Biology subjects

Safer, J.

Publications and source records attributed to Safer, J..

3 recordsLinked to original sources

bioRxiv2026

Human Proteome-wide Mechanistic Interpretation of Missense Variants through Protein Feature Enrichment Score

Missense variant interpretation remains a central challenge in clinical and medical genetics, with most observed variants being variants of uncertain significance (VUS). Computational variant effect predictors can achieve high pathogenicity classification performance, but without revealing the underlying mechanism and a translatable interpretation. Here we present the Protein Feature Enrichment Score (PFES), which quantifies the molecular context of missense variants through statistical enrichment of 103 protein structural, functional, and physicochemical features across 85,321 pathogenic and 130,719 control variants spanning 20 protein functional classes. We show that the protein feature (PF) enrichment patterns of variants are conserved within functional classes and vary substantially across classes, both in magnitude and directions depending on functional context. PFES not only partitions variants into PF-Enriched (pathogenic-like), PF-Neutral, and PF-Depleted (benign-like) categories but also provides a mechanistic interpretation by decomposing the score into subscores from biologically interpretable protein feature attributes. We demonstrate that PFES shows a high concordance with VUS reclassification and prioritization: across 596 genes, pathogenicity-leaning VUS-high variants were seven-fold enriched in PF-Enriched variants. PFES decomposition further revealed that loss-of-function and gain-of-function variants are distinguished by disproportionate enrichment of protein-protein interaction features in the latter. We computed PFES across 223 million possible missense variants (17.7% PF-Enriched) and built a publicly available resource that addresses not just whether a variant is pathogenic, but which protein characteristics are disrupted. Proteome-wide application across 20,153 genes prioritizes established rare disease genes and nominates therapeutically amenable targets whose pathogenic variation is driven by interpretable structural and functional protein feature disruption. One Sentence SummaryPFES is a proteome-wide resource to quantify the protein context of missense variants, enabling mechanistically transparent variant interpretation.

bioinformatics↗

bioRxiv2024

ema-tool: a Python Library for the Comparative Analysis of Embeddings from Biomedical Foundation Models

Foundation models, which encode patterns in large, high-dimensional data as embeddings, show promise in many machine learning related applications in molecular biology. Embeddings learned by the models provide informative features for downstream prediction tasks, however, the information captured by the model is often not interpretable. One approach to understanding the captured information is through the analysis of their learned embeddings, which in molecular biology so far has mainly focused on visualizing individual embedding spaces. This study introduces a quantitative framework for cross-space comparison, enabling intuitive exploration and comparison of embedding spaces in molecular biology. The framework emphasizes analyzing the distribution of known biological information within embedding space neighborhoods and provides insights into relationships between multiple embedding spaces. Comparison techniques include global pairwise distance measurements as well as local nearest neighbor analyses. By applying our framework to embeddings from protein language models, we demonstrate how embedding space analysis can serve as a valuable pre-filtering step for task-specific supervised machine learning applications and for the recognition of differential patterns in data encoded within and across different embedding spaces. To support a wide usability, we provide a Python library that implements all analysis methods, available at https://github.com/broadinstitute/EmmaEmb.

bioinformatics↗

bioRxiv2024

Genomics 2 Proteins portal: A resource and discovery tool for linking genetic screening outputs to protein sequences and structures

Recent advances in AI-based methods have revolutionized the field of structural biology. Concomitantly, high-throughput sequencing and functional genomics technologies have enabled the detection and generation of variants at an unprecedented scale. However, efficient tools and resources are needed to link these two disparate data types - to "map" variants onto protein structures, to better understand how the variation causes disease and thereby design therapeutics. Here we present the Genomics 2 Proteins Portal (G2P; g2p.broadinstitute.org/): a human proteome-wide resource that maps 19,996,443 genetic variants onto 42,413 protein sequences and 77,923 structures, with a comprehensive set of structural and functional features. Additionally, the G2P portal generalizes the capability of linking genomics to proteins beyond databases by allowing users to interactively upload protein residue-wise annotations (variants, scores, etc.) as well as the protein structure to establish the connection. The portal serves as an easy-to-use discovery tool for researchers and scientists to hypothesize the structure-function relationship between natural or synthetic variations and their molecular phenotype.

bioinformatics↗