1
|
Jung Y, Geng C, Bonvin AMJJ, Xue LC, Honavar VG. MetaScore: A Novel Machine-Learning-Based Approach to Improve Traditional Scoring Functions for Scoring Protein-Protein Docking Conformations. Biomolecules 2023; 13:121. [PMID: 36671507 PMCID: PMC9855734 DOI: 10.3390/biom13010121] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/01/2022] [Revised: 12/22/2022] [Accepted: 12/26/2022] [Indexed: 01/11/2023] Open
Abstract
Protein-protein interactions play a ubiquitous role in biological function. Knowledge of the three-dimensional (3D) structures of the complexes they form is essential for understanding the structural basis of those interactions and how they orchestrate key cellular processes. Computational docking has become an indispensable alternative to the expensive and time-consuming experimental approaches for determining the 3D structures of protein complexes. Despite recent progress, identifying near-native models from a large set of conformations sampled by docking-the so-called scoring problem-still has considerable room for improvement. We present MetaScore, a new machine-learning-based approach to improve the scoring of docked conformations. MetaScore utilizes a random forest (RF) classifier trained to distinguish near-native from non-native conformations using their protein-protein interfacial features. The features include physicochemical properties, energy terms, interaction-propensity-based features, geometric properties, interface topology features, evolutionary conservation, and also scores produced by traditional scoring functions (SFs). MetaScore scores docked conformations by simply averaging the score produced by the RF classifier with that produced by any traditional SF. We demonstrate that (i) MetaScore consistently outperforms each of the nine traditional SFs included in this work in terms of success rate and hit rate evaluated over conformations ranked among the top 10; (ii) an ensemble method, MetaScore-Ensemble, that combines 10 variants of MetaScore obtained by combining the RF score with each of the traditional SFs outperforms each of the MetaScore variants. We conclude that the performance of traditional SFs can be improved upon by using machine learning to judiciously leverage protein-protein interfacial features and by using ensemble methods to combine multiple scoring functions.
Collapse
Affiliation(s)
- Yong Jung
- Bioinformatics & Genomics Graduate Program, Pennsylvania State University, University Park, PA 16802, USA
- Artificial Intelligence Research Laboratory, Pennsylvania State University, University Park, PA 16802, USA
- Huck Institutes of the Life Sciences, Pennsylvania State University, University Park, PA 16802, USA
| | - Cunliang Geng
- Bijvoet Centre for Biomolecular Research, Faculty of Science—Chemistry, Utrecht University, Padualaan 8, 3584 CH Utrecht, The Netherlands
| | - Alexandre M. J. J. Bonvin
- Bijvoet Centre for Biomolecular Research, Faculty of Science—Chemistry, Utrecht University, Padualaan 8, 3584 CH Utrecht, The Netherlands
| | - Li C. Xue
- Bijvoet Centre for Biomolecular Research, Faculty of Science—Chemistry, Utrecht University, Padualaan 8, 3584 CH Utrecht, The Netherlands
- Center for Molecular and Biomolecular Informatics, Radboudumc, Greet Grooteplein 26-28, 6525 GA Nijmegen, The Netherlands
| | - Vasant G. Honavar
- Bioinformatics & Genomics Graduate Program, Pennsylvania State University, University Park, PA 16802, USA
- Artificial Intelligence Research Laboratory, Pennsylvania State University, University Park, PA 16802, USA
- Huck Institutes of the Life Sciences, Pennsylvania State University, University Park, PA 16802, USA
- Clinical and Translational Sciences Institute, Pennsylvania State University, University Park, PA 16802, USA
- College of Information Sciences & Technology, Pennsylvania State University, University Park, PA 16802, USA
- Institute for Computational and Data Sciences, Pennsylvania State University, University Park, PA 16802, USA
- Center for Big Data Analytics and Discovery Informatics, Pennsylvania State University, University Park, PA 16823, USA
| |
Collapse
|
2
|
Han Y, He F, Chen Y, Qin W, Yu H, Xu D. Quality Assessment of Protein Docking Models Based on Graph Neural Network. FRONTIERS IN BIOINFORMATICS 2021; 1:693211. [PMID: 36303780 PMCID: PMC9581034 DOI: 10.3389/fbinf.2021.693211] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2021] [Accepted: 08/02/2021] [Indexed: 11/24/2022] Open
Abstract
Protein docking provides a structural basis for the design of drugs and vaccines. Among the processes of protein docking, quality assessment (QA) is utilized to pick near-native models from numerous protein docking candidate conformations, and it directly determines the final docking results. Although extensive efforts have been made to improve QA accuracy, it is still the bottleneck of current protein docking systems. In this paper, we presented a Deep Graph Attention Neural Network (DGANN) to evaluate and rank protein docking candidate models. DGANN learns inter-residue physio-chemical properties and structural fitness across the two protein monomers in a docking model and generates their probabilities of near-native models. On the ZDOCK decoy benchmark, our DGANN outperformed the ranking provided by ZDOCK in terms of ranking good models into the top selections. Furthermore, we conducted comparative experiments on an independent testing dataset, and the results also demonstrated the superiority and generalization of our proposed method.
