1
|
Basu S, Kurgan L. Taxonomy-specific assessment of intrinsic disorder predictions at residue and region levels in higher eukaryotes, protists, archaea, bacteria and viruses. Comput Struct Biotechnol J 2024; 23:1968-1977. [PMID: 38765610 PMCID: PMC11098722 DOI: 10.1016/j.csbj.2024.04.059] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2024] [Revised: 04/23/2024] [Accepted: 04/24/2024] [Indexed: 05/22/2024] Open
Abstract
Intrinsic disorder predictors were evaluated in several studies including the two large CAID experiments. However, these studies are biased towards eukaryotic proteins and focus primarily on the residue-level predictions. We provide first-of-its-kind assessment that comprehensively covers the taxonomy and evaluates predictions at the residue and disordered region levels. We curate a benchmark dataset that uniformly covers eukaryotic, archaeal, bacterial, and viral proteins. We find that predictive performance differs substantially across taxonomy, where viruses are predicted most accurately, followed by protists and higher eukaryotes, while bacterial and archaeal proteins suffer lower levels of accuracy. These trends are consistent across predictors. We also find that current tools, except for flDPnn, struggle with reproducing native distributions of the numbers and sizes of the disordered regions. Moreover, analysis of two variants of disorder predictions derived from the AlphaFold2 predicted structures reveals that they produce accurate residue-level propensities for archaea, bacteria and protists. However, they underperform for higher eukaryotes and generally struggle to accurately identify disordered regions. Our results motivate development of new predictors that target bacteria and archaea and which produce accurate results at both residue and region levels. We also stress the need to include the region-level assessments in future assessments.
Collapse
Affiliation(s)
- Sushmita Basu
- Department of Computer Science, Virginia Commonwealth University, Richmond, VA 23284, USA
| | - Lukasz Kurgan
- Department of Computer Science, Virginia Commonwealth University, Richmond, VA 23284, USA
| |
Collapse
|
2
|
Siciliano AJ, Zhao C, Liu T, Wang Z. EGG: Accuracy Estimation of Individual Multimeric Protein Models Using Deep Energy-Based Models and Graph Neural Networks. Int J Mol Sci 2024; 25:6250. [PMID: 38892437 PMCID: PMC11173161 DOI: 10.3390/ijms25116250] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2024] [Revised: 05/25/2024] [Accepted: 05/29/2024] [Indexed: 06/21/2024] Open
Abstract
Reliable and accurate methods of estimating the accuracy of predicted protein models are vital to understanding their respective utility. Discerning how the quaternary structure conforms can significantly improve our collective understanding of cell biology, systems biology, disease formation, and disease treatment. Accurately determining the quality of multimeric protein models is still computationally challenging, as the space of possible conformations is significantly larger when proteins form in complex with one another. Here, we present EGG (energy and graph-based architectures) to assess the accuracy of predicted multimeric protein models. We implemented message-passing and transformer layers to infer the overall fold and interface accuracy scores of predicted multimeric protein models. When evaluated with CASP15 targets, our methods achieved promising results against single model predictors: fourth and third place for determining the highest-quality model when estimating overall fold accuracy and overall interface accuracy, respectively, and first place for determining the top three highest quality models when estimating both overall fold accuracy and overall interface accuracy.
Collapse
Affiliation(s)
- Andrew Jordan Siciliano
- Department of Computer Science, University of Miami, 1365 Memorial Drive, Coral Gables, FL 33124, USA; (A.J.S.); (T.L.)
| | - Chenguang Zhao
- Computer Information Sciences Department, St. Ambrose University, 518 W. Locust Street, Davenport, IA 52803, USA;
| | - Tong Liu
- Department of Computer Science, University of Miami, 1365 Memorial Drive, Coral Gables, FL 33124, USA; (A.J.S.); (T.L.)
| | - Zheng Wang
- Department of Computer Science, University of Miami, 1365 Memorial Drive, Coral Gables, FL 33124, USA; (A.J.S.); (T.L.)
