1
|
Vittorio S, Lunghini F, Morerio P, Gadioli D, Orlandini S, Silva P, Jan Martinovic, Pedretti A, Bonanni D, Del Bue A, Palermo G, Vistoli G, Beccari AR. Addressing docking pose selection with structure-based deep learning: Recent advances, challenges and opportunities. Comput Struct Biotechnol J 2024; 23:2141-2151. [PMID: 38827235 PMCID: PMC11141151 DOI: 10.1016/j.csbj.2024.05.024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/23/2024] [Revised: 05/15/2024] [Accepted: 05/15/2024] [Indexed: 06/04/2024] Open
Abstract
Molecular docking is a widely used technique in drug discovery to predict the binding mode of a given ligand to its target. However, the identification of the near-native binding pose in docking experiments still represents a challenging task as the scoring functions currently employed by docking programs are parametrized to predict the binding affinity, and, therefore, they often fail to correctly identify the ligand native binding conformation. Selecting the correct binding mode is crucial to obtaining meaningful results and to conveniently optimizing new hit compounds. Deep learning (DL) algorithms have been an area of a growing interest in this sense for their capability to extract the relevant information directly from the protein-ligand structure. Our review aims to present the recent advances regarding the development of DL-based pose selection approaches, discussing limitations and possible future directions. Moreover, a comparison between the performances of some classical scoring functions and DL-based methods concerning their ability to select the correct binding mode is reported. In this regard, two novel DL-based pose selectors developed by us are presented.
Collapse
Affiliation(s)
- Serena Vittorio
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Luigi Mangiagalli 25, I-20133 Milano, Italy
| | - Filippo Lunghini
- EXSCALATE, Dompé Farmaceutici SpA, Via Tommaso de Amicis 95, 80123 Naples, Italy
| | - Pietro Morerio
- Pattern Analysis and Computer Vision, Fondazione Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - Davide Gadioli
- Dipartimento di Elettronica Informazione e Bioingegneria, Politecnico di Milano, Via Ponzio 34/5, I-20133 Milano, Italy
| | - Sergio Orlandini
- SCAI, SuperComputing Applications and Innovation Department, CINECA, Via dei Tizii 6, Rome 00185, Italy
| | - Paulo Silva
- IT4Innovations, VSB – Technical University of Ostrava, 17. listopadu 2172/15, 70800 Ostrava-Poruba, Czech Republic
| | - Jan Martinovic
- IT4Innovations, VSB – Technical University of Ostrava, 17. listopadu 2172/15, 70800 Ostrava-Poruba, Czech Republic
| | - Alessandro Pedretti
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Luigi Mangiagalli 25, I-20133 Milano, Italy
| | - Domenico Bonanni
- Department of Physical and Chemical Sciences, University of L′Aquila, via Vetoio, L′Aquila 67010, Italy
| | - Alessio Del Bue
- Pattern Analysis and Computer Vision, Fondazione Istituto Italiano di Tecnologia, Via Morego, 30, 16163 Genova, Italy
| | - Gianluca Palermo
- Dipartimento di Elettronica Informazione e Bioingegneria, Politecnico di Milano, Via Ponzio 34/5, I-20133 Milano, Italy
| | - Giulio Vistoli
- Dipartimento di Scienze Farmaceutiche, Università degli Studi di Milano, Via Luigi Mangiagalli 25, I-20133 Milano, Italy
| | - Andrea R. Beccari
- EXSCALATE, Dompé Farmaceutici SpA, Via Tommaso de Amicis 95, 80123 Naples, Italy
| |
Collapse
|
2
|
Glick ZL, Metcalf DP, Glick CS, Spronk SA, Koutsoukas A, Cheney DL, Sherrill CD. A physics-aware neural network for protein-ligand interactions with quantum chemical accuracy. Chem Sci 2024; 15:13313-13324. [PMID: 39183910 PMCID: PMC11339967 DOI: 10.1039/d4sc01029a] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2024] [Accepted: 07/09/2024] [Indexed: 08/27/2024] Open
Abstract
Quantifying intermolecular interactions with quantum chemistry (QC) is useful for many chemical problems, including understanding the nature of protein-ligand interactions. Unfortunately, QC computations on protein-ligand systems are too computationally expensive for most use cases. The flourishing field of machine-learned (ML) potentials is a promising solution, but it is limited by an inability to easily capture long range, non-local interactions. In this work we develop an atomic-pairwise neural network (AP-Net) specialized for modeling intermolecular interactions. This model benefits from a number of physical constraints, including a two-component equivariant message passing neural network architecture that predicts interaction energies via an intermediate prediction of monomer electron densities. The AP-Net model is trained on a comprehensive dataset composed of paired ligand and protein fragments. This model accurately predicts QC-quality interaction energies of protein-ligand systems at a computational cost reduced by orders of magnitude. Applications of the AP-Net model to molecular crystal structure prediction are explored, as well as limitations in modeling highly polarizable systems.
Collapse
Affiliation(s)
- Zachary L Glick
- School of Chemistry and Biochemistry, School of Computational Science and Engineering, Georgia Institute of Technology Atlanta Georgia 30332-0400 USA
| | - Derek P Metcalf
- School of Chemistry and Biochemistry, School of Computational Science and Engineering, Georgia Institute of Technology Atlanta Georgia 30332-0400 USA
| | - Caroline S Glick
- School of Chemistry and Biochemistry, School of Computational Science and Engineering, Georgia Institute of Technology Atlanta Georgia 30332-0400 USA
| | - Steven A Spronk
- Molecular Structure and Design, Bristol Myers Squibb Company P.O. Box 5400 Princeton New Jersey 08543 USA
| | - Alexios Koutsoukas
- Molecular Structure and Design, Bristol Myers Squibb Company P.O. Box 5400 Princeton New Jersey 08543 USA
| | - Daniel L Cheney
- Molecular Structure and Design, Bristol Myers Squibb Company P.O. Box 5400 Princeton New Jersey 08543 USA
| | - C David Sherrill
- School of Chemistry and Biochemistry, School of Computational Science and Engineering, Georgia Institute of Technology Atlanta Georgia 30332-0400 USA
| |
Collapse
|
3
|
Li SC, Wu H, Menon A, Spiekermann KA, Li YP, Green WH. When Do Quantum Mechanical Descriptors Help Graph Neural Networks to Predict Chemical Properties? J Am Chem Soc 2024; 146:23103-23120. [PMID: 39106041 DOI: 10.1021/jacs.4c04670] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/07/2024]
Abstract
Deep graph neural networks are extensively utilized to predict chemical reactivity and molecular properties. However, because of the complexity of chemical space, such models often have difficulty extrapolating beyond the chemistry contained in the training set. Augmenting the model with quantum mechanical (QM) descriptors is anticipated to improve its generalizability. However, obtaining QM descriptors often requires CPU-intensive computational chemistry calculations. To identify when QM descriptors help graph neural networks predict chemical properties, we conduct a systematic investigation of the impact of atom, bond, and molecular QM descriptors on the performance of directed message passing neural networks (D-MPNNs) for predicting 16 molecular properties. The analysis surveys computational and experimental targets, as well as classification and regression tasks, and varied data set sizes from several hundred to hundreds of thousands of data points. Our results indicate that QM descriptors are mostly beneficial for D-MPNN performance on small data sets, provided that the descriptors correlate well with the targets and can be readily computed with high accuracy. Otherwise, using QM descriptors can add cost without benefit or even introduce unwanted noise that can degrade model performance. Strategic integration of QM descriptors with D-MPNN unlocks potential for physics-informed, data-efficient modeling with some interpretability that can streamline de novo drug and material designs. To facilitate the use of QM descriptors in machine learning workflows for chemistry, we provide a set of guidelines regarding when and how to best leverage QM descriptors, a high-throughput workflow to compute them, and an enhancement to Chemprop, a widely adopted open-source D-MPNN implementation for chemical property prediction.
Collapse
Affiliation(s)
- Shih-Cheng Li
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
- Department of Chemical Engineering, National Taiwan University, Taipei 10617, Taiwan
| | - Haoyang Wu
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Angiras Menon
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Kevin A Spiekermann
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| | - Yi-Pei Li
- Department of Chemical Engineering, National Taiwan University, Taipei 10617, Taiwan
| | - William H Green
- Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States
| |
Collapse
|
4
|
Mendes F, Santos-Pereira C, Vieira TF, Martins Pinto M, Castro BB, Sousa SF, Sousa MJ, Devin A, Chaves SR. The fungicide cymoxanil impairs respiration in Saccharomyces cerevisiae via cytochrome c oxidase inhibition. FEBS Lett 2024; 598:1655-1666. [PMID: 38750637 DOI: 10.1002/1873-3468.14907] [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: 02/08/2024] [Revised: 04/15/2024] [Accepted: 04/29/2024] [Indexed: 07/09/2024]
Abstract
Cymoxanil (CYM) is a widely used synthetic acetamide fungicide, but its biochemical mode of action remains elusive. Since CYM inhibits cell growth, biomass production, and respiration in Saccharomyces cerevisiae, we used this model to characterize the effect of CYM on mitochondria. We found it inhibits oxygen consumption in both whole cells and isolated mitochondria, specifically inhibiting cytochrome c oxidase (CcO) activity during oxidative phosphorylation. Based on molecular docking, we propose that CYM blocks the interaction of cytochrome c with CcO, hampering electron transfer and inhibiting CcO catalytic activity. Although other targets cannot be excluded, our data offer valuable insights into the mode of action of CYM that will be instrumental in driving informed management of the use of this fungicide.
Collapse
Affiliation(s)
- Filipa Mendes
- CBMA - Centre of Molecular and Environmental Biology/ARNET - Aquatic Research Network, Department of Biology, School of Sciences, University of Minho, Braga, Portugal
| | - Cátia Santos-Pereira
- CEB - Centre of Biological Engineering, University of Minho, Braga, Portugal
- LABBELS - Associate Laboratory, Braga, Portugal
| | - Tatiana F Vieira
- UCIBIO/REQUIMTE, BioSIM - Departamento de Medicina, Faculdade de Medicina da Universidade Do Porto, Portugal
- Associate Laboratory i4HB - Institute for Health and Bioeconomy, Faculdade de Medicina, Universidade do Porto, Portugal
| | | | - Bruno B Castro
- CBMA - Centre of Molecular and Environmental Biology/ARNET - Aquatic Research Network, Department of Biology, School of Sciences, University of Minho, Braga, Portugal
- IBS - Institute of Science and Innovation for Bio-Sustainability, School of Sciences, University of Minho, Braga, Portugal
| | - Sérgio F Sousa
- UCIBIO/REQUIMTE, BioSIM - Departamento de Medicina, Faculdade de Medicina da Universidade Do Porto, Portugal
- Associate Laboratory i4HB - Institute for Health and Bioeconomy, Faculdade de Medicina, Universidade do Porto, Portugal
| | - Maria João Sousa
- CBMA - Centre of Molecular and Environmental Biology/ARNET - Aquatic Research Network, Department of Biology, School of Sciences, University of Minho, Braga, Portugal
- IBS - Institute of Science and Innovation for Bio-Sustainability, School of Sciences, University of Minho, Braga, Portugal
| | - Anne Devin
- CNRS, UMR 5095, Institut de Biochimie et Génétique Cellulaires, Bordeaux, France
| | - Susana R Chaves
- CBMA - Centre of Molecular and Environmental Biology/ARNET - Aquatic Research Network, Department of Biology, School of Sciences, University of Minho, Braga, Portugal
| |
Collapse
|
5
|
Bhatt R, Koes DR, Durrant JD. CENsible: Interpretable Insights into Small-Molecule Binding with Context Explanation Networks. J Chem Inf Model 2024; 64:4651-4660. [PMID: 38847393 PMCID: PMC11200255 DOI: 10.1021/acs.jcim.4c00825] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2024] [Revised: 05/28/2024] [Accepted: 05/28/2024] [Indexed: 06/18/2024]
Abstract
We present a novel and interpretable approach for assessing small-molecule binding using context explanation networks. Given the specific structure of a protein/ligand complex, our CENsible scoring function uses a deep convolutional neural network to predict the contributions of precalculated terms to the overall binding affinity. We show that CENsible can effectively distinguish active vs inactive compounds for many systems. Its primary benefit over related machine-learning scoring functions, however, is that it retains interpretability, allowing researchers to identify the contribution of each precalculated term to the final affinity prediction, with implications for subsequent lead optimization.
