1
|
Liu J, Zhao K, Zhang G. Improved model quality assessment using sequence and structural information by enhanced deep neural networks. Brief Bioinform 2023; 24:6865134. [PMID: 36460624 DOI: 10.1093/bib/bbac507] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2022] [Revised: 10/02/2022] [Accepted: 10/24/2022] [Indexed: 12/04/2022] Open
Abstract
Protein model quality assessment plays an important role in protein structure prediction, protein design and drug discovery. In this work, DeepUMQA2, a substantially improved version of DeepUMQA for protein model quality assessment, is proposed. First, sequence features containing protein co-evolution information and structural features reflecting family information are extracted to complement model-dependent features. Second, a novel backbone network based on triangular multiplication update and axial attention mechanism is designed to enhance information exchange between inter-residue pairs. On CASP13 and CASP14 datasets, the performance of DeepUMQA2 increases by 20.5 and 20.4% compared with DeepUMQA, respectively (measured by top 1 loss). Moreover, on the three-month CAMEO dataset (11 March to 04 June 2022), DeepUMQA2 outperforms DeepUMQA by 15.5% (measured by local AUC0,0.2) and ranks first among all competing server methods in CAMEO blind test. Experimental results show that DeepUMQA2 outperforms state-of-the-art model quality assessment methods, such as ProQ3D-LDDT, ModFOLD8, and DeepAccNet and DeepUMQA2 can select more suitable best models than state-of-the-art protein structure methods, such as AlphaFold2, RoseTTAFold and I-TASSER, provided themselves.
Collapse
Affiliation(s)
- Jun Liu
- College of Information Engineering, Zhejiang University of Technology
| | - Kailong Zhao
- College of Information Engineering, Zhejiang University of Technology
| | - Guijun Zhang
- College of Information Engineering, Zhejiang University of Technology
| |
Collapse
|
2
|
Kaushik R, Zhang KY. An Integrated Protein Structure Fitness Scoring Approach for Identifying Native-Like Model Structures. Comput Struct Biotechnol J 2022; 20:6467-6472. [DOI: 10.1016/j.csbj.2022.11.032] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2022] [Revised: 11/14/2022] [Accepted: 11/14/2022] [Indexed: 11/18/2022] Open
|
3
|
Dong S, Wang S. Assembled graph neural network using graph transformer with edges for protein model quality assessment. J Mol Graph Model 2021; 110:108053. [PMID: 34773871 DOI: 10.1016/j.jmgm.2021.108053] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2021] [Revised: 10/13/2021] [Accepted: 10/13/2021] [Indexed: 10/19/2022]
Abstract
Acquainting protein's structure is of vital importance to accurately understanding its function. Computational method of deep learning has made great progress in protein structure prediction from sequence, and has the potential to help structural biology research. The computational methods usually require independent protein structure model quality assessment to select the best from the model pool or guide protein structure refinement. We construct a graph neural network finely assembled with Graph Transformer Feature Extractor and message-passing layers for protein model quality assessment. The graph based method can more naturally embody the protein structure than a sequence or voxelized representation method. Although the widely used graph convolutional network has a strong ability to learn spatial patterns, it does not weigh the dependencies of different nodes on other nodes. So we introduce Graph Transformer to excavate the different degrees of neighboring residue nodes contributing to their local environments and extract local features. This is subsequently followed by message-passing layers to transmit-receive local information. Our network makes better use of edge information and is lightweight since relatively few input features and number of network layers, and experimental results demonstrate that our model outperforms various existing methods. Core code is made freely available at: https://github.com/Crystal-Dsq/proteinqa.
Collapse
Affiliation(s)
- Shiqi Dong
- Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming, 650504, China
| | - Shunfang Wang
- Department of Computer Science and Engineering, School of Information Science and Engineering, Yunnan University, Kunming, 650504, China.
