arXiv subjects

Jacques Fellay

Publications and source records attributed to Jacques Fellay.

8 recordsLinked to original sources

arXiv2026

Large Language Models for Variant-Centric Functional Evidence Mining

Functional evidence is essential for clinical interpretation of genomic variants, but identifying relevant studies and translating experimental results into structured evidence remains labor intensive. We developed a benchmark based on ClinGen curated annotations to evaluate two large language models (LLMs), a non reasoning model (gpt-4o-mini) and a reasoning model (o4-mini), on tasks relevant to functional evidence curation: (1) abstract screening to determine whether a study reports functional experiments directly testing specific variants, and (2) full text evidence extraction and classification from matched variant-paper pairs, including interpretation of evidence direction and generation of evidence summaries. Starting from ClinGen variants annotated with functional evidence, we processed curator comments with an LLM to extract PubMed identifiers, evidence labels, and narrative, and retrieved titles, abstracts, and open access PDFs to construct variant-paper pairs. In abstract screening, both models achieved high recall (0.88-0.90) with moderate specificity (0.59-0.65). For full text evidence classification under an explicit variant matching gate, o4-mini achieved 96% accuracy and higher specificity (0.83 vs. 0.37) while maintaining high F1 (0.98 vs. 0.96) compared with gpt-4o-mini. We also used an LLM-as-judge protocol to compare model generated evidence summaries with expert curator comments. Finally, we developed AcmGENTIC, an end to end pipeline that expands variant identifiers, retrieves literature via LitVar2, filters abstracts with LLMs, acquires PDFs, performs multimodal evidence extraction, and generates evidence reports for curator review, with optional agentic parsing of figures and tables. Together, this benchmark and pipeline provide a practical framework for scaling functional evidence curation with human in the loop LLM assistance.

q-bio.GN↗

arXiv2025

HIVMedQA: Benchmarking large language models for HIV medical decision support

Large language models (LLMs) are emerging as valuable tools to support clinicians in routine decision-making. HIV management is a compelling use case due to its complexity, including diverse treatment options, comorbidities, and adherence challenges. However, integrating LLMs into clinical practice raises concerns about accuracy, potential harm, and clinician acceptance. Despite their promise, AI applications in HIV care remain underexplored, and LLM benchmarking studies are scarce. This study evaluates the current capabilities of LLMs in HIV management, highlighting their strengths and limitations. We introduce HIVMedQA, a benchmark designed to assess open-ended medical question answering in HIV care. The dataset consists of curated, clinically relevant questions developed with input from an infectious disease physician. We evaluated seven general-purpose and three medically specialized LLMs, applying prompt engineering to enhance performance. Our evaluation framework incorporates both lexical similarity and an LLM-as-a-judge approach, extended to better reflect clinical relevance. We assessed performance across key dimensions: question comprehension, reasoning, knowledge recall, bias, potential harm, and factual accuracy. Results show that Gemini 2.5 Pro consistently outperformed other models across most dimensions. Notably, two of the top three models were proprietary. Performance declined as question complexity increased. Medically fine-tuned models did not always outperform general-purpose ones, and larger model size was not a reliable predictor of performance. Reasoning and comprehension were more challenging than factual recall, and cognitive biases such as recency and status quo were observed. These findings underscore the need for targeted development and evaluation to ensure safe, effective LLM integration in clinical care.

cs.CL↗

arXiv2025

From Mutation to Degradation: Predicting Nonsense-Mediated Decay with NMDEP

Nonsense-mediated mRNA decay (NMD) is a critical post-transcriptional surveillance mechanism that degrades transcripts with premature termination codons, safeguarding transcriptome integrity and shaping disease phenotypes. However, accurately predicting NMD efficiency remains challenging, as existing models often rely on simplistic rule-based heuristics or limited feature sets, constraining their accuracy and generalizability. Using paired DNA and RNA data from The Cancer Genome Atlas, we benchmark embedding-only models and demonstrate that they underperform compared to a simple rule-based approach. To address this, we develop NMDEP (NMD Efficiency Predictor), an integrative framework that combines optimized rule-based methods, sequence embeddings, and curated biological features, achieving state-of-the-art predictive performance. Through explainable AI, we identify key NMD determinants, reaffirming established factors such as variant position while uncovering novel contributors like ribosome loading. Applied to over 2.9 million simulated stop-gain variants, NMDEP facilitates large-scale mRNA degradation assessments, advancing variant interpretation and disease research.

q-bio.GN↗

arXiv2024

Proteome-wide prediction of mode of inheritance and molecular mechanism underlying genetic diseases using structural interactomics