Collapse
Affiliation(s)
- Roshni Bhatt
- Department
of Computational and Systems Biology, University
of Pittsburgh, Pittsburgh, Pennsylvania 15260, United States
- Department
of Biological Sciences, University of Pittsburgh, Pittsburgh, Pennsylvania 15260, United States
| | - David Ryan Koes
- Department
of Computational and Systems Biology, University
of Pittsburgh, Pittsburgh, Pennsylvania 15260, United States
| | - Jacob D. Durrant
- Department
of Biological Sciences, University of Pittsburgh, Pittsburgh, Pennsylvania 15260, United States
| |
Collapse
|
6
|
Zhou Y, Chen SJ. Advances in machine-learning approaches to RNA-targeted drug design. ARTIFICIAL INTELLIGENCE CHEMISTRY 2024; 2:100053. [PMID: 38434217 PMCID: PMC10904028 DOI: 10.1016/j.aichem.2024.100053] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/05/2024]
Abstract
RNA molecules play multifaceted functional and regulatory roles within cells and have garnered significant attention in recent years as promising therapeutic targets. With remarkable successes achieved by artificial intelligence (AI) in different fields such as computer vision and natural language processing, there is a growing imperative to harness AI's potential in computer-aided drug design (CADD) to discover novel drug compounds that target RNA. Although machine-learning (ML) approaches have been widely adopted in the discovery of small molecules targeting proteins, the application of ML approaches to model interactions between RNA and small molecule is still in its infancy. Compared to protein-targeted drug discovery, the major challenges in ML-based RNA-targeted drug discovery stem from the scarcity of available data resources. With the growing interest and the development of curated databases focusing on interactions between RNA and small molecule, the field anticipates a rapid growth and the opening of a new avenue for disease treatment. In this review, we aim to provide an overview of recent advancements in computationally modeling RNA-small molecule interactions within the context of RNA-targeted drug discovery, with a particular emphasis on methodologies employing ML techniques.
Collapse
Affiliation(s)
- Yuanzhe Zhou
- Department of Physics and Astronomy, University of Missouri, Columbia, MO 65211-7010, USA
| | - Shi-Jie Chen
- Department of Physics and Astronomy, Department of Biochemistry, Institute of Data Sciences and Informatics, University of Missouri, Columbia, MO 65211-7010, USA
| |
Collapse
|
7
|
Qu X, Dong L, Luo D, Si Y, Wang B. Water Network-Augmented Two-State Model for Protein-Ligand Binding Affinity Prediction. J Chem Inf Model 2024; 64:2263-2274. [PMID: 37433009 DOI: 10.1021/acs.jcim.3c00567] [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: 07/13/2023]
Abstract
Water network rearrangement from the ligand-unbound state to the ligand-bound state is known to have significant effects on the protein-ligand binding interactions, but most of the current machine learning-based scoring functions overlook these effects. In this study, we endeavor to construct a comprehensive and realistic deep learning model by incorporating water network information into both ligand-unbound and -bound states. In particular, extended connectivity interaction features were integrated into graph representation, and graph transformer operator was employed to extract features of the ligand-unbound and -bound states. Through these efforts, we developed a water network-augmented two-state model called ECIFGraph::HM-Holo-Apo. Our new model exhibits satisfactory performance in terms of scoring, ranking, docking, screening, and reverse screening power tests on the CASF-2016 benchmark. In addition, it can achieve superior performance in large-scale docking-based virtual screening tests on the DEKOIS2.0 data set. Our study highlights that the use of a water network-augmented two-state model can be an effective strategy to bolster the robustness and applicability of machine learning-based scoring functions, particularly for targets with hydrophilic or solvent-exposed binding pockets.
Collapse
Affiliation(s)
- Xiaoyang Qu
- State Key Laboratory of Physical Chemistry of Solid Surfaces and Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen 361005, P. R. China
| | - Lina Dong
- State Key Laboratory of Physical Chemistry of Solid Surfaces and Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen 361005, P. R. China
| | - Ding Luo
- State Key Laboratory of Physical Chemistry of Solid Surfaces and Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen 361005, P. R. China
| | - Yubing Si
- College of Chemistry, Zhengzhou University, Zhengzhou 450001, P. R. China
| | - Binju Wang
- State Key Laboratory of Physical Chemistry of Solid Surfaces and Fujian Provincial Key Laboratory of Theoretical and Computational Chemistry, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen 361005, P. R. China
- Innovation Laboratory for Sciences and Technologies of Energy Materials of Fujian Province (IKKEM), Xiamen 361005, P. R. China
| |
Collapse
|
8
|
Zengin IN, Koca MS, Tayfuroglu O, Yildiz M, Kocak A. Benchmarking ANI potentials as a rescoring function and screening FDA drugs for SARS-CoV-2 M pro. J Comput Aided Mol Des 2024; 38:15. [PMID: 38532176 DOI: 10.1007/s10822-024-00554-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2024] [Accepted: 02/26/2024] [Indexed: 03/28/2024]
Abstract
Here, we introduce the use of ANI-ML potentials as a rescoring function in the host-guest interaction in molecular docking. Our results show that the "docking power" of ANI potentials can compete with the current scoring functions at the same level of computational cost. Benchmarking studies on CASF-2016 dataset showed that ANI is ranked in the top 5 scoring functions among the other 34 tested. In particular, the ANI predicted interaction energies when used in conjunction with GOLD-PLP scoring function can boost the top ranked solution to be the closest to the x-ray structure. Rapid and accurate calculation of interaction energies between ligand and protein also enables screening of millions of drug candidates/docking poses. Using a unique protocol in which docking by GOLD-PLP, rescoring by ANI-ML potentials and extensive MD simulations along with end state free energy methods are combined, we have screened FDA approved drugs against the SARS-CoV-2 main protease (Mpro). The top six drug molecules suggested by the consensus of these free energy methods have already been in clinical trials or proposed as potential drug molecules in previous theoretical and experimental studies, approving the validity and the power of accuracy in our screening method.
Collapse
Affiliation(s)
- Irem N Zengin
- Department of Chemistry, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey
| | - M Serdar Koca
- Department of Molecular Biology and Genetics, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey
- Pfizer - Universidad de Granada - Junta de Andalucía Centre for Genomics and Oncological Research (GENYO), 18016, Granada, Spain
| | - Omer Tayfuroglu
- Department of Chemistry, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey
| | - Muslum Yildiz
- Department of Molecular Biology and Genetics, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey
| | - Abdulkadir Kocak
- Department of Chemistry, Gebze Technical University, 41400, Gebze, Kocaeli, Turkey.
| |
Collapse
|
9
|
Clemente CM, Prieto JM, Martí M. Unlocking Precision Docking for Metalloproteins. J Chem Inf Model 2024; 64:1581-1592. [PMID: 38373276 DOI: 10.1021/acs.jcim.3c01853] [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: 02/21/2024]
Abstract
Metalloproteins play a fundamental role in molecular biology, contributing to various biological processes. However, the discovery of high-affinity ligands targeting metalloproteins has been delayed due, in part, to a lack of suitable tools and data. Molecular docking, a widely used technique for virtual screening of small-molecule ligand interactions with proteins, often faces challenges when applied to metalloproteins due to the particular nature of the ligand metal bond. To address these limitations associated with docking metalloproteins, we introduce a knowledge-driven docking approach known as "metalloprotein bias docking" (MBD), which extends the AutoDock Bias technique. We assembled a comprehensive data set of metalloprotein-ligand complexes from 15 different metalloprotein families, encompassing Ca, Co, Fe, Mg, Mn, and Zn metal ions. Subsequently, we conducted a performance analysis of our MBD method and compared it to the conventional docking (CD) program AutoDock4, applied to various metalloprotein targets within our data set. Our results demonstrate that MBD outperforms CD, significantly enhancing accuracy, selectivity, and precision in ligand pose prediction. Additionally, we observed a positive correlation between our predicted ligand free energies and the corresponding experimental values. These findings underscore the potential of MBD as a valuable tool for the effective exploration of metalloprotein-ligand interactions.
Collapse
Affiliation(s)
- Camila M Clemente
- Departamento de Química Biológica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires (FCEyN-UBA) e Instituto de Química Biológica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN) CONICET, Pabellón 2 de Ciudad Universitaria, Ciudad de Buenos Aires C1428EHA, Argentina
| | - Juan M Prieto
- Departamento de Química Biológica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires (FCEyN-UBA) e Instituto de Química Biológica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN) CONICET, Pabellón 2 de Ciudad Universitaria, Ciudad de Buenos Aires C1428EHA, Argentina
| | - Marcelo Martí
- Departamento de Química Biológica, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires (FCEyN-UBA) e Instituto de Química Biológica de la Facultad de Ciencias Exactas y Naturales (IQUIBICEN) CONICET, Pabellón 2 de Ciudad Universitaria, Ciudad de Buenos Aires C1428EHA, Argentina
| |
Collapse
|
10
|
Shin WH, Kihara D. PL-PatchSurfer3: Improved Structure-Based Virtual Screening for Structure Variation Using 3D Zernike Descriptors. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.02.22.581511. [PMID: 38464318 PMCID: PMC10925112 DOI: 10.1101/2024.02.22.581511] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 03/12/2024]
Abstract
Structure-based virtual screening (SBVS) is a widely used method in silico drug discovery. It necessitates a receptor structure or binding site to predict the binding pose and fitness of a ligand. Therefore, the performance of the SBVS is affected by the protein conformation. The most frequently used method in SBVS is the protein-ligand docking program, which utilizes atomic distance-based scoring functions. Hence, they are highly prone to sensitivity towards variation in receptor structure, and it is reported that the conformational change significantly drops the performance of the docking program. To address the problem, we have introduced a novel program of SBVS, named PL-PatchSurfer. This program makes use of molecular surface patches and the Zernike descriptor. The surfaces of the pocket and ligand are segmented into several patches by the program. These patches are then mapped with physico-chemical properties such as shape and electrostatic potential before being converted into the Zernike descriptor, which is rotationally invariant. A complementarity between the protein and the ligand is assessed by comparing the descriptors and geometric distribution of the patches in the molecules. A benchmarking study showed that PL-PatchSurfer2 was able to screen active molecules regardless of the receptor structure change with fast speed. However, the program could not achieve high performance for the targets that the hydrogen bonding feature is important such as nuclear hormone receptors. In this paper, we present the newer version of PL-PatchSurfer, PL-PatchSurfer3, which incorporates two new features: a change in the definition of hydrogen bond complementarity and consideration of visibility that contains curvature information of a patch. Our evaluation demonstrates that the new program outperforms its predecessor and other SBVS methods while retaining its characteristic tolerance to receptor structure changes. Interested individuals can access the program at kiharalab.org/plps3.
Collapse
Affiliation(s)
- Woong-Hee Shin
- Department of Biomedical Informatics, Korea University College of Medicine, Seoul, Republic of Korea
| | - Daisuke Kihara
- Department of Biological Science, Purdue University, West Lafayette, IN, USA
- Department of Computer Science, Purdue University, West Lafayette, IN, USA
- Center for Cancer Research, Purdue University, West Lafayette, IN, USA
| |
Collapse
|
11
|
Bansal N, Wang Y, Sciabola S. Machine Learning Methods as a Cost-Effective Alternative to Physics-Based Binding Free Energy Calculations. Molecules 2024; 29:830. [PMID: 38398581 PMCID: PMC10893267 DOI: 10.3390/molecules29040830] [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: 12/20/2023] [Revised: 01/24/2024] [Accepted: 02/09/2024] [Indexed: 02/25/2024] Open
Abstract
The rank ordering of ligands remains one of the most attractive challenges in drug discovery. While physics-based in silico binding affinity methods dominate the field, they still have problems, which largely revolve around forcefield accuracy and sampling. Recent advances in machine learning have gained traction for protein-ligand binding affinity predictions in early drug discovery programs. In this article, we perform retrospective binding free energy evaluations for 172 compounds from our internal collection spread over four different protein targets and five congeneric ligand series. We compared multiple state-of-the-art free energy methods ranging from physics-based methods with different levels of complexity and conformational sampling to state-of-the-art machine-learning-based methods that were available to us. Overall, we found that physics-based methods behaved particularly well when the ligand perturbations were made in the solvation region, and they did not perform as well when accounting for large conformational changes in protein active sites. On the other end, machine-learning-based methods offer a good cost-effective alternative for binding free energy calculations, but the accuracy of their predictions is highly dependent on the experimental data available for training the model.
