Analysis of distance-based protein structure prediction by deep learning in CASP13

By Jinbo Xu, Sheng Wang. 2019

122 citations recorded by the source corpus.

This paper reports the CASP13 results of distance-based contact prediction, threading and folding methods implemented in three RaptorX servers, which are built upon the powerful deep convolutional residual neural network (ResNet) method initiated by us for contact prediction in CASP12. On the 32 CASP13 FM (free-modeling) targets with a median MSA (multiple sequence alignment) depth of 36, RaptorX yielded the best contact prediction among 46 groups and almost the best 3D structure modeling among all server groups without time-consuming conformation sampling. In particular, RaptorX achieved top L/5, L/2 and L long-range contact precision of 70%, 58% and 45%, respectively, and predicted correct folds (TMscore>0.5) for 18 of 32 targets. Although on average underperforming AlphaFold in 3D modeling, RaptorX predicted correct folds for all FM targets with >300 residues (T0950-D1, T0969-D1 and T1000-D2) and generated the best 3D models for T0950-D1 and T0969-D1 among all groups. This CASP13 test confirms our previous findings: (1) predicted distance is more useful than contacts for both template-based and free modeling; and (2) structure modeling may be improved by integrating alignment and co-evolutionary information via deep learning. This paper will discuss progress we have made since CASP12, the strength and weakness of our methods, and why deep learning performed much better in CASP13.

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

Analysis of several key factors influencing deep learning-based inter-residue contact prediction (2019, methodology): “In the CASP13 experiment, some external deep learning methods performed better than our predictors, partially due to the difference in the architecture design and training strategy (Kandathil et al., 2019; Li et al., 2019; Xu and Wang, 2019).”
Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13) (2019, methodology): “Contact prediction has been extensively used in structure prediction(16,20,29,31) but previous work has also made residue distance predictions,(3,35) and these were used for structure prediction in CASP13 by other groups in distance geometry approaches.(10,32) While in some cases, these distances ar”
Recent developments in deep learning applied to protein structure prediction (2019, methodology): “In CASP13, dilated convolutions were used in a number of the top-performing CNN models.(7,41,42) Typical CNN models (eg, for image classification) take the output”
MMpred: a distance-assisted multimodal conformation sampling for de novo protein structure prediction (2021, methodology): “RaptorX inputs the predicted distance, secondary structure, and torsion angles predicted by deep convolutional neural networks into the Crystallography and NMR system (CNS) (Brunger et al., 2007) to quickly constructed an accurate 3D model (Xu, 2019; Wang et al., 2017).”