| |
Collapse
|
4
|
Baldassarre F, Menéndez Hurtado D, Elofsson A, Azizpour H. GraphQA: protein model quality assessment using graph convolutional networks. Bioinformatics 2021; 37:360-366. [PMID: 32780838 PMCID: PMC8058777 DOI: 10.1093/bioinformatics/btaa714] [Citation(s) in RCA: 37] [Impact Index Per Article: 12.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2020] [Revised: 07/03/2020] [Accepted: 08/05/2020] [Indexed: 11/25/2022] Open
Abstract
Motivation Proteins are ubiquitous molecules whose function in biological processes is determined by their 3D structure. Experimental identification of a protein’s structure can be time-consuming, prohibitively expensive and not always possible. Alternatively, protein folding can be modeled using computational methods, which however are not guaranteed to always produce optimal results. GraphQA is a graph-based method to estimate the quality of protein models, that possesses favorable properties such as representation learning, explicit modeling of both sequential and 3D structure, geometric invariance and computational efficiency. Results GraphQA performs similarly to state-of-the-art methods despite using a relatively low number of input features. In addition, the graph network structure provides an improvement over the architecture used in ProQ4 operating on the same input features. Finally, the individual contributions of GraphQA components are carefully evaluated. Availability and implementation PyTorch implementation, datasets, experiments and link to an evaluation server are available through this GitHub repository: github.com/baldassarreFe/graphqa. Supplementary information Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Federico Baldassarre
- Division of Robotics, Perception and Learning (RPL), KTH – Royal Institute of Technology, 10044 Stockholm, Sweden
| | - David Menéndez Hurtado
- Department of Intelligent Systems, Science for Life Laboratory, Stockholm University, Box 1031, 17121 Solna, Sweden
- Department of Biochemistry and Biophysics, school of Electrical Engineering and Computer Science (EECS), Stockholm University, 10691 Stockholm, Sweden
| | - Arne Elofsson
- Department of Intelligent Systems, Science for Life Laboratory, Stockholm University, Box 1031, 17121 Solna, Sweden
- Department of Biochemistry and Biophysics, school of Electrical Engineering and Computer Science (EECS), Stockholm University, 10691 Stockholm, Sweden
| | - Hossein Azizpour
- Division of Robotics, Perception and Learning (RPL), KTH – Royal Institute of Technology, 10044 Stockholm, Sweden
- To whom correspondence should be addressed.
| |
Collapse
|
5
|
Igashov I, Olechnovič L, Kadukova M, Venclovas Č, Grudinin S. VoroCNN: Deep convolutional neural network built on 3D Voronoi tessellation of protein structures. Bioinformatics 2021; 37:2332-2339. [PMID: 33620450 DOI: 10.1093/bioinformatics/btab118] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/04/2020] [Revised: 01/08/2021] [Accepted: 02/22/2021] [Indexed: 11/13/2022] Open
Abstract
MOTIVATION Effective use of evolutionary information has recently led to tremendous progress in computational prediction of three-dimensional (3D) structures of proteins and their complexes. Despite the progress, the accuracy of predicted structures tends to vary considerably from case to case. Since the utility of computational models depends on their accuracy, reliable estimates of deviation between predicted and native structures are of utmost importance. RESULTS For the first time, we present a deep convolutional neural network (CNN) constructed on a Voronoi tessellation of 3D molecular structures. Despite the irregular data domain, our data representation allows us to efficiently introduce both convolution and pooling operations and train the network in an end-to-end fashion without precomputed descriptors. The resultant model, VoroCNN, predicts local qualities of 3D protein folds. The prediction results are competitive to state of the art and superior to the previous 3D CNN architectures built for the same task. We also discuss practical applications of VoroCNN, for example, in recognition of protein binding interfaces. AVAILABILITY The model, data, and evaluation tests are available at https://team.inria.fr/nano-d/software/vorocnn/. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Ilia Igashov
- Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, 38000 Grenoble, France.,Moscow Institute of Physics and Technology, 141701 Dolgoprudniy, Russia
| | - Liment Olechnovič
- Institute of Biotechnology Life Sciences Center Vilnius University, Saulėtekio 7, Vilnius, LT 10257, Lithuania
| | - Maria Kadukova
- Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, 38000 Grenoble, France.,Moscow Institute of Physics and Technology, 141701 Dolgoprudniy, Russia
| | - Česlovas Venclovas
- Institute of Biotechnology Life Sciences Center Vilnius University, Saulėtekio 7, Vilnius, LT 10257, Lithuania
| | - Sergei Grudinin
- Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, 38000 Grenoble, France
| |
Collapse
|
6
|
Studer G, Rempfer C, Waterhouse AM, Gumienny R, Haas J, Schwede T. QMEANDisCo-distance constraints applied on model quality estimation. Bioinformatics 2020; 36:1765-1771. [PMID: 31697312 PMCID: PMC7075525 DOI: 10.1093/bioinformatics/btz828] [Citation(s) in RCA: 424] [Impact Index Per Article: 106.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/19/2019] [Revised: 10/24/2019] [Accepted: 11/06/2019] [Indexed: 01/13/2023] Open
Abstract