Collapse
Affiliation(s)
- Nupur Bansal
- Biotherapeutic and Medicinal Sciences, Biogen, 225 Binney Street, Cambridge, MA 02142, USA; (Y.W.); (S.S.)
| | | | | |
Collapse
|
12
|
Isert C, Atz K, Riniker S, Schneider G. Exploring protein-ligand binding affinity prediction with electron density-based geometric deep learning. RSC Adv 2024; 14:4492-4502. [PMID: 38312732 PMCID: PMC10835705 DOI: 10.1039/d3ra08650j] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2023] [Accepted: 01/19/2024] [Indexed: 02/06/2024] Open
Abstract
Rational structure-based drug design relies on accurate predictions of protein-ligand binding affinity from structural molecular information. Although deep learning-based methods for predicting binding affinity have shown promise in computational drug design, certain approaches have faced criticism for their potential to inadequately capture the fundamental physical interactions between ligands and their macromolecular targets or for being susceptible to dataset biases. Herein, we propose to include bond-critical points based on the electron density of a protein-ligand complex as a fundamental physical representation of protein-ligand interactions. Employing a geometric deep learning model, we explore the usefulness of these bond-critical points to predict absolute binding affinities of protein-ligand complexes, benchmark model performance against existing methods, and provide a critical analysis of this new approach. The models achieved root-mean-squared errors of 1.4-1.8 log units on the PDBbind dataset, and 1.0-1.7 log units on the PDE10A dataset, not indicating significant advantages over benchmark methods, and thus rendering the utility of electron density for deep learning models context-dependent. The relationship between intermolecular electron density and corresponding binding affinity was analyzed, and Pearson correlation coefficients r > 0.7 were obtained for several macromolecular targets.
Collapse
Affiliation(s)
- Clemens Isert
- ETH Zurich, Department of Chemistry and Applied Biosciences Vladimir-Prelog-Weg 4 8093 Zurich Switzerland +41 44 633 73 27
| | - Kenneth Atz
- ETH Zurich, Department of Chemistry and Applied Biosciences Vladimir-Prelog-Weg 4 8093 Zurich Switzerland +41 44 633 73 27
| | - Sereina Riniker
- ETH Zurich, Department of Chemistry and Applied Biosciences Vladimir-Prelog-Weg 4 8093 Zurich Switzerland +41 44 633 73 27
| | - Gisbert Schneider
- ETH Zurich, Department of Chemistry and Applied Biosciences Vladimir-Prelog-Weg 4 8093 Zurich Switzerland +41 44 633 73 27
| |
Collapse
|
13
|
Kotev M, Diaz Gonzalez C. Molecular Dynamics and Other HPC Simulations for Drug Discovery. Methods Mol Biol 2024; 2716:265-291. [PMID: 37702944 DOI: 10.1007/978-1-0716-3449-3_12] [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: 09/14/2023]
Abstract
High performance computing (HPC) is taking an increasingly important place in drug discovery. It makes possible the simulation of complex biochemical systems with high precision in a short time, thanks to the use of sophisticated algorithms. It promotes the advancement of knowledge in fields that are inaccessible or difficult to access through experimentation and it contributes to accelerating the discovery of drugs for unmet medical needs while reducing costs. Herein, we report how computational performance has evolved over the past years, and then we detail three domains where HPC is essential. Molecular dynamics (MD) is commonly used to explore the flexibility of proteins, thus generating a better understanding of different possible approaches to modulate their activity. Modeling and simulation of biopolymer complexes enables the study of protein-protein interactions (PPI) in healthy and disease states, thus helping the identification of targets of pharmacological interest. Virtual screening (VS) also benefits from HPC to predict in a short time, among millions or billions of virtual chemical compounds, the best potential ligands that will be tested in relevant assays to start a rational drug design process.
Collapse
Affiliation(s)
- Martin Kotev
- Evotec SE, Integrated Drug Discovery, Molecular Architects, Campus Curie, Toulouse, France
| | | |
Collapse
|
14
|
Libouban PY, Aci-Sèche S, Gómez-Tamayo JC, Tresadern G, Bonnet P. The Impact of Data on Structure-Based Binding Affinity Predictions Using Deep Neural Networks. Int J Mol Sci 2023; 24:16120. [PMID: 38003312 PMCID: PMC10671244 DOI: 10.3390/ijms242216120] [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: 09/14/2023] [Revised: 10/30/2023] [Accepted: 11/01/2023] [Indexed: 11/26/2023] Open
Abstract
Artificial intelligence (AI) has gained significant traction in the field of drug discovery, with deep learning (DL) algorithms playing a crucial role in predicting protein-ligand binding affinities. Despite advancements in neural network architectures, system representation, and training techniques, the performance of DL affinity prediction has reached a plateau, prompting the question of whether it is truly solved or if the current performance is overly optimistic and reliant on biased, easily predictable data. Like other DL-related problems, this issue seems to stem from the training and test sets used when building the models. In this work, we investigate the impact of several parameters related to the input data on the performance of neural network affinity prediction models. Notably, we identify the size of the binding pocket as a critical factor influencing the performance of our statistical models; furthermore, it is more important to train a model with as much data as possible than to restrict the training to only high-quality datasets. Finally, we also confirm the bias in the typically used current test sets. Therefore, several types of evaluation and benchmarking are required to understand models' decision-making processes and accurately compare the performance of models.
Collapse
Affiliation(s)
- Pierre-Yves Libouban
- Institute of Organic and Analytical Chemistry (ICOA), UMR7311, Université d’Orléans, CNRS, Pôle de Chimie rue de Chartres, 45067 Orléans, CEDEX 2, France; (P.-Y.L.); (S.A.-S.)
| | - Samia Aci-Sèche
- Institute of Organic and Analytical Chemistry (ICOA), UMR7311, Université d’Orléans, CNRS, Pôle de Chimie rue de Chartres, 45067 Orléans, CEDEX 2, France; (P.-Y.L.); (S.A.-S.)
| | - Jose Carlos Gómez-Tamayo
- Computational Chemistry, Janssen Research & Development, Janssen Pharmaceutica N. V., B-2340 Beerse, Belgium; (J.C.G.-T.); (G.T.)
| | - Gary Tresadern
- Computational Chemistry, Janssen Research & Development, Janssen Pharmaceutica N. V., B-2340 Beerse, Belgium; (J.C.G.-T.); (G.T.)
| | - Pascal Bonnet
- Institute of Organic and Analytical Chemistry (ICOA), UMR7311, Université d’Orléans, CNRS, Pôle de Chimie rue de Chartres, 45067 Orléans, CEDEX 2, France; (P.-Y.L.); (S.A.-S.)
| |
Collapse
|
15
|
Bhatt R, Koes DR, Durrant JD. CENsible: Interpretable Insights into Small-Molecule Binding with Context Explanation Networks. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.10.18.562959. [PMID: 37904961 PMCID: PMC10614872 DOI: 10.1101/2023.10.18.562959] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/01/2023]
Abstract
We present a novel and interpretable approach for predicting small-molecule binding affinities using context explanation networks (CENs). Given the specific structure of a protein/ligand complex, our CENsible scoring function uses a deep convolutional neural network to predict the contributions of pre-calculated terms to the overall binding affinity. We show that CENsible can effectively distinguish active vs. inactive compounds for many systems. Its primary benefit over related machine-learning scoring functions, however, is that it retains interpretability, allowing researchers to identify the contribution of each pre-calculated term to the final affinity prediction, with implications for subsequent lead optimization.
Collapse
Affiliation(s)
- Roshni Bhatt
- Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA 15260
- Department of Biological Sciences, University of Pittsburgh, Pittsburgh, PA 15260
| | - David Ryan Koes
- Department of Computational and Systems Biology, University of Pittsburgh, Pittsburgh, PA 15260
| | - Jacob D Durrant
- Department of Biological Sciences, University of Pittsburgh, Pittsburgh, PA 15260
| |
Collapse
|
16
|
Shiota K, Akutsu T. Multi-shelled ECIF: improved extended connectivity interaction features for accurate binding affinity prediction. BIOINFORMATICS ADVANCES 2023; 3:vbad155. [PMID: 37928345 PMCID: PMC10625475 DOI: 10.1093/bioadv/vbad155] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/01/2023] [Revised: 09/20/2023] [Accepted: 10/19/2023] [Indexed: 11/07/2023]
Abstract
Motivation Extended connectivity interaction features (ECIF) is a method developed to predict protein-ligand binding affinity, allowing for detailed atomic representation. It performed very well in terms of Comparative Assessment of Scoring Functions 2016 (CASF-2016) scoring power. However, ECIF has the limitation of not being able to adequately account for interatomic distances. Results To investigate what kind of distance representation is effective for P-L binding affinity prediction, we have developed two algorithms that improved ECIF's feature extraction method to take distance into account. One is multi-shelled ECIF, which takes into account the distance between atoms by dividing the distance between atoms into multiple layers. The other is weighted ECIF, which weights the importance of interactions according to the distance between atoms. A comparison of these two methods shows that multi-shelled ECIF outperforms weighted ECIF and the original ECIF, achieving a CASF-2016 scoring power Pearson correlation coefficient of 0.877. Availability and implementation All the codes and data are available on GitHub (https://github.com/koji11235/MSECIFv2).
Collapse
Affiliation(s)
- Koji Shiota
- Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Kyoto 606-8501, Japan
| | - Tatsuya Akutsu
- Department of Intelligence Science and Technology, Graduate School of Informatics, Kyoto University, Kyoto, Kyoto 606-8501, Japan
| |
Collapse
|
17
|
Naheed S, Din IU, Qamar MU, Rasool N, Ahmad M, Bilal M, Khalid A, Ahmad G, Al-Hussain SA, Zaki MEA. Synthesis, Anti-Bacterial and Molecular Docking Studies of Arylated Butyl 2-Bromoisonicotinate Against Clinical Isolates of ESBL-Producing Escherichia coli ST405 and Methicillin-Resistant Staphylococcus aureus. Infect Drug Resist 2023; 16:5295-5308. [PMID: 37601564 PMCID: PMC10438430 DOI: 10.2147/idr.s407891] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2023] [Accepted: 07/12/2023] [Indexed: 08/22/2023] Open
Abstract
Introduction Global public health concerns include the emergence and spread of methicillin-resistant Staphylococcus aureus (MRSA) and extended-spectrum beta-lactamase Escherichia coli (ESBL-E. coli). These pathogens cause infections that are difficult to treat, which can have fatal outcomes and require lengthy hospital stays. As a result, we created butyl 2-bromoisonicotinate and tested its antibacterial effectiveness against the ESBL-E. coli ST 405 and MRSA pathogens. Natural product discovery is complemented by synthetic compound synthesis because of the latter's potential for superior characteristics, target specificity, scalability, intellectual advantages, and chemical diversity. Because of this, the potential for discovering new medicinal compounds is increased, and the constraints placed on natural sources are overcome. Natural items are tough to obtain since they are hard to isolate and synthesize. Therefore, modern science is actively searching for small molecules as therapeutic agents by applying sustainable techniques that can be commercialized. Methods Two patients' blood samples were taken, and the BACTEC/Alert system was used to process them. On blood and MacConkey agar, the positive samples were subcultured and incubated aerobically at 37 °C. Using the VITEK 2 compact system, the isolates were subjected to isolate identification and MIC. MLST of the ESBL-E. coli was performed by PCR. Additionally, Fischer esterification was used to create butyl 2-bromoisonicotinate in excellent yields. A commercially available palladium catalyst was then used to arylate the compound, resulting in medium to good yields of arylated butyl 2-bromoisonicotinates. Using the agar well diffusion assay and the micro-broth dilution method, we assessed the in-vitro activities of the synthesized molecules (3, 5a-h) against clinically isolated ESBL-E. coli ST405, and MRSA. A molecular operating environment was used to carry out in silico validation of the synthesized compounds' binding to the active site and to evaluate the stability of their molecular interactions with the target E. coli 2Y2T protein. Results MRSA and ESBL-producing E. coli were identified as the two clinical isolates. While MRSA was also resistant to beta-lactam drugs and least resistant to vancomycin, ESBL-producing E. coli belonged to ST405 and was resistant to cephalosporins and sensitive to carbapenems. Good yields of the desired compounds were produced by our effective and economical synthesis. By using a micro-broth dilution assay, the Molecules (3, 5a, and 5d) were most effective against both resistant strains. The Molecules (3, 5a, 5b, and 5d) also displayed good binding energies. Conclusion The butyl 2-bromoisonicotinate displayed antibacterial efficacy against ESBL-producing E. coli ST405 and MRSA strains. After the in-vivo trial, this substance might offer an alternative therapeutic option.