Collapse
Affiliation(s)
- Ye Han
- School of Information Technology, Jilin Agricultural University, Changchun, China
- Department of Electrical Engineering and Computer Science, Christopher S. Bond Life Sciences Center, University of Missouri, Columbia, MO, United States
| | - Fei He
- Department of Electrical Engineering and Computer Science, Christopher S. Bond Life Sciences Center, University of Missouri, Columbia, MO, United States
- School of Information Science and Technology, Northeast Normal University, Changchun, China
| | - Yongbing Chen
- School of Information Science and Technology, Northeast Normal University, Changchun, China
| | - Wenyuan Qin
- School of Information Science and Technology, Northeast Normal University, Changchun, China
| | - Helong Yu
- School of Information Technology, Jilin Agricultural University, Changchun, China
- *Correspondence: Helong Yu, ; Dong Xu,
| | - Dong Xu
- Department of Electrical Engineering and Computer Science, Christopher S. Bond Life Sciences Center, University of Missouri, Columbia, MO, United States
- *Correspondence: Helong Yu, ; Dong Xu,
| |
Collapse
|
3
|
Wang X, Flannery ST, Kihara D. Protein Docking Model Evaluation by Graph Neural Networks. Front Mol Biosci 2021; 8:647915. [PMID: 34113650 PMCID: PMC8185212 DOI: 10.3389/fmolb.2021.647915] [Citation(s) in RCA: 27] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2020] [Accepted: 04/26/2021] [Indexed: 12/03/2022] Open
Abstract
Physical interactions of proteins play key functional roles in many important cellular processes. To understand molecular mechanisms of such functions, it is crucial to determine the structure of protein complexes. To complement experimental approaches, which usually take a considerable amount of time and resources, various computational methods have been developed for predicting the structures of protein complexes. In computational modeling, one of the challenges is to identify near-native structures from a large pool of generated models. Here, we developed a deep learning-based approach named Graph Neural Network-based DOcking decoy eValuation scorE (GNN-DOVE). To evaluate a protein docking model, GNN-DOVE extracts the interface area and represents it as a graph. The chemical properties of atoms and the inter-atom distances are used as features of nodes and edges in the graph, respectively. GNN-DOVE was trained, validated, and tested on docking models in the Dockground database and further tested on a combined dataset of Dockground and ZDOCK benchmark as well as a CAPRI scoring dataset. GNN-DOVE performed better than existing methods, including DOVE, which is our previous development that uses a convolutional neural network on voxelized structure models.
Collapse
Affiliation(s)
- Xiao Wang
- Department of Computer Science, Purdue University, West Lafayette, IN, United States
| | - Sean T. Flannery
- Department of Computer Science, Purdue University, West Lafayette, IN, United States
| | - Daisuke Kihara
- Department of Computer Science, Purdue University, West Lafayette, IN, United States
- Department of Biological Sciences, Purdue University, West Lafayette, IN, United States
| |
Collapse
|
4
|
Das S, Chakrabarti S. Classification and prediction of protein-protein interaction interface using machine learning algorithm. Sci Rep 2021; 11:1761. [PMID: 33469042 PMCID: PMC7815773 DOI: 10.1038/s41598-020-80900-2] [Citation(s) in RCA: 33] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2020] [Accepted: 12/15/2020] [Indexed: 01/29/2023] Open
Abstract
Structural insight of the protein-protein interaction (PPI) interface can provide knowledge about the kinetics, thermodynamics and molecular functions of the complex while elucidating its role in diseases and further enabling it as a potential therapeutic target. However, owing to experimental lag in solving protein-protein complex structures, three-dimensional (3D) knowledge of the PPI interfaces can be gained via computational approaches like molecular docking and post-docking analyses. Despite development of numerous docking tools and techniques, success in identification of native like interfaces based on docking score functions is limited. Hence, we employed an in-depth investigation of the structural features of the interface that might successfully delineate native complexes from non-native ones. We identify interface properties, which show statistically significant difference between native and non-native interfaces belonging to homo and hetero, protein-protein complexes. Utilizing these properties, a support vector machine (SVM) based classification scheme has been implemented to differentiate native and non-native like complexes generated using docking decoys. Benchmarking and comparative analyses suggest very good performance of our SVM classifiers. Further, protein interactions, which are proven via experimental findings but not resolved structurally, were subjected to this approach where 3D-models of the complexes were generated and most likely interfaces were predicted. A web server called Protein Complex Prediction by Interface Properties (PCPIP) is developed to predict whether interface of a given protein-protein dimer complex resembles known protein interfaces. The server is freely available at http://www.hpppi.iicb.res.in/pcpip/ .
