Aqueous Solubility

secondsCodeProduction Ready

Predict aqueous solubility (logS)

Readiness

Readiness: Production Ready
Smoke: passed
Artifacts: passed
Production: production_pass_rdkit_esol
Storage: <5
Strategy: shared python312_slim.sif + existing RDKit chemistry Python layer for ESOL/logS; xTB solvation deferred
Next: Production Ready for ESOL/RDKit mode. Optional hardening: keep computeSolvation/xTB disabled until QM SIF validation.

No obvious large model/database dependency identified; validate upstream docs before install. 2026-07-05 SOP batch recheck: backend inventory found no staged aqueous-solubility runner/artifacts. ESOL/RDKit path can use existing RDKit chemistry runtime, but computeSolvation/xTB is out of scope until selected runtime exists. Kept Smoke Pending. 2026-07-05 18:35 +08:00 backend re-audit: no staged aqueous-solubility runner/artifacts or object-store/API artifacts found; ESOL/RDKit scope remains first path. Kept Smoke Pending. 2026-07-06 implementation pass: ran direct Slurm job 444 at /media/nik/seagate_nik/bio_server/runs/aqueous-solubility/smoke_20260706_033000 using RDKit 2026.03.3. ESOL-style Delaney logS smoke with compute_solvation=false scored aspirin, ethanol, and benzene; sanity ordering passed and artifacts summary.json, results.csv, job.log, slurm.out, and slurm.err were produced. xTB/QM solvation remains deferred. 2026-07-08T11:39:15+08:00: Production Ready promotion: backend runner API job 3fe3b6753992 / Slurm job 541 completed cleanly. RDKit ESOL-style adapter produced zero-byte slurm.out/slurm.err and finite logS values for aspirin, ethanol, and benzene.