Collapse
Affiliation(s)
- Shazia Naheed
- Department of Chemistry, Government College University Faisalabad, Faisalabad, 38000, Pakistan
| | - Irum Umar Din
- Department of Chemistry, Government College University Faisalabad, Faisalabad, 38000, Pakistan
| | - Muhammad Usman Qamar
- Institute of Microbiology, Faculty of Life Sciences, Government College University, Faisalabad, 38000, Pakistan
| | - Nasir Rasool
- Department of Chemistry, Government College University Faisalabad, Faisalabad, 38000, Pakistan
| | - Matloob Ahmad
- Department of Chemistry, Government College University Faisalabad, Faisalabad, 38000, Pakistan
| | - Muhammad Bilal
- Department of Chemistry, Government College University Faisalabad, Faisalabad, 38000, Pakistan
| | - Aqsa Khalid
- School of Interdisciplinary Engineering & Science (SINES), National University of Sciences and Technology (NUST), Islamabad, 44000, Pakistan
| | - Gulraiz Ahmad
- Department of Chemistry, Government College University Faisalabad, Faisalabad, 38000, Pakistan
| | - Sami A Al-Hussain
- Department of Chemistry, Faculty of Science, Imam Mohammad Ibn Saud Islamic University, Riyad, 11623, Saudi Arabia
| | - Magdi E A Zaki
- Department of Chemistry, Faculty of Science, Imam Mohammad Ibn Saud Islamic University, Riyad, 11623, Saudi Arabia
| |
Collapse
|
18
|
Abdel-Rehim A, Orhobor O, Hang L, Ni H, King RD. Protein-ligand binding affinity prediction exploiting sequence constituent homology. Bioinformatics 2023; 39:btad502. [PMID: 37572302 PMCID: PMC10463547 DOI: 10.1093/bioinformatics/btad502] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Revised: 07/10/2023] [Accepted: 08/11/2023] [Indexed: 08/14/2023] Open
Abstract
MOTIVATION Molecular docking is a commonly used approach for estimating binding conformations and their resultant binding affinities. Machine learning has been successfully deployed to enhance such affinity estimations. Many methods of varying complexity have been developed making use of some or all the spatial and categorical information available in these structures. The evaluation of such methods has mainly been carried out using datasets from PDBbind. Particularly the Comparative Assessment of Scoring Functions (CASF) 2007, 2013, and 2016 datasets with dedicated test sets. This work demonstrates that only a small number of simple descriptors is necessary to efficiently estimate binding affinity for these complexes without the need to know the exact binding conformation of a ligand. RESULTS The developed approach of using a small number of ligand and protein descriptors in conjunction with gradient boosting trees demonstrates high performance on the CASF datasets. This includes the commonly used benchmark CASF2016 where it appears to perform better than any other approach. This methodology is also useful for datasets where the spatial relationship between the ligand and protein is unknown as demonstrated using a large ChEMBL-derived dataset. AVAILABILITY AND IMPLEMENTATION Code and data uploaded to https://github.com/abbiAR/PLBAffinity.
Collapse
Affiliation(s)
- Abbi Abdel-Rehim
- Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge CB3 0AS, United Kingdom
| | | | - Lou Hang
- Department of Mathematics, University College London, London WC1H 0AY, United Kingdom
| | - Hao Ni
- Department of Mathematics, University College London, London WC1H 0AY, United Kingdom
- The Alan Turing Institute, London NW1 2DB, United Kingdom
| | - Ross D King
- Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge CB3 0AS, United Kingdom
- The Alan Turing Institute, London NW1 2DB, United Kingdom
- Department of Biology and Biological Engineering, Chalmers University of Technology, Gothenburg 412 96, Sweden
- Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg 412 96, Sweden
| |
Collapse
|
19
|
Graef J, Ehrt C, Rarey M. Binding Site Detection Remastered: Enabling Fast, Robust, and Reliable Binding Site Detection and Descriptor Calculation with DoGSite3. J Chem Inf Model 2023; 63:3128-3137. [PMID: 37130052 DOI: 10.1021/acs.jcim.3c00336] [Citation(s) in RCA: 14] [Impact Index Per Article: 14.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/03/2023]
Abstract
Binding site prediction on protein structures is a crucial step in early phase drug discovery whenever experimental or predicted structure models are involved. DoGSite belongs to the widely used tools for this task. It is a grid-based method that uses a Difference-of-Gaussian filter to detect cavities on the protein surface. We recently reimplemented the first version of this method, released in 2010, focusing on improved binding site detection in the presence of ligands and optimized parameters for more robust, reliable, and fast predictions and binding site descriptor calculations. Here, we introduce the new version, DoGSite3, compare it to its predecessor, and re-evaluate DoGSite on published data sets for a large-scale comparative performance evaluation.
Collapse
Affiliation(s)
- Joel Graef
- Universität Hamburg, ZBH - Center for Bioinformatics, Bundesstraße 43, 20146 Hamburg, Germany
| | - Christiane Ehrt
- Universität Hamburg, ZBH - Center for Bioinformatics, Bundesstraße 43, 20146 Hamburg, Germany
| | - Matthias Rarey
- Universität Hamburg, ZBH - Center for Bioinformatics, Bundesstraße 43, 20146 Hamburg, Germany
| |
Collapse
|
20
|
Rayka M, Firouzi R. GB-score: Minimally designed machine learning scoring function based on distance-weighted interatomic contact features. Mol Inform 2023; 42:e2200135. [PMID: 36722733 DOI: 10.1002/minf.202200135] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2022] [Revised: 11/24/2022] [Accepted: 11/28/2022] [Indexed: 02/02/2023]
Abstract
In recent years, thanks to advances in computer hardware and dataset availability, data-driven approaches (like machine learning) have become one of the essential parts of the drug design framework to accelerate drug discovery procedures. Constructing a new scoring function, a function that can predict the binding score for a generated protein-ligand pose during docking procedure or a crystal complex, based on machine and deep learning has become an active research area in computer-aided drug design. GB-Score is a state-of-the-art machine learning-based scoring function that utilizes distance-weighted interatomic contact features, PDBbind-v2019 general set, and Gradient Boosting Trees algorithm to the binding affinity prediction. The distance-weighted interatomic contact featurization method used the distance between different ligand and protein atom types for numerical representation of the protein-ligand complex. GB-Score attains Pearson's correlation 0.862 and RMSE 1.190 on the CASF-2016 benchmark test in the scoring power metric. GB-Score's codes are freely available on the web at https://github.com/miladrayka/GB_Score.
Collapse
Affiliation(s)
- Milad Rayka
- Department of Physical Chemistry, Chemistry and Chemical Engineering Research Center of Iran, Tehran, Iran
| | - Rohoullah Firouzi
- Department of Physical Chemistry, Chemistry and Chemical Engineering Research Center of Iran, Tehran, Iran
| |
Collapse
|
21
|
New avenues in artificial-intelligence-assisted drug discovery. Drug Discov Today 2023; 28:103516. [PMID: 36736583 DOI: 10.1016/j.drudis.2023.103516] [Citation(s) in RCA: 23] [Impact Index Per Article: 23.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2022] [Revised: 12/08/2022] [Accepted: 01/26/2023] [Indexed: 02/05/2023]
Abstract
Over the past decade, the amount of biomedical data available has grown at unprecedented rates. Increased automation technology and larger data volumes have encouraged the use of machine learning (ML) or artificial intelligence (AI) techniques for mining such data and extracting useful patterns. Because the identification of chemical entities with desired biological activity is a crucial task in drug discovery, AI technologies have the potential to accelerate this process and support decision making. In addition, the advent of deep learning (DL) has shown great promise in addressing diverse problems in drug discovery, such as de novo molecular design. Herein, we will appraise the current state-of-the-art in AI-assisted drug discovery, discussing the recent applications covering generative models for chemical structure generation, scoring functions to improve binding affinity and pose prediction, and molecular dynamics to assist in the parametrization, featurization and generalization tasks. Finally, we will discuss current hurdles and the strategies to overcome them, as well as potential future directions.
Collapse
|
22
|
Rzęsikowska K, Kalinowska-Tłuścik J, Krawczuk A. Hierarchical analysis of the target-based scoring function modification for the example of selected class A GPCRs. Phys Chem Chem Phys 2023; 25:3513-3520. [PMID: 36637161 DOI: 10.1039/d2cp04671g] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/23/2022]
Abstract
Computational methods, especially molecular docking-based calculations, have become indispensable in the modern drug discovery workflow. The constantly increasing chemical space requires fast, robust but most of all highly predictive methods to search for new bioactive agents. Thus, the scoring function (SF) is a useful and broadly applied energy-based element of docking software, allowing quick and effective evaluation of a ligand's propensity to bind to selected protein targets. Despite many spectacular successes of molecular docking applications in virtual screening (VS), the obtained results are often far from ideal, leading to incorrect selection of hit molecules and poor pose prediction. In our study we focused on docking calculation for the selected class A G-protein coupled receptors (GPCRs), with experimentally determined 3D structures and a sufficient set of known ligands with affinity values reported in the ChEMBL database. Our goal is to investigate how much the energy-based scoring function for this particular target class changes when changing from the default to the re-estimated weighting scheme on the specified energy terms in the SF definition. Additionally, we want to verify if indeed more accurate results are obtained when considering different levels of the biological hierarchy, namely: the whole class A GPCRs, sub-subfamilies, or just the individual proteins while applying default or specifically designed weighting coefficients. The performed calculation and evaluation factor values suggest a significant improvement of docking results for the designed SF definition. This individual approach improves the accuracy of binding affinity prediction and active compound recognition. The designed scoring function for classes, sub-subfamilies, or proteins leads to a significant improvement of molecular docking performance, especially at the level of individual proteins. Our results show that to increase the efficiency and predictive power of molecular docking calculations applied in classical VS, the strategy based on the individual approach for scoring function definition for selected proteins should be considered.
Collapse
Affiliation(s)
- Katarzyna Rzęsikowska
- Department of Crystal Chemistry and Crystal Physics, Faculty of Chemistry, Jagiellonian University, Gronostajowa 2, 30-387 Kraków, Poland.
| | - Justyna Kalinowska-Tłuścik
- Department of Crystal Chemistry and Crystal Physics, Faculty of Chemistry, Jagiellonian University, Gronostajowa 2, 30-387 Kraków, Poland.
| | - Anna Krawczuk
- Institute of Inorganic Chemistry, Georg-August University, Tammannstrasse 4, 37077, Goettingen, Germany.
| |
Collapse
|
23
|
Cope KR, Prates ET, Miller JI, Demerdash ON, Shah M, Kainer D, Cliff A, Sullivan KA, Cashman M, Lane M, Matthiadis A, Labbé J, Tschaplinski TJ, Jacobson DA, Kalluri UC. Exploring the role of plant lysin motif receptor-like kinases in regulating plant-microbe interactions in the bioenergy crop Populus. Comput Struct Biotechnol J 2022; 21:1122-1139. [PMID: 36789259 PMCID: PMC9900275 DOI: 10.1016/j.csbj.2022.12.052] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/02/2022] [Revised: 12/18/2022] [Accepted: 12/30/2022] [Indexed: 01/02/2023] Open
Abstract
For plants, distinguishing between mutualistic and pathogenic microbes is a matter of survival. All microbes contain microbe-associated molecular patterns (MAMPs) that are perceived by plant pattern recognition receptors (PRRs). Lysin motif receptor-like kinases (LysM-RLKs) are PRRs attuned for binding and triggering a response to specific MAMPs, including chitin oligomers (COs) in fungi, lipo-chitooligosaccharides (LCOs), which are produced by mycorrhizal fungi and nitrogen-fixing rhizobial bacteria, and peptidoglycan in bacteria. The identification and characterization of LysM-RLKs in candidate bioenergy crops including Populus are limited compared to other model plant species, thus inhibiting our ability to both understand and engineer microbe-mediated gains in plant productivity. As such, we performed a sequence analysis of LysM-RLKs in the Populus genome and predicted their function based on phylogenetic analysis with known LysM-RLKs. Then, using predictive models, molecular dynamics simulations, and comparative structural analysis with previously characterized CO and LCO plant receptors, we identified probable ligand-binding sites in Populus LysM-RLKs. Using several machine learning models, we predicted remarkably consistent binding affinity rankings of Populus proteins to CO. In addition, we used a modified Random Walk with Restart network-topology based approach to identify a subset of Populus LysM-RLKs that are functionally related and propose a corresponding signal transduction cascade. Our findings provide the first look into the role of LysM-RLKs in Populus-microbe interactions and establish a crucial jumping-off point for future research efforts to understand specificity and redundancy in microbial perception mechanisms.