Collapse
Affiliation(s)
- Subhrangshu Das
- grid.417635.20000 0001 2216 5074Structural Biology and Bioinformatics Division, CSIR-Indian Institute of Chemical Biology, Kolkata, WB India
| | - Saikat Chakrabarti
- grid.417635.20000 0001 2216 5074Structural Biology and Bioinformatics Division, CSIR-Indian Institute of Chemical Biology, Kolkata, WB India
| |
Collapse
|
5
|
Wang X, Terashi G, Christoffer CW, Zhu M, Kihara D. Protein docking model evaluation by 3D deep convolutional neural networks. Bioinformatics 2020; 36:2113-2118. [PMID: 31746961 DOI: 10.1093/bioinformatics/btz870] [Citation(s) in RCA: 57] [Impact Index Per Article: 14.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2019] [Revised: 08/25/2019] [Accepted: 11/19/2019] [Indexed: 02/06/2023] Open
Abstract
MOTIVATION Many important cellular processes involve physical interactions of proteins. Therefore, determining protein quaternary structures provide critical insights for understanding molecular mechanisms of functions of the complexes. To complement experimental methods, many computational methods have been developed to predict structures of protein complexes. One of the challenges in computational protein complex structure prediction is to identify near-native models from a large pool of generated models. RESULTS We developed a convolutional deep neural network-based approach named DOcking decoy selection with Voxel-based deep neural nEtwork (DOVE) for evaluating protein docking models. To evaluate a protein docking model, DOVE scans the protein-protein interface of the model with a 3D voxel and considers atomic interaction types and their energetic contributions as input features applied to the neural network. The deep learning models were trained and validated on docking models available in the ZDock and DockGround databases. Among the different combinations of features tested, almost all outperformed existing scoring functions. AVAILABILITY AND IMPLEMENTATION Codes available at http://github.com/kiharalab/DOVE, http://kiharalab.org/dove/. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Xiao Wang
- Department of Computer Science, Purdue University, West Lafayette, IN 47907, USA
| | - Genki Terashi
- Department of Biological Sciences, Purdue University, West Lafayette, IN 47907, USA
| | | | - Mengmeng Zhu
- Department of Biological Sciences, Purdue University, West Lafayette, IN 47907, USA
| | - Daisuke Kihara
- Department of Computer Science, Purdue University, West Lafayette, IN 47907, USA.,Department of Biological Sciences, Purdue University, West Lafayette, IN 47907, USA
| |
Collapse
|
6
|
Geng C, Jung Y, Renaud N, Honavar V, Bonvin AMJJ, Xue LC. iScore: a novel graph kernel-based function for scoring protein-protein docking models. Bioinformatics 2020; 36:112-121. [PMID: 31199455 PMCID: PMC6956772 DOI: 10.1093/bioinformatics/btz496] [Citation(s) in RCA: 42] [Impact Index Per Article: 10.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2018] [Revised: 05/08/2019] [Accepted: 06/11/2019] [Indexed: 11/12/2022] Open
Abstract
MOTIVATION Protein complexes play critical roles in many aspects of biological functions. Three-dimensional (3D) structures of protein complexes are critical for gaining insights into structural bases of interactions and their roles in the biomolecular pathways that orchestrate key cellular processes. Because of the expense and effort associated with experimental determinations of 3D protein complex structures, computational docking has evolved as a valuable tool to predict 3D structures of biomolecular complexes. Despite recent progress, reliably distinguishing near-native docking conformations from a large number of candidate conformations, the so-called scoring problem, remains a major challenge. RESULTS Here we present iScore, a novel approach to scoring docked conformations that combines HADDOCK energy terms with a score obtained using a graph representation of the protein-protein interfaces and a measure of evolutionary conservation. It achieves a scoring performance competitive with, or superior to, that of state-of-the-art scoring functions on two independent datasets: (i) Docking software-specific models and (ii) the CAPRI score set generated by a wide variety of docking approaches (i.e. docking software-non-specific). iScore ranks among the top scoring approaches on the CAPRI score set (13 targets) when compared with the 37 scoring groups in CAPRI. The results demonstrate the utility of combining evolutionary, topological and energetic information for scoring docked conformations. This work represents the first successful demonstration of graph kernels to protein interfaces for effective discrimination of near-native and non-native conformations of protein complexes. AVAILABILITY AND IMPLEMENTATION The iScore code is freely available from Github: https://github.com/DeepRank/iScore (DOI: 10.5281/zenodo.2630567). And the docking models used are available from SBGrid: https://data.sbgrid.org/dataset/684). SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Cunliang Geng
