Andrea M. Gazzo

This study benchmarks generative AI tools for summarizing genomic variant literature, finding VarChat and Gpt-4o perform best with expert validation needed for reliability.

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

This study identifies RRASQ87L and RRAS2Q72L mutations as recurrent oncogenic drivers in lung cancer and shows sensitivity to the pan-RAS inhibitor RMC-6236.

This study identifies APOBEC3 mutagenesis as a common driver of therapy resistance in breast cancer, associated with poorer clinical outcomes.

This study demonstrates that RNA transcripts can serve as templates for double-strand break repair in human cells, identifying DNA polymerase-zeta as a key enzyme and revealing genomic scars associated with this process.

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

This paper introduces VarCoPP, a machine-learning method that identifies pathogenic variant combinations in gene pairs, achieving high accuracy and providing interpretable explanations for predictions.