PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction
Abstract
Proteins are essential component of human life and their structures are important for function and mechanism analysis. Recent work has shown the potential of AI-driven methods for protein structure prediction. However, the development of new models is restricted by the lack of dataset and benchmark training procedure. To the best of our knowledge, the existing open source datasets are far less to satisfy the needs of modern protein sequence-structure related research. To solve this problem, we present the first million-level protein structure prediction dataset with high coverage and diversity, named as PSP. This dataset consists of 570k true structure sequences (10TB) and 745k complementary distillation sequences (15TB). We provide in addition the benchmark training procedure for SOTA protein structure prediction model on this dataset. We validate the utility of this dataset for training by participating CAMEO contest in which our model won the first place. We hope our PSP dataset together with the training benchmark can enable a broader community of AI/biology researchers for AI-driven protein related research.
Cite
@article{arxiv.2206.12240,
title = {PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction},
author = {Sirui Liu and Jun Zhang and Haotian Chu and Min Wang and Boxin Xue and Ningxi Ni and Jialiang Yu and Yuhao Xie and Zhenyu Chen and Mengyun Chen and Yuan Liu and Piya Patra and Fan Xu and Jie Chen and Zidong Wang and Lijiang Yang and Fan Yu and Lei Chen and Yi Qin Gao},
journal= {arXiv preprint arXiv:2206.12240},
year = {2022}
}