- Bijvoet Center for Biomolecular Research, Faculty of Science – Chemistry, Utrecht University, Utrecht 3584 CH, The Netherlands
| | - Yong Jung
- Bioinformatics & Genomics Graduate Program, Pennsylvania State University, University Park, PA 16802, USA
- Artificial Intelligence Research Laboratory, Pennsylvania State University, University Park, PA 16823, USA
- Huck Institutes of the Life Sciences, Pennsylvania State University, University Park, PA 16802, USA
| | - Nicolas Renaud
- Netherlands eScience Center, Amsterdam 1098 XG, The Netherlands
| | - Vasant Honavar
- Bioinformatics & Genomics Graduate Program, Pennsylvania State University, University Park, PA 16802, USA
- Artificial Intelligence Research Laboratory, Pennsylvania State University, University Park, PA 16823, USA
- Huck Institutes of the Life Sciences, Pennsylvania State University, University Park, PA 16802, USA
- Center for Big Data Analytics and Discovery Informatics, Pennsylvania State University, University Park, PA 16823, USA
- Institute for Cyberscience, University Park, PA 16802, USA
- Clinical and Translational Sciences Institute, University Park, PA 16802, USA
- College of Information Sciences & Technology, Pennsylvania State University, University Park, PA 16802, USA
| | - Alexandre M J J Bonvin
- Bijvoet Center for Biomolecular Research, Faculty of Science – Chemistry, Utrecht University, Utrecht 3584 CH, The Netherlands
| | - Li C Xue
- Bijvoet Center for Biomolecular Research, Faculty of Science – Chemistry, Utrecht University, Utrecht 3584 CH, The Netherlands
| |
Collapse
|
7
|
Perthold JW, Oostenbrink C. GroScore: Accurate Scoring of Protein–Protein Binding Poses Using Explicit-Solvent Free-Energy Calculations. J Chem Inf Model 2019; 59:5074-5085. [DOI: 10.1021/acs.jcim.9b00687] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Affiliation(s)
- Jan Walther Perthold
- Institute of Molecular Modeling and Simulation, University of Natural Resources and Life Sciences, Muthgasse 18, 1190 Vienna, Austria
| | - Chris Oostenbrink
- Institute of Molecular Modeling and Simulation, University of Natural Resources and Life Sciences, Muthgasse 18, 1190 Vienna, Austria
| |
Collapse
|
8
|
Reyes-Espinosa F, Juárez-Saldivar A, Palos I, Herrera-Mayorga V, García-Pérez C, Rivera G. In Silico Analysis of Homologous Heterodimers of Cruzipain-Chagasin from Structural Models Built by Homology. Int J Mol Sci 2019; 20:ijms20061320. [PMID: 30875920 PMCID: PMC6470822 DOI: 10.3390/ijms20061320] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/12/2019] [Revised: 03/08/2019] [Accepted: 03/11/2019] [Indexed: 12/04/2022] Open
Abstract
The present study gives an overview of the binding energetics of the homologous heterodimers of cruzipain−chagasin based on the binding energy (ΔGb) prediction obtained with FoldX. This analysis involves a total of 70 homologous models of the cruzipain−chagasin complex which were constructed by homology from the combinatory variation of nine papain-like cysteine peptidase structures and seven cysteine protease inhibitor structures (as chagasin-like and cystatin-like inhibitors). Only 32 systems have been evaluated experimentally, ΔGbexperimental values previously reported. Therefore, the result of the multiple analysis in terms of the thermodynamic parameters, are shown as relative energy |ΔΔG| = |ΔGbfromFoldX − ΔGbexperimental|. Nine models were identified that recorded |ΔΔG| < 1.3, five models to 2.8 > |ΔΔG| > 1.3 and the other 18 models, values of |ΔΔG| > 2.8. The energetic analysis of the contribution of ΔH and ΔS to ΔGb to the 14-molecular model presents a ΔGb mostly ΔH-driven at neutral pH and at an ionic strength (I) of 0.15 M. The dependence of ΔGb(I,pH) at 298 K to the cruzipain−chagasin complex predicts a linear dependence of ΔGb(I). The computational protocol allowed the identification and prediction of thermodynamics binding energy parameters for cruzipain−chagasin-like heterodimers.