Collapse
Affiliation(s)
- Kevin R. Cope
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
| | - Erica T. Prates
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
| | - John I. Miller
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
| | - Omar N.A. Demerdash
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
| | - Manesh Shah
- Genome Science and Technology, The University of Tennessee–Knoxville, Knoxville, TN 37996, USA
| | - David Kainer
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
| | - Ashley Cliff
- The Bredesen Center for Interdisciplinary Research and Graduate Education, University of Tennessee Knoxville, Knoxville 37996, USA
| | - Kyle A. Sullivan
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
| | - Mikaela Cashman
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
| | - Matthew Lane
- The Bredesen Center for Interdisciplinary Research and Graduate Education, University of Tennessee Knoxville, Knoxville 37996, USA
| | - Anna Matthiadis
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
| | - Jesse Labbé
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA
| | | | - Daniel A. Jacobson
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA,The Bredesen Center for Interdisciplinary Research and Graduate Education, University of Tennessee Knoxville, Knoxville 37996, USA
| | - Udaya C. Kalluri
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, TN 37831, USA,Corresponding author.
| |
Collapse
|
24
|
Blanes-Mira C, Fernández-Aguado P, de Andrés-López J, Fernández-Carvajal A, Ferrer-Montiel A, Fernández-Ballester G. Comprehensive Survey of Consensus Docking for High-Throughput Virtual Screening. Molecules 2022; 28:molecules28010175. [PMID: 36615367 PMCID: PMC9821981 DOI: 10.3390/molecules28010175] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2022] [Revised: 12/19/2022] [Accepted: 12/21/2022] [Indexed: 12/28/2022] Open
Abstract
The rapid advances of 3D techniques for the structural determination of proteins and the development of numerous computational methods and strategies have led to identifying highly active compounds in computer drug design. Molecular docking is a method widely used in high-throughput virtual screening campaigns to filter potential ligands targeted to proteins. A great variety of docking programs are currently available, which differ in the algorithms and approaches used to predict the binding mode and the affinity of the ligand. All programs heavily rely on scoring functions to accurately predict ligand binding affinity, and despite differences in performance, none of these docking programs is preferable to the others. To overcome this problem, consensus scoring methods improve the outcome of virtual screening by averaging the rank or score of individual molecules obtained from different docking programs. The successful application of consensus docking in high-throughput virtual screening highlights the need to optimize the predictive power of molecular docking methods.
Collapse
|
25
|
Guo Z, Yamaguchi R. Machine learning methods for protein-protein binding affinity prediction in protein design. FRONTIERS IN BIOINFORMATICS 2022; 2:1065703. [PMID: 36591334 PMCID: PMC9800603 DOI: 10.3389/fbinf.2022.1065703] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/10/2022] [Accepted: 12/01/2022] [Indexed: 12/23/2022] Open
Abstract
Protein-protein interactions govern a wide range of biological activity. A proper estimation of the protein-protein binding affinity is vital to design proteins with high specificity and binding affinity toward a target protein, which has a variety of applications including antibody design in immunotherapy, enzyme engineering for reaction optimization, and construction of biosensors. However, experimental and theoretical modelling methods are time-consuming, hinder the exploration of the entire protein space, and deter the identification of optimal proteins that meet the requirements of practical applications. In recent years, the rapid development in machine learning methods for protein-protein binding affinity prediction has revealed the potential of a paradigm shift in protein design. Here, we review the prediction methods and associated datasets and discuss the requirements and construction methods of binding affinity prediction models for protein design.
Collapse
Affiliation(s)
- Zhongliang Guo
- Division of Cancer Systems Biology, Aichi Cancer Center Research Institute, Nagoya, Aichi, Japan
| | - Rui Yamaguchi
- Division of Cancer Systems Biology, Aichi Cancer Center Research Institute, Nagoya, Aichi, Japan,Division of Cancer Informatics, Nagoya University Graduate School of Medicine, Nagoya, Aichi, Japan,*Correspondence: Rui Yamaguchi,
| |
Collapse
|
26
|
Kawama K, Fukushima Y, Ikeguchi M, Ohta M, Yoshidome T. gr Predictor: A Deep Learning Model for Predicting the Hydration Structures around Proteins. J Chem Inf Model 2022; 62:4460-4473. [PMID: 36068974 DOI: 10.1021/acs.jcim.2c00987] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Abstract
Among the factors affecting biological processes such as protein folding and ligand binding, hydration, which is represented by a three-dimensional water site distribution function around the protein, is crucial. The typical methods for computing the distribution functions, including molecular dynamics simulations and the three-dimensional reference interaction site model (3D-RISM) theory, require a long computation time ranging from hours to tens of hours. Here, we propose a deep learning (DL) model that rapidly estimates the distribution functions around proteins obtained using the 3D-RISM theory from the protein 3D structure. The distribution functions predicted using our DL model are in good agreement with those obtained using the 3D-RISM theory. Particularly, the coefficient of determination between the distribution function obtained by the DL model and that obtained using the 3D-RISM theory is approximately 0.98. Furthermore, using a graphics processing unit, the prediction by the DL model is completed in less than 1 min, more than 2 orders of magnitude faster than the calculation time of the 3D-RISM theory. The position of water molecules around the protein was estimated based on the distribution function obtained by our DL model, and the position of waters estimated by our DL model was in good agreement with that of water molecules estimated using the 3D-RISM theory and of crystallographic waters. Therefore, our DL model provides a practical and efficient way to calculate the three-dimensional water site distribution functions and to estimate the position of water molecules around the protein. The program called "gr Predictor" is available under the GNU General Public License from https://github.com/YoshidomeGroup-Hydration/gr-predictor.
Collapse
Affiliation(s)
- Kosuke Kawama
- Department of Applied Physics, Graduate School of Engineering, Tohoku University, Sendai 980-8579, Japan
| | - Yusaku Fukushima
- Department of Applied Physics, Graduate School of Engineering, Tohoku University, Sendai 980-8579, Japan
| | - Mitsunori Ikeguchi
- AI-Driven Drug Discovery Collaborative Unit, HPC- and AI-Driven Drug Development Platform Division, Center for Computational Science, RIKEN, 1-7-29, Suehiro-cho, Tsurumi-ku, Yokohama 230-0045, Japan.,Graduate School of Medical Life Science, Yokohama City University, 1-7-29, Suehiro-cho, Tsurumi-ku, Yokohama 230-0045, Japan
| | - Masateru Ohta
- AI-Driven Drug Discovery Collaborative Unit, HPC- and AI-Driven Drug Development Platform Division, Center for Computational Science, RIKEN, 1-7-29, Suehiro-cho, Tsurumi-ku, Yokohama 230-0045, Japan
| | - Takashi Yoshidome
- Department of Applied Physics, Graduate School of Engineering, Tohoku University, Sendai 980-8579, Japan
| |
Collapse
|
27
|
Liu SH, Xiao Z, Mishra SK, Mitchell JC, Smith JC, Quarles LD, Petridis L. Identification of Small-Molecule Inhibitors of Fibroblast Growth Factor 23 Signaling via In Silico Hot Spot Prediction and Molecular Docking to α-Klotho. J Chem Inf Model 2022; 62:3627-3637. [PMID: 35868851 PMCID: PMC10018682 DOI: 10.1021/acs.jcim.2c00633] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
Fibroblast growth factor 23 (FGF23) is a therapeutic target for treating hereditary and acquired hypophosphatemic disorders, such as X-linked hypophosphatemic (XLH) rickets and tumor-induced osteomalacia (TIO), respectively. FGF23-induced hypophosphatemia is mediated by signaling through a ternary complex formed by FGF23, the FGF receptor (FGFR), and α-Klotho. Currently, disorders of excess FGF23 are treated with an FGF23-blocking antibody, burosumab. Small-molecule drugs that disrupt protein/protein interactions necessary for the ternary complex formation offer an alternative to disrupting FGF23 signaling. In this study, the FGF23:α-Klotho interface was targeted to identify small-molecule protein/protein interaction inhibitors since it was computationally predicted to have a large fraction of hot spots and two druggable residues on α-Klotho. We further identified Tyr433 on the KL1 domain of α-Klotho as a promising hot spot and α-Klotho as an appropriate drug-binding target at this interface. Subsequently, we performed in silico docking of ∼5.5 million compounds from the ZINC database to the interface region of α-Klotho from the ternary crystal structure. Following docking, 24 and 20 compounds were in the final list based on the lowest binding free energies to α-Klotho and the largest number of contacts with Tyr433, respectively. Five compounds were assessed experimentally by their FGF23-mediated extracellular signal-regulated kinase (ERK) activities in vitro, and two of these reduced activities significantly. Both these compounds were predicted to have favorable binding affinities to α-Klotho but not have a large number of contacts with the hot spot Tyr433. ZINC12409120 was found experimentally to disrupt FGF23:α-Klotho interaction to reduce FGF23-mediated ERK activities by 70% and have a half maximal inhibitory concentration (IC50) of 5.0 ± 0.23 μM. Molecular dynamics (MD) simulations of the ZINC12409120:α-Klotho complex starting from in silico docking poses reveal that the ligand exhibits contacts with residues on the KL1 domain, the KL1-KL2 linker, and the KL2 domain of α-Klotho simultaneously, thereby possibly disrupting the regular function of α-Klotho and impeding FGF23:α-Klotho interaction. ZINC12409120 is a candidate for lead optimization.
Collapse
Affiliation(s)
- Shih-Hsien Liu
- UT/ORNL Center for Molecular Biophysics, Oak Ridge National Laboratory, Oak Ridge, Tennessee37831, United States
- Department of Biochemistry and Cellular and Molecular Biology, University of Tennessee, Knoxville, Tennessee37996, United States
| | - Zhousheng Xiao
- Department of Medicine, College of Medicine, University of Tennessee Health Science Center, Memphis, Tennessee38163, United States
| | - Sambit K Mishra
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee37831, United States
| | - Julie C Mitchell
- Biosciences Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee37831, United States
| | - Jeremy C Smith
- UT/ORNL Center for Molecular Biophysics, Oak Ridge National Laboratory, Oak Ridge, Tennessee37831, United States
- Department of Biochemistry and Cellular and Molecular Biology, University of Tennessee, Knoxville, Tennessee37996, United States
| | - L Darryl Quarles
- Department of Medicine, College of Medicine, University of Tennessee Health Science Center, Memphis, Tennessee38163, United States
| | - Loukas Petridis
- UT/ORNL Center for Molecular Biophysics, Oak Ridge National Laboratory, Oak Ridge, Tennessee37831, United States
- Department of Biochemistry and Cellular and Molecular Biology, University of Tennessee, Knoxville, Tennessee37996, United States
| |
Collapse
|
28
|
Menezes F, Popowicz GM. ULYSSES: An Efficient and Easy to Use Semiempirical Library for C+. J Chem Inf Model 2022; 62:3685-3694. [PMID: 35930308 DOI: 10.1021/acs.jcim.2c00757] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
We introduce ULYSSES, a user-friendly and robust C++ library for semiempirical quantum chemical calculations. In its current version, ULYSSES is equipped with a large set of different semiempirical models, most of which are based on the Neglect of Diatomic Differential Overlap (NDDO) approximation. Empirical corrections for dispersion and hydrogen bonding are available for most methods, so that higher quality is achieved in the calculation of energies of nonbonded complexes. The library is furthermore equipped with geometry optimization, as well as modules for calculating molecular properties of general interest. Ideal gas thermodynamics is available and allows single structure as well as conformer (multistructure) averaged properties to be calculated. We offer the possibility to use several vibrational partition functions according to the nature of interactions being studied: for covalent systems, the traditional harmonic oscillator approximation is available; for nonbonded complexes, we systematically extended the partition function proposed by Grimme for all thermodynamic functions. The library is also capable of running Born-Oppenheimer molecular dynamics.
Collapse
Affiliation(s)
- Filipe Menezes
- Institute of Structural Biology, Helmholtz Zentrum Muenchen, Ingolstaedter Landstrasse 1, 85764 Neuherberg, Germany
| | - Grzegorz M Popowicz
- Institute of Structural Biology, Helmholtz Zentrum Muenchen, Ingolstaedter Landstrasse 1, 85764 Neuherberg, Germany
| |
Collapse
|
29
|
Meli R, Morris GM, Biggin PC. Scoring Functions for Protein-Ligand Binding Affinity Prediction using Structure-Based Deep Learning: A Review. FRONTIERS IN BIOINFORMATICS 2022; 2:885983. [PMID: 36187180 PMCID: PMC7613667 DOI: 10.3389/fbinf.2022.885983] [Citation(s) in RCA: 20] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/28/2022] [Accepted: 05/11/2022] [Indexed: 01/01/2023] Open
Abstract
The rapid and accurate in silico prediction of protein-ligand binding free energies or binding affinities has the potential to transform drug discovery. In recent years, there has been a rapid growth of interest in deep learning methods for the prediction of protein-ligand binding affinities based on the structural information of protein-ligand complexes. These structure-based scoring functions often obtain better results than classical scoring functions when applied within their applicability domain. Here we review structure-based scoring functions for binding affinity prediction based on deep learning, focussing on different types of architectures, featurization strategies, data sets, methods for training and evaluation, and the role of explainable artificial intelligence in building useful models for real drug-discovery applications.
