ProteinMPNN-ddG

1-5 minutesPaperCodeProduction Ready

Predict stability of point mutations

Readiness

Readiness: Production Ready
Smoke: passed
Artifacts: passed
Production: production_pass
Storage: <5
Strategy: shared PyTorch SIF + tool ext3 overlay; avoid per-tool torch duplication
Next: Production Ready. Optional next hardening: expose chain/model/seed controls and uploaded PDB validation in the UI.

No obvious large model/database dependency identified; validate upstream docs before install. Production evidence 2026-07-01: source https://github.com/PeptoneLtd/proteinmpnn_ddg revision 98302b5 staged at /media/nik/seagate_nik/bio_server/tools/proteinmpnn-ddg/source. Worker Slurm job 269 passed in reusable Python 3.10 micromamba env /home/nik/bio_server_venvs/proteinmpnn_ddg_py310_mamba. Web runner adapter was wired to runner_tool proteinmpnn-ddg and submitted through cluster runner API as Slurm job 270, remote id 4b1a7ad3f55b. Runtime_seconds 5.931. Artifacts: input.pdb, proteinmpnn_ddg_predictions.csv, results.csv preview, summary.json, stdout/stderr, Slurm logs. Sanity: 4300 mutation rows, expected columns pre/post/pos/logit_difference/logit_difference_ddg; first logit_difference_ddg -2.3459811.