Collapse
Affiliation(s)
- Francisco Reyes-Espinosa
- Laboratorio de Biotecnología Farmacéutica, Centro de Biotecnología Genómica, Instituto Politécnico Nacional, Boulevard del Maestro s/n esq. Elías Piña, Col. Narciso Mendoza, Reynosa 88710, Mexico.
| | - Alfredo Juárez-Saldivar
- Laboratorio de Biotecnología Farmacéutica, Centro de Biotecnología Genómica, Instituto Politécnico Nacional, Boulevard del Maestro s/n esq. Elías Piña, Col. Narciso Mendoza, Reynosa 88710, Mexico.
| | - Isidro Palos
- Unidad Académica Multidisciplinaria Reynosa-Rodhe, Universidad Autónoma Tamaulipas, Carr. Reynosa-San Fernando, Reynosa 88779, Mexico.
| | - Verónica Herrera-Mayorga
- Laboratorio de Biotecnología Farmacéutica, Centro de Biotecnología Genómica, Instituto Politécnico Nacional, Boulevard del Maestro s/n esq. Elías Piña, Col. Narciso Mendoza, Reynosa 88710, Mexico.
- Departamento de Ingeniería Bioquímica, Unidad Académica Multidisciplinaria Mante, Universidad Autónoma Tamaulipas, Blvd. Enrique Cárdenas González 1201, Mante 89840, Mexico.
| | - Carlos García-Pérez
- Scientific Computing Research Unit, Helmholtz Zentrum München, 85764 Munich, Germany.
| | - Gildardo Rivera
- Laboratorio de Biotecnología Farmacéutica, Centro de Biotecnología Genómica, Instituto Politécnico Nacional, Boulevard del Maestro s/n esq. Elías Piña, Col. Narciso Mendoza, Reynosa 88710, Mexico.
| |
Collapse
|
9
|
Geng C, Xue LC, Roel‐Touris J, Bonvin AMJJ. Finding the ΔΔ
G
spot: Are predictors of binding affinity changes upon mutations in protein–protein interactions ready for it? WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE 2019. [DOI: 10.1002/wcms.1410] [Citation(s) in RCA: 43] [Impact Index Per Article: 8.6] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/01/2023]
Affiliation(s)
- Cunliang Geng
- Bijvoet Center for Biomolecular Research, Faculty of Science—Chemistry Utrecht University Utrecht The Netherlands
| | - Li C. Xue
- Bijvoet Center for Biomolecular Research, Faculty of Science—Chemistry Utrecht University Utrecht The Netherlands
| | - Jorge Roel‐Touris
- Bijvoet Center for Biomolecular Research, Faculty of Science—Chemistry Utrecht University Utrecht The Netherlands
| | - Alexandre M. J. J. Bonvin
- Bijvoet Center for Biomolecular Research, Faculty of Science—Chemistry Utrecht University Utrecht The Netherlands
| |
Collapse
|
10
|
Nadalin F, Carbone A. Protein-protein interaction specificity is captured by contact preferences and interface composition. Bioinformatics 2018; 34:459-468. [PMID: 29028884 PMCID: PMC5860360 DOI: 10.1093/bioinformatics/btx584] [Citation(s) in RCA: 25] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2016] [Accepted: 09/18/2017] [Indexed: 12/24/2022] Open
Abstract
Motivation Large-scale computational docking will be increasingly used in future years to discriminate protein–protein interactions at the residue resolution. Complete cross-docking experiments make in silico reconstruction of protein–protein interaction networks a feasible goal. They ask for efficient and accurate screening of the millions structural conformations issued by the calculations. Results We propose CIPS (Combined Interface Propensity for decoy Scoring), a new pair potential combining interface composition with residue–residue contact preference. CIPS outperforms several other methods on screening docking solutions obtained either with all-atom or with coarse-grain rigid docking. Further testing on 28 CAPRI targets corroborates CIPS predictive power over existing methods. By combining CIPS with atomic potentials, discrimination of correct conformations in all-atom structures reaches optimal accuracy. The drastic reduction of candidate solutions produced by thousands of proteins docked against each other makes large-scale docking accessible to analysis. Availability and implementation CIPS source code is freely available at http://www.lcqb.upmc.fr/CIPS. Supplementary information Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Francesca Nadalin
- Sorbonne Universités, UPMC-Univ P6, CNRS, IBPS, Laboratoire de Biologie Computationnelle et Quantitative-UMR 7238, 75005 Paris, France
| | - Alessandra Carbone
- Sorbonne Universités, UPMC-Univ P6, CNRS, IBPS, Laboratoire de Biologie Computationnelle et Quantitative-UMR 7238, 75005 Paris, France.,Institut Universitaire de France, 75005 Paris, France
