1
|
Wang H, Chen B, Sun H, Zhang Y. Carbon-based molecular properties efficiently predicted by deep learning-based quantum chemical simulation with large language models. Comput Biol Med 2024; 176:108531. [PMID: 38728991 DOI: 10.1016/j.compbiomed.2024.108531] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/11/2024] [Revised: 04/21/2024] [Accepted: 04/28/2024] [Indexed: 05/12/2024]
Abstract
The prediction of thermodynamic properties of carbon-based molecules based on their geometrical conformation using fluctuation and density functional theories has achieved great success in the field of energy chemistry, while the excessive computational cost provides both opportunities and challenges for the integration of machine learning. In this work, a deep learning-based quantum chemical prediction model was constructed for efficient prediction of thermodynamic properties of carbon-based molecules. We constructed a novel framework - encoding the 3D information into a large language model (LLM), which in turn generates a 2D SMILES string, while embedding a learnable encoding designed to preserve the integrity of the original 3D information, providing better structural information for the model. Additionally, we have designed an equivariant learning module to encompass representations of conformations and feature learning for conformational sampling. This framework aims to predict thermodynamic properties more accurately than learning from 2D topology alone, while providing faster computational speeds than conventional simulations. By combining machine learning and quantum chemistry, we pioneer efficient practical applications in the field of energy chemistry. Our model advances the integration of data-driven and physics-based modeling to unlock novel insights into carbon-based molecules.
Collapse
Affiliation(s)
- Haoyu Wang
- University of Shanghai for Science and Technology, Shanghai, China; School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai, China.
| | - Bin Chen
- University of Shanghai for Science and Technology, Shanghai, China; School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China.
| | - Hangling Sun
- Hengtu Imalligent Technology (Shanghai) Co., Ltd., Shanghai, China
| | - Yuxuan Zhang
- University of Shanghai for Science and Technology, Shanghai, China
| |
Collapse
|
2
|
Chen X, Liu J, Park N, Cheng J. A Survey of Deep Learning Methods for Estimating the Accuracy of Protein Quaternary Structure Models. Biomolecules 2024; 14:574. [PMID: 38785981 PMCID: PMC11117562 DOI: 10.3390/biom14050574] [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: 03/01/2024] [Revised: 04/07/2024] [Accepted: 05/09/2024] [Indexed: 05/25/2024] Open
Abstract
The quality prediction of quaternary structure models of a protein complex, in the absence of its true structure, is known as the Estimation of Model Accuracy (EMA). EMA is useful for ranking predicted protein complex structures and using them appropriately in biomedical research, such as protein-protein interaction studies, protein design, and drug discovery. With the advent of more accurate protein complex (multimer) prediction tools, such as AlphaFold2-Multimer and ESMFold, the estimation of the accuracy of protein complex structures has attracted increasing attention. Many deep learning methods have been developed to tackle this problem; however, there is a noticeable absence of a comprehensive overview of these methods to facilitate future development. Addressing this gap, we present a review of deep learning EMA methods for protein complex structures developed in the past several years, analyzing their methodologies, data and feature construction. We also provide a prospective summary of some potential new developments for further improving the accuracy of the EMA methods.
Collapse
Affiliation(s)
- Xiao Chen
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, USA
| | - Jian Liu
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, USA
- NextGen Precision Health Institute, University of Missouri, Columbia, MO 65211, USA
| | - Nolan Park
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, USA
| | - Jianlin Cheng
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65211, USA
- NextGen Precision Health Institute, University of Missouri, Columbia, MO 65211, USA
| |
Collapse
|
3
|
Zhang Y, Wang X, Zhang Z, Huang Y, Kihara D. Assessment of Protein-Protein Docking Models Using Deep Learning. Methods Mol Biol 2024; 2780:149-162. [PMID: 38987469 DOI: 10.1007/978-1-0716-3985-6_10] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/12/2024]
Abstract
Protein-protein interactions are involved in almost all processes in a living cell and determine the biological functions of proteins. To obtain mechanistic understandings of protein-protein interactions, the tertiary structures of protein complexes have been determined by biophysical experimental methods, such as X-ray crystallography and cryogenic electron microscopy. However, as experimental methods are costly in resources, many computational methods have been developed that model protein complex structures. One of the difficulties in computational protein complex modeling (protein docking) is to select the most accurate models among many models that are usually generated by a docking method. This article reviews advances in protein docking model assessment methods, focusing on recent developments that apply deep learning to several network architectures.
Collapse
Affiliation(s)
- Yuanyuan Zhang
- Department of Computer Science, Purdue University, West Lafayette, IN, USA
| | - Xiao Wang
- Department of Computer Science, Purdue University, West Lafayette, IN, USA
| | - Zicong Zhang
- Department of Computer Science, Purdue University, West Lafayette, IN, USA
| | - Yunhan Huang
- Department of Computer Science, Purdue University, West Lafayette, IN, USA
| | - Daisuke Kihara
- Department of Computer Science, Purdue University, West Lafayette, IN, USA.
