Research Appraisals
Evidence-based critical appraisals of the latest medical research, systematically evaluated using Oxford CEBM methodology.
Showing 30 appraisals
PloS one
Fundus image analysis of retinitis pigmentosa using artificial intelligence
Retinitis pigmentosa (RP) is a group of inherited retinal diseases that are caused by genetic defects that lead to progressive photoreceptor loss and eventual blindness. Early diagnosis would be helpful for effective management of the disease; however, many patients stay unaware of early symptoms. Meanwhile, fundus images are widely obtained during routine medical checkups but are underused for detecting RP. This study explores the effectiveness of finetuning deep learning models, pre-trained for general visual tasks, to identify RP from color fundus images. The dataset comprised 321 color fundus images from 201 Japanese subjects at Keio University Hospital, including 200 images from 107 patients with retinitis pigmentosa and 121 images from 94 non-retinitis pigmentosa subjects. Multiple images were available for some subjects. Using transfer learning, pretrained convolutional neural network models -VGG16, Resnet50, and InceptionV3- were finetuned to detect RP. As a result, Inception V3 achieved the best accuracy of 96.97%, which matches the average diagnostic accuracy of ophthalmologists. Gradient-weighted Class Activation Mapping (Grad-CAM) suggested that the model attended to clinically relevant fundus regions, including the peripheral retina and posterior pole, which may reflect features such as peripheral degenerative changes and retinal vascular attenuation. These findings support the potential interpretability of the finetuned model and suggest that deep learning may assist ophthalmologists in RP screening as a supportive tool.
25 July 2026
Read appraisal →Journal of medical Internet research
Initial-Visit Specialty Triage in Rare Diseases Using Large Language Models: Retrospective Benchmarking Study
BACKGROUND: Specialty triage at first contact is an overlooked step in early diagnostic pathways for rare diseases. Patients often present with overlapping, multisystem, and atypical manifestations, making first-visit specialty selection challenging and potentially prolonging diagnostic pathways. OBJECTIVE: The aim of this study is to evaluate the accuracy, response time, and consistency of large language models (LLMs) for initial-visit specialty triage in rare diseases across multiple datasets, and to compare their performance with registered nurses and nonmedical participants. METHODS: In this retrospective benchmarking study, we used 5 rare disease datasets: a publication-derived case set, 3 RareBench-derived datasets, and a Facial phenotype-Gene-Disease Dataset-derived set. Fourteen LLMs were evaluated over 5 independent runs per case. Performance was assessed using accuracy, response time, and consistency, with subgroup analyses by model accessibility, reasoning mode, parameter scale, and phenotype count. Human comparison was conducted on the publication-derived case set using registered nurses and nonmedical participants. RESULTS: Across datasets, model accuracy ranged from 0.4378 to 0.7141. Claude-opus-4-5 achieved the highest accuracy (0.7141) and consistency (0.9653), averaging 10.79 seconds per case. GPT-5.1 had the shortest response time (3.39 s/case) and high accuracy (0.6948). Proprietary models had numerically higher average accuracy than open-weight models (0.6973 vs 0.6365). Nonthinking models achieved higher average accuracy than thinking models (0.6789 vs 0.5826) and had shorter response times, although this exploratory comparison was based on a small number of thinking models. Accuracy varied by phenotype count, with higher performance in cases with 1 to 2 or more than 14 phenotypes. On the publication-derived case set, LLMs achieved higher average accuracy than registered nurses and nonmedical participants (0.5978 vs 0.4914 and 0.4573). CONCLUSIONS: LLMs showed potential as assistive tools for initial-visit specialty triage in rare diseases. Model choice, reasoning mode, and phenotype information density influenced performance, but subgroup findings should be interpreted cautiously. Future work should evaluate LLM-based specialty triage in prospective clinical settings and develop clinician-supervised workflows with traceable evidence support.
24 July 2026
Read appraisal →Nucleic acids research
SNPnexus: an enhanced web platform for large-scale and multi-sample variant analysis (2025 update)
SNPnexus is a long-standing web-based platform for the functional annotation and prioritization of genetic variants. Since its previous release, SNPnexus has undergone substantial backend re-engineering resulting in major performance improvements and a complete restructuring of the underlying datasets. A redesigned interface now enables larger queries and multi-sample analysis enabling comparative workflows such as identifying shared pathogenic variants in disease cohorts and divergent mutations in cancer evolution studies. SNPnexus increased its capacity to 150 000 variants per query and introduced pre-annotation filters that allow users to restrict analyses to selected genes or genomic regions, improving efficiency while enabling targeted interrogation of high-priority targets. SNPnexus integrates updated and expanded annotations across both GRCh37 and GRCh38, covering genomic consequences, in silico pathogenicity predictions, population allele frequencies, evolutionary conservation, regulatory elements, biological pathways, and clinical associations. The refreshed result interface provides interactive visualizations for single-sample and cohort-level outputs, together with advanced filtering and export options. Optional user accounts now support query history and real-time job monitoring while preserving full, unregistered access for all users. SNPnexus remains free and open to all users without login requirements at https://snpnexus.org/.
