Federica De Paoli

PhenoXtract: combining Large Language Model and Knowledge Graph embedding to extract phenotypes from clinical descriptions

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

Digenic variant interpretation with hypothesis-driven explainable AI

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

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

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.