| |
Collapse
|
11
|
Tamò G, Maesani A, Träger S, Degiacomi MT, Floreano D, Dal Peraro M. Disentangling constraints using viability evolution principles in integrative modeling of macromolecular assemblies. Sci Rep 2017; 7:235. [PMID: 28331186 PMCID: PMC5427971 DOI: 10.1038/s41598-017-00266-w] [Citation(s) in RCA: 12] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2016] [Accepted: 02/14/2017] [Indexed: 11/22/2022] Open
Abstract
Predicting the structure of large molecular assemblies remains a challenging task in structural biology when using integrative modeling approaches. One of the main issues stems from the treatment of heterogeneous experimental data used to predict the architecture of native complexes. We propose a new method, applied here for the first time to a set of symmetrical complexes, based on evolutionary computation that treats every available experimental input independently, bypassing the need to balance weight components assigned to aggregated fitness functions during optimization.
Collapse
Affiliation(s)
- Giorgio Tamò
- Laboratory for Biomolecular Modeling, Institute of Bioengineering, School of Life Sciences, École Polytechnique Fédérale de Lausanne, Lausanne, CH-1015, Switzerland.,Swiss Institute of Bioinformatics (SIB), Lausanne, CH-1015, Switzerland
| | - Andrea Maesani
- Laboratory of Intelligent Systems, Institute of Microengineering, École Polytechnique Fédérale de Lausanne, Lausanne, CH-1015, Switzerland
| | - Sylvain Träger
- Laboratory for Biomolecular Modeling, Institute of Bioengineering, School of Life Sciences, École Polytechnique Fédérale de Lausanne, Lausanne, CH-1015, Switzerland.,Swiss Institute of Bioinformatics (SIB), Lausanne, CH-1015, Switzerland
| | - Matteo T Degiacomi
- Chemistry Research Laboratory, Department of Chemistry, University of Oxford, Oxford, UK
| | - Dario Floreano
- Laboratory of Intelligent Systems, Institute of Microengineering, École Polytechnique Fédérale de Lausanne, Lausanne, CH-1015, Switzerland.
| | - Matteo Dal Peraro
- Laboratory for Biomolecular Modeling, Institute of Bioengineering, School of Life Sciences, École Polytechnique Fédérale de Lausanne, Lausanne, CH-1015, Switzerland. .,Swiss Institute of Bioinformatics (SIB), Lausanne, CH-1015, Switzerland.
| |
Collapse
|
12
|
Pfeiffenberger E, Chaleil RA, Moal IH, Bates PA. A machine learning approach for ranking clusters of docked protein-protein complexes by pairwise cluster comparison. Proteins 2017; 85:528-543. [PMID: 27935158 PMCID: PMC5396268 DOI: 10.1002/prot.25218] [Citation(s) in RCA: 18] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2016] [Revised: 11/14/2016] [Accepted: 11/21/2016] [Indexed: 01/28/2023]
Abstract
Reliable identification of near-native poses of docked protein-protein complexes is still an unsolved problem. The intrinsic heterogeneity of protein-protein interactions is challenging for traditional biophysical or knowledge based potentials and the identification of many false positive binding sites is not unusual. Often, ranking protocols are based on initial clustering of docked poses followed by the application of an energy function to rank each cluster according to its lowest energy member. Here, we present an approach of cluster ranking based not only on one molecular descriptor (e.g., an energy function) but also employing a large number of descriptors that are integrated in a machine learning model, whereby, an extremely randomized tree classifier based on 109 molecular descriptors is trained. The protocol is based on first locally enriching clusters with additional poses, the clusters are then characterized using features describing the distribution of molecular descriptors within the cluster, which are combined into a pairwise cluster comparison model to discriminate near-native from incorrect clusters. The results show that our approach is able to identify clusters containing near-native protein-protein complexes. In addition, we present an analysis of the descriptors with respect to their power to discriminate near native from incorrect clusters and how data transformations and recursive feature elimination can improve the ranking performance. Proteins 2017; 85:528-543. © 2016 Wiley Periodicals, Inc.
