Siwei Chen

This paper introduces ReCLIP, a transformer-based framework that models protein-protein interactions at the residue level, showing high accuracy in predicting mutation effects and peptide-MHC binding.

This study analyzes 42 de novo CACNA1A missense variants in neurodevelopmental disorders, finding most alter channel function and correlate with clinical outcomes.

This study identifies shared and distinct ultra-rare genetic risk factors for epilepsy subtypes using whole-exome sequencing of 20,979 patients and 33,444 controls.

The paper develops a computational framework to analyze mutational hotspots in cancer genomes using a human 3D interactome network, identifying clinically relevant interactions and proteins.

GeMSTONE is a cloud-based tool for prioritizing germline mutations from whole-genome/exome sequencing data, offering customizable workflows and reproducibility through recipe files.