Motivation Methods that estimate the quality of a 3D protein structure model in absence of an experimental reference structure are crucial to determine a model’s utility and potential applications. Single model methods assess individual models whereas consensus methods require an ensemble of models as input. In this work, we extend the single model composite score QMEAN that employs statistical potentials of mean force and agreement terms by introducing a consensus-based distance constraint (DisCo) score. Results DisCo exploits distance distributions from experimentally determined protein structures that are homologous to the model being assessed. Feed-forward neural networks are trained to adaptively weigh contributions by the multi-template DisCo score and classical single model QMEAN parameters. The result is the composite score QMEANDisCo, which combines the accuracy of consensus methods with the broad applicability of single model approaches. We also demonstrate that, despite being the de-facto standard for structure prediction benchmarking, CASP models are not the ideal data source to train predictive methods for model quality estimation. For performance assessment, QMEANDisCo is continuously benchmarked within the CAMEO project and participated in CASP13. For both, it ranks among the top performers and excels with low response times. Availability and implementation QMEANDisCo is available as web-server at https://swissmodel.expasy.org/qmean. The source code can be downloaded from https://git.scicore.unibas.ch/schwede/QMEAN. Supplementary information Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Gabriel Studer
- Biozentrum, University of Basel, Basel 4056, Switzerland.,SIB Swiss Institute of Bioinformatics, Basel 4056, Switzerland
| | - Christine Rempfer
- Biozentrum, University of Basel, Basel 4056, Switzerland.,SIB Swiss Institute of Bioinformatics, Basel 4056, Switzerland
| | - Andrew M Waterhouse
- Biozentrum, University of Basel, Basel 4056, Switzerland.,SIB Swiss Institute of Bioinformatics, Basel 4056, Switzerland
| | - Rafal Gumienny
- Biozentrum, University of Basel, Basel 4056, Switzerland.,SIB Swiss Institute of Bioinformatics, Basel 4056, Switzerland
| | - Juergen Haas
- Biozentrum, University of Basel, Basel 4056, Switzerland.,SIB Swiss Institute of Bioinformatics, Basel 4056, Switzerland
| | - Torsten Schwede
- Biozentrum, University of Basel, Basel 4056, Switzerland.,SIB Swiss Institute of Bioinformatics, Basel 4056, Switzerland
| |
Collapse
|
7
|
Olechnovič K, Monastyrskyy B, Kryshtafovych A, Venclovas Č. Comparative analysis of methods for evaluation of protein models against native structures. Bioinformatics 2019; 35:937-944. [PMID: 30169622 DOI: 10.1093/bioinformatics/bty760] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2018] [Revised: 08/04/2018] [Accepted: 08/28/2018] [Indexed: 12/17/2022] Open
Abstract
MOTIVATION Measuring discrepancies between protein models and native structures is at the heart of development of protein structure prediction methods and comparison of their performance. A number of different evaluation methods have been developed; however, their comprehensive and unbiased comparison has not been performed. RESULTS We carried out a comparative analysis of several popular model assessment methods (RMSD, TM-score, GDT, QCS, CAD-score, LDDT, SphereGrinder and RPF) to reveal their relative strengths and weaknesses. The analysis, performed on a large and diverse model set derived in the course of three latest community-wide CASP experiments (CASP10-12), had two major directions. First, we looked at general differences between the scores by analyzing distribution, correspondence and correlation of their values as well as differences in selecting best models. Second, we examined the score differences taking into account various structural properties of models (stereochemistry, hydrogen bonds, packing of domains and chain fragments, missing residues, protein length and secondary structure). Our results provide a solid basis for an informed selection of the most appropriate score or combination of scores depending on the task at hand. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Kliment Olechnovič
- Institute of Biotechnology Life Sciences Center Vilnius University, Saulėtekio 7, Vilnius, Lithuania
| | | | | | - Česlovas Venclovas
- Institute of Biotechnology Life Sciences Center Vilnius University, Saulėtekio 7, Vilnius, Lithuania
| |
Collapse
|
8
|
Cheng J, Choe MH, Elofsson A, Han KS, Hou J, Maghrabi AHA, McGuffin LJ, Menéndez-Hurtado D, Olechnovič K, Schwede T, Studer G, Uziela K, Venclovas Č, Wallner B. Estimation of model accuracy in CASP13. Proteins 2019; 87:1361-1377. [PMID: 31265154 DOI: 10.1002/prot.25767] [Citation(s) in RCA: 51] [Impact Index Per Article: 10.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/30/2019] [Revised: 06/04/2019] [Accepted: 06/15/2019] [Indexed: 12/28/2022]
Abstract
Methods to reliably estimate the accuracy of 3D models of proteins are both a fundamental part of most protein folding pipelines and important for reliable identification of the best models when multiple pipelines are used. Here, we describe the progress made from CASP12 to CASP13 in the field of estimation of model accuracy (EMA) as seen from the progress of the most successful methods in CASP13. We show small but clear progress, that is, several methods perform better than the best methods from CASP12 when tested on CASP13 EMA targets. Some progress is driven by applying deep learning and residue-residue contacts to model accuracy prediction. We show that the best EMA methods select better models than the best servers in CASP13, but that there exists a great potential to improve this further. Also, according to the evaluation criteria based on local similarities, such as lDDT and CAD, it is now clear that single model accuracy methods perform relatively better than consensus-based methods.
