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

Abstract

Recently exciting progress has been made on protein contact prediction, but the predicted contacts for proteins without many sequence homologs is still of low quality and not very useful for de novo structure prediction. This paper presents a new deep learning method that predicts contacts by integrating both evolutionary coupling (EC) and sequence conservation information through an ultra-deep neural network formed by two deep residual networks. This deep neural network allows us to model very complex sequence-contact relationship as well as long-range inter-contact correlation. Our method greatly outperforms existing contact prediction methods and leads to much more accurate contact-assisted protein folding. Tested on three datasets of 579 proteins, the average top L long-range prediction accuracy obtained our method, the representative EC method CCMpred and the CASP11 winner MetaPSICOV is 0.47, 0.21 and 0.30, respectively; the average top L/10 long-range accuracy of our method, CCMpred and MetaPSICOV is 0.77, 0.47 and 0.59, respectively. Ab initio folding using our predicted contacts as restraints can yield correct folds (i.e., TMscore>0.6) for 203 test proteins, while that using MetaPSICOV- and CCMpred-predicted contacts can do so for only 79 and 62 proteins, respectively. Further, our contact-assisted models have much better quality than template-based models. Using our predicted contacts as restraints, we can (ab initio) fold 208 of the 398 membrane proteins with TMscore>0.5. By contrast, when the training proteins of our method are used as templates, homology modeling can only do so for 10 of them. One interesting finding is that even if we do not train our prediction models with any membrane proteins, our method works very well on membrane protein prediction. Finally, in recent blind CAMEO benchmark our method successfully folded 5 test proteins with a novel fold.

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Direct-coupling analysis of residue co-evolution captures native contacts across many protein families
• Training Very Deep Networks
• Identification of direct residue contacts in protein-protein interaction by message passing
• Improved contact prediction in proteins: Using pseudolikelihoods to infer Potts models
• Fast pseudolikelihood maximization for direct-coupling analysis of protein structure from many homologous amino-acid sequences
• Predicting protein contact map using evolutionary and physical constraints by integer programming (extended version)

Cited by in corpus (39)

• DeepGO: Predicting protein functions from sequence and interactions using a deep ontology-aware classifier
• Distance-based Protein Folding Powered by Deep Learning
• Inverse statistical problems: from the inverse Ising problem to data science
• Inverse Statistical Physics of Protein Sequences: A Key Issues Review
• The prospects of quantum computing in computational molecular biology
• Computational Protein Design with Deep Learning Neural Networks
• How pairwise coevolutionary models capture the collective residue variability in proteins
• Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review
• Efficient generative modeling of protein sequences using simple autoregressive models
• Inter-residue, inter-protein and inter-family coevolution: bridging the scales
• Advances to tackle backbone flexibility in protein docking
• Influence of Multiple Sequence Alignment Depth on Potts Statistical Models of Protein Covariation
• HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels
• A glance into the evolution of template-free protein structure prediction methodologies
• Learning to Evolve Structural Ensembles of Unfolded and Disordered Proteins Using Experimental Solution Data
• Computational protein design with evolutionary-based and physics-inspired modeling: current and future synergies
• RNA Secondary Structure Prediction By Learning Unrolled Algorithms
• Towards Compact and Robust Deep Neural Networks
• Deep Learning in Protein Structural Modeling and Design
• Correlation-Compressed Direct Coupling Analysis
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Generating Tertiary Protein Structures via an Interpretative Variational Autoencoder
• Estimating probabilistic context-free grammars for proteins using contact map constraints
• Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model
• DeepSF: deep convolutional neural network for mapping protein sequences to folds
• ImJoy: an open-source computational platform for the deep learning era
• Universal Transforming Geometric Network
• G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation
• Which transformer architecture fits my data? A vocabulary bottleneck in self-attention
• Explainable Deep Relational Networks for Predicting Compound-Protein Affinities and Contacts
• Deep learning in bioinformatics: introduction, application, and perspective in big data era
• Pandemic Drugs at Pandemic Speed: Infrastructure for Accelerating COVID-19 Drug Discovery with Hybrid Machine Learning- and Physics-based Simulations on High Performance Computers
• Predicting protein inter-residue contacts using composite likelihood maximization and deep learning
• Prediction of Structures and Interactions from Genome Information
• Deep Multi-attribute Graph Representation Learning on Protein Structures
• Cross-Modality Protein Embedding for Compound-Protein Affinity and Contact Prediction
• Direct Information Reweighted by Contact Templates: Improved RNA Contact Prediction by Combining Structural Features
• Unsupervised and Supervised Structure Learning for Protein Contact Prediction
• AmoebaContact and GDFold: a new pipeline for rapid prediction of protein structures