ColabDock

30-60 minutesPaperCodeNeed >5GB

Protein-protein docking using inverted AlphaFold

Readiness

Readiness: Need >5GB
Smoke: not_run
Artifacts: not_run
Production: need_gt5gb_af2_params_legacy_jax_tensorflow_gpu_runtime
Storage: 5-20GB
Strategy: large shared SIF/database/model bundle phase
Next: Stage AF2 params and build a dedicated Python 3.8/3.9 JAX/TensorFlow/AF2 SIF or modernized fork, then submit a small GPU docking smoke through Slurm.

2026-07-17T13:13:16+08:00 SOP Need >5GB batch: remains Need >5GB. Source exists, but production needs AF2 params and a compatible legacy Python/JAX/TensorFlow GPU runtime; current backend Python 3.12/shared runtime is unsuitable and no AF2 params/Slurm docking smoke are staged.