Deploy app from main@a3254bf (no paper/ binaries)

Fix _derive_salt to pick optimum entries — salt MAE 2.52 → 2.17 (-13.7%)

Expand training corpus to 46K strains: species-name → NCBI genome + isolation features

v2 scaffolding: ESM-2 embedding extraction + GPU runner doc

Phase E #2: scripts/recommend.py — single-genome → ranked media + phenotype CLI

Phase E modeling: per-medium classifiers + recommender training script

Phase E scaffolding: MediaDive integration + strain↔medium links

v1 features: wire tetranucleotides + codon usage into streaming pipeline

Add v1 composition features (tetranucleotides + codon usage)

Fix predictions parquet type mix + plumb feature_cols through eval

Add feature↔target correlation analysis to eval report

Eval report enhancements: TL;DR + per-strain predictions + per-family error

Fix classification fold bug + add end-to-end integration tests

Add eval report generator + training table persistence + group-col override

Streaming fetch+featurize pipeline + 6× pyrodigal speedup + GCA version resolution

Rewrite BacDive client for v2 public API (no auth required)

Scaffold v0: BacDive + NCBI ingestion, genome feature extractor, XGBoost baseline