13 July 2026
Read appraisal →American journal of human genetics
A transparent and generalizable deep-learning framework for genomic ancestry prediction
Accurately characterizing genetic ancestry is critical for ensuring reproducibility and fairness in genomic studies and downstream health research. This study aims to address the prediction of ancestry from genetic data using deep learning, with a focus on generalizability across datasets with diverse populations and on explainability to improve model transparency. We adapt the Diet Network, a deep-learning architecture proven to be effective in handling high-dimensional data, to learn population ancestry from single-nucleotide polymorphism (SNP) data using the populational Thousand Genomes Project dataset. Our results highlight the model's ability to generalize to diverse populations in the CARTaGENE, Montreal Heart Institute, and All of Us biobanks and that predictions remain robust to high levels of missing SNPs. We show that, despite the lack of North African populations in the training dataset, the model learns latent representations that reflect meaningful population structure for North African individuals in the biobanks. To improve model transparency, we apply Saliency Maps, DeepLift, GradientShap, and Integrated Gradients attribution techniques and evaluate their performance in identifying SNPs leveraged by the model. Using DeepLift, we show that the model's predictions are driven by population-specific signals consistent with those identified by traditional population-genetics metrics. This work presents a generalizable and interpretable deep-learning framework for genetic-ancestry inference in large-scale biobanks with genetic data. By enabling more widespread genomic ancestry characterization in these cohorts, this study contributes practical tools for integrating genetic data into downstream biomedical applications, supporting more inclusive and equitable healthcare solutions.
4 July 2026
Read appraisal →Croatian medical journal
Artificial intelligence enables scale, consistency, and rigor in forensic identity inference.
Advances in forensic genomics, which include massively parallel sequencing, dense single nucleotide polymorphism testing, and forensic genetic genealogy (FGG), have greatly expanded the range of cases in which DNA evidence can generate investigative leads. As a result, the primary limitations in modern forensic DNA analysis are no longer analytical sensitivity or marker availability, but the ability to reason consistently, transparently, and at scale over increasingly complex genetic, genealogical, and contextual information. Current forensic workflows remain predominantly human-centered, relying on manual reasoning that is difficult to standardize, reproduce, document, or scale across growing case inventories. The potential of artificial intelligence (AI) is described as an enabling layer for forensic identity inference, defined here as computational decision-support systems that structure, prioritize, and document reasoning over genetic associations, genealogical structures, and investigative context during identity hypothesis development. While formal statistical inference quantifies evidentiary weight, identity inference governs how evidence is explored, combined, and acted upon during investigations. AI-assisted systems can augment, but not replace, expert judgment by supporting scalable prioritization, relational reasoning, and systematic documentation of analytical decisions, while reducing bias. Properly designed AI-enabled systems offer a path to sustainably scaling FGG while supporting scientific rigor, accountability, and public trust.
15 June 2026
Read appraisal →The New England journal of medicine
Subretinal Gene Therapy for X-Linked Retinoschisis
BACKGROUND: X-linked retinoschisis is a recessive disease characterized by progressive macular degeneration and vision loss due to pathogenic variation in RS1. METHODS: We administered a single subretinal injection of an AAV8 vector containing human RS1 complementary DNA (scAAV8-hRS1) into one eye of patients 5 to 18 years of age who had X-linked retinoschisis. The primary end point was safety during the 52-week period after injection. Secondary end points included the change from baseline to week 52 in the best corrected visual acuity (BCVA), retinal structure (assessed with swept-source optical coherence tomography; SS-OCT), the function of photoreceptor and bipolar cells (assessed with full-field electroretinography), and macular sensitivity to light (assessed with microperimetry). RESULTS: A total of 12 patients were enrolled. The dose-escalation phase included two cohorts of 3 patients each who received scAAV8-hRS1 at a dose of 7.5×1010 or 1×1011 vector genomes. In the dose-expansion phase, 3 additional patients were enrolled in each cohort. Overall, 56 adverse events were reported during the 52 weeks after surgery. No patient was reported to have an adverse event of grade 3 or higher or ocular inflammation. A macular hole in the treated eye was observed at week 1 in 1 patient. The mean increase at week 52 in the BCVA was 10.8 letters among the treated eyes and 2.4 letters among the untreated eyes. SS-OCT imaging showed closure of the macular schisis cavity by week 13 in the treated eye in all 12 patients. The mean change at week 52 in central retinal thickness was -437.7 μm among the treated eyes and -17.2 μm among the untreated eyes; the outer retinal layers in the treated eyes of 9 patients were continuous at week 52. No clinically meaningful changes in the function of photoreceptor and bipolar cells or macular retinal sensitivity were observed in the treated eyes. CONCLUSIONS: In this study of subretinal gene therapy with scAAV8-hRS1 in 12 patients with X-linked retinoschisis, there were no reports of adverse events of grade 3 or higher or ocular inflammation. Further clinical testing of scAAV8-hRS1 is warranted. (Funded by the National Natural Science Foundation of China and others; Chinese Clinical Trial Registry number, ChiCTR2300076682.).