- Department of Biological Sciences, Purdue University, West Lafayette, IN, USA.
| |
Collapse
|
4
|
Wu F, Wu L, Radev D, Xu J, Li SZ. Integration of pre-trained protein language models into geometric deep learning networks. Commun Biol 2023; 6:876. [PMID: 37626165 PMCID: PMC10457366 DOI: 10.1038/s42003-023-05133-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2023] [Accepted: 07/11/2023] [Indexed: 08/27/2023] Open
Abstract
Geometric deep learning has recently achieved great success in non-Euclidean domains, and learning on 3D structures of large biomolecules is emerging as a distinct research area. However, its efficacy is largely constrained due to the limited quantity of structural data. Meanwhile, protein language models trained on substantial 1D sequences have shown burgeoning capabilities with scale in a broad range of applications. Several preceding studies consider combining these different protein modalities to promote the representation power of geometric neural networks but fail to present a comprehensive understanding of their benefits. In this work, we integrate the knowledge learned by well-trained protein language models into several state-of-the-art geometric networks and evaluate a variety of protein representation learning benchmarks, including protein-protein interface prediction, model quality assessment, protein-protein rigid-body docking, and binding affinity prediction. Our findings show an overall improvement of 20% over baselines. Strong evidence indicates that the incorporation of protein language models' knowledge enhances geometric networks' capacity by a significant margin and can be generalized to complex tasks.
Collapse
Affiliation(s)
- Fang Wu
- AI Research and Innovation Laboratory, Westlake University, 310030, Hangzhou, China
| | - Lirong Wu
- AI Research and Innovation Laboratory, Westlake University, 310030, Hangzhou, China
| | - Dragomir Radev
- Department of Computer Science, Yale University, New Haven, CT, 06511, USA
| | - Jinbo Xu
- Institute of AI Industry Research, Tsinghua University, Haidian Street, 100084, Beijing, China
- Toyota Technological Institute at Chicago, Chicago, IL, 60637, USA
| | - Stan Z Li
- AI Research and Innovation Laboratory, Westlake University, 310030, Hangzhou, China.
| |
Collapse
|
5
|
Chen X, Morehead A, Liu J, Cheng J. A gated graph transformer for protein complex structure quality assessment and its performance in CASP15. Bioinformatics 2023; 39:i308-i317. [PMID: 37387159 PMCID: PMC10311325 DOI: 10.1093/bioinformatics/btad203] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/01/2023] Open
Abstract
MOTIVATION Proteins interact to form complexes to carry out essential biological functions. Computational methods such as AlphaFold-multimer have been developed to predict the quaternary structures of protein complexes. An important yet largely unsolved challenge in protein complex structure prediction is to accurately estimate the quality of predicted protein complex structures without any knowledge of the corresponding native structures. Such estimations can then be used to select high-quality predicted complex structures to facilitate biomedical research such as protein function analysis and drug discovery. RESULTS In this work, we introduce a new gated neighborhood-modulating graph transformer to predict the quality of 3D protein complex structures. It incorporates node and edge gates within a graph transformer framework to control information flow during graph message passing. We trained, evaluated and tested the method (called DProQA) on newly-curated protein complex datasets before the 15th Critical Assessment of Techniques for Protein Structure Prediction (CASP15) and then blindly tested it in the 2022 CASP15 experiment. The method was ranked 3rd among the single-model quality assessment methods in CASP15 in terms of the ranking loss of TM-score on 36 complex targets. The rigorous internal and external experiments demonstrate that DProQA is effective in ranking protein complex structures. AVAILABILITY AND IMPLEMENTATION The source code, data, and pre-trained models are available at https://github.com/jianlin-cheng/DProQA.
Collapse
Affiliation(s)
- Xiao Chen
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65201, United States
| | - Alex Morehead
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65201, United States
| | - Jian Liu
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65201, United States
| | - Jianlin Cheng
- Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, MO 65201, United States
| |
Collapse
|
6
|
Krapp LF, Abriata LA, Cortés Rodriguez F, Dal Peraro M. PeSTo: parameter-free geometric deep learning for accurate prediction of protein binding interfaces. Nat Commun 2023; 14:2175. [PMID: 37072397 PMCID: PMC10113261 DOI: 10.1038/s41467-023-37701-8] [Citation(s) in RCA: 20] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Accepted: 03/28/2023] [Indexed: 04/20/2023] Open
Abstract
Proteins are essential molecular building blocks of life, responsible for most biological functions as a result of their specific molecular interactions. However, predicting their binding interfaces remains a challenge. In this study, we present a geometric transformer that acts directly on atomic coordinates labeled only with element names. The resulting model-the Protein Structure Transformer, PeSTo-surpasses the current state of the art in predicting protein-protein interfaces and can also predict and differentiate between interfaces involving nucleic acids, lipids, ions, and small molecules with high confidence. Its low computational cost enables processing high volumes of structural data, such as molecular dynamics ensembles allowing for the discovery of interfaces that remain otherwise inconspicuous in static experimentally solved structures. Moreover, the growing foldome provided by de novo structural predictions can be easily analyzed, providing new opportunities to uncover unexplored biology.
