I build provenance-first scientific AI systems: MCP servers, bioinformatics agents, and reproducible ML/research tooling.
My strongest public work is in agentic research infrastructure: tools that let AI systems query scientific sources with typed APIs, provenance records, verification hooks, and explicit limitations.
- uniprot-mcp — UniProt MCP server with per-response SHA-256 provenance, release pinning, verification, and offline replay.
- semantic-scholar-mcp — Semantic Scholar MCP server with 14 typed tools for paper search, citation graphs, author profiles, and recommendations.
- alphafold-sovereign-mcp — local-first biomedical MCP over AlphaFold DB and related public sources, with a SQLite knowledge graph and explicit clinical-use limits.
Current published releases: UniProt MCP · Semantic Scholar MCP · AlphaFold Sovereign MCP. See each project's CI, release verification, and limitations for evidence of what has actually been validated.
- pca-topology-crossdomain-replication: research on PCA(50) and H1 persistence across omics cohorts, with a corrected matched-null comparison, explicit methodological corrections, executable audit records, and versioned Zenodo archives. The matched study supports dependence-sensitive geometry, not an established biological topology beyond covariance; independent-cohort validation remains a separate research task.
- TopoGeoML — topology-aware ML toolkit plus a preregistered graph-classification study whose headline result is negative.
- cohomology-wall — mathematical/reproducibility archive for a tetraquadric Calabi-Yau cohomology-jumping calculation.
- GROUPOID — pre-alpha groupoid/sheaf/Riemannian aggregation prototype for federated learning, with reproducible six-seed neural gauge evidence and clearly scoped scientific limitations.
- homology-cliff — ESM-2 protein-retrieval failure-mode study with archived experimental evidence, calibration analysis, and explicit limits on preregistration chronology, label curation, and external generalization.
These five repositories are archived forks of other maintainers' projects. They are retained for reference, not presented as original research, original software, or actively maintained releases.
- democafa_package — archived fork of anphan0828/democafa_package; CAFA-style prediction and evaluation reference.
- LAFA_container_guide — archived fork of anphan0828/LAFA_container_guide; containerization reference for protein-function prediction.
- icbo-ai-tutorial — archived fork of ai4curation/icbo-ai-tutorial; ontology and AI tutorial reference.
- awesome-mcp-servers — archived fork of punkpeye/awesome-mcp-servers; MCP server directory reference.
- awesome-remote-mcp-servers — archived fork of Appnova-EU-OU/awesome-remote-mcp-servers; remote MCP server directory reference.
I lead these projects independently and am the sole scientific author of their research contributions. AI-assisted tools support parts of implementation, analysis workflows, and internal review; research design, interpretation, and release decisions remain my responsibility. Upstream software, data, and prior research are credited in the respective repositories.