13 June 2026
Read appraisal →Medicine
Prevalence of GJB2 gene mutations in nonsyndromic hearing impairments: A systematic review and meta-analysis
BACKGROUND: Nonsyndromic hearing impairment (NSHI) is the most common type of inherited hearing loss. Mutations in GJB2, which encodes connexin 26, are a major cause worldwide, but their prevalence and variant distribution vary across populations. To systematically evaluate the global prevalence of GJB2 mutations and 5 hotspot variants (c.35delG, c.176_191del16, c.235delC, c.299_300delAT, and c.109G > A) in NSHI patients, and assess their diagnostic relevance. METHODS: A meta-analysis was conducted on studies published between January 2019 and June 2024 retrieved from PubMed, Scopus, Web of Science, and Cochrane Library. Only high-quality studies (Newcastle-Ottawa Scale ≥ 7) with molecular diagnostic data were included. Pooled prevalence, 95% confidence intervals, and heterogeneity (I2) were calculated. Subgroup and meta-regression analyses were performed according to geographic region. RESULTS: Fifty-one studies from 24 countries covering 18,968 patients with NSHI were included. The overall prevalence of GJB2 mutations was 25.9% (95% confidence intervals: 21.7-30.1%; I2 = 96%). The variant-specific rates included c.235delC (15.2%), c.35delG (12.0%), c.109G > A (7.6%), c.299_300delAT (3.1%), and c.176_191del16 (0.7%). The highest prevalence occurred in the Middle East (38.5%), whereas Africa had the lowest (11.1%). CONCLUSION: GJB2 mutations show marked geographic and ethnic variability in populations with NSHI. These findings support region-specific genetic screening to improve the early diagnosis, counseling, and targeted interventions for hereditary hearing loss.
31 May 2026
Read appraisal →Journal of medical Internet research
Adaptive Fast-Slow Large Language Model Framework for Multidimensional Classification of Prenatal Ultrasound Reports: Comparative Study
BACKGROUND: Phenotype-driven prenatal diagnosis relies on the precise correlation between ultrasound findings and genetic outcomes; however, this process is hindered by the unstructured nature of clinical ultrasound reports. While large language models (LLMs) hold the potential to address this challenge, their specific application in this domain remains systematically underexplored. OBJECTIVE: To establish an effective LLM implementation framework for the clinical multidimensional classification of prenatal ultrasound reports, we evaluated the open-source DeepSeek-V3.2 family on real-world anomalous reports-covering both factual and subjective categories-while integrating retrieval-augmented generation (RAG) and chain-of-thought (CoT) reasoning. METHODS: From a cohort of 4256 pregnancies, we extracted 254 reports with fetal anomalies. We comprehensively evaluated both the high-speed base model (DeepSeek-V3.2-B) and the reasoning-enhanced model (DeepSeek-V3.2-R) across all 5 classification dimensions, comprising 4 factual extraction tasks-primary classification, standardized terminology, anatomical system, and abnormality count-and 1 subjective severity assessment. We further explicitly evaluated the efficacy of RAG for the subjective tasks. Finally, to validate the clinical utility of this approach, we performed a correlation analysis between the expert-validated multidimensional phenotypic profiles and definitive genetic outcomes derived from amniocentesis. RESULTS: While V3.2-B achieved high efficiency in factual tasks (accuracy and F1-score >90%), it underperformed in subjective severity grading (56.6% accuracy), exhibiting a recall of 0 for minor anomalies. Crucially, while RAG significantly improved both models' performance on internal retrieval datasets (P<.05), this benefit did not generalize to external test datasets (P>.05). In contrast, the V3.2-R model utilizing CoT reasoning achieved superior robustness (86% accuracy and F1-score=0.75) on external data without RAG; notably, introducing RAG to V3.2-R degraded performance to 81%, suggesting potential noise interference. Clinical validation against amniocentesis outcomes confirmed that accurate multidimensional phenotypic profiles significantly stratified pathogenic genetic risks. CONCLUSIONS: The rapid base models are efficient for factual classification, and RAG enhances performance on data similar to the knowledge base, whereas CoT is indispensable for subjective assessment. Within the constraints of our dataset and current retrieval implementation, CoT proved more robust than RAG for subjective assessment. However, this finding is specifically tied to our experimental setup and should not be generalized as a universal conclusion. We recommend clinically adopting this adaptive "fast-slow" LLM framework to efficiently perform the multidimensional classification of prenatal ultrasound anomalies. This privacy-preserving, locally deployable solution provides a scalable path to accelerate phenotype-genotype research and optimize invasive diagnostic decision-making.