Collapse
Affiliation(s)
- Lucien F Krapp
- Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL) and Swiss Institute of Bioinformatics (SIB), Lausanne, 1015, Switzerland
| | - Luciano A Abriata
- Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL) and Swiss Institute of Bioinformatics (SIB), Lausanne, 1015, Switzerland
| | - Fabio Cortés Rodriguez
- Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL) and Swiss Institute of Bioinformatics (SIB), Lausanne, 1015, Switzerland
| | - Matteo Dal Peraro
- Institute of Bioengineering, School of Life Sciences, Ecole Fédérale de Lausanne (EPFL) and Swiss Institute of Bioinformatics (SIB), Lausanne, 1015, Switzerland.
| |
Collapse
|
7
|
Isert C, Atz K, Schneider G. Structure-based drug design with geometric deep learning. Curr Opin Struct Biol 2023; 79:102548. [PMID: 36842415 DOI: 10.1016/j.sbi.2023.102548] [Citation(s) in RCA: 26] [Impact Index Per Article: 26.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2022] [Revised: 01/16/2023] [Accepted: 01/24/2023] [Indexed: 02/26/2023]
Abstract
Structure-based drug design uses three-dimensional geometric information of macromolecules, such as proteins or nucleic acids, to identify suitable ligands. Geometric deep learning, an emerging concept of neural-network-based machine learning, has been applied to macromolecular structures. This review provides an overview of the recent applications of geometric deep learning in bioorganic and medicinal chemistry, highlighting its potential for structure-based drug discovery and design. Emphasis is placed on molecular property prediction, ligand binding site and pose prediction, and structure-based de novo molecular design. The current challenges and opportunities are highlighted, and a forecast of the future of geometric deep learning for drug discovery is presented.
Collapse
Affiliation(s)
- Clemens Isert
- ETH Zurich, Department of Chemistry and Applied Biosciences, Vladimir-Prelog-Weg 4, Zurich, 8093, Switzerland
| | - Kenneth Atz
- ETH Zurich, Department of Chemistry and Applied Biosciences, Vladimir-Prelog-Weg 4, Zurich, 8093, Switzerland
| | - Gisbert Schneider
- ETH Zurich, Department of Chemistry and Applied Biosciences, Vladimir-Prelog-Weg 4, Zurich, 8093, Switzerland; ETH Singapore SEC Ltd, 1 CREATE Way, #06-01 CREATE Tower, Singapore, 8093, Singapore.
| |
Collapse
|
8
|
Rui H, Ashton KS, Min J, Wang C, Potts PR. Protein-protein interfaces in molecular glue-induced ternary complexes: classification, characterization, and prediction. RSC Chem Biol 2023; 4:192-215. [PMID: 36908699 PMCID: PMC9994104 DOI: 10.1039/d2cb00207h] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2022] [Accepted: 01/02/2023] [Indexed: 01/04/2023] Open
Abstract
Molecular glues are a class of small molecules that stabilize the interactions between proteins. Naturally occurring molecular glues are present in many areas of biology where they serve as central regulators of signaling pathways. Importantly, several clinical compounds act as molecular glue degraders that stabilize interactions between E3 ubiquitin ligases and target proteins, leading to their degradation. Molecular glues hold promise as a new generation of therapeutic agents, including those molecular glue degraders that can redirect the protein degradation machinery in a precise way. However, rational discovery of molecular glues is difficult in part due to the lack of understanding of the protein-protein interactions they stabilize. In this review, we summarize the structures of known molecular glue-induced ternary complexes and the interface properties. Detailed analysis shows different mechanisms of ternary structure formation. Additionally, we also review computational approaches for predicting protein-protein interfaces and highlight the promises and challenges. This information will ultimately help inform future approaches for rational molecular glue discovery.
