Computational Biologist II · Broad Institute of MIT and Harvard

Computational biology.
Machine learning.
Scientific data systems.

At the Broad Institute, I lead computational development for drug-discovery screens, develop quantitative methods, and build reproducible scientific systems. I partner with experimental scientists to define analytical requirements and criteria for what advances to follow-up.

View work Résumé

100K+small-molecule compounds analyzed

10B+compound virtual-screening pipeline

Top 1%prioritized for follow-up

Selected Work

From experimental questions to evidence scientists can use.

Functional genomics and drug discovery connect my quantitative work with scientific software and AI.

Functional genomics · Perturbation biology · Broad Institute

Leading large-scale perturbation screening from assay signal to experimental follow-up.

I lead computational development for PROSPECT, analyzing 100K+ small-molecule compounds from barcode and replicate QC through dose-response modeling, hit prioritization, and mechanism-of-action inference. I partner with experimental scientists to define analytical requirements and go/no-go criteria, diagnose assay issues, and guide follow-up experiments. Reusable Nextflow workflows support the analytical process.

Scale: 100K+ compounds
Ownership: Computational lead
Outcome: Top 1% prioritized

Screening methods and context →

Virtual screening · MoA inference · Candidate prioritization · Compound triage

Turning virtual-screening predictions into biologically informed compound-selection decisions.

I built the analytical pipeline for mechanism-of-action inference and candidate prioritization, guide selection-algorithm design, and evaluate strategies for scaffold generalization and biological relevance. Deterministic medicinal-chemistry and ADMET triage connects DuckDB-backed results with Streamlit scientist review.

Scale: 10B+ compounds
Analysis: MoA + scaffold-aware prioritization
Decision: Human-reviewed compound triage

See methods and final triage →

The discovery workflow Screening & QC → quantitative analysis & MoA hypotheses → virtual screening & algorithm evaluation → candidate and ADMET triage → scientist review & experimental follow-up.

Scientific AI · Knowledge graphs · Data integration

Connecting biological evidence for reviewable AI-assisted hypothesis generation.

At Broad, I integrate genomic, metabolic, and pathway evidence into provenance-aware knowledge systems. In my public MetaMorph project, I use Python, LangGraph, and Pydantic to turn inconsistent metadata into validated outputs, with bounded retries and run manifests. BulkQC provides a scientist-facing RNA-seq QC application with CI and tests.

Explore scientific AI and data systems →

From the Work

Scientific structure you can inspect.

Selected public analyses show how I use visual evidence to test whether computational models preserve meaningful biological structure.

Spatial transcriptomics tissue representation with spot-level expression counts — Spatial transcriptomics · Tissue to graphTissue position and gene expression define the graph for a collaborative course model.

Spatial graph connecting neighboring breast-tissue observations by tissue position — Spatial transcriptomics · Tissue to graphTissue position and gene expression define the graph for a collaborative course model.

UMAP of single-cell gene-expression states colored by measured capture time — Single-cell · Representation learningCapture time informs the training objective. These views inspect the learned structure; they are not held-out validation.

UMAP of single-cell gene-expression states colored by inferred developmental time — Single-cell · Representation learningCapture time informs the training objective. These views inspect the learned structure; they are not held-out validation.

Spatial transcriptomics · Graph ML · Disease biology

Learning from spatial and expression structure in breast tissue.

In a collaborative course project, I co-implemented, optimized, and trained a graph convolutional network to distinguish cancer-annotated from other tissue spots. The report records AUROC 0.91 on a stratified spot split, with weaker minority-class performance and no external validation.

Review the model evidence →

Multi-omics · Biomarkers · Translational biology

Integrating transcriptomic and epigenetic evidence across a human cohort.

I integrated adolescent RNA-seq and cord-blood DNA methylation across 250+ pediatric biospecimens to identify heavy-metal exposure signatures connected to immune and neurodevelopmental pathways. I also built automated RNA-seq workflows that improved processing speed by 50% and made the analysis reproducible across the cohort.

Read the research record →

Broad Institute descriptions use public or aggregate information and exclude confidential research details.

Technical Expertise

Three capabilities, integrated around scientific decisions.

Computational biology, applied data science, and scientific software grounded in experimental context.

Computational Biology

Biological questions and decision context.

Functional genomics, CRISPRi, and perturbation screening
Target discovery, mechanism of action, and biomarkers
Multi-omics, spatial transcriptomics, and translational biology

Machine Learning & Scientific AI

Methods built and evaluated for scientific use.

Representation learning, graph neural networks, and virtual screening
Model benchmarking and selection-algorithm evaluation
Knowledge graphs, RAG/LLM workflows, and agentic systems

Scientific Data Systems

Infrastructure that carries analysis into practice.

Python, R, SQL, APIs, and structured scientific data products
Workflow orchestration, containers, testing, and provenance
HPC and cloud computing across AWS and Azure

Translational Differentiator

Biological depth behind the computation.

MS Bioinformatics + MS Toxicology, with earlier IND-enabling PK and toxicology under GLP at Charles River. That experience informs how I assess dose, mechanism, and data integrity. Experience and training →

Additional Experience & Deeper Record

Scientific systems and evidence beyond the flagship projects.

Additional work demonstrates production-minded genomics infrastructure, while the deeper pages document research methods, public software, publications, and training.

Scientific informatics · APIs · Parallel computing

Reducing microbial-genomics turnaround with scalable data infrastructure.

I optimized API-driven retrieval, probabilistic filtering, and parallel processing across 15M+ sequences and 11+ taxa, reducing diagnostic turnaround by more than two days. The work demonstrates scientific data engineering tied directly to a biological operating need.

See the full experience →

Research · Public software · Full experience

Follow the evidence beyond the homepage.

Research details expose methods and limitations; public repositories show how I structure scientific systems; the full experience record connects that work to training and experimental context.

Connect

Building computational biology, scientific ML, or research data systems?

I am interested in computational biology, life-sciences data science, and scientific AI roles that connect quantitative methods with reliable software and experimental decisions.

Start a conversation Open résumé →

Computational biology.Machine learning.Scientific data systems.