| |
Collapse
|
3
|
Zhao C, Liu T, Wang Z. Predicting residue-specific qualities of individual protein models using residual neural networks and graph neural networks. Proteins 2022; 90:2091-2102. [PMID: 35842895 PMCID: PMC9796650 DOI: 10.1002/prot.26400] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/16/2022] [Revised: 06/24/2022] [Accepted: 07/08/2022] [Indexed: 01/02/2023]
Abstract
The estimation of protein model accuracy (EMA) or model quality assessment (QA) is important for protein structure prediction. An accurate EMA algorithm can guide the refinement of models or pick the best model or best parts of models from a pool of predicted tertiary structures. We developed two novel methods: MASS2 and LAW, for predicting residue-specific or local qualities of individual models, which incorporate residual neural networks and graph neural networks, respectively. These two methods use similar features extracted from protein models but different architectures of neural networks to predict the local accuracies of single models. MASS2 and LAW participated in the QA category of CASP14, and according to our evaluations based on CASP14 official criteria, MASS2 and LAW are the best and second-best methods based on the Z-scores of ASE/100, AUC, and ULR-1.F1. We also evaluated MASS2, LAW, and the residue-specific predicted deviations (between model and native structure) generated by AlphaFold2 on CASP14 AlphaFold2 tertiary structure (TS) models. LAW achieved comparable or better performances compared to the predicted deviations generated by AlphaFold2 on AlphaFold2 TS models, even though LAW was not trained on any AlphaFold2 TS models. Specifically, LAW performed better on AUC and ULR scores, and AlphaFold2 performed better on ASE scores. This means that AlphaFold2 is better at predicting deviations, but LAW is better at classifying accurate and inaccurate residues and detecting unreliable local regions. MASS2 and LAW can be freely accessed from http://dna.cs.miami.edu/MASS2-CASP14/ and http://dna.cs.miami.edu/LAW-CASP14/, respectively.
Collapse
Affiliation(s)
- Chenguang Zhao
- Department of Computer ScienceUniversity of MiamiCoral GablesFloridaUSA
| | - Tong Liu
- Department of Computer ScienceUniversity of MiamiCoral GablesFloridaUSA
| | - Zheng Wang
- Department of Computer ScienceUniversity of MiamiCoral GablesFloridaUSA
| |
Collapse
|
4
|
Ismi DP, Pulungan R, Afiahayati. Deep learning for protein secondary structure prediction: Pre and post-AlphaFold. Comput Struct Biotechnol J 2022; 20:6271-6286. [PMID: 36420164 PMCID: PMC9678802 DOI: 10.1016/j.csbj.2022.11.012] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/06/2022] [Revised: 11/05/2022] [Accepted: 11/05/2022] [Indexed: 11/13/2022] Open
Abstract
This paper aims to provide a comprehensive review of the trends and challenges of deep neural networks for protein secondary structure prediction (PSSP). In recent years, deep neural networks have become the primary method for protein secondary structure prediction. Previous studies showed that deep neural networks had uplifted the accuracy of three-state secondary structure prediction to more than 80%. Favored deep learning methods, such as convolutional neural networks, recurrent neural networks, inception networks, and graph neural networks, have been implemented in protein secondary structure prediction. Methods adapted from natural language processing (NLP) and computer vision are also employed, including attention mechanism, ResNet, and U-shape networks. In the post-AlphaFold era, PSSP studies focus on different objectives, such as enhancing the quality of evolutionary information and exploiting protein language models as the PSSP input. The recent trend to utilize pre-trained language models as input features for secondary structure prediction provides a new direction for PSSP studies. Moreover, the state-of-the-art accuracy achieved by previous PSSP models is still below its theoretical limit. There are still rooms for improvement to be made in the field.
