Ensembling multiple raw coevolutionary features with deep residual neural networks for contact-map prediction in CASP13
By Yang Li, Chengxin Zhang, Eric W. Bell, Dong-Jun Yu, Yang Zhang. 2019
88 citations recorded by the source corpus.
We report the results of residue‐residue contact prediction of a new pipeline built purely on the learning of coevolutionary features in the CASP13 experiment. For a query sequence, the pipeline starts with the collection of multiple sequence alignments (MSAs) from multiple genome and metagenome sequence databases using two complementary Hidden Markov Model (HMM)‐based searching tools. Three profile matrices, built on covariance, precision, and pseudolikelihood maximization respectively, are then created from the MSAs, which are used as the input features of a deep residual convolutional neural network architecture for contact‐map training and prediction. Two ensembling strategies have been proposed to integrate the matrix features through end‐to‐end training and stacking, resulting in two complementary programs called TripletRes and ResTriplet, respectively. For the 31 free‐modeling domains that do not have homologous templates in the PDB, TripletRes and ResTriplet generated comparable results with an average accuracy of 0.640 and 0.646, respectively, for the top L/5 long‐range predictions, where 71% and 74% of the cases have an accuracy above 0.5. Detailed data analyses showed that the strength of the pipeline is due to the sensitive MSA construction and the advanced strategies for coevolutionary feature ensembling. Domain splitting was also found to help enhance the contact prediction performance. Nevertheless, contact models for tail regions, which often involve a high number of alignment gaps, and for targets with few homologous sequences are still suboptimal. Development of new approaches where the model is specifically trained on these regions and targets might help address these problems.
Subfields: Molecular Biology
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Molecular Biology
Citations in the corpus
- Deep learning methods in protein structure prediction (2020, background): “TripletRes [122] is a contact map predictor that ranked first in”
- Deep learning-based prediction of protein structure using learned representations of multiple sequence alignments (2020, background): “The latter have produced increasingly precise predictions of inter-residue contacts in recent years [4–6] , and have also been adapted to output probabilistic predictions of the distance between the residues in contact, either as a probability distribution [7–10] , or as real values [11–13] .”
- Recent developments in deep learning applied to protein structure prediction (2019, methodology): “These so-called residual NNs (ResNets) are becoming the standard architecture for training very deep CNNs, and have been used in the best-performing methods for contact and distance prediction in CASP, 9,10,41,42,47,48 including those by the Zhang and A7D groups in CASP13.”
- Ultrafast end-to-end protein structure prediction enables high-throughput exploration of uncharacterized proteins (2022, unknown): “The network makes use of just three recurrent networks and a stack of residual convolutional layers, making the predictor very fast to run, and easy to install and use.”
- Toward the solution of the protein structure prediction problem (2021, methodology): “One particularly successful method in CASP13, TripletRes (168, 169), used a similar ResNet basic block for its deep learning architecture but with a triplet of coevolutionary matrices.”
- Folding non-homologous proteins by coupling deep-learning contact maps with I-TASSER assembly simulations (2021, background): “, 2019a), ResPLM (Li et al., 2019b; Zheng et al., 2019a), and NeBconA/NeBconB (He et al.”