Collapse
Affiliation(s)
- Huan Rui
- Center for Research Acceleration by Digital Innovation, Amgen Research Thousand Oaks CA 91320 USA
| | - Kate S Ashton
- Medicinal Chemistry, Amgen Research Thousand Oaks CA 91320 USA
| | - Jaeki Min
- Induced Proximity Platform, Amgen Research Thousand Oaks CA 91320 USA
| | - Connie Wang
- Digital, Technology & Innovation, Amgen Thousand Oaks CA 91320 USA
| | | |
Collapse
|
9
|
Kim HY, Kim S, Park WY, Kim D. G-RANK: an equivariant graph neural network for the scoring of protein-protein docking models. BIOINFORMATICS ADVANCES 2023; 3:vbad011. [PMID: 36818727 PMCID: PMC9927558 DOI: 10.1093/bioadv/vbad011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/07/2022] [Revised: 01/25/2023] [Accepted: 02/01/2023] [Indexed: 02/05/2023]
Abstract
Motivation Protein complex structure prediction is important for many applications in bioengineering. A widely used method for predicting the structure of protein complexes is computational docking. Although many tools for scoring protein-protein docking models have been developed, it is still a challenge to accurately identify near-native models for unknown protein complexes. A recently proposed model called the geometric vector perceptron-graph neural network (GVP-GNN), a subtype of equivariant graph neural networks, has demonstrated success in various 3D molecular structure modeling tasks. Results Herein, we present G-RANK, a GVP-GNN-based method for the scoring of protein-protein docking models. When evaluated on two different test datasets, G-RANK achieved a performance competitive with or better than the state-of-the-art scoring functions. We expect G-RANK to be a useful tool for various applications in biological engineering. Availability and implementation Source code is available at https://github.com/ha01994/grank. Contact kds@kaist.ac.kr. Supplementary information Supplementary data are available at Bioinformatics Advances online.
Collapse
Affiliation(s)
- Ha Young Kim
- Department of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, South Korea
| | | | - Woong-Yang Park
- GENINUS Inc., Seoul 05836, South Korea,Samsung Genome Institute, Samsung Medical Center, Seoul 06351, South Korea,Department of Molecular Cell Biology, Sungkyunkwan University School of Medicine, Suwon 16419, South Korea
| | | |
Collapse
|
10
|
Rogers JR, Nikolényi G, AlQuraishi M. Growing ecosystem of deep learning methods for modeling protein-protein interactions. Protein Eng Des Sel 2023; 36:gzad023. [PMID: 38102755 DOI: 10.1093/protein/gzad023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2023] [Revised: 12/06/2023] [Accepted: 12/07/2023] [Indexed: 12/17/2023] Open
Abstract
Numerous cellular functions rely on protein-protein interactions. Efforts to comprehensively characterize them remain challenged however by the diversity of molecular recognition mechanisms employed within the proteome. Deep learning has emerged as a promising approach for tackling this problem by exploiting both experimental data and basic biophysical knowledge about protein interactions. Here, we review the growing ecosystem of deep learning methods for modeling protein interactions, highlighting the diversity of these biophysically informed models and their respective trade-offs. We discuss recent successes in using representation learning to capture complex features pertinent to predicting protein interactions and interaction sites, geometric deep learning to reason over protein structures and predict complex structures, and generative modeling to design de novo protein assemblies. We also outline some of the outstanding challenges and promising new directions. Opportunities abound to discover novel interactions, elucidate their physical mechanisms, and engineer binders to modulate their functions using deep learning and, ultimately, unravel how protein interactions orchestrate complex cellular behaviors.
Collapse
Affiliation(s)
- Julia R Rogers
- Department of Systems Biology, Columbia University, New York, NY 10032, USA
| | - Gergő Nikolényi
- Department of Systems Biology, Columbia University, New York, NY 10032, USA
| | | |
Collapse
|
11
|
Yang X, Zheng Y, Xing X, Sui X, Jia W, Pan H. Immune subtype identification and multi-layer perceptron classifier construction for breast cancer. Front Oncol 2022; 12:943874. [PMID: 36568197 PMCID: PMC9780074 DOI: 10.3389/fonc.2022.943874] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2022] [Accepted: 11/17/2022] [Indexed: 12/13/2022] Open
Abstract
Introduction Breast cancer is a heterogeneous tumor. Tumor microenvironment (TME) has an important effect on the proliferation, metastasis, treatment, and prognosis of breast cancer. Methods In this study, we calculated the relative proportion of tumor infiltrating immune cells (TIICs) in the breast cancer TME, and used the consensus clustering algorithm to cluster the breast cancer subtypes. We also developed a multi-layer perceptron (MLP) classifier based on a deep learning framework to detect breast cancer subtypes, which 70% of the breast cancer research cohort was used for the model training and 30% for validation. Results By performing the K-means clustering algorithm, the research cohort was clustered into two subtypes. The Kaplan-Meier survival estimate analysis showed significant differences in the overall survival (OS) between the two identified subtypes. Estimating the difference in the relative proportion of TIICs showed that the two subtypes had significant differences in multiple immune cells, such as CD8, CD4, and regulatory T cells. Further, the expression level of immune checkpoint molecules (PDL1, CTLA4, LAG3, TIGIT, CD27, IDO1, ICOS) and tumor mutational burden (TMB) also showed significant differences between the two subtypes, indicating the clinical value of the two subtypes. Finally, we identified a 38-gene signature and developed a multilayer perceptron (MLP) classifier that combined multi-gene signature to identify breast cancer subtypes. The results showed that the classifier had an accuracy rate of 93.56% and can be robustly used for the breast cancer subtype diagnosis. Conclusion Identification of breast cancer subtypes based on the immune signature in the tumor microenvironment can assist clinicians to effectively and accurately assess the progression of breast cancer and formulate different treatment strategies for different subtypes.
