Deducing high-accuracy protein contact-maps from a triplet of coevolutionary matrices through deep residual convolutional networks

By Yang Li, Chengxin Zhang, Eric W. Bell, Wei Zheng, Xiaogen Zhou, Dong-Jun Yu, Yang Zhang. 2020

72 citations recorded by the source corpus.

The topology of protein folds can be specified by the inter-residue contact-maps and accurate contact-map prediction can help ab initio structure folding. We developed TripletRes to deduce protein contact-maps from discretized distance profiles by end-to-end training of deep residual neural-networks. Compared to previous approaches, the major advantage of TripletRes is in its ability to learn and directly fuse a triplet of coevolutionary matrices extracted from the whole-genome and metagenome databases and therefore minimize the information loss during the course of contact model training. TripletRes was tested on a large set of 245 non-homologous proteins from CASP and CAMEO experiments, and outperformed other state-of-the-art methods by at least 58.4% for the CASP 11&12 and 44.4% for the CAMEO targets in the top-L long-range contact precision. On the 31 FM targets from the latest CASP13 challenge, TripletRes achieved the highest precision (71.6%) for the top-L/5 long-range contact predictions. These results demonstrate a novel efficient approach to extend the power of deep convolutional networks for high-accuracy medium- and long-range protein contact-map predictions starting from primary sequences, which are critical for constructing 3D structure of proteins that lack homologous templates in the PDB library. Availability The training and testing data, standalone package, and the online server for TripletRes are available at https://zhanglab.ccmb.med.umich.edu/TripletRes/. Author Summary Ab initio protein folding has been a major unsolved problem in computational biology for more than half a century. Recent community-wide Critical Assessment of Structure Prediction (CASP) experiments have witnessed exciting progress on ab initio structure prediction, which was mainly powered by the boosting of contact-map prediction as the latter can be used as constraints to guide ab initio folding simulations. In this work, we proposed a new open-source deep-learning architecture, TripletRes, built on the residual convolutional neural networks for high-accuracy contact prediction. The large-scale benchmark and blind test results demonstrate significant advancement of the proposed methods over other approaches in predicting medium- and long-range contact-maps that are critical for guiding protein folding simulations. Detailed data analyses showed that the major advantage of TripletRes lies in the unique protocol to fuse multiple evolutionary feature matrices which are directly extracted from whole-genome and metagenome databases and therefore minimize the information loss during the contact model training.

Subfields: Materials Chemistry, 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 Materials Chemistry

In Molecular Biology

Citations in the corpus

I-TASSER-MTD: a deep-learning-based platform for multi-domain protein structure and function prediction (2022, methodology): “The contact maps are also predicted by four deep-learning-based methods (ResPre 10 , DeepPLM 31 , ResTriplet 62 and TripletRes 63 ) and a naïve Bayes-based contact predictor (NeBcon 64 ) (see the description and benchmark results reported in Supplementary Note 1).”
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, methodology): “reliable distance predictions are for short distances (Li et al., 2021), we believe it is still of significant importance to examine separately the impact of contact maps on ab initio structure prediction, especially in conjunction with the most advanced structure folding simulations that can help e”
Protein language model embeddings for fast, accurate, alignment-free protein structure prediction (2021, background): “…distances/contacts; 3D, three-dimensional; 3D structure: concept, expanded into deep learning inter-residue distances (Jones et al., 2015; Li et al., 2021; Wang et al., 2017) which through Alphafold’s deep dilated residual network became so accurate to serve as constraints for subsequent…”