platform for connecting molecular pathways to cellular mesoscale organization.
25 July 2026
Read appraisal →Journal of medicinal chemistry
SMDNet: A Self-Training-Aware and Multi-Modal-Adaptive Deep Learning Network for Low-Data Aβ42 Probe Design and Optimization
Amyloid-β (Aβ) plaque accumulation is a crucial hallmark of Alzheimer's disease, and fluorescence imaging can support disease diagnosis and monitoring. However, Aβ42 probe development is often hindered by trial-and-error experiments due to subtle structure-property effects. Here, we developed SMDNet, a self-training-aware and multimodal-adaptive deep learning (DL) framework for low-data Aβ42 probe design and optimization. SMDNet combines iterative self-training with confidence-aware and distribution-aware sampling to improve data quality, while integrating molecular graphs, fingerprints and protein descriptors through cross-attention and protein-conditional adaptive layer normalization. Ablation studies, external validation and generalization analyses confirmed the strong predictive ability of SMDNet. Interpretability analyses further highlighted chemically meaningful substructures associated with model predictions. As a proof of concept, SMDNet guided the rational design of five ThT-derived probe candidates, with TA3 showing favorable binding affinity and high-contrast imaging performance. Additional validation on coumarin- and naphthalimide-based candidates further supported useful predictive discrimination across distinct fluorescent scaffold classes.
24 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 →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 →Biomacromolecules
Challenges and Vision for Standardization of Biopolymer Data Sets for Machine Learning
Machine learning (ML) is transforming materials research, yet potential for biopolymer discovery remains constrained by fragmented data and nonstandardized reporting. Biopolymers differ significantly from synthetic polymers, requiring specialized approaches to represent their biosynthetic origins, hierarchical structures, and application-specific metrics. In this Perspective, we identify three core challenges limiting biopolymer representation: information encoding, data quality, and data sharing. We describe the most pressing issues and propose commensurate approaches to address each key challenge. Recommendations include the design and adoption of biopolymer-specific fingerprinting and representation frameworks, development of hybrid human-large language model (LLM) data extraction strategies, and expanding Findable, Accessible, Interoperable, Reusable (FAIR)-compliant repositories. We propose a robust foundation to define interoperable, high-quality data sets that capture the full context of biopolymer materials. Standardized metadata, shared ontologies, and community-driven infrastructure would enable scalable, reproducible workflows and accelerate the ML-driven development of biopolymers.
14 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
FABIAN-variant 2026: improved prediction of the effects of DNA variants on transcription factor binding
Variants in promoters and enhancers can alter the binding of transcription factors (TFs), but their functional assessment remains difficult. FABIAN-variant is a web application that predicts the effects of DNA variants on TF binding by comparing position weight matrix (PWM) and transcription factor flexible model (TFFM) scores between reference and variant alleles. Here, we present FABIAN-variant 2026, a major update that expands the prediction model library from ~5000 to over 40 000 models for >1500 human TFs, sourced from nine PWM databases and including 1290 TFFMs. The application now supports the mouse genome (GRCm38 and GRCm39) with over 35 000 models for >1100 mouse TFs. An optional BPNet deep learning scorer provides neural network-based binding predictions for 240 human TFs. Known TF binding site information has been expanded from three to five sources. Predictions for over 1400 heterodimer TF complexes have been added. The web server has been rewritten in Rust and the scoring engine optimized, reducing runtime by ~70%. A RESTful JSON API and a standalone command-line version enable programmatic access and local high-throughput analysis. FABIAN-variant 2026 is available at https://fabianapp.org/variant26/. The web server is free and open to all users and there is no login requirement.
13 July 2026
Read appraisal →Briefings in bioinformatics
Literature-informed gene extraction and ranking for multimodal data fusion.
Published biomedical experiments provide an increasingly rich collection of results and identify genes potentially involved in diverse biological mechanisms. However, individual studies are often confined to narrow experimental contexts and are restricted to single omics layers. Cross-study knowledge aggregation can broaden this perspective and enable the construction of global, context-aware gene rankings. Recent developments in natural language processing have made large-scale literature mining increasingly feasible. This enables the systematic extraction and fusion of symbolic knowledge from published experiments. We present pathXcite, a software that extracts genes associated with specific contexts, such as diseases or biological mechanisms from the literature, and ranks them by contextual relevance. These relevance-based gene rankings can compress a scientific context into a symbolic representation. This representation enables diverse downstream analyses, including cross-context comparisons, network-based analysis, enrichment analysis, and integration with experimental omics data. In multiple use cases, we show how our extraction and fusion strategy can be applied to uncover hidden aspects in biological data.
