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

By Wei Zheng, Yang Li, Chengxin Zhang, Robin Pearce, S. Mortuza, Yang Zhang. 2019

182 citations recorded by the source corpus.

We report the results of two fully automated structure prediction pipelines, “Zhang‐Server” and “QUARK”, in CASP13. The pipelines were built upon the C‐I‐TASSER and C‐QUARK programs, which in turn are based on I‐TASSER and QUARK but with three new modules: (a) a novel multiple sequence alignment (MSA) generation protocol to construct deep sequence‐profiles for contact prediction; (b) an improved meta‐method, NeBcon, which combines multiple contact predictors, including ResPRE that predicts contact‐maps by coupling precision‐matrices with deep residual convolutional neural‐networks; and (c) an optimized contact potential to guide structure assembly simulations. For 50 CASP13 FM domains that lacked homologous templates, average TM‐scores of the first models produced by C‐I‐TASSER and C‐QUARK were 28% and 56% higher than those constructed by I‐TASSER and QUARK, respectively. For the first time, contact‐map predictions demonstrated usefulness on TBM domains with close homologous templates, where TM‐scores of C‐I‐TASSER models were significantly higher than those of I‐TASSER models with a P‐value <.05. Detailed data analyses showed that the success of C‐I‐TASSER and C‐QUARK was mainly due to the increased accuracy of deep‐learning‐based contact‐maps, as well as the careful balance between sequence‐based contact restraints, threading templates, and generic knowledge‐based potentials. Nevertheless, challenges still remain for predicting quaternary structure of multi‐domain proteins, due to the difficulties in domain partitioning and domain reassembly. In addition, contact prediction in terminal regions was often unsatisfactory due to the sparsity of MSAs. Development of new contact‐based domain partitioning and assembly methods and training contact models on sparse MSAs may help address these issues.

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

Improved protein structure prediction using predicted interresidue orientations (2019, positive): “[6] All scores are then converted into smooth energy potential by the spline function in Rosetta and used as restraints to guide the energy minimization.”
Deep learning techniques have significantly impacted protein structure prediction and protein design. (2021, methodology): “Both QUARK and Rosetta have demonstrated excellent performance in the FM section of the CASP experiment by successfully folding protein targets that lack identifiable homology templates [16 ,17,18].”
Toward the solution of the protein structure prediction problem (2021, methodology): “These deep learning restraints were found to greatly improve the modeling accuracy, especially for targets without readily identi ﬁ able template structures (27).”
Deducing high-accuracy protein contact-maps from a triplet of coevolutionary matrices through deep residual convolutional networks (2020, background): “Recent CASP experiments have witnessed encouraging progress in protein contact predictions, which have been proven to be helpful to improve accuracy and success rate for distant-homologous protein targets(3-6).”
Detecting distant-homology protein structures by aligning deep neural-network based contact maps (2019, methodology): “In the CEthreader/C-I-TASSER pipeline, since both contact-map and threading template were considered in the structural assembly simulations, the final model had a reasonable accuracy on both N- and C-terminal regions (Fig 5F), which resulted in a full-length model with a much higher TM-score (0.792)”
Mapping the Landscape of Artificial Intelligence Applications against COVID-19 (2020, result): “Heo and Feig (2020) reﬁne trRosetta and AlphaFold’s predicted structures using molecular dynamics simulations and compare the results with structure predictions from a third approach – C-I-TASSER (Zheng et al., 2019) – which incorporates nine diﬀerent methods for contact prediction.”