Collapse
Affiliation(s)
- Dewi Pramudi Ismi
- Department of Computer Science and Electronics, Faculty of Mathematics and Natural Sciences, Universitas Gadjah Mada, Yogyakarta, Indonesia
- Department of Infomatics, Faculty of Industrial Technology, Universitas Ahmad Dahlan, Yogyakarta, Indonesia
| | - Reza Pulungan
- Department of Computer Science and Electronics, Faculty of Mathematics and Natural Sciences, Universitas Gadjah Mada, Yogyakarta, Indonesia
| | - Afiahayati
- Department of Computer Science and Electronics, Faculty of Mathematics and Natural Sciences, Universitas Gadjah Mada, Yogyakarta, Indonesia
| |
Collapse
|
5
|
Stapor K, Kotowski K, Smolarczyk T, Roterman I. Lightweight ProteinUnet2 network for protein secondary structure prediction: a step towards proper evaluation. BMC Bioinformatics 2022; 23:100. [PMID: 35317722 PMCID: PMC8939211 DOI: 10.1186/s12859-022-04623-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/13/2021] [Accepted: 02/28/2022] [Indexed: 11/10/2022] Open
Abstract
Background The prediction of protein secondary structures is a crucial and significant step for ab initio tertiary structure prediction which delivers the information about proteins activity and functions. As the experimental methods are expensive and sometimes impossible, many SS predictors, mainly based on different machine learning methods have been proposed for many years. Currently, most of the top methods use evolutionary-based input features produced by PSSM and HHblits software, although quite recently the embeddings—the new description of protein sequences generated by language models (LM) have appeared that could be leveraged as input features. Apart from input features calculation, the top models usually need extensive computational resources for training and prediction and are barely possible to run on a regular PC. SS prediction as the imbalanced classification problem should not be judged by the commonly used Q3/Q8 metrics. Moreover, as the benchmark datasets are not random samples, the classical statistical null hypothesis testing based on the Neyman–Pearson approach is not appropriate. Results We present a lightweight deep network ProteinUnet2 for SS prediction which is based on U-Net convolutional architecture and evolutionary-based input features (from PSSM and HHblits) as well as SPOT-Contact features. Through an extensive evaluation study, we report the performance of ProteinUnet2 in comparison with top SS prediction methods based on evolutionary information (SAINT and SPOT-1D). We also propose a new statistical methodology for prediction performance assessment based on the significance from Fisher–Pitman permutation tests accompanied by practical significance measured by Cohen’s effect size. Conclusions Our results suggest that ProteinUnet2 architecture has much shorter training and inference times while maintaining results similar to SAINT and SPOT-1D predictors. Taking into account the relatively long times of calculating evolutionary-based features (from PSSM in particular), it would be worth conducting the predictive ability tests on embeddings as input features in the future. We strongly believe that our proposed here statistical methodology for the evaluation of SS prediction results will be adopted and used (and even expanded) by the research community. Supplementary Information The online version contains supplementary material available at 10.1186/s12859-022-04623-z.
Collapse
Affiliation(s)
- Katarzyna Stapor
- Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland.
| | - Krzysztof Kotowski
- Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland
| | - Tomasz Smolarczyk
- Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland
| | - Irena Roterman
- Department of Bioinformatics and Telemedicine, Jagiellonian University Medical College, Medyczna 7, 30-688, Kraków, Poland
| |
Collapse
|
6
|
Li B, Mendenhall J, Capra JA, Meiler J. A Multitask Deep-Learning Method for Predicting Membrane Associations and Secondary Structures of Proteins. J Proteome Res 2021; 20:4089-4100. [PMID: 34236204 PMCID: PMC8650144 DOI: 10.1021/acs.jproteome.1c00410] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
Prediction of residue-level structural attributes and protein-level structural classes helps model protein tertiary structures and understand protein functions. Existing methods are either specialized on only one class of proteins or developed to predict only a specific type of residue-level attribute. In this work, we develop a new deep-learning method, named Membrane Association and Secondary Structure Predictor (MASSP), for accurately predicting both residue-level structural attributes (secondary structure, location, orientation, and topology) and protein-level structural classes (bitopic, α-helical, β-barrel, and soluble). MASSP integrates a multilayer two-dimensional convolutional neural network (2D-CNN) with a long short-term memory (LSTM) neural network into a multitasking framework. Our comparison shows that MASSP performs equally well or better than the state-of-the-art methods in predicting residue-level secondary structures, boundaries of transmembrane segments, and topology. Furthermore, it achieves outstanding accuracy in predicting protein-level structural classes. MASSP automatically distinguishes the structural classes of input sequences and identifies transmembrane segments and topologies if present, making it broadly applicable to different classes of proteins. In summary, MASSP's good performance and broad applicability make it well suited for annotating residue-level attributes and protein-level structural classes at the proteome scale.