Collapse
Affiliation(s)
- Xinbo Yang
- School of Information Science and Engineering, Shandong Normal University, Jinan, China
| | - Yuanjie Zheng
- School of Information Science and Engineering, Shandong Normal University, Jinan, China,*Correspondence: Yuanjie Zheng, ; Huali Pan,
| | - Xianrong Xing
- Department of Pharmacy, Shandong Medical College, Jinan, China
| | - Xiaodan Sui
- School of Information Science and Engineering, Shandong Normal University, Jinan, China
| | - Weikuan Jia
- School of Information Science and Engineering, Shandong Normal University, Jinan, China
| | - Huali Pan
- School of Information Science and Engineering, Shandong Normal University, Jinan, China,Business School, Shandong Normal University, Jinan, China,*Correspondence: Yuanjie Zheng, ; Huali Pan,
| |
Collapse
|
12
|
Mohseni Behbahani Y, Crouzet S, Laine E, Carbone A. Deep Local Analysis evaluates protein docking conformations with locally oriented cubes. Bioinformatics 2022; 38:4505-4512. [PMID: 35962985 PMCID: PMC9525006 DOI: 10.1093/bioinformatics/btac551] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2022] [Revised: 07/04/2022] [Accepted: 08/08/2022] [Indexed: 12/24/2022] Open
Abstract
MOTIVATION With the recent advances in protein 3D structure prediction, protein interactions are becoming more central than ever before. Here, we address the problem of determining how proteins interact with one another. More specifically, we investigate the possibility of discriminating near-native protein complex conformations from incorrect ones by exploiting local environments around interfacial residues. RESULTS Deep Local Analysis (DLA)-Ranker is a deep learning framework applying 3D convolutions to a set of locally oriented cubes representing the protein interface. It explicitly considers the local geometry of the interfacial residues along with their neighboring atoms and the regions of the interface with different solvent accessibility. We assessed its performance on three docking benchmarks made of half a million acceptable and incorrect conformations. We show that DLA-Ranker successfully identifies near-native conformations from ensembles generated by molecular docking. It surpasses or competes with other deep learning-based scoring functions. We also showcase its usefulness to discover alternative interfaces. AVAILABILITY AND IMPLEMENTATION http://gitlab.lcqb.upmc.fr/dla-ranker/DLA-Ranker.git. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Yasser Mohseni Behbahani
- Sorbonne Université, CNRS, IBPS, Laboratory of Computational and Quantitative Biology (LCQB), UMR 7238, Paris 75005, France
| | - Simon Crouzet
- Sorbonne Université, CNRS, IBPS, Laboratory of Computational and Quantitative Biology (LCQB), UMR 7238, Paris 75005, France
| | | | | |
Collapse
|
13
|
Tubiana J, Schneidman-Duhovny D, Wolfson HJ. ScanNet: A web server for structure-based prediction of protein binding sites with geometric deep learning. J Mol Biol 2022; 434:167758. [DOI: 10.1016/j.jmb.2022.167758] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2022] [Revised: 07/18/2022] [Accepted: 07/19/2022] [Indexed: 11/28/2022]
|
14
|
|
15
|
Leveraging nonstructural data to predict structures and affinities of protein-ligand complexes. Proc Natl Acad Sci U S A 2021; 118:2112621118. [PMID: 34921117 PMCID: PMC8713799 DOI: 10.1073/pnas.2112621118] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/15/2021] [Indexed: 01/02/2023] Open
Abstract
Structure-based drug design depends on the ability to predict both the three-dimensional structures of candidate molecules bound to their targets and the associated binding affinities. We demonstrate that one can substantially improve the accuracy of these predictions using easily obtained data about completely different molecules that bind to the same target without requiring any target-bound structures of these molecules. The approach we developed to integrate physical and data-driven modeling may find a variety of applications in the rapidly growing field of artificial intelligence for drug discovery. Over the past five decades, tremendous effort has been devoted to computational methods for predicting properties of ligands—i.e., molecules that bind macromolecular targets. Such methods, which are critical to rational drug design, fall into two categories: physics-based methods, which directly model ligand interactions with the target given the target’s three-dimensional (3D) structure, and ligand-based methods, which predict ligand properties given experimental measurements for similar ligands. Here, we present a rigorous statistical framework to combine these two sources of information. We develop a method to predict a ligand’s pose—the 3D structure of the ligand bound to its target—that leverages a widely available source of information: a list of other ligands that are known to bind the same target but for which no 3D structure is available. This combination of physics-based and ligand-based modeling improves pose prediction accuracy across all major families of drug targets. Using the same framework, we develop a method for virtual screening of drug candidates, which outperforms standard physics-based and ligand-based virtual screening methods. Our results suggest broad opportunities to improve prediction of various ligand properties by combining diverse sources of information through customized machine-learning approaches.
