Improved protein model quality assessment by integrating sequential and pairwise features using deep learning

Global Quality ◽

Protein Model ◽

Experimental Structure

AbstractMotivationAccurately estimating protein model quality in the absence of experimental structure is not only important for model evaluation and selection, but also useful for model refinement. Progress has been steadily made by introducing new features and algorithms (especially deep neural networks), but accuracy of quality assessment (QA) is still not very satisfactory, especially local QA on hard protein targets.ResultsWe propose a new single-model-based QA method ResNetQA for both local and global quality assessment. Our method predicts model quality by integrating sequential and pairwise features using a deep neural network composed of both 1D and 2D convolutional residual neural networks (ResNet). The 2D ResNet module extracts useful information from pairwise features such as model-derived distance maps, co-evolution information and predicted distance potential. The 1D ResNet is used to predict local (global) model quality from sequential features and pooled pairwise information generated by 2D ResNet. Tested on the CASP12 and CASP13 datasets, our experimental results show that our method greatly outperforms existing state-of-the-art methods. Our ablation studies indicate that the 2D ResNet module and pairwise features play an important role in improving model quality assessment.Availability and Implementationhttps://github.com/AndersJing/[email protected]

Improved protein model quality assessment by integrating sequential and pairwise features using deep learning

Bioinformatics ◽

10.1093/bioinformatics/btaa1037 ◽

2020 ◽

Author(s):

Xiaoyang Jing ◽

Jinbo Xu

Keyword(s):

Neural Networks ◽

Quality Assessment ◽

Supplementary Information ◽

Model Quality ◽

Protein Targets ◽

Global Quality ◽

Protein Model ◽

Experimental Structure

Abstract Motivation Accurately estimating protein model quality in the absence of experimental structure is not only important for model evaluation and selection but also useful for model refinement. Progress has been steadily made by introducing new features and algorithms (especially deep neural networks), but the accuracy of quality assessment (QA) is still not very satisfactory, especially local QA on hard protein targets. Results We propose a new single-model-based QA method ResNetQA for both local and global quality assessment. Our method predicts model quality by integrating sequential and pairwise features using a deep neural network composed of both 1D and 2D convolutional residual neural networks (ResNet). The 2D ResNet module extracts useful information from pairwise features such as model-derived distance maps, co-evolution information, and predicted distance potential from sequences. The 1D ResNet is used to predict local (global) model quality from sequential features and pooled pairwise information generated by 2D ResNet. Tested on the CASP12 and CASP13 datasets, our experimental results show that our method greatly outperforms existing state-of-the-art methods. Our ablation studies indicate that the 2D ResNet module and pairwise features play an important role in improving model quality assessment. Availability and implementation https://github.com/AndersJing/ResNetQA. Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

Protein model quality assessment using 3D oriented convolutional neural networks

Bioinformatics ◽

10.1093/bioinformatics/btz122 ◽

2019 ◽

Vol 35 (18) ◽

pp. 3313-3319 ◽

Cited By ~ 14

Author(s):

Guillaume Pagès ◽

Benoit Charmettant ◽

Sergei Grudinin

Keyword(s):

Neural Networks ◽

Quality Assessment ◽

Convolutional Neural Networks ◽

Single Model ◽

Model Quality ◽

Density Maps ◽

Protein Model ◽

3D Cnn

Abstract Motivation Protein model quality assessment (QA) is a crucial and yet open problem in structural bioinformatics. The current best methods for single-model QA typically combine results from different approaches, each based on different input features constructed by experts in the field. Then, the prediction model is trained using a machine-learning algorithm. Recently, with the development of convolutional neural networks (CNN), the training paradigm has changed. In computer vision, the expert-developed features have been significantly overpassed by automatically trained convolutional filters. This motivated us to apply a three-dimensional (3D) CNN to the problem of protein model QA. Results We developed Ornate (Oriented Routed Neural network with Automatic Typing)—a novel method for single-model QA. Ornate is a residue-wise scoring function that takes as input 3D density maps. It predicts the local (residue-wise) and the global model quality through a deep 3D CNN. Specifically, Ornate aligns the input density map, corresponding to each residue and its neighborhood, with the backbone topology of this residue. This circumvents the problem of ambiguous orientations of the initial models. Also, Ornate includes automatic identification of atom types and dynamic routing of the data in the network. Established benchmarks (CASP 11 and CASP 12) demonstrate the state-of-the-art performance of our approach among single-model QA methods. Availability and implementation The method is available at https://team.inria.fr/nano-d/software/Ornate/. It consists of a C++ executable that transforms molecular structures into volumetric density maps, and a Python code based on the TensorFlow framework for applying the Ornate model to these maps. Supplementary information Supplementary data are available at Bioinformatics online.

