Assistant Project Scientist · Department of Cellular and Molecular Medicine
Director · Center for Precision Computational Systems Network (PreCSN)
University of California San Diego
I am a computational and systems biologist working at the intersection of network medicine, interpretable AI, and multi-omic biology. My research asks how cells decide when to change state, how those decisions go wrong in disease, and how we can predict and reverse them. I work across the full arc from data to experiment, building mechanistic models and designing the validation that tests them in patient-derived organoids, xenografts, and primary human systems. I lead the PreCSN center at UC San Diego and collaborate with groups across the United States, the United Kingdom, and Europe.
- Boolean and dynamical network modeling of cellular decision making
- Multi omic integration across bulk and single cell transcriptomics, ATAC seq, proteomics, and lipidomics
- Network medicine applied to cancer, immunology, inflammatory bowel disease, and lung fibrosis
- Therapeutic target identification and prioritization from human evidence
- New Approach Methodologies (NAMs) for translational relevance scoring
- Interpretable AI for mechanism discovery from high dimensional biology
| Platform | Purpose | Code |
|---|---|---|
| CANDiT | Machine learning prioritization of differentiation therapy targets in cancer and fibrosis · Cell Reports Medicine 2025 | Prodiff |
| COMPASS | Composite activity scoring for deterministic digital biomarkers, delivered as a browser based platform | COMPASSprep · GEO2COMPASS |
| SMaRT | Boolean to continuum model of macrophage reactivity and tolerance, validated across >12,500 transcriptomic profiles · eBioMedicine 2023, JCI 2025 | see publications |
| F.O.R.W.A.R.D | Network based therapeutic target prioritization across multi omic datasets | patent pending — code not public |
| PICASSO | Human first framework anchoring federally mandated New Approach Methodologies | preprint |
| AXIOM Bio | Foundational Boolean logic model of cellular decision making and disease · Trends Open, Cell Press 2026 | in press |
- Sinha S. et al. CANDiT: a machine learning framework for differentiation therapy in colorectal cancer. Cell Reports Medicine 6(11):102421, 2025. → code
- Sinha S. et al. Breast cancers that disseminate to bone marrow acquire aggressive phenotypes through CX43 related tumor stroma tunnels. Journal of Clinical Investigation 134(24), 2024. → code
- Sinha S. et al. Growth signaling autonomy in circulating tumor cells aids metastatic seeding. PNAS Nexus 3(2), 2024. → code
- Ghosh P, Sinha S. et al. Machine learning identifies signatures of macrophage reactivity and tolerance that predict disease outcomes. eBioMedicine 94:104719, 2023.
- Sinha S. et al. COVID 19 lung disease shares driver AT2 cytopathic features with idiopathic pulmonary fibrosis. eBioMedicine 82:104185, 2022. → code
Full list on Google Scholar and ORCID.
- US Provisional 63/667,291 — Machine learning based approach for precision target prioritization in drug discovery
- US Provisional 63/378,625 — Growth signaling autonomy in circulating tumor cells aiding metastatic seeding
Co Investigator or Senior Key Person on active awards from NCI, NICHD, NIAID, NHLBI, and the Helmsley Charitable Trust. Actively pursuing independent funding through the Stephen I. Katz Early Stage Investigator R01 mechanism.
Python · R · scanpy · Seurat · scikit-learn · PyTorch · Docker/Singularity · SLURM/HPC · Git · single cell and bulk RNA seq · ATAC seq · proteomics · network analysis · Boolean modeling
I welcome inquiries on collaborations, code, data, and trainee positions.
- Email: sasinha@health.ucsd.edu
- Location: San Diego, California
- Center site: PreCSN, UC San Diego
Pinned repositories below reflect published or actively maintained methods. Each links to the corresponding manuscript.