1
|
Wang J, Wang X, Chu Y, Li C, Li X, Meng X, Fang Y, No KT, Mao J, Zeng X. Exploring the Conformational Ensembles of Protein-Protein Complex with Transformer-Based Generative Model. J Chem Theory Comput 2024; 20:4469-4480. [PMID: 38816696 DOI: 10.1021/acs.jctc.4c00255] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/01/2024]
Abstract
Protein-protein interactions are the basis of many protein functions, and understanding the contact and conformational changes of protein-protein interactions is crucial for linking the protein structure to biological function. Although difficult to detect experimentally, molecular dynamics (MD) simulations are widely used to study the conformational ensembles and dynamics of protein-protein complexes, but there are significant limitations in sampling efficiency and computational costs. In this study, a generative neural network was trained on protein-protein complex conformations obtained from molecular simulations to directly generate novel conformations with physical realism. We demonstrated the use of a deep learning model based on the transformer architecture to explore the conformational ensembles of protein-protein complexes through MD simulations. The results showed that the learned latent space can be used to generate unsampled conformations of protein-protein complexes for obtaining new conformations complementing pre-existing ones, which can be used as an exploratory tool for the analysis and enhancement of molecular simulations of protein-protein complexes.
Collapse
Affiliation(s)
- Jianmin Wang
- The Interdisciplinary Graduate Program in Integrative Biotechnology, Yonsei University, Incheon 21983, Korea
| | - Xun Wang
- School of Computer Science and Technology, China University of Petroleum, Qingdao, Shandong 266580, P. R. China
- High Performance Computer Research Center, University of Chinese Academy of Sciences, Beijing 100190, P. R. China
| | - Yanyi Chu
- Department of Pathology, Stanford University School of Medicine, Stanford, California 94305, United States
| | - Chunyan Li
- School of Informatics, Yunnan Normal University, Kunming, Yunnan 650500, P. R. China
| | - Xue Li
- School of Computer Science and Technology, China University of Petroleum, Qingdao, Shandong 266580, P. R. China
| | - Xiangyu Meng
- School of Computer Science and Technology, China University of Petroleum, Qingdao, Shandong 266580, P. R. China
| | - Yitian Fang
- School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai 200030, P. R. China
| | - Kyoung Tai No
- The Interdisciplinary Graduate Program in Integrative Biotechnology, Yonsei University, Incheon 21983, Korea
| | - Jiashun Mao
- School of Medical Information and Engineering, Southwest Medical University, Luzhou, Sichuan 646000, P. R. China
| | - Xiangxiang Zeng
- College of Computer Science and Electronic Engineering, Hunan University, Changsha, Hunan 410082, P. R. China
| |
Collapse
|
2
|
Chu L, Ruffolo JA, Harmalkar A, Gray JJ. Flexible protein-protein docking with a multitrack iterative transformer. Protein Sci 2024; 33:e4862. [PMID: 38148272 PMCID: PMC10804679 DOI: 10.1002/pro.4862] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/09/2023] [Revised: 11/17/2023] [Accepted: 12/06/2023] [Indexed: 12/28/2023]
Abstract
Conventional protein-protein docking algorithms usually rely on heavy candidate sampling and reranking, but these steps are time-consuming and hinder applications that require high-throughput complex structure prediction, for example, structure-based virtual screening. Existing deep learning methods for protein-protein docking, despite being much faster, suffer from low docking success rates. In addition, they simplify the problem to assume no conformational changes within any protein upon binding (rigid docking). This assumption precludes applications when binding-induced conformational changes play a role, such as allosteric inhibition or docking from uncertain unbound model structures. To address these limitations, we present GeoDock, a multitrack iterative transformer network to predict a docked structure from separate docking partners. Unlike deep learning models for protein structure prediction that input multiple sequence alignments, GeoDock inputs just the sequences and structures of the docking partners, which suits the tasks when the individual structures are given. GeoDock is flexible at the protein residue level, allowing the prediction of conformational changes upon binding. On the Database of Interacting Protein Structures (DIPS) test set, GeoDock achieves a 43% top-1 success rate, outperforming all other tested methods. However, in the standard DIPS train/test splits, we discovered contamination of close homologs in the training set. After decontaminating the training set, the success rate is 31%. On the DB5.5 test set and a benchmark dataset of antibody-antigen complexes, GeoDock outperforms the deep learning models trained using the same dataset but falls behind most of the conventional methods and AlphaFold-Multimer. GeoDock attains an average inference speed of under 1 s on a single GPU, enabling its application in large-scale structure screening. Although binding-induced conformational changes are still a challenge owing to limited training and evaluation data, our architecture sets up the foundation to capture this backbone flexibility. Code and a demonstration Jupyter notebook are available at https://github.com/Graylab/GeoDock.