Protein model quality assessment using 3D oriented convolutional neural networks

10.1101/432146 ◽

2018 ◽

Cited By ~ 1

Author(s):

Guillaume Pagès ◽

Benoit Charmettant ◽

Sergei Grudinin

Keyword(s):

Neural Networks ◽

Quality Assessment ◽

Convolutional Neural Networks ◽

Single Model ◽

Model Quality ◽

Density Maps ◽

Protein Model ◽

3D Cnn

Protein model quality assessment (QA) is a crucial and yet open problem in structural bioinformatics. The current best methods for single-model QA typically combine results from different approaches, each based on different input features constructed by experts in the field. Then, the prediction model is trained using a machine-learning algorithm. Recently, with the development of convolutional neural networks (CNN), the training paradigm has changed. In computer vision, the expert-developed features have been significantly overpassed by automatically trained convolutional filters. This motivated us to apply a three-dimensional (3D) CNN to the problem of protein model QA.We developed a novel method for single-model QA called Ornate. Ornate (Oriented Routed Neural network with Automatic Typing) is a residue-wise scoring function that takes as input 3D density maps. It predicts the local (residue-wise) and the global model quality through a deep 3D CNN. Specifically, Ornate aligns the input density map, corresponding to each residue and its neighborhood, with the backbone topology of this residue. This circumvents the problem of ambiguous orientations of the initial models. Also, Ornate includes automatic identification of atom types and dynamic routing of the data in the network. Established benchmarks (CASP 11 and CASP 12) demonstrate the state-of-the-art performance of our approach among singlemodel QA methods.The method is available at https://team.inria.fr/nanod/software/Ornate/. It consists of a C++ executable that transforms molecular structures into volumetric density maps, and a Python code based on the TensorFlow framework for applying the Ornate model to these maps.

TopScore: Using Deep Neural Networks and Large Diverse Data Sets for Accurate Protein Model Quality Assessment

Journal of Chemical Theory and Computation ◽

10.1021/acs.jctc.8b00690 ◽

2018 ◽

Vol 14 (11) ◽

pp. 6117-6126 ◽

Cited By ~ 10

Author(s):

Daniel Mulnaes ◽

Holger Gohlke

Keyword(s):

Neural Networks ◽

Quality Assessment ◽

Deep Neural Networks ◽

Data Sets ◽

Model Quality ◽

Protein Model ◽

Diverse Data

DeepUMQA: Ultrafast Shape Recognition-based Protein Model Quality Assessment using Deep Learning

10.1101/2021.10.02.462491 ◽

2021 ◽

Author(s):

Sai-Sai Guo ◽

Jun Liu ◽

Xiao-Gen Zhou ◽

Gui-Jun Zhang

Keyword(s):

Deep Learning ◽

Quality Assessment ◽

Shape Recognition ◽

Residue Level ◽

Model Assessment ◽

Single Model ◽

Model Quality ◽

Protein Model ◽

Protein Model Quality Assessment

AbstractMotivationProtein model quality assessment is a key component of protein structure prediction. In recent research, the voxelization feature was used to characterize the local structural information of residues, but it may be insufficient for describing residue-level topological information. Design features that can further reflect residue-level topology when combined with deep learning methods are therefore crucial to improve the performance of model quality assessment.ResultsWe developed a deep-learning method, DeepUMQA, based on Ultrafast Shape Recognition (USR) for the residue-level single-model quality assessment. In the framework of the deep residual neural network, the residue-level USR feature was introduced to describe the topological relationship between the residue and overall structure by calculating the first moment of a set of residue distance sets and then combined with 1D, 2D, and voxelization features to assess the quality of the model. Experimental results on test datasets of CASP13, CASP14, and CAMEO show that USR could complement the voxelization feature to comprehensively characterize residue structure information and significantly improve the model assessment accuracy. DeepUMQA outperformed the state-of-the-art single-model quality assessment methods, including ProQ2, ProQ3, ProQ3D, Ornate, VoroMQA, and DeepAccNet.AvailabilityThe source code and executable are freely available at https://github.com/iobio-zjut/[email protected]