Collapse
|
16
|
Renaud N, Geng C, Georgievska S, Ambrosetti F, Ridder L, Marzella DF, Réau MF, Bonvin AMJJ, Xue LC. DeepRank: a deep learning framework for data mining 3D protein-protein interfaces. Nat Commun 2021; 12:7068. [PMID: 34862392 PMCID: PMC8642403 DOI: 10.1038/s41467-021-27396-0] [Citation(s) in RCA: 40] [Impact Index Per Article: 13.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2021] [Accepted: 11/12/2021] [Indexed: 11/08/2022] Open
Abstract
Three-dimensional (3D) structures of protein complexes provide fundamental information to decipher biological processes at the molecular scale. The vast amount of experimentally and computationally resolved protein-protein interfaces (PPIs) offers the possibility of training deep learning models to aid the predictions of their biological relevance. We present here DeepRank, a general, configurable deep learning framework for data mining PPIs using 3D convolutional neural networks (CNNs). DeepRank maps features of PPIs onto 3D grids and trains a user-specified CNN on these 3D grids. DeepRank allows for efficient training of 3D CNNs with data sets containing millions of PPIs and supports both classification and regression. We demonstrate the performance of DeepRank on two distinct challenges: The classification of biological versus crystallographic PPIs, and the ranking of docking models. For both problems DeepRank is competitive with, or outperforms, state-of-the-art methods, demonstrating the versatility of the framework for research in structural biology.
Collapse
Affiliation(s)
- Nicolas Renaud
- Netherlands eScience Center, Science Park 140, 1098 XG, Amsterdam, The Netherlands
| | - Cunliang Geng
- Netherlands eScience Center, Science Park 140, 1098 XG, Amsterdam, The Netherlands
- Bijvoet Centre for Biomolecular Research, Faculty of Science - Chemistry, Utrecht University, Padualaan 8, 3584, Utrecht, CH, The Netherlands
| | - Sonja Georgievska
- Netherlands eScience Center, Science Park 140, 1098 XG, Amsterdam, The Netherlands
| | - Francesco Ambrosetti
- Bijvoet Centre for Biomolecular Research, Faculty of Science - Chemistry, Utrecht University, Padualaan 8, 3584, Utrecht, CH, The Netherlands
| | - Lars Ridder
- Netherlands eScience Center, Science Park 140, 1098 XG, Amsterdam, The Netherlands
| | - Dario F Marzella
- Center for Molecular and Biomolecular Informatics, Radboudumc, Greet Grooteplein 26-28, 6525, Nijmegen, GA, The Netherlands
| | - Manon F Réau
- Bijvoet Centre for Biomolecular Research, Faculty of Science - Chemistry, Utrecht University, Padualaan 8, 3584, Utrecht, CH, The Netherlands
| | - Alexandre M J J Bonvin
- Bijvoet Centre for Biomolecular Research, Faculty of Science - Chemistry, Utrecht University, Padualaan 8, 3584, Utrecht, CH, The Netherlands.
| | - Li C Xue
- Bijvoet Centre for Biomolecular Research, Faculty of Science - Chemistry, Utrecht University, Padualaan 8, 3584, Utrecht, CH, The Netherlands.
- Center for Molecular and Biomolecular Informatics, Radboudumc, Greet Grooteplein 26-28, 6525, Nijmegen, GA, The Netherlands.
| |
Collapse
|
17
|
Abstract
The biological significance of proteins attracted the scientific community in exploring their characteristics. The studies shed light on the interaction patterns and functions of proteins in a living body. Due to their practical difficulties, reliable experimental techniques pave the way for introducing computational methods in the interaction prediction. Automated methods reduced the difficulties but could not yet replace experimental studies as the field is still evolving. Interaction prediction problem being critical needs highly accurate results, but none of the existing methods could offer reliable performance that can parallel with experimental results yet. This article aims to assess the existing computational docking algorithms, their challenges, and future scope. Blind docking techniques are quite helpful when no information other than the individual structures are available. As more and more complex structures are being added to different databases, information-driven approaches can be a good alternative. Artificial intelligence, ruling over the major fields, is expected to take over this domain very shortly.
Collapse
|
18
|
Defresne M, Barbe S, Schiex T. Protein Design with Deep Learning. Int J Mol Sci 2021; 22:11741. [PMID: 34769173 PMCID: PMC8584038 DOI: 10.3390/ijms222111741] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2021] [Revised: 10/23/2021] [Accepted: 10/26/2021] [Indexed: 12/21/2022] Open
Abstract
Computational Protein Design (CPD) has produced impressive results for engineering new proteins, resulting in a wide variety of applications. In the past few years, various efforts have aimed at replacing or improving existing design methods using Deep Learning technology to leverage the amount of publicly available protein data. Deep Learning (DL) is a very powerful tool to extract patterns from raw data, provided that data are formatted as mathematical objects and the architecture processing them is well suited to the targeted problem. In the case of protein data, specific representations are needed for both the amino acid sequence and the protein structure in order to capture respectively 1D and 3D information. As no consensus has been reached about the most suitable representations, this review describes the representations used so far, discusses their strengths and weaknesses, and details their associated DL architecture for design and related tasks.