Collapse
Affiliation(s)
- Bian Li
- Department of Biological Sciences, Vanderbilt University, Nashville, Tennessee 37203, United States.,Center for Structural Biology, Vanderbilt University, Nashville, Tennessee 37203, United States
| | - Jeffrey Mendenhall
- Center for Structural Biology, Vanderbilt University, Nashville, Tennessee 37203, United States.,Department of Chemistry, Vanderbilt University, Nashville, Tennessee 37203, United States
| | - John A Capra
- Bakar Computational Health Sciences Institute and Department of Epidemiology and Biostatistics, University of California, San Francisco, California 94143, United States
| | - Jens Meiler
- Center for Structural Biology, Vanderbilt University, Nashville, Tennessee 37203, United States.,Department of Chemistry, Vanderbilt University, Nashville, Tennessee 37203, United States.,Institute for Drug Discovery, University Leipzig Medical School, Leipzig 04109, Germany
| |
Collapse
|
7
|
Simm D, Hatje K, Waack S, Kollmar M. Critical assessment of coiled-coil predictions based on protein structure data. Sci Rep 2021; 11:12439. [PMID: 34127723 PMCID: PMC8203680 DOI: 10.1038/s41598-021-91886-w] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2021] [Accepted: 05/28/2021] [Indexed: 02/05/2023] Open
Abstract
Coiled-coil regions were among the first protein motifs described structurally and theoretically. The simplicity of the motif promises that coiled-coil regions can be detected with reasonable accuracy and precision in any protein sequence. Here, we re-evaluated the most commonly used coiled-coil prediction tools with respect to the most comprehensive reference data set available, the entire Protein Data Bank, down to each amino acid and its secondary structure. Apart from the 30-fold difference in minimum and maximum number of coiled coils predicted the tools strongly vary in where they predict coiled-coil regions. Accordingly, there is a high number of false predictions and missed, true coiled-coil regions. The evaluation of the binary classification metrics in comparison with naïve coin-flip models and the calculation of the Matthews correlation coefficient, the most reliable performance metric for imbalanced data sets, suggests that the tested tools' performance is close to random. This implicates that the tools' predictions have only limited informative value. Coiled-coil predictions are often used to interpret biochemical data and are part of in-silico functional genome annotation. Our results indicate that these predictions should be treated very cautiously and need to be supported and validated by experimental evidence.
Collapse
Affiliation(s)
- Dominic Simm
- grid.418140.80000 0001 2104 4211Group Systems Biology of Motor Proteins, Department of NMR-Based Structural Biology, Max-Planck-Institute for Biophysical Chemistry, Göttingen, Germany ,grid.7450.60000 0001 2364 4210Theoretical Computer Science and Algorithmic Methods, Institute of Computer Science, Georg-August-University Göttingen, Göttingen, Germany
| | - Klas Hatje
- grid.418140.80000 0001 2104 4211Group Systems Biology of Motor Proteins, Department of NMR-Based Structural Biology, Max-Planck-Institute for Biophysical Chemistry, Göttingen, Germany ,grid.417570.00000 0004 0374 1269Present Address: Roche Pharmaceutical Research and Early Development, Pharmaceutical Sciences, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
| | - Stephan Waack
- grid.7450.60000 0001 2364 4210Theoretical Computer Science and Algorithmic Methods, Institute of Computer Science, Georg-August-University Göttingen, Göttingen, Germany
| | - Martin Kollmar
- grid.418140.80000 0001 2104 4211Group Systems Biology of Motor Proteins, Department of NMR-Based Structural Biology, Max-Planck-Institute for Biophysical Chemistry, Göttingen, Germany ,grid.7450.60000 0001 2364 4210Theoretical Computer Science and Algorithmic Methods, Institute of Computer Science, Georg-August-University Göttingen, Göttingen, Germany
| |
Collapse
|
8
|
Cao X, He W, Chen Z, Li Y, Wang K, Zhang H, Wei L, Cui L, Su R, Wei L. PSSP-MVIRT: peptide secondary structure prediction based on a multi-view deep learning architecture. Brief Bioinform 2021; 22:6296508. [PMID: 34117740 DOI: 10.1093/bib/bbab203] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2021] [Revised: 04/21/2021] [Accepted: 05/07/2021] [Indexed: 11/14/2022] Open
Abstract
