Siwei Chen

Our lab strives to unlock the full potential of genomic data for genomic medicine: given near-complete genomic information from a patient, what can we reliably infer to improve their clinical care? We pursue this goal by developing foundational, scalable, and interpretable computational frameworks that guide us through the full 'genomic medicine cycle' – beginning with the discovery of disease-associated variants (variant-to-disease), progressing toward understanding their molecular mechanisms (variant-to-function), and culminating in translating these insights into improved patient care (variant-to-care).

Harvard Medical School
Boston
Instructor - Statistical Genetics
2025

Massachusetts General Hospital
Boston
Postdoc - Statistical Genetics
2024

Cornell University
Ithaca
PhD - Systems Biology
2020

Genome-wide association meta-analyses of drug-resistant epilepsy.
Genome-wide association meta-analyses of drug-resistant epilepsy. EBioMedicine. 2025 May; 115:105675.
PMID: 40240269

Tutorial: guidelines for quality filtering of whole-exome and whole-genome sequencing data for population-scale association analyses.
Tutorial: guidelines for quality filtering of whole-exome and whole-genome sequencing data for population-scale association analyses. Nat Protoc. 2025 Mar 28.
PMID: 40155705

Large Context, Deeper Insights: Harnessing Large Language Models for Advancing Protein-Protein Interaction Analysis.
Large Context, Deeper Insights: Harnessing Large Language Models for Advancing Protein-Protein Interaction Analysis. Methods Mol Biol. 2025; 2941:243-267.
PMID: 40601262

Exome sequencing of 20,979 individuals with epilepsy reveals shared and distinct ultra-rare genetic risk across disorder subtypes.
Exome sequencing of 20,979 individuals with epilepsy reveals shared and distinct ultra-rare genetic risk across disorder subtypes. Nat Neurosci. 2024 Oct; 27(10):1864-1879.
PMID: 39363051

A genomic mutational constraint map using variation in 76,156 human genomes.
A genomic mutational constraint map using variation in 76,156 human genomes. Nature. 2024 Jan; 625(7993):92-100.
PMID: 38057664

GWAS meta-analysis of over 29,000 people with epilepsy identifies 26 risk loci and subtype-specific genetic architecture.
GWAS meta-analysis of over 29,000 people with epilepsy identifies 26 risk loci and subtype-specific genetic architecture. Nat Genet. 2023 09; 55(9):1471-1482.
PMID: 37653029

Epilepsies of presumed genetic etiology show enrichment of rare variants that occur in the general population.
Epilepsies of presumed genetic etiology show enrichment of rare variants that occur in the general population. Am J Hum Genet. 2023 07 06; 110(7):1110-1122.
PMID: 37369202

A full-proteome, interaction-specific characterization of mutational hotspots across human cancers.
A full-proteome, interaction-specific characterization of mutational hotspots across human cancers. Genome Res. 2022 01; 32(1):135-149.
PMID: 34963661

De novo missense variants disrupting protein-protein interactions affect risk for autism through gene co-expression and protein networks in neuronal cell types.
De novo missense variants disrupting protein-protein interactions affect risk for autism through gene co-expression and protein networks in neuronal cell types. Mol Autism. 2020 10 08; 11(1):76.
PMID: 33032641

BraInMap Elucidates the Macromolecular Connectivity Landscape of Mammalian Brain.
BraInMap Elucidates the Macromolecular Connectivity Landscape of Mammalian Brain. Cell Syst. 2020 04 22; 10(4):333-350.e14.
PMID: 32325033

View All Publications