Collapse
Affiliation(s)
- Marianne Defresne
- Toulouse Biotechnology Institute, Université de Toulouse, CNRS, INRAE, INSA, ANITI, 31077 Toulouse, France; (M.D.); (S.B.)
- Université Fédérale de Toulouse, ANITI, INRAE, UR 875, 31326 Toulouse, France
| | - Sophie Barbe
- Toulouse Biotechnology Institute, Université de Toulouse, CNRS, INRAE, INSA, ANITI, 31077 Toulouse, France; (M.D.); (S.B.)
| | - Thomas Schiex
- Université Fédérale de Toulouse, ANITI, INRAE, UR 875, 31326 Toulouse, France
| |
Collapse
|
19
|
Tam C, Kumar A, Zhang KYJ. NbX: Machine Learning-Guided Re-Ranking of Nanobody-Antigen Binding Poses. Pharmaceuticals (Basel) 2021; 14:ph14100968. [PMID: 34681192 PMCID: PMC8537642 DOI: 10.3390/ph14100968] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2021] [Revised: 09/17/2021] [Accepted: 09/21/2021] [Indexed: 12/02/2022] Open
Abstract
Modeling the binding pose of an antibody is a prerequisite to structure-based affinity maturation and design. Without knowing a reliable binding pose, the subsequent structural simulation is largely futile. In this study, we have developed a method of machine learning-guided re-ranking of antigen binding poses of nanobodies, the single-domain antibody which has drawn much interest recently in antibody drug development. We performed a large-scale self-docking experiment of nanobody–antigen complexes. By training a decision tree classifier through mapping a feature set consisting of energy, contact and interface property descriptors to a measure of their docking quality of the refined poses, significant improvement in the median ranking of native-like nanobody poses by was achieved eightfold compared with ClusPro and an established deep 3D CNN classifier of native protein–protein interaction. We further interpreted our model by identifying features that showed relatively important contributions to the prediction performance. This study demonstrated a useful method in improving our current ability in pose prediction of nanobodies.
Collapse
Affiliation(s)
- Chunlai Tam
- Laboratory for Structural Bioinformatics, Center for Biosystems Dynamics Research, RIKEN, 1-7-22 Suehiro, Tsurumi, Yokohama, Kanagawa 230-0045, Japan; (C.T.); (A.K.)
- Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa, Chiba 277-8561, Japan
| | - Ashutosh Kumar
- Laboratory for Structural Bioinformatics, Center for Biosystems Dynamics Research, RIKEN, 1-7-22 Suehiro, Tsurumi, Yokohama, Kanagawa 230-0045, Japan; (C.T.); (A.K.)
| | - Kam Y. J. Zhang
- Laboratory for Structural Bioinformatics, Center for Biosystems Dynamics Research, RIKEN, 1-7-22 Suehiro, Tsurumi, Yokohama, Kanagawa 230-0045, Japan; (C.T.); (A.K.)
- Department of Computational Biology and Medical Sciences, Graduate School of Frontier Sciences, The University of Tokyo, Kashiwa, Chiba 277-8561, Japan
- Correspondence:
| |
Collapse
|
20
|
Laine E, Eismann S, Elofsson A, Grudinin S. Protein sequence-to-structure learning: Is this the end(-to-end revolution)? Proteins 2021; 89:1770-1786. [PMID: 34519095 DOI: 10.1002/prot.26235] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2021] [Revised: 08/16/2021] [Accepted: 09/03/2021] [Indexed: 01/08/2023]
Abstract
The potential of deep learning has been recognized in the protein structure prediction community for some time, and became indisputable after CASP13. In CASP14, deep learning has boosted the field to unanticipated levels reaching near-experimental accuracy. This success comes from advances transferred from other machine learning areas, as well as methods specifically designed to deal with protein sequences and structures, and their abstractions. Novel emerging approaches include (i) geometric learning, that is, learning on representations such as graphs, three-dimensional (3D) Voronoi tessellations, and point clouds; (ii) pretrained protein language models leveraging attention; (iii) equivariant architectures preserving the symmetry of 3D space; (iv) use of large meta-genome databases; (v) combinations of protein representations; and (vi) finally truly end-to-end architectures, that is, differentiable models starting from a sequence and returning a 3D structure. Here, we provide an overview and our opinion of the novel deep learning approaches developed in the last 2 years and widely used in CASP14.
