PeptiVerse

1-5 minutesCodeNeed >5GB

Unified platform for therapeutic peptide property prediction using sequence and SMILES

Readiness

Readiness: Need >5GB
Smoke: not_tested
Artifacts: not_applicable
Production: need_gt5gb_cuda_rapids_peptiverse_sif_pending
Storage: 5-20GB
Strategy: shared CUDA/RAPIDS PeptiVerse SIF or upstream Apptainer image
Next: Stage upstream PeptiVerse SIF or build CUDA/RAPIDS PeptiVerse image, then run direct Slurm inference.py smoke before runner wiring.

No obvious large model/database dependency identified; validate upstream docs before install. 2026-07-05 SOP batch recheck: backend inventory found no staged PeptiVerse repo/SIF/artifacts/runner. Upstream Hugging Face repo is about 1.74 GB, full setup needs RAPIDS cuML/CUDA, and the optional Apptainer image is about 7.52 GB. Reclassified from Smoke Pending to Need >5GB.