Collapse
Affiliation(s)
- Rocco Meli
- Department of Biochemistry, University of Oxford, Oxford, United Kingdom
| | - Garrett M. Morris
- Department of Statistics, University of Oxford, Oxford, United Kingdom
| | - Philip C. Biggin
- Department of Biochemistry, University of Oxford, Oxford, United Kingdom
| |
Collapse
|
30
|
Fujimoto KJ, Minami S, Yanai T. Machine-Learning- and Knowledge-Based Scoring Functions Incorporating Ligand and Protein Fingerprints. ACS OMEGA 2022; 7:19030-19039. [PMID: 35694525 PMCID: PMC9178954 DOI: 10.1021/acsomega.2c02822] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 05/06/2022] [Accepted: 05/12/2022] [Indexed: 06/15/2023]
Abstract
We propose a novel machine-learning-based scoring function for drug discovery that incorporates ligand and protein structural information into a knowledge-based PMF score. Molecular docking, a simulation method for structure-based drug design (SBDD), is expected to reduce the enormous costs associated with conventional experimental methods in terms of rational drug discovery. Molecular docking has two main purposes: to predict ligand-binding structures for target proteins and to predict protein-ligand binding affinity. Currently available programs of molecular docking offer an accurate prediction of ligand binding structures for many systems. However, the accurate prediction of binding affinity remains challenging. In this study, we developed a new scoring function that incorporates fingerprints representing ligand and protein structures as descriptors in the PMF score. Here, regression analysis of the scoring function was performed using the following machine learning techniques: least absolute shrinkage and selection operator (LASSO) and light gradient boosting machine (LightGBM). The results on a test data set showed that the binding affinity delivered by the newly developed scoring function has a Pearson correlation coefficient of 0.79 with the experimental value, which surpasses that of the conventional scoring functions. Further analysis provided a chemical understanding of the descriptors that contributed significantly to the improvement in prediction accuracy. Our approach and findings are useful for rational drug discovery.
Collapse
Affiliation(s)
- Kazuhiro J. Fujimoto
- Institute
of Transformative Bio-Molecules (WPI-ITbM), Nagoya University, Furocho, Chikusa, Nagoya 464-8601, Japan
- Department
of Chemistry, Graduate School of Science, Nagoya University, Furocho, Chikusa, Nagoya 464-8601, Japan
| | - Shota Minami
- Department
of Chemistry, Graduate School of Science, Nagoya University, Furocho, Chikusa, Nagoya 464-8601, Japan
| | - Takeshi Yanai
- Institute
of Transformative Bio-Molecules (WPI-ITbM), Nagoya University, Furocho, Chikusa, Nagoya 464-8601, Japan
- Department
of Chemistry, Graduate School of Science, Nagoya University, Furocho, Chikusa, Nagoya 464-8601, Japan
| |
Collapse
|
31
|
Yau MQ, Loo JSE. Consensus scoring evaluated using the GPCR-Bench dataset: Reconsidering the role of MM/GBSA. J Comput Aided Mol Des 2022; 36:427-441. [PMID: 35581483 DOI: 10.1007/s10822-022-00456-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2021] [Accepted: 04/28/2022] [Indexed: 01/09/2023]
Abstract
The recent availability of large numbers of GPCR crystal structures has provided an unprecedented opportunity to evaluate their performance in virtual screening protocols using established benchmarking datasets. In this study, we evaluated the ability of MM/GBSA in consensus scoring-based virtual screening enrichment together with nine classical scoring functions, using the GPCR-Bench dataset consisting of 24 GPCR crystal structures and 254,646 actives and decoys. While the performance of consensus scoring was modest overall, combinations which included MM/GBSA performed relatively well compared to combinations of classical scoring functions. Combinations of MM/GBSA and good-performing scoring functions provided the highest proportion of improvements, with improvements observed in 32% and 19% of all combinations across all targets at the EF1% and EF5% levels respectively. Combinations of MM/GBSA and poor-performing scoring functions still outperformed classical scoring functions, with improvements observed in 26% and 17% of all combinations at the EF1% and EF5% levels. In comparison, only 14-22% and 6-11% of combinations of classical scoring functions produced improvements at EF1% and EF5% respectively. Efforts to improve performance by increasing the number of scoring functions in consensus scoring to three were mostly ineffective. We also observed that consensus scoring performed better for individual scoring functions possessing initially low enrichment factors, potentially implying their benefits are more relevant in such scenarios. Overall, this study demonstrated the first implementation of MM/GBSA in consensus scoring using the GPCR-Bench dataset and could provide a valuable benchmark of the performance of MM/GBSA in comparison to classical scoring functions in consensus scoring for GPCRs.
Collapse
Affiliation(s)
- Mei Qian Yau
- Centre for Drug Discovery and Molecular Pharmacology, Faculty of Health and Medical Sciences, Taylor's University, No. 1 Jalan Taylor's, 47500, Subang Jaya, Selangor, Malaysia.,School of Pharmacy, Faculty of Health and Medical Sciences, Taylor's University, No. 1 Jalan Taylors, 47500, Subang Jaya, Selangor, Malaysia
| | - Jason S E Loo
- Centre for Drug Discovery and Molecular Pharmacology, Faculty of Health and Medical Sciences, Taylor's University, No. 1 Jalan Taylor's, 47500, Subang Jaya, Selangor, Malaysia. .,School of Pharmacy, Faculty of Health and Medical Sciences, Taylor's University, No. 1 Jalan Taylors, 47500, Subang Jaya, Selangor, Malaysia.
| |
Collapse
|
32
|
Yang C, Zhang Y. Delta Machine Learning to Improve Scoring-Ranking-Screening Performances of Protein-Ligand Scoring Functions. J Chem Inf Model 2022; 62:2696-2712. [PMID: 35579568 DOI: 10.1021/acs.jcim.2c00485] [Citation(s) in RCA: 22] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/01/2023]
Abstract
Protein-ligand scoring functions are widely used in structure-based drug design for fast evaluation of protein-ligand interactions, and it is of strong interest to develop scoring functions with machine-learning approaches. In this work, by expanding the training set, developing physically meaningful features, employing our recently developed linear empirical scoring function Lin_F9 (Yang, C. J. Chem. Inf. Model. 2021, 61, 4630-4644) as the baseline, and applying extreme gradient boosting (XGBoost) with Δ-machine learning, we have further improved the robustness and applicability of machine-learning scoring functions. Besides the top performances for scoring-ranking-screening power tests of the CASF-2016 benchmark, the new scoring function ΔLin_F9XGB also achieves superior scoring and ranking performances in different structure types that mimic real docking applications. The scoring powers of ΔLin_F9XGB for locally optimized poses, flexible redocked poses, and ensemble docked poses of the CASF-2016 core set achieve Pearson's correlation coefficient (R) values of 0.853, 0.839, and 0.813, respectively. In addition, the large-scale docking-based virtual screening test on the LIT-PCBA data set demonstrates the reliability and robustness of ΔLin_F9XGB in virtual screening application. The ΔLin_F9XGB scoring function and its code are freely available on the web at (https://yzhang.hpc.nyu.edu/Delta_LinF9_XGB).
Collapse
Affiliation(s)
- Chao Yang
- Department of Chemistry, New York University, New York, New York 10003, United States
| | - Yingkai Zhang
- Department of Chemistry, New York University, New York, New York 10003, United States.,NYU-ECNU Center for Computational Chemistry at NYU Shanghai, Shanghai 200062, China
| |
Collapse
|
33
|
Orhobor OI, Rehim AA, Lou H, Ni H, King RD. A simple spatial extension to the extended connectivity interaction features for binding affinity prediction. ROYAL SOCIETY OPEN SCIENCE 2022; 9:211745. [PMID: 35573039 PMCID: PMC9066299 DOI: 10.1098/rsos.211745] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/08/2021] [Accepted: 04/13/2022] [Indexed: 05/03/2023]
Abstract
The representation of the protein-ligand complexes used in building machine learning models play an important role in the accuracy of binding affinity prediction. The Extended Connectivity Interaction Features (ECIF) is one such representation. We report that (i) including the discretized distances between protein-ligand atom pairs in the ECIF scheme improves predictive accuracy, and (ii) in an evaluation using gradient boosted trees, we found that the resampling method used in selecting the best hyperparameters has a strong effect on predictive performance, especially for benchmarking purposes.
Collapse
Affiliation(s)
| | - Abbi Abdel Rehim
- Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge, UK
| | - Hang Lou
- Department of Mathematics, University College London, London, UK
| | - Hao Ni
- Department of Mathematics, University College London, London, UK
- The Alan Turing Institute, London, UK
| | - Ross D. King
- Department of Chemical Engineering and Biotechnology, University of Cambridge, Cambridge, UK
- Department of Biology and Biological Engineering, Chalmers University of Technology, Göteborg, Sweden
- The Alan Turing Institute, London, UK
| |
Collapse
|
34
|
Zhou Y, Jiang Y, Chen SJ. RNA-ligand molecular docking: advances and challenges. WILEY INTERDISCIPLINARY REVIEWS. COMPUTATIONAL MOLECULAR SCIENCE 2022; 12:e1571. [PMID: 37293430 PMCID: PMC10250017 DOI: 10.1002/wcms.1571] [Citation(s) in RCA: 23] [Impact Index Per Article: 11.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/26/2021] [Accepted: 07/20/2021] [Indexed: 12/16/2022]
Abstract
With rapid advances in computer algorithms and hardware, fast and accurate virtual screening has led to a drastic acceleration in selecting potent small molecules as drug candidates. Computational modeling of RNA-small molecule interactions has become an indispensable tool for RNA-targeted drug discovery. The current models for RNA-ligand binding have mainly focused on the docking-and-scoring method. Accurate docking and scoring should tackle four crucial problems: (1) conformational flexibility of ligand, (2) conformational flexibility of RNA, (3) efficient sampling of binding sites and binding poses, and (4) accurate scoring of different binding modes. Moreover, compared with the problem of protein-ligand docking, predicting ligand binding to RNA, a negatively charged polymer, is further complicated by additional effects such as metal ion effects. Thermodynamic models based on physics-based and knowledge-based scoring functions have shown highly encouraging success in predicting ligand binding poses and binding affinities. Recently, kinetic models for ligand binding have further suggested that including dissociation kinetics (residence time) in ligand docking would result in improved performance in estimating in vivo drug efficacy. More recently, the rise of deep-learning approaches has led to new tools for predicting RNA-small molecule binding. In this review, we present an overview of the recently developed computational methods for RNA-ligand docking and their advantages and disadvantages.
Collapse
Affiliation(s)
- Yuanzhe Zhou
- Department of Physics and Astronomy, Department of Biochemistry, Institute of Data Sciences and Informatics, University of Missouri, Columbia, MO 65211-7010, USA
| | - Yangwei Jiang
- Department of Physics and Astronomy, Department of Biochemistry, Institute of Data Sciences and Informatics, University of Missouri, Columbia, MO 65211-7010, USA
| | - Shi-Jie Chen
- Department of Physics and Astronomy, Department of Biochemistry, Institute of Data Sciences and Informatics, University of Missouri, Columbia, MO 65211-7010, USA
| |
Collapse
|
35
|
Nikolaienko T, Gurbych O, Druchok M. Complex machine learning model needs complex testing: Examining predictability of molecular binding affinity by a graph neural network. J Comput Chem 2022; 43:728-739. [PMID: 35201629 DOI: 10.1002/jcc.26831] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2021] [Revised: 01/04/2022] [Accepted: 02/09/2022] [Indexed: 12/12/2022]
Abstract
Drug discovery pipelines typically involve high-throughput screening of large amounts of compounds in a search of potential drugs candidates. As a chemical space of small organic molecules is huge, a "navigation" over it urges for fast and lightweight computational methods, thus promoting machine-learning approaches for processing huge pools of candidates. In this contribution, we present a graph-based deep neural network for prediction of protein-drug binding affinity and assess its predictive power under thorough testing conditions. Within the suggested approach, both protein and drug molecules are represented as graphs and passed to separate graph sub-networks, then concatenated and regressed towards a binding affinity. The neural network is trained on two binding affinity datasets-PDBbind and data imported from RCSB Protein Data Bank. In order to explore the generalization capabilities of the model we go beyond traditional random or leave-cluster-out techniques and demonstrate the need for more elaborate model performance assessment - six different strategies for test/train data partitioning (random, time- and property-arranged, protein- and ligand-clustered) with a k-fold cross-validation are engaged. Finally, we discuss the model performance in terms of a set of metrics for different split strategies and fold arrangement. Our code is available at https://github.com/SoftServeInc/affinity-by-GNN.