Genetic diseases can be classified according to their modes of inheritance and their underlying molecular mechanisms. Autosomal dominant disorders often result from DNA variants that cause loss-of-function, gain-of-function, or dominant-negative effects, while autosomal recessive diseases are primarily linked to loss-of-function variants. In this study, we introduce a graph-of-graphs approach that leverages protein-protein interaction networks and high-resolution protein structures to predict the mode of inheritance of diseases caused by variants in autosomal genes, and to classify dominant-associated proteins based on their functional effect. Our approach integrates graph neural networks, structural interactomics and topological network features to provide proteome-wide predictions, thus offering a scalable method for understanding genetic disease mechanisms.

q-bio.QM↗

arXiv2024

DNA Language Model and Interpretable Graph Neural Network Identify Genes and Pathways Involved in Rare Diseases

Identification of causal genes and pathways is a critical step for understanding the genetic underpinnings of rare diseases. We propose novel approaches to gene prioritization and pathway identification using DNA language model, graph neural networks, and genetic algorithm. Using HyenaDNA, a long-range genomic foundation model, we generated dynamic gene embeddings that reflect changes caused by deleterious variants. These gene embeddings were then utilized to identify candidate genes and pathways. We validated our method on a cohort of rare disease patients with partially known genetic diagnosis, demonstrating the re-identification of known causal genes and pathways and the detection of novel candidates. These findings have implications for the prevention and treatment of rare diseases by enabling targeted identification of new drug targets and therapeutic pathways.

q-bio.QM↗

arXiv2024

Fine-tuning the ESM2 protein language model to understand the functional impact of missense variants

Elucidating the functional effect of missense variants is of crucial importance, yet challenging. To understand the impact of such variants, we fine-tuned the ESM2 protein language model to classify 20 protein features at amino acid resolution. We used the resulting models to: 1) identify protein features that are enriched in either pathogenic or benign missense variants, 2) compare the characteristics of proteins with reference or alternate alleles to understand how missense variants affect protein functionality. We show that our model can be used to reclassify some variants of unknown significance. We also demonstrate the usage of our models for understanding the potential effect of variants on protein features.

q-bio.QM↗

arXiv2020

Revolutionizing Medical Data Sharing Using Advanced Privacy Enhancing Technologies: Technical, Legal and Ethical Synthesis

Multisite medical data sharing is critical in modern clinical practice and medical research. The challenge is to conduct data sharing that preserves individual privacy and data usability. The shortcomings of traditional privacy-enhancing technologies mean that institutions rely on bespoke data sharing contracts. These contracts increase the inefficiency of data sharing and may disincentivize important clinical treatment and medical research. This paper provides a synthesis between two novel advanced privacy enhancing technologies (PETs): Homomorphic Encryption and Secure Multiparty Computation (defined together as Multiparty Homomorphic Encryption or MHE). These PETs provide a mathematical guarantee of privacy, with MHE providing a performance advantage over separately using HE or SMC. We argue MHE fulfills legal requirements for medical data sharing under the General Data Protection Regulation (GDPR) which has set a global benchmark for data protection. Specifically, the data processed and shared using MHE can be considered anonymized data. We explain how MHE can reduce the reliance on customized contractual measures between institutions. The proposed approach can accelerate the pace of medical research whilst offering additional incentives for healthcare and research institutes to employ common data interoperability standards.

cs.CR↗

arXiv2015

Privacy in the Genomic Era

Genome sequencing technology has advanced at a rapid pace and it is now possible to generate highly-detailed genotypes inexpensively. The collection and analysis of such data has the potential to support various applications, including personalized medical services. While the benefits of the genomics revolution are trumpeted by the biomedical community, the increased availability of such data has major implications for personal privacy; notably because the genome has certain essential features, which include (but are not limited to) (i) an association with traits and certain diseases, (ii) identification capability (e.g., forensics), and (iii) revelation of family relationships. Moreover, direct-to-consumer DNA testing increases the likelihood that genome data will be made available in less regulated environments, such as the Internet and for-profit companies. The problem of genome data privacy thus resides at the crossroads of computer science, medicine, and public policy. While the computer scientists have addressed data privacy for various data types, there has been less attention dedicated to genomic data. Thus, the goal of this paper is to provide a systematization of knowledge for the computer science community. In doing so, we address some of the (sometimes erroneous) beliefs of this field and we report on a survey we conducted about genome data privacy with biomedical specialists. Then, after characterizing the genome privacy problem, we review the state-of-the-art regarding privacy attacks on genomic data and strategies for mitigating such attacks, as well as contextualizing these attacks from the perspective of medicine and public policy. This paper concludes with an enumeration of the challenges for genome data privacy and presents a framework to systematize the analysis of threats and the design of countermeasures as the field moves forward.

cs.CR↗