29 May 2026
Read appraisal →Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology
Genetic Creutzfeldt-Jakob disease associated with 5-octapeptide repeat insertion in the PRNP gene: case and pedigree report and literature review
BACKGROUND: Genetic prion diseases caused by octapeptide repeat insertions in the PRNP gene are rare. 5-octapeptide repeat insertion (5-OPRI) is an uncommon subtype that usually manifests as Creutzfeldt-Jakob disease (CJD) but shows marked variability in clinical phenotype and disease course. DISCUSSION: We report a patient with rapidly progressive gCJD caused by a 5-OPRI mutation. A systematic PubMed review identified genetically confirmed 5-OPRI cases with available clinical data. Demographic characteristics, clinical features, ancillary investigations, disease course, and PRNP codon 129 polymorphisms were analyzed. A total of 25 patients from 14 families were included. Age at onset ranged from 26 to 63 years (mean 44.8 ± 9.9 years). Disease duration ranged from 4 to 192 months. Dementia was present in all patients, and 84% showed frontotemporal dementia-like features. Cerebellar signs, extrapyramidal symptoms, and myoclonus occurred in 68%, 60%, and 44% of patients, respectively. Periodic sharp wave complexes were detected in 29.4% of EEGs, and cerebral atrophy was observed in all patients with neuroimaging. Most patients carried the MM genotype at PRNP codon 129 (83.3%). A short disease course was associated with more frequent akinetic mutism and myoclonus, while MM carriers had a younger age at onset than MV carriers. CONCLUSIONS: 5-OPRI-associated CJD exhibits marked heterogeneity in clinical and disease duration. The PRNP codon 129 polymorphism appears to influence disease onset and progression.
26 May 2026
Read appraisal →Journal of neuro-oncology
Therapeutic effects of selumetinib on diffuse neurofibroma and optic pathway glioma in neurofibromatosis type 1.
PURPOSE: Selumetinib is approved for the treatment of inoperable plexiform neurofibromas (PN) in patients with neurofibromatosis type 1 (NF1). However, its efficacy in treating NF1-associated diffuse neurofibromas (NF1-DN) or optic pathway gliomas (NF1-OPG) remains unclear. We evaluated the efficacy and safety of selumetinib in these subgroups. METHODS: This was a sub-analysis of a Korean phase II open-label trial focusing on non-target treatment effects on NF1-DN and NF1-OPG. A total of 88 pediatric and adult patients with NF1-PN (59 children and 29 adults) in this trial had been treated for at least 2 years (~ 26 cycles, 28-day cycle) with oral selumetinib (20 or 25 mg/m², or 50 mg/dose every 12 h). Tumor volume, quality of life (QoL), and visual acuity were assessed. RESULTS: Among the 88 included patients, NF1-DN was diagnosed in 25 (28%), and NF1-OPG in 3 (3%). All NF1-DN patients exhibited disfigurement, two experienced pain, and a partial response (PR; ≥20% tumor reduction at a single time) was achieved in 9 of these cases (36%). The median time to PR was 6 cycles (range, 6-12), and the median time to best response was 18 cycles (range, 6-26), with a median volume change of - 11.9% (range, - 55.4% to + 36.3%). Confirmed PR (cPR; PR sustained for > 6 cycles) was observed in 6 NF1-DN patients (24%), stable disease (SD) was observed in 9 of these patients (36%), and progressive disease (PD) in 10 cases (40%). In a paired comparison, cPR was significantly lower for NF1-DN than for NF1-PN (24% vs. 88%, P < 0.001), and the median best volume reduction was also smaller (- 11.9% vs. -42.1%, P < 0.001). For the 3 NF1-OPG patients, visual impairment was present in all cases at baseline. One patient achieved PR at cycle 12 (- 36.1% from baseline) and complete response (CR) at cycle 26 but the visual acuity did not improve in this case. SD was maintained in the other two patients. Within these subgroups, QoL improved in 16 patients (57%) by cycle 26. No serious adverse events or treatment discontinuations were reported. CONCLUSIONS: Selumetinib shows therapeutic potential against NF1-DN, although with a lower response than that observed against NF1-PN. The NF1-OPG findings herein for this drug were exploratory only because of the small number of cases, but they may provide an additional clinical context for evaluating the broader effects of selumetinib across NF1-associated lesions. TRIAL REGISTRATION INFORMATION: KCT0003700, cris.nih.go.kr/cris/search/detailSearch.do/19,080, first submission March 4, 2019; first patient enrolled May 14, 2019.
25 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 →International journal of cancer
Testicular cancer in intersex individuals: A systematic review for clinical practice
The objective of this systematic review was to identify the evidence of testicular cancer risk for people with intersex conditions. This assessment is hoped to help refine risk stratification tools for assessing gonadal malignancy risk and guide the development of more robust evidence-based management strategies. The literature was searched in Ovid MEDLINE, Embase, and Cumulative Index of Nursing and Allied Health using a search string developed by a multidisciplinary team. The protocol was registered at Prospective Register of Systematic Reviews as CRD42021231313. A total of 3608 articles were found. After selection, 301 publications were included (1215 individuals). The results identified significant evidence that pre-pubertal gonadectomy may be linked to lower rates of malignant gonadal changes for patients with partial gonadal dysgenesis, Turner's syndrome with Y-chromosome material, complete androgen insensitivity, partial androgen insensitivity, and patients with ovotestis/es. The evidence was not significant for patients with complete gonadal dysgenesis, Klinefelter syndrome, nor WT1-related syndromes. Specific cancer outcomes were unable to be assessed due to small sample sizes and thus it is unknown if clinically significant cancer outcomes are meaningfully altered by pre-pubertal gonadectomy. Importantly, the quality of data on the topic of gonadal malignancy in intersex patients with testicular tissue was determined to be poor overall. The quality was relatively more robust regarding the conditions of Complete Androgen Insensitivity, Klinefelter syndrome, and patients with ovotestis/es. More high-quality research is needed to draw specific conclusions on the risks and benefits of performing pre-pubertal gonadectomy for intersex patients. When counseling these patients, clinicians should be transparent regarding the paucity of data supporting pre-pubertal gonadectomy.