Collapse
Affiliation(s)
- Tymofii Nikolaienko
- SoftServe, Inc., Lviv, Ukraine.,Faculty of Physics, Taras Shevchenko National University of Kyiv, Kyiv, Ukraine
| | - Oleksandr Gurbych
- Blackthorn AI Ltd., London, UK.,Department of Artificial Intelligence Systems, Lviv Polytechnic National University, Lviv, Ukraine
| | - Maksym Druchok
- SoftServe, Inc., Lviv, Ukraine.,Institute for Condensed Matter Physics, NAS of Ukraine, Lviv, Ukraine
| |
Collapse
|
36
|
van der Westhuizen CJ, Stander A, Riley DL, Panayides JL. Discovery of Novel Acetylcholinesterase Inhibitors by Virtual Screening, In Vitro Screening, and Molecular Dynamics Simulations. J Chem Inf Model 2022; 62:1550-1572. [PMID: 35139637 DOI: 10.1021/acs.jcim.1c01443] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
Alzheimer's disease is the most common neurodegenerative disease and currently poses a significant socioeconomic problem. This study describes the uses of computer-aided drug discovery techniques to identify novel inhibitors of acetylcholinesterase, a target for Alzheimer's disease. High-throughput virtual screening was employed to predict potential inhibitors of acetylcholinesterase. Validation of enrichment was performed with the DUD-E data set, showing that an ensemble of binding pocket conformations is critical when a diverse set of ligands are being screened. A total of 720 compounds were submitted for in vitro screening, which led to 25 hits being identified with IC50 values of less than 50 μM. The majority of these hits belonged to two scaffolds: 1-ethyl-3-methoxy-3-methylpyrrolidine and 1H-pyrrolo[3,2-c]pyridin-6-amine both of which are noted to be promising compounds for further optimization. As various possible binding poses were suggested from molecular docking, molecular dynamics simulations were employed to validate the poses. In the case of the most active compounds identified, a critical, stable water bridge formed deep within the binding pocket was identified potentially explaining in part the lack of activity for subsets of compounds that are not able to form this water bridge.
Collapse
Affiliation(s)
- C Johan van der Westhuizen
- Department of Chemistry, Faculty of Natural and Agricultural Sciences, University of Pretoria, Lynnwood Road, Pretoria 0028, South Africa.,Pharmaceutical Technologies, CSIR Future Production: Chemicals, Meiring Naudé Road, Pretoria 0184, South Africa
| | - André Stander
- Department of Physiology, Faculty of Health Science, University of Pretoria, Lynnwood Road, Pretoria 0031, South Africa
| | - Darren L Riley
- Department of Chemistry, Faculty of Natural and Agricultural Sciences, University of Pretoria, Lynnwood Road, Pretoria 0028, South Africa
| | - Jenny-Lee Panayides
- Pharmaceutical Technologies, CSIR Future Production: Chemicals, Meiring Naudé Road, Pretoria 0184, South Africa
| |
Collapse
|
37
|
Suay-García B, Bueso-Bordils JI, Falcó A, Antón-Fos GM, Alemán-López PA. Virtual Combinatorial Chemistry and Pharmacological Screening: A Short Guide to Drug Design. Int J Mol Sci 2022; 23:ijms23031620. [PMID: 35163543 PMCID: PMC8836228 DOI: 10.3390/ijms23031620] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2021] [Revised: 01/24/2022] [Accepted: 01/28/2022] [Indexed: 02/04/2023] Open
Abstract
Traditionally, drug development involved the individual synthesis and biological evaluation of hundreds to thousands of compounds with the intention of highlighting their biological activity, selectivity, and bioavailability, as well as their low toxicity. On average, this process of new drug development involved, in addition to high economic costs, a period of several years before hopefully finding a drug with suitable characteristics to drive its commercialization. Therefore, the chemical synthesis of new compounds became the limiting step in the process of searching for or optimizing leads for new drug development. This need for large chemical libraries led to the birth of high-throughput synthesis methods and combinatorial chemistry. Virtual combinatorial chemistry is based on the same principle as real chemistry—many different compounds can be generated from a few building blocks at once. The difference lies in its speed, as millions of compounds can be produced in a few seconds. On the other hand, many virtual screening methods, such as QSAR (Quantitative Sturcture-Activity Relationship), pharmacophore models, and molecular docking, have been developed to study these libraries. These models allow for the selection of molecules to be synthesized and tested with a high probability of success. The virtual combinatorial chemistry–virtual screening tandem has become a fundamental tool in the process of searching for and developing a drug, as it allows the process to be accelerated with extraordinary economic savings.
Collapse
Affiliation(s)
- Beatriz Suay-García
- ESI International @ UCHCEU, Departamento de Matemáticas, Física y Ciencias Tecnológicas, Universidad Cardenal Herrera—CEU, CEU Universities San Bartolomé 55, Alfara del Patriarca, 46115 Valencia, Spain;
- Correspondence:
| | - Jose I. Bueso-Bordils
- Departamento de Farmacia, Universidad Cardenal Herrera—CEU, CEU Universities, C/Ramón y Cajal s/n, Alfara del Patriarca, 46115 Valencia, Spain; (G.M.A.-F.); (P.A.A.-L.); (J.I.B.-B.)
| | - Antonio Falcó
- ESI International @ UCHCEU, Departamento de Matemáticas, Física y Ciencias Tecnológicas, Universidad Cardenal Herrera—CEU, CEU Universities San Bartolomé 55, Alfara del Patriarca, 46115 Valencia, Spain;
| | - Gerardo M. Antón-Fos
- Departamento de Farmacia, Universidad Cardenal Herrera—CEU, CEU Universities, C/Ramón y Cajal s/n, Alfara del Patriarca, 46115 Valencia, Spain; (G.M.A.-F.); (P.A.A.-L.); (J.I.B.-B.)
| | - Pedro A. Alemán-López
- Departamento de Farmacia, Universidad Cardenal Herrera—CEU, CEU Universities, C/Ramón y Cajal s/n, Alfara del Patriarca, 46115 Valencia, Spain; (G.M.A.-F.); (P.A.A.-L.); (J.I.B.-B.)
| |
Collapse
|
38
|
Rezaei MA, Li Y, Wu D, Li X, Li C. Deep Learning in Drug Design: Protein-Ligand Binding Affinity Prediction. IEEE/ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2022; 19:407-417. [PMID: 33360998 PMCID: PMC8942327 DOI: 10.1109/tcbb.2020.3046945] [Citation(s) in RCA: 19] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
Computational drug design relies on the calculation of binding strength between two biological counterparts especially a chemical compound, i.e., a ligand, and a protein. Predicting the affinity of protein-ligand binding with reasonable accuracy is crucial for drug discovery, and enables the optimization of compounds to achieve better interaction with their target protein. In this paper, we propose a data-driven framework named DeepAtom to accurately predict the protein-ligand binding affinity. With 3D Convolutional Neural Network (3D-CNN) architecture, DeepAtom could automatically extract binding related atomic interaction patterns from the voxelized complex structure. Compared with the other CNN based approaches, our light-weight model design effectively improves the model representational capacity, even with the limited available training data. We carried out validation experiments on the PDBbind v.2016 benchmark and the independent Astex Diverse Set. We demonstrate that the less feature engineering dependent DeepAtom approach consistently outperforms the other baseline scoring methods. We also compile and propose a new benchmark dataset to further improve the model performances. With the new dataset as training input, DeepAtom achieves Pearson's R=0.83 and RMSE=1.23 pK units on the PDBbind v.2016 core set. The promising results demonstrate that DeepAtom models can be potentially adopted in computational drug development protocols such as molecular docking and virtual screening.
Collapse
Affiliation(s)
- Mohammad A. Rezaei
- Department of Medicinal Chemistry, Center for Natural Products, Drug Discovery and Development (CNPD3), University of Florida
| | - Yanjun Li
- Large-scale Intelligent Systems Laboratory, NSF Center for Big Learning, University of Florida Gainesville, FL, USA
| | - Dapeng Wu
- Large-scale Intelligent Systems Laboratory, NSF Center for Big Learning, University of Florida Gainesville, FL, USA
| | - Xiaolin Li
- Cognization Lab, Palo Alto, California, USA
| | - Chenglong Li
- Department of Medicinal Chemistry, Center for Natural Products, Drug Discovery and Development (CNPD3), University of Florida
- Large-scale Intelligent Systems Laboratory, NSF Center for Big Learning, University of Florida Gainesville, FL, USA
| |
Collapse
|
39
|
Zlotnikov ID, Kudryashova EV. Computer simulation of the Receptor-Ligand Interactions of Mannose Receptor CD206 in Comparison with the Lectin Concanavalin A Model. BIOCHEMISTRY. BIOKHIMIIA 2022; 87:54-69. [PMID: 35491020 PMCID: PMC8769089 DOI: 10.1134/s0006297922010059] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
Computer modeling of complexation of mono- and oligosaccharide ligands with the main (fourth) carbohydrate-binding domain of the mannose receptor CD206 (CRD4), as well as with the model receptor concanavalin A (ConA), was carried out for the first time, using methods of molecular dynamics and neural network analysis. ConA was shown to be a relevant model of CD206 (CRD4) due to similarity of the structural organization of the binding sites and high correlation of the values of free energies of complexation between the literature data and computer modeling (r > 0.9). Role of the main factors affecting affinity of the ligand–receptor interactions is discussed: the number and nature of carbohydrate residues, presence of Me-group in the O1 position, type of the glycoside bond in dimannose. Complexation of ConA and CD206 with ligands is shown to be energetically caused by electrostatic interactions (E) of the charged residues (Asn, Asp, Arg) with oxygen and hydrogen atoms in carbohydrates; contributions of hydrophobic and van der Waals components is lower. Possibility of the additional stabilization of complexes due to the CH–π stacking interactions of Tyr with the Man plane is discussed. The role of calcium and manganese ions in binding ligands has been studied. The values of free energies of complexation calculated in the course of molecular dynamics simulation correlate with experimental data (published for the model ConA): correlation coefficient r = 0.68. The Pafnucy neural network was trained based on the set of PDBbind2020 ligand–receptor complexes, which significantly increased accuracy of the energy predictions to r = 0.8 and 0.82 for CD206 and ConA receptors, respectively. A model of normalization of the complexation energy values for calculating the relevant values of ΔGbind, Kd is proposed. Based on the developed technique, values of the dissociation constants of a series of CD206 complexes with nine carbohydrate ligands of different structures were determined, which were not previously known. The obtained data open up possibilities for using computer modeling for the development of optimal drug carriers capable of active macrophage targeting, and also determine the limits of applicability of using ConA as a relevant model for studying parameters of the CD206 binding to various carbohydrate ligands.
Collapse
Affiliation(s)
- Igor D Zlotnikov
- Faculty of Chemistry, Lomonosov Moscow State University, Moscow, 119991, Russia
| | - Elena V Kudryashova
- Faculty of Chemistry, Lomonosov Moscow State University, Moscow, 119991, Russia.
| |
Collapse
|
40
|
Can docking scoring functions guarantee success in virtual screening? VIRTUAL SCREENING AND DRUG DOCKING 2022. [DOI: 10.1016/bs.armc.2022.08.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/23/2022]
|
41
|
Wu Y, Brooks CL. Flexible CDOCKER: Hybrid Searching Algorithm and Scoring Function with Side Chain Conformational Entropy. J Chem Inf Model 2021; 61:5535-5549. [PMID: 34704754 PMCID: PMC8684595 DOI: 10.1021/acs.jcim.1c01078] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/09/2023]
Abstract
The binding of small-molecule ligands to protein or nucleic acid targets is important to numerous biological processes. Accurate prediction of the binding modes between a ligand and a macromolecule is of fundamental importance in structure-based structure-function exploration. When multiple ligands with different sizes are docked to a target receptor, it is reasonable to assume that the residues in the binding pocket may adopt alternative conformations upon interacting with the different ligands. In addition, it has been suggested that the entropic contribution to binding can be important. However, only a few attempts to include the side chain conformational entropy upon binding within the application of flexible receptor docking methodology exist. Here, we propose a new physics-based scoring function that includes both enthalpic and entropic contributions upon binding by considering the conformational variability of the flexible side chains within the ensemble of docked poses. We also describe a novel hybrid searching algorithm that combines both molecular dynamics (MD)-based simulated annealing and genetic algorithm crossovers to address the enhanced sampling of the increased search space. We demonstrate improved accuracy in flexible cross-docking experiments compared with rigid cross-docking. We test our developments by considering five protein targets, thrombin, dihydrofolate reductase(DHFR), T4 L99A, T4 L99A/M102Q, and PDE10A, which belong to different enzyme classes with different binding pocket environments, as a representative set of diverse ligands and receptors. Each target contains dozens of different ligands bound to the same binding pocket. We also demonstrate that this flexible docking algorithm may be applicable to RNA docking with a representative riboswitch example. Our findings show significant improvements in top ranking accuracy across this set, with the largest improvement relative to rigid, 23.64%, occurring for ligands binding to DHFR. We then evaluate the ability to identify lead compounds among a large chemical space for the proposed flexible receptor docking algorithm using a subset of the DUD-E containing receptor targets MCR, GCR, and ANDR. We demonstrate that our new algorithms show improved performance in modeling flexible binding site residues compared to DOCK. Finally, we select the T4 L99A and T4 L99A/M102Q decoy sets, containing dozens of binders and experimentally validated nonbinders, to test our approach in distinguishing binders from nonbinders. We illustrate that our new algorithms for searching and scoring have superior performance to rigid receptor CDOCKER as well as AutoDock Vina. Finally, we suggest that flexible CDOCKER is sufficiently fast to be utilized in high-throughput docking screens in the context of hierarchical approaches.