The prediction of peptide secondary structures is fundamentally important to reveal the functional mechanisms of peptides with potential applications as therapeutic molecules. In this study, we propose a multi-view deep learning method named Peptide Secondary Structure Prediction based on Multi-View Information, Restriction and Transfer learning (PSSP-MVIRT) for peptide secondary structure prediction. To sufficiently exploit discriminative information, we introduce a multi-view fusion strategy to integrate different information from multiple perspectives, including sequential information, evolutionary information and hidden state information, respectively, and generate a unified feature space. Moreover, we construct a hybrid network architecture of Convolutional Neural Network and Bi-directional Gated Recurrent Unit to extract global and local features of peptides. Furthermore, we utilize transfer learning to effectively alleviate the lack of training samples (peptides with experimentally validated structures). Comparative results on independent tests demonstrate that our proposed method significantly outperforms state-of-the-art methods. In particular, our method exhibits better performance at the segment level, suggesting the strong ability of our model in capturing local discriminative information. The case study also shows that our PSSP-MVIRT achieves promising and robust performance in the prediction of new peptide secondary structures. Importantly, we establish a webserver to implement the proposed method, which is currently accessible via http://server.malab.cn/PSSP-MVIRT. We expect it can be a useful tool for the researchers of interest, facilitating the wide use of our method.
Collapse
Affiliation(s)
- Xiao Cao
- School of Software, Shandong University, Jinan, China.,Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan, China
| | - Wenjia He
- School of Software, Shandong University, Jinan, China.,Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan, China
| | - Zitan Chen
- School of Software, Shandong University, Jinan, China
| | - Yifan Li
- School of Software, Shandong University, Jinan, China
| | - Kexin Wang
- School of Software, Shandong University, Jinan, China
| | - Hongbo Zhang
- School of Software, Shandong University, Jinan, China
| | - Lesong Wei
- Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan
| | - Lizhen Cui
- School of Software, Shandong University, Jinan, China.,Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan, China
| | - Ran Su
- College of Intelligence and Computing, Tianjin University, Tianjin, China
| | - Leyi Wei
- School of Software, Shandong University, Jinan, China.,Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan, China
| |
Collapse
|
9
|
Liu T, Wang Z. MASS: predict the global qualities of individual protein models using random forests and novel statistical potentials. BMC Bioinformatics 2020; 21:246. [PMID: 32631256 PMCID: PMC7336608 DOI: 10.1186/s12859-020-3383-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2020] [Accepted: 01/22/2020] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Protein model quality assessment (QA) is an essential procedure in protein structure prediction. QA methods can predict the qualities of protein models and identify good models from decoys. Clustering-based methods need a certain number of models as input. However, if a pool of models are not available, methods that only need a single model as input are indispensable. RESULTS We developed MASS, a QA method to predict the global qualities of individual protein models using random forests and various novel energy functions. We designed six novel energy functions or statistical potentials that can capture the structural characteristics of a protein model, which can also be used in other protein-related bioinformatics research. MASS potentials demonstrated higher importance than the energy functions of RWplus, GOAP, DFIRE and Rosetta when the scores they generated are used as machine learning features. MASS outperforms almost all of the four CASP11 top-performing single-model methods for global quality assessment in terms of all of the four evaluation criteria officially used by CASP, which measure the abilities to assign relative and absolute scores, identify the best model from decoys, and distinguish between good and bad models. MASS has also achieved comparable performances with the leading QA methods in CASP12 and CASP13. CONCLUSIONS MASS and the source code for all MASS potentials are publicly available at http://dna.cs.miami.edu/MASS/ .