17 May 2026
Read appraisal →PloS one
Using deep learning to identify inherited retinal diseases based on wide-field retinal imaging data
OBJECTIVE: To evaluate a novel image-based deep learning method for the automated identification of inherited retinal diseases (IRDs) and to explore the feasibility of predicting selected causative gene groups using a multimodal analysis of wide-field fundus autofluorescence (FAF) and pseudocolor fundus (pCF) images. DESIGN: The method was evaluated using a retrospective dataset of patient studies containing FAF and pCF images, as well as genetic tests for IRD. PARTICIPANTS: Patients with confirmed IRD for which both wide-field FAF and pCF images and genetic tests for IRD performed at Hadassah University Medical Center were included. The dataset consisted of 409 patients (330 patients with IRD with the 25 most commonly affected genes in our population and patients without IRD, and 79 patients without IRD). METHODS: Nine EfficientNet-V2-m convolutional neural networks were trained for the following three classification tasks: a binary IRD vs. non-IRD classification, and classification into two groups of five causative genes (Groups 1 and 2). For each task, three models were trained on the FAF images only, the pCF images only, and both the FAF and pCF images. The performance of the models was then evaluated and compared using 5-fold cross-validation. MAIN OUTCOME MEASURES: Accuracy, precision, F1 scores, AUC, and confusion matrices. RESULTS: The multimodal classification models that were trained on both the FAF and pCF images yielded the best results. The binary classification model had a mean (±SD) accuracy of 0.95 ± 0.01, a mean precision of 0.92 ± 0.01, and a mean F1 score of 0.90 ± 0.02. The Group 1 classification model had a mean accuracy of 0.92 ± 0.03, a mean precision of 0.93 ± 0.03, and a mean F1 score of 0.89 ± 0.03. Finally, the Group 2 classification model had a mean accuracy of 0.85 ± 0.03, a mean precision of 0.87 ± 0.04, and a mean F1 score of 0.83 ± 0.04. CONCLUSIONS: Our results indicate that determining whether a patient has IRD can be performed with high accuracy within this retrospective cohort based on FAF and pCF images using image-based deep learning classifiers. This image-based approach may assist clinicians during the patient's initial visit by providing decision support prior to genetic testing. It may also help prioritize patients for genetic workup, particularly in settings in which genetic testing is not readily available. Further prospective and external validation is required before clinical implementation.
13 May 2026
Read appraisal →Cerebellum (London, England)
Novel Imaging Phenotype in Spinal Cerebellar Ataxia Type 8: Symmetrical White Matter Changes without Cerebellar Atrophy
Spinal Cerebellar Ataxia Type 8 (SCA8) is a rare autosomal dominant neurodegenerative disorder characterized by progressive cerebellar dysfunction. It is caused by pathogenic expansions of a CTG/CAG trinucleotide repeat sequence within the ATXN8OS/ATXN8 gene locus on chromosome 13q21. Although cerebellar atrophy is widely recognized as a cardinal neuroimaging feature of SCA8, the phenotypic spectrum remains incompletely characterized. This study identified two cases of SCA8 through genetic analysis. Pedigree information was gathered and analyzed for all available family members. A systematic literature review was conducted to identify all published SCA8 cases with available neuroimaging data. The distinctive clinical and radiological features of SCA8 were analyzed through detailed case characterization integrated with a comprehensive review of existing literature. We report two genetically confirmed SCA8 cases exhibiting a previously undescribed neuroimaging phenotype. Case 1: A 36-year-old woman presented with a one-year history of progressive gait ataxia. Brain MRI revealed confluent, symmetric white matter signal abnormalities without cerebellar atrophy. Repeat expansion analysis detected a pathogenic CTG/CAG expansion of 9/77 in the ATXN8 gene. Case 2: A 64-year-old man (father of case 1) exhibited significant gait abnormalities, cognitive impairment and dysarthria. Brain MRI showed symmetric white matter lesions similar to case 1, with a CTG/CAG repeat length of 17/73. Notably, our systematic review revealed no prior reports of SCA8 presenting with isolated, symmetric white matter abnormalities in the absence of cerebellar atrophy. These findings delineate a novel neuroimaging phenotype of SCA8, characterized by symmetric white matter alterations without cerebellar volume loss. This atypical presentation expands the radiological spectrum of SCA8 and underscores the importance of considering repeat expansion disorders in the differential diagnosis of leukoencephalopathies, even in the absence of classic neurodegenerative imaging signatures.