Collapse
Affiliation(s)
- Lee‐Shin Chu
- Department of Chemical and Biomolecular EngineeringJohns Hopkins UniversityBaltimoreMarylandUSA
| | - Jeffrey A. Ruffolo
- Program in Molecular BiophysicsJohns Hopkins UniversityBaltimoreMarylandUSA
| | - Ameya Harmalkar
- Department of Chemical and Biomolecular EngineeringJohns Hopkins UniversityBaltimoreMarylandUSA
| | - Jeffrey J. Gray
- Department of Chemical and Biomolecular EngineeringJohns Hopkins UniversityBaltimoreMarylandUSA
- Program in Molecular BiophysicsJohns Hopkins UniversityBaltimoreMarylandUSA
| |
Collapse
|
3
|
Naji SA, Sağlik BN, Agamennone M, Evren AE, Gundogdu-Karaburun N, Karaburun AÇ. Design and Evaluation of Synthesized Pyrrole Derivatives as Dual COX-1 and COX-2 Inhibitors Using FB-QSAR Approach. ACS OMEGA 2023; 8:48884-48903. [PMID: 38162789 PMCID: PMC10753557 DOI: 10.1021/acsomega.3c06344] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/25/2023] [Revised: 11/16/2023] [Accepted: 11/17/2023] [Indexed: 01/03/2024]
Abstract
This study delves into the intricate dynamics of the inflammatory response, unraveling the pivotal role played by cyclooxygenase (COX) enzymes, particularly COX-1 and COX-2 subtypes. Motivated by the pursuit of advancing scientific knowledge, our contribution to this field is marked by the design and synthesis of novel pyrrole derivatives. Crafted as potential inhibitors of COX-1 and COX-2 enzymes, our goal was to unearth molecules with heightened efficacy in modulating enzyme activity. A meticulous exploration of a synthesis library, housing around 3000 compounds, expedited the identification of potent candidates. Employing advanced docking studies and field-based Quantitative Structure-Activity Relationship (FB-QSAR) analyses enriched our understanding of the complex interactions between synthesized compounds and COX enzymes. Guided by FB-QSAR insights, our synthesis path led to the identification of compounds 4g, 4h, 4l, and 4k as potent COX-2 inhibitors, surpassing COX-1 efficacy. Conversely, compounds 5b and 5e exhibited heightened inhibitory activity against COX-1 relative to COX-2. The utilization of pyrrole derivatives as COX enzyme inhibitors holds promise for groundbreaking advancements in the domain of anti-inflammatory therapeutics, presenting avenues for innovative pharmaceutical exploration.
Collapse
Affiliation(s)
- Shoruq Ahmed Naji
- Faculty
of Pharmacy, Department of Pharmaceutical Chemistry, Anadolu University, 26470 Eskişehir, Turkey
| | - Begüm Nurpelin Sağlik
- Faculty
of Pharmacy, Department of Pharmaceutical Chemistry, Anadolu University, 26470 Eskişehir, Turkey
| | - Mariangela Agamennone
- Department
of Pharmacy, University “G. d’Annunzio”
of Chieti-Pescara, Via
dei Vestini 31, 66100 Chieti, Italy
| | - Asaf Evrim Evren
- Faculty
of Pharmacy, Department of Pharmaceutical Chemistry, Anadolu University, 26470 Eskişehir, Turkey
- Vocational
School of Health Services, Pharmacy Services, Bilecik Seyh Edebali University, 11230 Bilecik, Turkey
| | - Nalan Gundogdu-Karaburun
- Faculty
of Pharmacy, Department of Pharmaceutical Chemistry, Anadolu University, 26470 Eskişehir, Turkey
| | - Ahmet Çagrı Karaburun
- Faculty
of Pharmacy, Department of Pharmaceutical Chemistry, Anadolu University, 26470 Eskişehir, Turkey
| |
Collapse
|
4
|
Chu LS, Ruffolo JA, Harmalkar A, Gray JJ. Flexible Protein-Protein Docking with a Multi-Track Iterative Transformer. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.06.29.547134. [PMID: 37425754 PMCID: PMC10327054 DOI: 10.1101/2023.06.29.547134] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/11/2023]
Abstract
