ADAPT

30-60 minutesCodeNeed >20GB

Structure-based TCR design for peptide-MHC targets

Readiness

Readiness: Need >20GB
Smoke: not_tested
Artifacts: not_applicable
Production: need_gt20gb_af2_proteinmpnn_zenodo_stack_pending
Storage: >20
Strategy: large AF2/ProteinMPNN/RFantibody shared stack with database/model storage
Next: Stage ADAPT, Zenodo data, AF2-compatible runtime/databases, ProteinMPNN, optional RFantibody, run bounded direct Slurm pMHC design smoke, then wire adapter/artifacts.

No obvious large model/database dependency identified; validate upstream docs before install. 2026-07-05 SOP batch recheck: backend inventory found no staged ADAPT source/AF2 databases/ProteinMPNN/RFantibody/data/SIF/artifacts/runner. Upstream calls AlphaFold2, ProteinMPNN, optional RFantibody, and large Zenodo parameters/databases, so this is not a small shared-SIF smoke. Reclassified from Smoke Pending to Need >20GB.