13 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 →Proceedings of the National Academy of Sciences of the United States of America
The persistence and loss of hard selective sweeps amid admixture in ancient Eurasians
The extent to which human adaptations have persisted throughout history despite strong eroding demographic events such as admixture, genetic drift, and fluctuations in selection pressures remains unknown. Understanding which adaptations were resilient to such forces may shed light on traits that were important for humans across time. Yet, detecting selection from ancient DNA is challenging due to severe degradation of the data and/or signal. Here we detect selective sweeps using a domain-adaptive neural network (DANN) trained on simulated data and applied to more than 800 ancient and modern Eurasian genomes spanning the last 7,000 y. We show that the DANN can account for simulation misspecification, or discrepancies between simulations and real ancient DNA, improving the ability to detect sweeps in real data compared to standard convolutional neural networks or standard statistics. Application of the DANN to data recovered 16 known sweeps at loci including LCT, HLA, KITLG, and OCA2/HERC2, and revealed 32 novel sweeps. All identified sweeps were classified as hard, consistent with historically low population sizes. While some sweeps were lost over time, 14 sweeps at loci involved in functions including neuronal, reproductive, pigmentation, and signaling traits persisted from the earliest to the most recent time periods. In most cases, the most frequent haplotype remained at high frequency across time. Together, these results indicate that hard sweeps predominated in ancient Eurasians and that several ancient selective events were resilient to strong admixture events.
2 May 2026
Read appraisal →Journal of medicinal chemistry
The Discovery of RGH-706, a Highly Efficacious MCH1 Receptor Antagonist, for the Treatment of Obesity and Insatiable Hunger
The discovery and characterization of a novel 2,3,4,5-tetrahydro-1H-[1,4]diazepino[1,7-a]indole derivative MCH1 receptor antagonist (37) is disclosed. Starting from our previously investigated pyrazino[1,2-a]indole series and utilizing a scaffold hopping strategy, pyrimidine- and 1,4-diazepine-fused indole derivatives were designed and synthesized. Among these, only the prototype molecule containing the 2,3,4,5-tetrahydro-1H-[1,4]diazepino[1,7-a]indole scaffold emerged as a chemically stable and potent MCHR1 antagonist. Previous SAR knowledge coupled with an ex vivo occupancy assay helped us to optimize this advanced lead to our candidate (37). The high MCHR1 potency and excellent receptor occupancy profile of 37 translated into statistically significant body weight loss after 14 days in a DIO mice study, supporting the potential use of this compound as a weight loss agent. Compound 37 (RGH-706) has successfully completed a phase I (SAD & MAD) clinical study in the indication of obesity, followed by an exploratory Phase II study in patients with Prader-Willi Syndrome (PWS).
25 Apr 2026
Read appraisal →Nature communications
Accelerating Leigh syndrome drug discovery through deep learning screening in brain organoids
Leigh syndrome (Leigh) is an untreatable mitochondrial disorder characterized by lactic acidosis and basal ganglia and midbrain pathology, leading to psychomotor regression and early death. We previously uncovered impaired neuronal morphogenesis in Leigh cerebral organoids carrying SURF1 gene variants. Leveraging this phenotype, we here develop a deep learning algorithm tailored for cell type-specific drug repurposing screening. In parallel, we perform a survival drug screen in a yeast model of Leigh. The two approaches independently converge on azole compounds, two of which - talarozole and sertaconazole - rescue neuronal morphogenesis in Leigh neurons and lower lactate release and improve growth rate in Leigh midbrain organoids. Mechanistically, these compounds modulate the retinoic acid pathway and membrane-associate lipid metabolism. The findings highlight azoles as promising candidates for Leigh and demonstrate the potential of combining in silico screens with human brain organoids as new approach methodologies (NAMs) to advance the discovery of therapeutics addressing rare neurodevelopmental disorders.
22 Apr 2026
Read appraisal →Proceedings of the National Academy of Sciences of the United States of America
Coalescence and translation: A language model for population genetics.
Probabilistic models such as the sequentially Markovian coalescent have long provided a powerful framework for population genetic inference, enabling reconstruction of demographic history and ancestral relationships from genomic data. However, these methods are inherently specialized, relying on predefined assumptions and/or limited scalability. Recent advances in simulation and deep learning provide an alternative approach: learning directly to generalize from synthetic genetic data to infer hidden evolutionary processes. Here we reframe the inference of coalescence times as a problem of translation between two biological languages: the sparse, observable patterns of mutation along the genome and the unobservable ancestral recombination graph that gave rise to them. Inspired by large language models, we develop cxt, a decoder-only transformer that autoregressively predicts coalescent events conditioned on local mutational context. We show that cxt performs competitively with state-of-the-art Markov Chain Monte Carlo-based likelihood models across a broad range of demographic scenarios, matching their accuracy in-distribution and approaching it in out-of-distribution, with the potential for improvement via fine-tuning. Trained on simulations spanning the stdpopsim catalog [J. R. Adrion et al., eLife 9, e54967 (2020); M. E. Lauterbur et al., eLife 12, e84874 (2023); G. Gower et al., Accessible, realistic genome simulation with selection using stdpopsim. bioRxiv [Preprint] (2025). https://doi.org/10.1101/2025.03.23.644823.], the model generalizes robustly and enables efficient inference at scale, producing over a million coalescence predictions in minutes. cxt also produces well-calibrated approximate posteriors, enabling principled uncertainty quantification. We apply cxt to population genomic data from both humans and mosquitoes, highlighting the model's ability to deal with the complexities of empirical data.
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 →Epigenetics
The role of R-loops-mediated epigenetic regulation in genome stability maintenance and disease pathogenesis: a systematic review.
