PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction (2022-06-24T00:00:00.000000Z)

TL;DR

This work presents the first million-level protein structure prediction dataset with high coverage and diversity, named as PSP, and provides in addition the benchmark training procedure for SOTA protein structure prediction model on this dataset.

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.

Authors

Lei Chen

4 papers

Fan Yu

3 papers

Sirui Liu

1 papers

TL;DR

Abstract

Authors

References42 items

State-of-the-Art Estimation of Protein Model Accuracy Using AlphaFold

ColabFold: making protein folding accessible to all

Improved Protein Structure Prediction Using a New Multi‐Scale Network and Homologous Templates

Continuous Automated Model EvaluatiOn (CAMEO)—Perspectives on the future of fully automated evaluation of structure prediction methods

Faculty Opinions recommendation of Accurate prediction of protein structures and interactions using a three-track neural network.

Highly accurate protein structure prediction with AlphaFold

Deep learning techniques have significantly impacted protein structure prediction and protein design.

MSA Transformer

Protein storytelling through physics

ProtTrans: Towards Cracking the Language of Life’s Code Through Self-Supervised Deep Learning and High Performance Computing

Advances in methods for atomic resolution macromolecular structure determination

Improved protein structure prediction using potentials from deep learning

Improved protein structure prediction using predicted interresidue orientations

Critical assessment of methods of protein structure prediction (CASP)—Round XIII

Introducing “best single template” models as reference baseline for the Continuous Automated Model Evaluation (CAMEO)

Deep‐learning contact‐map guided protein structure prediction in CASP13

A further leap of improvement in tertiary structure prediction in CASP13 prompts new routes for future assessments

Evaluating Protein Transfer Learning with TAPE

Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences

HH-suite3 for fast remote homology detection and deep protein annotation

ProteinNet: a standardized data set for machine learning of protein structure

Distance-based protein folding powered by deep learning

Critical assessment of methods of protein structure prediction (CASP)—Round XII

Continuous Automated Model EvaluatiOn (CAMEO) complementing the critical assessment of structure prediction in CASP12

MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets

OpenMM 7: Rapid development of high performance algorithms for molecular dynamics

Uniclust databases of clustered and deeply annotated protein sequences and alignments

Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Model

UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches

A brief history of macromolecular crystallography, illustrated by a family tree and its Nobel fruits

lDDT: a local superposition-free score for comparing protein structures and models using distance difference tests

The Protein Model Portal—a comprehensive resource for protein structure and model information

Protein data bank

PSICOV: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments

How significant is a protein structure similarity with TM-score = 0.5?

Biopython: freely available Python tools for computational molecular biology and bioinformatics

Scoring function for automated assessment of protein structure template quality

The way to NMR structures of proteins

Crystallography & NMR system: A new software suite for macromolecular structure determination.

How cryo-EM is revolutionizing structural biology.

CRITICAL ASSESSMENT OF TECHNIQUES FOR PROTEIN STRUCTURE PREDICTION

MSA of the sequence, with number encoding 20+1 amino acids • deletion_matrix_int (N M SA , N seq ), numbers of deletion for MSA of the sequence • num_alignments (N seq

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names