PhenoXtract extracts phenotypes from clinical descriptions using a hybrid approach of Large Language Models and Knowledge Graph embeddings, achieving high recall and precision.

bioRxiv · Jun 26, 2026 · PreprintGenomics

Digenic variant interpretation with hypothesis-driven explainable AI

Federica De Paoli, Giovanna Nicora, Silvia Berardelli, Andrea M. Gazzo, Riccardo Bellazzi, Paolo Magni, Ettore Rizzo, Ivan Limongelli, Susanna Zucca

diVas interprets digenic variants using hypothesis-driven machine learning and XAI, achieving 73% sensitivity in prioritizing causative gene pairs across 11 cases.

NAR Genomics and Bioinformatics · Mar 10, 2025Peer-reviewedBioinformatics

Critical assessment of variant prioritization methods for rare disease diagnosis within the Rare Genomes Project

Sarah L. Stenton, Melanie O’Leary, Gabrielle Lemire, Grace E. VanNoy, Stephanie P. DiTroia, Vijay S. Ganesh, Emily Groopman, Emily O’Heir, Brian E. Mangilog, Ikeoluwa Osei‐Owusu, Lynn S. Pais, Jillian Serrano, Moriel Singer‐Berk, Ben Weisburd, Michael W. Wilson, , Anne O’Donnell‐Luria

The paper evaluates variant prioritization methods for rare disease diagnosis using data from the Rare Genomes Project, finding that top models identify causal variants in most solved families and uncover potential candidates in unsolved ones.

Human Genomics · Apr 29, 2024Peer-reviewedGenetic & Genomic Medicine