This systematic review synthesizes current evidence linking R-loops - associated processes with epigenetic regulation, genome stability, and human disease, integrating findings across DNA/RNA/protein modifications and 3D genome organization, and highlighting key mechanistic and technical gaps relevant to future studies, including longer-term translational exploration. Following PRISMA guidelines (Registration No.: INPLASY202560055), PubMed and ScienceDirect databases were searched through 18 January 2026. Two independent reviewers conducted blinded screening via the Rayyan platform. From 1290 initial articles, 71 studies met inclusion criteria. Methodological rigour was assessed using a modified SYRCLE risk-of-bias tool. Thematic synthesis identifies R-loops as recurrent intermediates linking transcription, chromatin regulation, and genome maintenance; feedback-like relationships are reported in selected systems. They spatially impede DNMTs to sustain promoter hypomethylation while recruiting TET enzymes for demethylation, and RNA modifications (e.g. m5C/m6A) may tune hybrid stability and, in some contexts, influence effector recruitment. R-loops facilitate the recruitment of histone-modifying complexes (PRC1/PRC2, G9a/GLP), thereby influencing chromatin landscapes and 3D genome architecture - including associations with TAD boundary insulation and with LLPS-related repair compartments in specific contexts. Dysregulation of R-loop homeostasis links to disease-related epigenetic alterations and genome instability with distinct disease-, locus- and cell-state specificity, and its context-dependent roles in diverse disorders involve transcriptional silencing, DNA damage, replication-transcription conflicts, repair pathways, chromatin regulation and mitochondrial genome maintenance. Integrating DRIP-seq with epigenomic profiling and functional tests supports mapping of context-specific relationships.
14 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 →Archives of gynecology and obstetrics
Misdiagnosis of different types of aneuploidy in preimplantation genetic testing (PGT): a systematic review and meta-analysis
PURPOSE: Recent studies have reported that embryos diagnosed as aneuploid by preimplantation genetic testing (PGT) can still result in successful live births after transfer. This suggests that, in addition to mosaic embryos, fully aneuploid embryos may also carry a risk of diagnostic error, potentially reducing the overall accuracy of PGT. Therefore, thoroughly investigating the risk and characteristics of aneuploidy misdiagnosis is crucial for optimizing PGT strategies and improving clinical outcomes in assisted reproductive technology (ART). METHODS: Relevant studies published from January 2000 to December 2024 were identified through PubMed and Web of Science. Study quality was assessed using the Newcastle-Ottawa Scale (NOS). A diagnostic meta-analysis was conducted using a random-effects model to calculate pooled odds ratios (ORs) with 95% confidence intervals (CIs), combining sensitivity and specificity. Results were visualized using forest plots. RESULTS: A total of 22 studies were included to assess the discordance between trophectoderm (TE) biopsy and inner cell mass (ICM) or whole blastocyst (WB) results. The discordance rate for euploid embryo diagnosis was low (2.6%), whereas it was significantly higher for aneuploid embryos (9.2%). Segmental aneuploidies showed the highest discordance rate (17.4%). In the PGT-A population, misdiagnosis of segmental aneuploid embryos was particularly prominent (OR = 10.04, 95% CI: 7.60-13.27, I2 = 0%, P < 0.001). CONCLUSION: The results indicate that embryos with segmental aneuploidies have a significantly higher risk of misdiagnosis, especially in the PGT-A population. This highlights the need for caution when interpreting trophectoderm (TE) biopsy results involving segmental aneuploidies, to avoid misdiagnosis and the inadvertent discard of potentially viable embryos.
8 Apr 2026
Read appraisal →Genetics
Mapping whole-organism genetic comorbidities across model Species using unified ontologies
Understanding how genetic variation contributes to organism-wide phenotypes is critical for identifying mechanisms of disease. Here, we present a computational approach to analyze whole-organism comorbidities associated with genes underlying non-obstructive azoospermia (NOA), the most severe form of male infertility. We curated 204 mouse genes with experimentally validated spermatogenic failure and mapped their orthologs and phenotype annotations across humans, M. musculus, D. rerio, D. melanogaster, and C. elegans using a unified cross-species phenotype structure. This framework integrates a newly developed reproductive phenotype ontology with standardized whole-body phenotype categories to enable direct cross-species comparisons, using thousands of genotype-phenotype associations stored in model organism databases. Our analysis shows that most NOA genes have conserved orthologs across models, and that perturbation of these genes is frequently associated with non-reproductive phenotypes. In particular, integumentary defects and neoplastic phenotypes recur across species, supporting a shared genetic basis for epidemiological links between male infertility and systemic disease. Gene-level comorbidity patterns are partially predictable from single-cell RNA-seq, whole-body gene expression, and Gene Ontology annotations, suggesting that fundamental biological constraints shape the systemic consequences of reproductive gene dysfunction. Clustering genes by comorbidity profiles further distinguished genes with isolated reproductive effects from those with broad organismal consequences. This work demonstrates the power of ontology-based cross-species analysis for identifying pleiotropic effects of Mendelian disease mutations, and provides a resource, CoMorbidity DataBase Mapper (CoMo DBM), for joint analysis of genotype-phenotype associations in model organism databases.
