Protein tertiary structure modeling driven by deep learning and contact distance prediction in CASP13

By Jianlin Cheng. 2019

148 citations recorded by the source corpus.

Prediction of residue-residue distance relationships (e.g. contacts) has become the key direction to advance protein tertiary structure prediction since 2014 CASP11 experiment, while deep learning has revolutionized the technology for contact and distance distribution prediction since its debut in 2012 CASP10 experiment. During 2018 CASP13 experiment, we enhanced our MULTICOM protein structure prediction system with three major components: contact distance prediction based on deep convolutional neural networks, contact distance-driven template-free (ab initio) modeling, and protein model ranking empowered by deep learning and contact prediction, in addition to an update of other components such as template library, sequence database, and alignment tools. Our experiment demonstrates that contact distance prediction and deep learning methods are the key reasons that MULTICOM was ranked 3rd out of all 98 predictors in both template-free and template-based protein structure modeling in CASP13. Deep convolutional neural network can utilize global information in pairwise residue-residue features such as co-evolution scores to substantially improve inter-residue contact distance prediction, which played a decisive role in correctly folding some free modeling and hard template-based modeling targets from scratch. Deep learning also successfully integrated 1D structural features, 2D contact information, and 3D structural quality scores to improve protein model quality assessment, where the contact prediction was demonstrated to consistently enhance ranking of protein models for the first time. The success of MULTICOM system in the CASP13 experiment clearly shows that protein contact distance prediction and model selection driven by powerful deep learning holds the key of solving protein structure prediction problem. However, there are still major challenges in accurately predicting protein contact distance when there are few homologous sequences to generate co-evolutionary signals, folding proteins from noisy contact distances, and ranking models of hard targets.

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): “Multiple groups showed that application of deep learning-based methods to the protein structure prediction problem makes it possible to generate fold-level accuracy models of proteins lacking homologs in the Protein Data Bank (PDB) (2) directly from multiple sequence alignments (MSAs) (3-6).”
Estimation of model accuracy in CASP13 (2019, methodology): “13 We used the predicted structures of that did not use deep learning and contact features.”
Integrating model simulation tools and cryo‐electron microscopy (2022, methodology): “241 These methods have been used successfully to score predicted models in the CASP competitions, 242 but are also applicable to models refined into cryo-EM density.”
Assessing the accuracy of contact predictions in CASP13 (2019, background): “Individual articles in the same special issue of proteins from the top performers dissect the main drivers of their performances.(55,56) We”
Deep learning methods in protein structure prediction (2020, methodology): “E.g. MUL-TICOM exploits DNCON2 - a multi-class contact map predictor - to build structural models and to feed DeepRank - an ensemble of FFNN to rank such models [138].”