Sewage-to-Signal: Early Warning for Immune-Escape Mutations
An AI-assisted wastewater surveillance workflow that detects pathogens of concern, tracks their prevalence, and flags emerging immune-escape and therapeutic-resistance mutations.
Goal
Develop an AI-assisted wastewater surveillance workflow to detect pathogens of concern, track their prevalence, identify emerging mutations, and assess potential immune-escape or therapeutic impact.
Three-Day MVP
Starting from target-capture wastewater sequencing, classify reads and identify NIAID pathogens of concern. Call protein mutations, track their geographic, temporal, and lineage distribution using public sequence repositories, and use literature RAG plus curated databases to identify mutations associated with immune escape, therapeutic resistance, or altered pathogenicity.
Generate a provenance-linked early-warning report highlighting high-priority mutations.
Evaluation
Taxonomic classification accuracy; concordance of mutation calls with standard pipelines; accuracy of geographic/temporal context; precision of literature-derived mutation–phenotype associations; and ability to recover known escape or resistance mutations as high-priority signals.
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.