Published August 26, 2024 | Version v2
Dataset Open

PepBench: Dataset for Protein-Binding Peptide Design

Creators

  • 1. ROR icon Tsinghua University
  • 2. ROR icon Renmin University of China

Description

Datasets and splits of protein-peptide complexes benchmark from PepGLAD.

V2 Updates:

  1. The size of ProtFrag augmentation dataset is 70498 instead of 70645. The latest index file has deleted duplicated entries.
  2. Clustering results for complexes in training/validation sets are uploaded in train_valid.

Files

README.md

Files (1.9 GB)

Name Size Download all
md5:6fb5d7fd47f96a02cb756f4e10f79286
10.9 MB Download
md5:8d7203a8610f26b26c95e02390879f1b
1.7 GB Download
md5:8e68e690d6d9137c0df74eac93389e74
3.0 kB Preview Download
md5:d385c7163c283e222fa5a6ff43c2b530
192.6 MB Download

Additional details

References

  • X. Kong, Y. Jia, W. Huang, and Y. Liu. Full-atom peptide design with geometric latent diffusion. Advances in Neural Information Processing Systems, 37:74808–74839, 2025