Collapse
Affiliation(s)
| | | | - Iain H. Moal
- European Molecular Biology LaboratoryEuropean Bioinformatics Institute, Wellcome Trust Genome Campus, HinxtonCambridgeCB10 1SDUK
| | - Paul A. Bates
- Biomolecular Modelling LaboratoryThe Francis Crick InstituteLondonNW1 1ATUK
| |
Collapse
|
13
|
Shih ESC, Hwang MJ. NPPD: A Protein-Protein Docking Scoring Function Based on Dyadic Differences in Networks of Hydrophobic and Hydrophilic Amino Acid Residues. BIOLOGY 2015; 4:282-97. [PMID: 25811640 PMCID: PMC4498300 DOI: 10.3390/biology4020282] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/27/2014] [Accepted: 03/16/2015] [Indexed: 11/16/2022]
Abstract
Protein-protein docking (PPD) predictions usually rely on the use of a scoring function to rank docking models generated by exhaustive sampling. To rank good models higher than bad ones, a large number of scoring functions have been developed and evaluated, but the methods used for the computation of PPD predictions remain largely unsatisfactory. Here, we report a network-based PPD scoring function, the NPPD, in which the network consists of two types of network nodes, one for hydrophobic and the other for hydrophilic amino acid residues, and the nodes are connected when the residues they represent are within a certain contact distance. We showed that network parameters that compute dyadic interactions and those that compute heterophilic interactions of the amino acid networks thus constructed allowed NPPD to perform well in a benchmark evaluation of 115 PPD scoring functions, most of which, unlike NPPD, are based on some sort of protein-protein interaction energy. We also showed that NPPD was highly complementary to these energy-based scoring functions, suggesting that the combined use of conventional scoring functions and NPPD might significantly improve the accuracy of current PPD predictions.
Collapse
Affiliation(s)
- Edward S C Shih
- Institute of Biomedical Sciences, Academia Sinica, Nankang, Taipei 115, Taiwan.
| | - Ming-Jing Hwang
- Institute of Biomedical Sciences, Academia Sinica, Nankang, Taipei 115, Taiwan.
| |
Collapse
|
14
|
Moal IH, Torchala M, Bates PA, Fernández-Recio J. The scoring of poses in protein-protein docking: current capabilities and future directions. BMC Bioinformatics 2013; 14:286. [PMID: 24079540 PMCID: PMC3850738 DOI: 10.1186/1471-2105-14-286] [Citation(s) in RCA: 76] [Impact Index Per Article: 6.9] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2013] [Accepted: 09/25/2013] [Indexed: 12/16/2022] Open
Abstract
BACKGROUND Protein-protein docking, which aims to predict the structure of a protein-protein complex from its unbound components, remains an unresolved challenge in structural bioinformatics. An important step is the ranking of docked poses using a scoring function, for which many methods have been developed. There is a need to explore the differences and commonalities of these methods with each other, as well as with functions developed in the fields of molecular dynamics and homology modelling. RESULTS We present an evaluation of 115 scoring functions on an unbound docking decoy benchmark covering 118 complexes for which a near-native solution can be found, yielding top 10 success rates of up to 58%. Hierarchical clustering is performed, so as to group together functions which identify near-natives in similar subsets of complexes. Three set theoretic approaches are used to identify pairs of scoring functions capable of correctly scoring different complexes. This shows that functions in different clusters capture different aspects of binding and are likely to work together synergistically. CONCLUSIONS All functions designed specifically for docking perform well, indicating that functions are transferable between sampling methods. We also identify promising methods from the field of homology modelling. Further, differential success rates by docking difficulty and solution quality suggest a need for flexibility-dependent scoring. Investigating pairs of scoring functions, the set theoretic measures identify known scoring strategies as well as a number of novel approaches, indicating promising augmentations of traditional scoring methods. Such augmentation and parameter combination strategies are discussed in the context of the learning-to-rank paradigm.