Collapse
Affiliation(s)
- Elodie Laine
- Sorbonne Université, CNRS, IBPS, Laboratoire de Biologie Computationnelle et Quantitative (LCQB), Paris, France
| | - Stephan Eismann
- Department of Computer Science and Applied Physics, Stanford University, Stanford, California, USA
| | - Arne Elofsson
- Department of Biochemistry and Biophysics and Science for Life Laboratory, Stockholm University, Solna, Sweden
| | - Sergei Grudinin
- Univ. Grenoble Alpes, CNRS, Grenoble INP, LJK, Grenoble, France
| |
Collapse
|
21
|
Townshend RJL, Eismann S, Watkins AM, Rangan R, Karelina M, Das R, Dror RO. Geometric deep learning of RNA structure. Science 2021; 373:1047-1051. [PMID: 34446608 PMCID: PMC9829186 DOI: 10.1126/science.abe5650] [Citation(s) in RCA: 155] [Impact Index Per Article: 51.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2020] [Accepted: 07/14/2021] [Indexed: 01/28/2023]
Abstract
RNA molecules adopt three-dimensional structures that are critical to their function and of interest in drug discovery. Few RNA structures are known, however, and predicting them computationally has proven challenging. We introduce a machine learning approach that enables identification of accurate structural models without assumptions about their defining characteristics, despite being trained with only 18 known RNA structures. The resulting scoring function, the Atomic Rotationally Equivariant Scorer (ARES), substantially outperforms previous methods and consistently produces the best results in community-wide blind RNA structure prediction challenges. By learning effectively even from a small amount of data, our approach overcomes a major limitation of standard deep neural networks. Because it uses only atomic coordinates as inputs and incorporates no RNA-specific information, this approach is applicable to diverse problems in structural biology, chemistry, materials science, and beyond.
Collapse
Affiliation(s)
| | - Stephan Eismann
- Department of Computer Science, Stanford University, Stanford, CA, USA
- Department of Computer Science, Stanford University, Stanford, CA, USA
- Department of Applied Physics, Stanford University, Stanford, CA, USA
| | - Andrew M Watkins
- Department of Biochemistry, Stanford University, Stanford, CA, USA
| | - Ramya Rangan
- Department of Biochemistry, Stanford University, Stanford, CA, USA
- Biophysics Program, Stanford University, Stanford, CA, USA
| | - Masha Karelina
- Department of Computer Science, Stanford University, Stanford, CA, USA
- Biophysics Program, Stanford University, Stanford, CA, USA
| | - Rhiju Das
- Department of Biochemistry, Stanford University, Stanford, CA, USA.
- Department of Physics, Stanford University, Stanford, CA, USA
| | - Ron O Dror
- Department of Computer Science, Stanford University, Stanford, CA, USA.
- Department of Structural Biology, Stanford University, Stanford, CA, USA
- Department of Molecular and Cellular Physiology, Stanford University, Stanford, CA, USA
- Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA, USA
| |
Collapse
|
22
|
Sotudian S, Desta IT, Hashemi N, Zarbafian S, Kozakov D, Vakili P, Vajda S, Paschalidis IC. Improved cluster ranking in protein-protein docking using a regression approach. Comput Struct Biotechnol J 2021; 19:2269-2278. [PMID: 33995918 PMCID: PMC8102165 DOI: 10.1016/j.csbj.2021.04.028] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2021] [Revised: 04/08/2021] [Accepted: 04/09/2021] [Indexed: 11/21/2022] Open
Abstract
We develop a Regression-based Ranking by Pairwise Cluster Comparisons (RRPCC) method to rank clusters of similar protein complex conformations generated by an underlying docking program. The method leverages robust regression to predict the relative quality difference between any pair or clusters and combines these pairwise assessments to form a ranked list of clusters, from higher to lower quality. We apply RRPCC to clusters produced by the automated docking server ClusPro and, depending on the training/validation strategy, we show improvement by 24-100% in ranking acceptable or better quality clusters first, and by 15-100% in ranking medium or better quality clusters first. We compare the RRPCC-ClusPro combination to a number of alternatives, and show that very different machine learning approaches to scoring docked structures yield similar success rates. Finally, we discuss the current limitations on sampling and scoring, looking ahead to further improvements. Interestingly, some features important for improved scoring are internal energy terms that occur only due to the local energy minimization applied in the refinement stage following rigid body docking.
Collapse
Affiliation(s)
| | | | - Nasser Hashemi
- Division of Systems Engineering, Boston University, Boston, USA
| | | | - Dima Kozakov
- Laufer Center for Physical and Quantitative Biology, Institute for Advanced Computational Sciences, Stony Brook University, Stony Brook, USA
| | - Pirooz Vakili
- Division of Systems Engineering, Boston University, Boston, USA
| | - Sandor Vajda
- Department of Biomedical Engineering, Boston University
- Department of Chemistry, Boston University
| | - Ioannis Ch. Paschalidis
- Division of Systems Engineering, Boston University, Boston, USA
- Department of Biomedical Engineering, Boston University
- Department of Electrical & Computer Engineering, and Faculty for Computing & Data Sciences, Boston University
| |
Collapse
|