Collapse
Affiliation(s)
- Tong Liu
- Department of Computer Science, University of Miami, 1365 Memorial Drive, P.O. Box 248154, Coral Gables, FL, 33124, USA
| | - Zheng Wang
- Department of Computer Science, University of Miami, 1365 Memorial Drive, P.O. Box 248154, Coral Gables, FL, 33124, USA.
| |
Collapse
|
10
|
Torrisi M, Kaleel M, Pollastri G. Deeper Profiles and Cascaded Recurrent and Convolutional Neural Networks for state-of-the-art Protein Secondary Structure Prediction. Sci Rep 2019; 9:12374. [PMID: 31451723 PMCID: PMC6710256 DOI: 10.1038/s41598-019-48786-x] [Citation(s) in RCA: 51] [Impact Index Per Article: 10.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/26/2019] [Accepted: 08/12/2019] [Indexed: 01/10/2023] Open
Abstract
Protein Secondary Structure prediction has been a central topic of research in Bioinformatics for decades. In spite of this, even the most sophisticated ab initio SS predictors are not able to reach the theoretical limit of three-state prediction accuracy (88–90%), while only a few predict more than the 3 traditional Helix, Strand and Coil classes. In this study we present tests on different models trained both on single sequence and evolutionary profile-based inputs and develop a new state-of-the-art system with Porter 5. Porter 5 is composed of ensembles of cascaded Bidirectional Recurrent Neural Networks and Convolutional Neural Networks, incorporates new input encoding techniques and is trained on a large set of protein structures. Porter 5 achieves 84% accuracy (81% SOV) when tested on 3 classes and 73% accuracy (70% SOV) on 8 classes on a large independent set. In our tests Porter 5 is 2% more accurate than its previous version and outperforms or matches the most recent predictors of secondary structure we tested. When Porter 5 is retrained on SCOPe based sets that eliminate homology between training/testing samples we obtain similar results. Porter is available as a web server and standalone program at http://distilldeep.ucd.ie/porter/ alongside all the datasets and alignments.
Collapse
Affiliation(s)
- Mirko Torrisi
- School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland
| | - Manaz Kaleel
- School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland
| | - Gianluca Pollastri
- School of Computer Science, University College Dublin, Belfield, Dublin 4, Ireland.
| |
Collapse
|
11
|
Zhang B, Li J, Lü Q. Prediction of 8-state protein secondary structures by a novel deep learning architecture. BMC Bioinformatics 2018; 19:293. [PMID: 30075707 PMCID: PMC6090794 DOI: 10.1186/s12859-018-2280-5] [Citation(s) in RCA: 60] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2018] [Accepted: 07/09/2018] [Indexed: 11/16/2022] Open
Abstract
Background Protein secondary structure can be regarded as an information bridge that links the primary sequence and tertiary structure. Accurate 8-state secondary structure prediction can significantly give more precise and high resolution on structure-based properties analysis. Results We present a novel deep learning architecture which exploits an integrative synergy of prediction by a convolutional neural network, residual network, and bidirectional recurrent neural network to improve the performance of protein secondary structure prediction. A local block comprised of convolutional filters and original input is designed for capturing local sequence features. The subsequent bidirectional recurrent neural network consisting of gated recurrent units can capture global context features. Furthermore, the residual network can improve the information flow between the hidden layers and the cascaded recurrent neural network. Our proposed deep network achieved 71.4% accuracy on the benchmark CB513 dataset for the 8-state prediction; and the ensemble learning by our model achieved 74% accuracy. Our model generalization capability is also evaluated on other three independent datasets CASP10, CASP11 and CASP12 for both 8- and 3-state prediction. These prediction performances are superior to the state-of-the-art methods. Conclusion Our experiment demonstrates that it is a valuable method for predicting protein secondary structure, and capturing local and global features concurrently is very useful in deep learning. Electronic supplementary material The online version of this article (10.1186/s12859-018-2280-5) contains supplementary material, which is available to authorized users.
Collapse
Affiliation(s)
- Buzhong Zhang
- School of Computer Science and Technology, Soochow University, Suzhou, China.,School of Computer and Information, and the University Key Laboratory of Intelligent Perception and Computing of Anhui Province, Anqing Normal University, Anqing, 246011, China
| | - Jinyan Li
- Advanced Analytics Institute, Faculty of Engineering and IT, University of Technology Sydney, Broadway, NSW 2007, Sydney, PO Box 123, Australia
| | - Qiang Lü
- School of Computer Science and Technology, Soochow University, Suzhou, China.
| |
Collapse
|