Conventional protein-protein docking algorithms usually rely on heavy candidate sampling and re-ranking, but these steps are time-consuming and hinder applications that require high-throughput complex structure prediction, e.g., structure-based virtual screening. Existing deep learning methods for protein-protein docking, despite being much faster, suffer from low docking success rates. In addition, they simplify the problem to assume no conformational changes within any protein upon binding (rigid docking). This assumption precludes applications when binding-induced conformational changes play a role, such as allosteric inhibition or docking from uncertain unbound model structures. To address these limitations, we present GeoDock, a multi-track iterative transformer network to predict a docked structure from separate docking partners. Unlike deep learning models for protein structure prediction that input multiple sequence alignments (MSAs), GeoDock inputs just the sequences and structures of the docking partners, which suits the tasks when the individual structures are given. GeoDock is flexible at the protein residue level, allowing the prediction of conformational changes upon binding. For a benchmark set of rigid targets, GeoDock obtains a 41% success rate, outperforming all the other tested methods. For a more challenging benchmark set of flexible targets, GeoDock achieves a similar number of top-model successes as the traditional method ClusPro [1], but fewer than ReplicaDock2 [2]. GeoDock attains an average inference speed of under one second on a single GPU, enabling its application in large-scale structure screening. Although binding-induced conformational changes are still a challenge owing to limited training and evaluation data, our architecture sets up the foundation to capture this backbone flexibility. Code and a demonstration Jupyter notebook are available at https://github.com/Graylab/GeoDock.
Collapse
Affiliation(s)
- Lee-Shin Chu
- Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD 21218, USA
| | - Jeffrey A Ruffolo
- Program in Molecular Biophysics, Johns Hopkins University, Baltimore, MD 21218, USA
| | - Ameya Harmalkar
- Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD 21218, USA
| | - Jeffrey J Gray
- Department of Chemical and Biomolecular Engineering, Johns Hopkins University, Baltimore, MD 21218, USA
- Program in Molecular Biophysics, Johns Hopkins University, Baltimore, MD 21218, USA
| |
Collapse
|
5
|
Ruffolo JA, Chu LS, Mahajan SP, Gray JJ. Fast, accurate antibody structure prediction from deep learning on massive set of natural antibodies. Nat Commun 2023; 14:2389. [PMID: 37185622 PMCID: PMC10129313 DOI: 10.1038/s41467-023-38063-x] [Citation(s) in RCA: 59] [Impact Index Per Article: 59.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/21/2022] [Accepted: 04/14/2023] [Indexed: 05/17/2023] Open
Abstract
Antibodies have the capacity to bind a diverse set of antigens, and they have become critical therapeutics and diagnostic molecules. The binding of antibodies is facilitated by a set of six hypervariable loops that are diversified through genetic recombination and mutation. Even with recent advances, accurate structural prediction of these loops remains a challenge. Here, we present IgFold, a fast deep learning method for antibody structure prediction. IgFold consists of a pre-trained language model trained on 558 million natural antibody sequences followed by graph networks that directly predict backbone atom coordinates. IgFold predicts structures of similar or better quality than alternative methods (including AlphaFold) in significantly less time (under 25 s). Accurate structure prediction on this timescale makes possible avenues of investigation that were previously infeasible. As a demonstration of IgFold's capabilities, we predicted structures for 1.4 million paired antibody sequences, providing structural insights to 500-fold more antibodies than have experimentally determined structures.
Collapse
Affiliation(s)
- Jeffrey A Ruffolo
- Program in Molecular Biophysics, The Johns Hopkins University, Baltimore, MD, 21218, USA
| | - Lee-Shin Chu
- Department of Chemical and Biomolecular Engineering, The Johns Hopkins University, Baltimore, MD, 21218, USA
| | - Sai Pooja Mahajan
- Department of Chemical and Biomolecular Engineering, The Johns Hopkins University, Baltimore, MD, 21218, USA
| | - Jeffrey J Gray
- Program in Molecular Biophysics, The Johns Hopkins University, Baltimore, MD, 21218, USA.
- Department of Chemical and Biomolecular Engineering, The Johns Hopkins University, Baltimore, MD, 21218, USA.
| |
Collapse
|