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 →Journal of medical Internet research
Artificial Intelligence, Connected Care, and Enabling Digital Health Technologies in Rare Diseases With a Focus on Lysosomal Storage Disorders: Scoping Review
BACKGROUND: Rare diseases affect more than 300 million people globally, and only about 5% have approved therapies. Lysosomal storage disorders (LSDs) exemplify the diagnostic and long-term care complexity typical of rare diseases, and digital health technologies (DHTs), especially artificial intelligence (AI) and connected care (CC), are emerging tools to support LSD management. OBJECTIVE: We aimed to map and synthesize peer-reviewed and gray literature from the past decade on DHTs relevant for LSD care, with a primary analytic focus on AI-enabled and CC solutions and a contextual mapping of other enabling DHTs. Evidence distribution was charted by population, care-journey phase, and outcome domains to identify gaps, methodological limitations, and timely priorities relevant for research, clinical practice implementation, and policies. METHODS: We conducted a scoping review guided by a population, concept, context framework and operationalized through a Population, Intervention, Comparison, and Outcome (PICO)-informed data-charting structure to map study characteristics and reported outcomes, without causal or effectiveness assumptions and without risk-of-bias assessment. We searched PubMed, Google Scholar, and ClinicalTrials.gov for studies published between October 2015 and September 2024, complemented by AI-assisted discovery tools for citation extension. Reproducibility logs (search strings, run dates, filters, and stepwise counts) were maintained. Of 1751 records retrieved, 245 were included. Evidence was charted by LSD population, intervention class (AI, CC, and other enabling DHTs), outcome domains (patient, health care, and societal), and phase of the care journey. RESULTS: Among 245 included records, 92.2% (226/245) were peer-reviewed, and 7.8% (19/245) were gray literature; no completed and published randomized controlled trials or LSD-specific systematic reviews were identified, with evidence dominated by small, single-center observational studies. Overall, 40 peer-reviewed records reported AI-driven DHTs, 89 reported CC DHTs, and 144 reported other enabling DHTs (some multilabeled). Evidence was concentrated mostly in Gaucher and Fabry diseases. Nearly half of the mapped literature focused on screening and diagnosis, with fewer records addressing treatment intensification, rehabilitation, and end-of-life care. Outcomes were predominantly health care delivery performance measures, with fewer patient and societal outcomes. AI applications mainly supported diagnostic decision support, phenotyping, monitoring, tracking, and risk stratification; CC commonly involved telemedicine, remote monitoring, and patient-engagement platforms; enabling DHTs included interoperable data systems, registries, and digital infrastructures. CONCLUSIONS: The evidence base is appreciable for a niche field and reflects growing interest in AI and CC for LSD care, but heterogeneity and methodological limitations preclude inferences on effectiveness or routine implementation. This evidence map highlights relatively stronger areas and gaps, providing a structured foundation to inform timely expert consensus-building and research prioritization. Key priorities include interoperable data infrastructures and data availability, prospective multicenter evaluations, transparent reporting of algorithms and workflows, and implementation-relevant outcomes to support safe, equitable, and scalable adoption aligned with evolving European Union and global rare-disease priorities.
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 →GeroScience
Integrative machine learning approach to risk prediction for dementia and Alzheimer's disease
Dementia, particularly Alzheimer's disease (AD), presents a growing global health challenge characterized by cognitive decline, behavioral changes, and loss of independence. With increasing life expectancy, early diagnosis and improved clinical strategies are urgently needed. This study developed and evaluated machine learning (ML) models to predict AD risk using UK Biobank data, integrating health, genetic, and lifestyle factors. The cohort included 2878 AD cases and 72,366 controls. Among several algorithms, CatBoost performed best (ROC-AUC = 0.773), especially in females. Inputs included ICD-10 codes from 5 years pre-diagnosis, ApoE-ε4 genotype, and large collection of modifiable risk factors. Despite fewer cases, the risk predictive models for vascular dementia (VaD) outperformed the unique AD models. ApoE-ε4 was the most predictive genetic marker, while other common variants had limited utility. Key non-genetic predictors included comorbidities (e.g., diabetes, hypertension), education, physical activity, and diet. These findings highlight the value of integrating diverse data sources for dementia risk prediction and emphasize the role of sex-specific modeling and modifiable factors in early, personalized intervention strategies.
2 Apr 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 →Curr Opin Pediatr
Artificial intelligence supported facial feature analysis in medical genetics
PURPOSE OF REVIEW: This review highlights recent developments in the use of machine learning supported facial feature analysis in the context of genetic and syndromic conditions. The review focusses on 2D image-based tools. The 2D images are easily obtained using handheld devices such as mobile phones and are more relevant to general practice than 3D image based systems. RECENT FINDINGS: Different algorithms are used widely in pediatric clinics, medical genetics clinics, for gene variant analysis and in research. Integrated systems combining next-generation phenotyping with next-generation genotyping support a shortened diagnostic odyssey for patients. SUMMARY: Future integration of phenotyping using data available in electronic medical records with genotyping data will likely result in earlier identification of possible genetic conditions.
1 Dec 2025
Read appraisal →