6 July 2026
Read appraisal →Briefings in bioinformatics
EssTFNet: integration of adaptive time-frequency and DNA language models for interpretable human essential gene prediction
Essential genes are defined as indispensable for an organism's survival. The loss of function of these genes results in cell death or an inability to complete the normal life cycle. Research on essential genes is pivotal in elucidating the origin and evolution of life, as well as in identifying potential therapeutic targets. Therefore, predicting essential genes is of great scientific importance and has many applications in basic research and the biomedical field. In this study, we propose EssTFNet, a novel, interpretable deep learning framework that combines adaptive time-frequency analysis with a DNA language model to achieve accurate prediction of human essential genes while enabling mechanistic biological interpretation. EssTFNet leverages the architecture of ATFNet, which maps DNA and protein sequences into equivalent time-series signals to extract periodic and nonstationary features, enhancing the model's capacity to capture complex sequence patterns. Through feature selection and architectural optimization, EssTFNet achieves a favorable balance among prediction accuracy, model interpretability, and cross-tissue generalization. On the S1 benchmark task, EssTFNet outperformed mainstream sequence-based deep learning methods, achieving an area under the curve of 0.9679 and an area under the precision-recall curve of 0.8491. Additionally, the DeepLIFT attribution method was employed to identify functional motifs associated with gene essentiality, offering valuable insights for experimental validation. For the convenience of researchers, we have developed an easy-to-use web server and made it along with the source code in a GitHub repository: https://github.com/QIANJINYDX/EssTFNet. Overall, this study presents a potentially useful methodological framework for human essential genes prediction, which could provide valuable insights for future research and applications in this field.
5 July 2026
Read appraisal →BioEssays : news and reviews in molecular, cellular and developmental biology
AI in Genomics: From Variant Calling to Multi-Omics Integration
Artificial intelligence (AI) strategies are revolutionizing genomics by extracting complex patterns that traditional statistical pipelines are likely to miss. This mini-review aims to provide a concise overview of how AI is transforming major genomic technologies including variant calling, gene expression analysis, single-cell transcriptomics, CRISPR-Cas9 optimization, and multi-omics integration. In genome sequencing, machine learning variant callers greatly improve the accuracy and the rate at which single nucleotide and structural variants are called. In bulk RNA-Seq, AI augmented quantification, denoising, and differential expression modules complement the highly established STAR-featureCounts-DESeq2 pipeline, revealing subtle signals in big data sets. In single cell transcriptomics, deep learning approaches enhance batch correction, automate cell type annotation, and track developmental trajectories, hence clarifying cellular heterogeneity. AI-assisted guide RNA design, outcome prediction, and nuclease engineering enable more efficient CRISPR-Cas9 editing, reducing experimental cycles, and off-target effects. Finally, integrated platforms that combine genomic, transcriptomic, epigenomic, proteomic, and metabolomic layers provide an integrative view of cellular regulation and disease mechanisms. The review also covers current limitations, sparsity of data, model bias, privacy, and the need for standardized benchmarks and offers future directions in the form of interpretable models, collaborative learning, and open science practices. Together, these developments render AI an indispensable partner to unravel genomic complexity and accelerate precision medicine applications.
3 July 2026
Read appraisal →Scientific reports
Oral cancer in the era of precision medicine: molecular targets and technological innovations
This topical Collection presents a series of studies that examine molecular mechanisms, diagnostic approaches, and therapeutic strategies relevant to oral cancer. The included investigations explore topics ranging from metastasis-associated pathways and immune evasion to emerging detection technologies such as deep learning-based impedance spectroscopy and volatile organic compound analysis. Together, these studies reflect the growing convergence of molecular oncology, digital diagnostics, and translational clinical research in shaping the future of oral cancer management. This Collection represents an ongoing effort to consolidate current knowledge and guide future research in oral squamous cell carcinoma.
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 →Neuroscience
Comparative analysis of key phagocytic genes in humans and mice using machine learning integrated with single-cell RNA sequencing
Microglial phagocytosis is essential for neurological recovery after intracerebral hemorrhage (ICH). Using single-cell RNA sequencing, we compared microglial responses in murine and human ICH and identified striking species-specific temporal patterns. Murine microglia exhibited a sustained enhancement of phagocytic activity, whereas human microglia showed only a transient increase followed by a decline and persistent inflammation. To identify genes associated with phagocytic differences, we evaluated five machine learning models and selected XGBoost as the best-performing model. This analysis identified Tlr2 in mice and CLEC7A in humans as genes associated with microglial phagocytic status. Inferred transcription factor activity analysis further revealed stronger phagocytosis- and inflammation-associated transcriptional activity in murine phagocytic microglial subclusters, whereas human microglia were predominantly characterized by inflammation-associated transcription factors. Consistent with these results, Tlr2 expression was markedly increased at day 14 in single-cell data, and immunostaining confirmed its colocalization with IBA1+ microglia and upregulation at days 3 and 7 after ICH. Together, our findings demonstrate that integrating single-cell RNA sequencing with machine learning facilitates the identification of phagocytosis-associated genes and reveals both conserved and divergent patterns of microglial phagocytosis, providing new insights into species-specific responses to ICH.
6 Apr 2026
Read appraisal →