Collapse
Affiliation(s)
- Jianlin Cheng
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri
| | - Myong-Ho Choe
- Department of Life Science, University of Science, Pyongyang, DPR Korea
| | - Arne Elofsson
- Department of Biochemistry and Biophysics and Science for Life Laboratory, Stockholm University, Stockholm, Sweden
| | - Kun-Sop Han
- Department of Life Science, University of Science, Pyongyang, DPR Korea
| | - Jie Hou
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, Missouri
| | - Ali H A Maghrabi
- School of Biological Sciences, University of Reading, Reading, UK
| | - Liam J McGuffin
- School of Biological Sciences, University of Reading, Reading, UK
| | - David Menéndez-Hurtado
- Department of Biochemistry and Biophysics and Science for Life Laboratory, Stockholm University, Stockholm, Sweden
| | - Kliment Olechnovič
- Institute of Biotechnology, Life Sciences Center, Vilnius University, Vilnius, Lithuania
| | - Torsten Schwede
- Biozentrum, University of Basel, Basel, Switzerland.,SIB Swiss Institute of Bioinformatics, Biozentrum, University of Basel, Basel, Switzerland
| | - Gabriel Studer
- Biozentrum, University of Basel, Basel, Switzerland.,SIB Swiss Institute of Bioinformatics, Biozentrum, University of Basel, Basel, Switzerland
| | - Karolis Uziela
- Department of Biochemistry and Biophysics and Science for Life Laboratory, Stockholm University, Stockholm, Sweden
| | - Česlovas Venclovas
- Institute of Biotechnology, Life Sciences Center, Vilnius University, Vilnius, Lithuania
| | - Björn Wallner
- Department of Physics, Chemistry, and Biology, Bioinformatics Division, Linköping University, Linköping, Sweden
| |
Collapse
|
9
|
Bassot C, Menendez Hurtado D, Elofsson A. Using PconsC4 and PconsFold2 to Predict Protein Structure. ACTA ACUST UNITED AC 2019; 66:e75. [PMID: 31063641 DOI: 10.1002/cpbi.75] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
In spite of the fact that there has been a significant increase in the number of solved protein structures, structural information is missing for many proteins. Although structural information is codified in the amino acid sequence, computational prediction using only this information is still an unsolved problem. However, one successful method to model a protein's structure starting from the primary sequence is to use contact prediction derived from multiple sequence alignment (MSA). Here we use our contact predictor PconsC4 to generate a list of probable contacts between residues in the primary sequences. These contacts are then used together with the secondary structure prediction as constraints for the CONFOLD folding method. In this way, a 3D protein model can be built starting directly from the primary sequence. © 2019 by John Wiley & Sons, Inc.
Collapse
Affiliation(s)
- Claudio Bassot
- Department of Biochemistry and Biophysics, Stockholm University and Science for Life Laboratory, Solna, Sweden
| | - David Menendez Hurtado
- Department of Biochemistry and Biophysics, Stockholm University and Science for Life Laboratory, Solna, Sweden
| | - Arne Elofsson
- Department of Biochemistry and Biophysics, Stockholm University and Science for Life Laboratory, Solna, Sweden
| |
Collapse
|