Collapse
Affiliation(s)
- Iain H Moal
- Joint BSC-IRB Research Program in Computational Biology, Life Science Department, Barcelona Super computing Center, Barcelona 08034, Spain
| | - Mieczyslaw Torchala
- Biomolecular Modelling Laboratory, Cancer Research UK London Research Institute, London WC2A 3LY, UK
| | - Paul A Bates
- Biomolecular Modelling Laboratory, Cancer Research UK London Research Institute, London WC2A 3LY, UK
| | - Juan Fernández-Recio
- Joint BSC-IRB Research Program in Computational Biology, Life Science Department, Barcelona Super computing Center, Barcelona 08034, Spain
| |
Collapse
|
15
|
Moal IH, Moretti R, Baker D, Fernández-Recio J. Scoring functions for protein-protein interactions. Curr Opin Struct Biol 2013; 23:862-7. [PMID: 23871100 DOI: 10.1016/j.sbi.2013.06.017] [Citation(s) in RCA: 52] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2013] [Revised: 06/26/2013] [Accepted: 06/29/2013] [Indexed: 12/24/2022]
Abstract
The computational evaluation of protein-protein interactions will play an important role in organising the wealth of data being generated by high-throughput initiatives. Here we discuss future applications, report recent developments and identify areas requiring further investigation. Many functions have been developed to quantify the structural and energetic properties of interacting proteins, finding use in interrelated challenges revolving around the relationship between sequence, structure and binding free energy. These include loop modelling, side-chain refinement, docking, multimer assembly, affinity prediction, affinity change upon mutation, hotspots location and interface design. Information derived from models optimised for one of these challenges can be used to benefit the others, and can be unified within the theoretical frameworks of multi-task learning and Pareto-optimal multi-objective learning.
Collapse
Affiliation(s)
- Iain H Moal
- Joint BSC-IRB Research Program in Computational Biology, Life Science Department, Barcelona Supercomputing Center, C/ Jordi Girona 29, 08034 Barcelona, Spain
| | | | | | | |
Collapse
|
16
|
Oliva R, Vangone A, Cavallo L. Ranking multiple docking solutions based on the conservation of inter-residue contacts. Proteins 2013; 81:1571-84. [PMID: 23609916 DOI: 10.1002/prot.24314] [Citation(s) in RCA: 31] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2013] [Revised: 03/16/2013] [Accepted: 04/08/2013] [Indexed: 01/11/2023]
Abstract
Molecular docking is the method of choice for investigating the molecular basis of recognition in a large number of functional protein complexes. However, correctly scoring the obtained docking solutions (decoys) to rank native-like (NL) conformations in the top positions is still an open problem. Herein we present CONSRANK, a simple and effective tool to rank multiple docking solutions, which relies on the conservation of inter-residue contacts in the analyzed decoys ensemble. First it calculates a conservation rate for each inter-residue contact, then it ranks decoys according to their ability to match the more frequently observed contacts. We applied CONSRANK to 102 targets from three different benchmarks, RosettaDock, DOCKGROUND, and Critical Assessment of PRedicted Interactions (CAPRI). The method performs consistently well, both in terms of NL solutions ranked in the top positions and of values of the area under the receiver operating characteristic curve. Its ideal application is to solutions coming from different docking programs and procedures, as in the case of CAPRI targets. For all the analyzed CAPRI targets where a comparison is feasible, CONSRANK outperforms the CAPRI scorers. The fraction of NL solutions in the top ten positions in the RosettaDock, DOCKGROUND, and CAPRI benchmarks is enriched on average by a factor of 3.0, 1.9, and 9.9, respectively. Interestingly, CONSRANK is also able to specifically single out the high/medium quality (HMQ) solutions from the docking decoys ensemble: it ranks 46.2 and 70.8% of the total HMQ solutions available for the RosettaDock and CAPRI targets, respectively, within the top 20 positions.
Collapse
Affiliation(s)
- Romina Oliva
- Department of Applied Sciences, University "Parthenope" of Naples, Centro Direzionale Isola C4, 80143, Naples, Italy
| | | | | |
Collapse
|
17
|
Zellner H, Staudigel M, Trenner T, Bittkowski M, Wolowski V, Icking C, Merkl R. Prescont: Predicting protein-protein interfaces utilizing four residue properties. Proteins 2011; 80:154-68. [DOI: 10.1002/prot.23172] [Citation(s) in RCA: 37] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2011] [Revised: 08/18/2011] [Accepted: 08/29/2011] [Indexed: 12/26/2022]
|