NIAID · BRCs AI Codeathon 2.0
Projects  ·  2026

Hypothesis2Omics: Agentic Multi-Omics Validation

Translating a biological hypothesis into a reproducible search and analysis of public transcriptomic, proteomic, metabolomic, microbiome, or immune-system datasets.

Goal

Translate a biological hypothesis into a reproducible search and analysis of public transcriptomic, proteomic, metabolomic, microbiome, or immune-system datasets.

Three-Day MVP

Use one predefined hypothesis, for example, “A specified pathway or biomarker is associated with protection following vaccination.” The agent should discover appropriate datasets, assess eligibility, configure workflows, execute analyses through BRC Analytics or Galaxy, integrate results across datasets, and produce an evidence table.

A microbiome causal-inference branch could expose HUMAnN, differential abundance, sensitivity analysis, protein-language-model annotation, and SHAP interpretation as MCP tools.

Evaluation

Dataset-retrieval recall, workflow success, consistency with published findings, robustness across datasets, and expert assessment of the final evidence report.

Team

Team assignments are being finalized ahead of the codeathon. Participants can review project teams, and request reassignment, in the shared participant spreadsheet circulated by the organizing team.