Broad Institute of MIT and Harvard
Computational Biologist II
- Lead computational development for PROSPECT, analyzing 100K+ small-molecule compounds through screening QC, dose-response modeling, clustering, hit prioritization, and mechanism-of-action inference.
- Built a 10B+ compound virtual-screening pipeline for MoA inference and candidate prioritization, contributed to selection-algorithm design, and evaluated strategies for scaffold generalization and biological relevance.
- Developed a deterministic medicinal-chemistry triage system integrating structural liabilities, drug-likeness metrics, applicability-aware ADMET predictions, and TB chemical precedent into a reproducible human-review workflow for final compound selection.
- Develop quantitative target and mechanism methods, interpret CRISPRi phenotypes, and build provenance-aware biological knowledge systems using graph methods and LLM-assisted workflows.
- Partner with experimental scientists on assay development and go/no-go decisions; optimized API-driven microbial-genomics workflows across 15M+ sequences and 11+ taxa to reduce diagnostic turnaround by more than two days.