Collapse
Affiliation(s)
- Yujin Wu
- Department of Chemistry, University of Michigan, Ann Arbor, Michigan 48109, United States
| | - Charles L Brooks
- Department of Chemistry, University of Michigan, Ann Arbor, Michigan 48109, United States
- Biophysics Program, University of Michigan, Ann Arbor, Michigan 48109, United States
| |
Collapse
|
42
|
Using diverse potentials and scoring functions for the development of improved machine-learned models for protein-ligand affinity and docking pose prediction. J Comput Aided Mol Des 2021; 35:1095-1123. [PMID: 34708263 DOI: 10.1007/s10822-021-00423-4] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/03/2021] [Accepted: 10/11/2021] [Indexed: 10/20/2022]
Abstract
The advent of computational drug discovery holds the promise of significantly reducing the effort of experimentalists, along with monetary cost. More generally, predicting the binding of small organic molecules to biological macromolecules has far-reaching implications for a range of problems, including metabolomics. However, problems such as predicting the bound structure of a protein-ligand complex along with its affinity have proven to be an enormous challenge. In recent years, machine learning-based methods have proven to be more accurate than older methods, many based on simple linear regression. Nonetheless, there remains room for improvement, as these methods are often trained on a small set of features, with a single functional form for any given physical effect, and often with little mention of the rationale behind choosing one functional form over another. Moreover, it is not entirely clear why one machine learning method is favored over another. In this work, we endeavor to undertake a comprehensive effort towards developing high-accuracy, machine-learned scoring functions, systematically investigating the effects of machine learning method and choice of features, and, when possible, providing insights into the relevant physics using methods that assess feature importance. Here, we show synergism among disparate features, yielding adjusted R2 with experimental binding affinities of up to 0.871 on an independent test set and enrichment for native bound structures of up to 0.913. When purely physical terms that model enthalpic and entropic effects are used in the training, we use feature importance assessments to probe the relevant physics and hopefully guide future investigators working on this and other computational chemistry problems.
Collapse
|
43
|
Wang Z, Zheng L, Liu Y, Qu Y, Li YQ, Zhao M, Mu Y, Li W. OnionNet-2: A Convolutional Neural Network Model for Predicting Protein-Ligand Binding Affinity Based on Residue-Atom Contacting Shells. Front Chem 2021; 9:753002. [PMID: 34778208 PMCID: PMC8579074 DOI: 10.3389/fchem.2021.753002] [Citation(s) in RCA: 38] [Impact Index Per Article: 12.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/04/2021] [Accepted: 10/06/2021] [Indexed: 01/31/2023] Open
Abstract
One key task in virtual screening is to accurately predict the binding affinity (△G) of protein-ligand complexes. Recently, deep learning (DL) has significantly increased the predicting accuracy of scoring functions due to the extraordinary ability of DL to extract useful features from raw data. Nevertheless, more efforts still need to be paid in many aspects, for the aim of increasing prediction accuracy and decreasing computational cost. In this study, we proposed a simple scoring function (called OnionNet-2) based on convolutional neural network to predict △G. The protein-ligand interactions are characterized by the number of contacts between protein residues and ligand atoms in multiple distance shells. Compared to published models, the efficacy of OnionNet-2 is demonstrated to be the best for two widely used datasets CASF-2016 and CASF-2013 benchmarks. The OnionNet-2 model was further verified by non-experimental decoy structures from docking program and the CSAR NRC-HiQ data set (a high-quality data set provided by CSAR), which showed great success. Thus, our study provides a simple but efficient scoring function for predicting protein-ligand binding free energy.
Collapse
Affiliation(s)
- Zechen Wang
- School of Physics, Shandong University, Jinan, China
| | | | - Yang Liu
- School of Physics, Shandong University, Jinan, China
| | - Yuanyuan Qu
- School of Physics, Shandong University, Jinan, China
| | - Yong-Qiang Li
- School of Physics, Shandong University, Jinan, China
| | - Mingwen Zhao
- School of Physics, Shandong University, Jinan, China
| | - Yuguang Mu
- School of Biological Sciences, Nanyang Technological University, Singapore
| | - Weifeng Li
- School of Physics, Shandong University, Jinan, China
| |
Collapse
|
44
|
Abstract
Molecular docking is one of the most widely used computational tools in structure-based drug design and is critically dependent on accuracy and robustness of the scoring function. In this work, we introduce a new scoring function Lin_F9, which is a linear combination of nine empirical terms, including a unified metal bond term to specifically describe metal-ligand interactions. Parameters in Lin_F9 are obtained with a multistage fitting protocol using explicit water-included structures. For the CASF-2016 benchmark test set, Lin_F9 achieves the top scoring power among all 34 classical scoring functions for both original crystal poses and locally optimized poses with Pearson correlation coefficients (R) of 0.680 and 0.687, respectively. Meanwhile, in comparison with Vina, Lin_F9 achieves consistently better scoring power and ranking power with various types of protein-ligand complex structures that mimic real docking applications, including end-to-end flexible docking for the CASF-2016 benchmark test set using a single or an ensemble of protein receptor structures, as well as for D3R Grand Challenge (GC4) test sets. Lin_F9 has been implemented in a fork of Smina as an optional built-in scoring function that can be used for docking applications as well as for further improvement of scoring functions and docking protocols. Lin_F9 is accessible through https://yzhang.hpc.nyu.edu/Lin_F9/.
Collapse
Affiliation(s)
- Chao Yang
- Department of Chemistry, New York University, New York, New York 10003, United States
| | - Yingkai Zhang
- Department of Chemistry, New York University, New York, New York 10003, United States
- NYU-ECNU Center for Computational Chemistry at NYU Shanghai, Shanghai 200062, China
| |
Collapse
|
45
|
Di Filippo JI, Cavasotto CN. Guided structure-based ligand identification and design via artificial intelligence modeling. Expert Opin Drug Discov 2021; 17:71-78. [PMID: 34544293 DOI: 10.1080/17460441.2021.1979514] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
Abstract
INTRODUCTION The implementation of Artificial Intelligence (AI) methodologies to drug discovery (DD) are on the rise. Several applications have been developed for structure-based DD, where AI methods provide an alternative framework for the identification of ligands for validated therapeutic targets, as well as the de novo design of ligands through generative models. AREAS COVERED Herein, the authors review the contributions between the 2019 to present period regarding the application of AI methods to structure-based virtual screening (SBVS) which encompasses mainly molecular docking applications - binding pose prediction and binary classification for ligand or hit identification-, as well as de novo drug design driven by machine learning (ML) generative models, and the validation of AI models in structure-based screening. Studies are reviewed in terms of their main objective, used databases, implemented methodology, input and output, and key results . EXPERT OPINION More profound analyses regarding the validity and applicability of AI methods in DD have begun to appear. In the near future, we expect to see more structure-based generative models- which are scarce in comparison to ligand-based generative models-, the implementation of standard guidelines for validating the generated structures, and more analyses regarding the validation of AI methods in structure-based DD.
Collapse
Affiliation(s)
- Juan I Di Filippo
- Computational Drug Design and Biomedical Informatics Laboratory, Instituto de Investigaciones en Medicina Traslacional (IIMT), CONICET-Universidad Austral, Pilar, Buenos Aires, Argentina.,Facultad de Ciencias Biomédicas, and Facultad de Ingeniería, Universidad Austral, Pilar, Buenos Aires, Argentina.,Austral Institute for Applied Artificial Intelligence, Universidad Austral, Pilar, Buenos Aires, Argentina
| | - Claudio N Cavasotto
- Computational Drug Design and Biomedical Informatics Laboratory, Instituto de Investigaciones en Medicina Traslacional (IIMT), CONICET-Universidad Austral, Pilar, Buenos Aires, Argentina.,Facultad de Ciencias Biomédicas, and Facultad de Ingeniería, Universidad Austral, Pilar, Buenos Aires, Argentina.,Austral Institute for Applied Artificial Intelligence, Universidad Austral, Pilar, Buenos Aires, Argentina
| |
Collapse
|
46
|
Gusmão AS, Abreu LS, Tavares JF, de Freitas HF, Silva da Rocha Pita S, Dos Santos EG, Caldas IS, Vieira AA, Silva EO. Computer-Guided Trypanocidal Activity of Natural Lactones Produced by Endophytic Fungus of Euphorbia umbellata. Chem Biodivers 2021; 18:e2100493. [PMID: 34403573 DOI: 10.1002/cbdv.202100493] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2021] [Accepted: 08/17/2021] [Indexed: 11/11/2022]
Abstract
Hundreds of millions of people worldwide are affected by Chagas' disease caused by Trypanosoma cruzi. Since the current treatment lack efficacy, specificity, and suffers from several side-effects, novel therapeutics are mandatory. Natural products from endophytic fungi have been useful sources of lead compounds. In this study, three lactones isolated from an endophytic strain culture were in silico evaluated for rational guidance of their bioassay screening. All lactones displayed in vitro activity against T. cruzi epimastigote and trypomastigote forms. Notably, the IC50 values of (+)-phomolactone were lower than benznidazole (0.86 vs. 30.78 μM against epimastigotes and 0.41 vs. 4.88 μM against trypomastigotes). Target-based studies suggested that lactones displayed their trypanocidal activities due to T. cruzi glyceraldehyde-3-phosphate dehydrogenase (TcGAPDH) inhibition, and the binding free energy for all three TcGAPDH-lactone complexes suggested that (+)-phomolactone has a lower score value (-3.38), corroborating with IC50 assays. These results highlight the potential of these lactones for further anti-T. cruzi drug development.
Collapse
Affiliation(s)
- Amanda Santos Gusmão
- Organic Chemistry Department, Chemistry Institute, Federal University of Bahia, Barão de Jeremoabo 147, Salvador, 40170115, Bahia, Brazil
| | - Lucas Silva Abreu
- Institute for Research in Pharmaceuticals and Medications, Federal University of Paraíba, Campus I, João Pessoa, 58051900, Paraíba, Brazil
| | - Josean Fechine Tavares
- Institute for Research in Pharmaceuticals and Medications, Federal University of Paraíba, Campus I, João Pessoa, 58051900, Paraíba, Brazil
| | - Humberto Fonseca de Freitas
- Laboratory of Bioinformatics and Molecular Modeling (LaBiMM), Pharmacy College, Federal University of Bahia, Barão de Jeremoabo 147, Salvador, 40170115, Bahia, Brazil
| | - Samuel Silva da Rocha Pita
- Laboratory of Bioinformatics and Molecular Modeling (LaBiMM), Pharmacy College, Federal University of Bahia, Barão de Jeremoabo 147, Salvador, 40170115, Bahia, Brazil
| | - Elda Gonçalves Dos Santos
- Pathology and Parasitology Department, Institute of Biomedical Sciences, Federal University of Alfenas, Gabriel Monteiro da Silva 500, Alfenas, 37130001, Minas Gerais, Brazil
| | - Ivo Santana Caldas
- Pathology and Parasitology Department, Institute of Biomedical Sciences, Federal University of Alfenas, Gabriel Monteiro da Silva 500, Alfenas, 37130001, Minas Gerais, Brazil
| | - André Alexandre Vieira
- Organic Chemistry Department, Chemistry Institute, Federal University of Bahia, Barão de Jeremoabo 147, Salvador, 40170115, Bahia, Brazil
| | - Eliane Oliveira Silva
- Organic Chemistry Department, Chemistry Institute, Federal University of Bahia, Barão de Jeremoabo 147, Salvador, 40170115, Bahia, Brazil
| |
Collapse
|
47
|
Meli R, Anighoro A, Bodkin MJ, Morris GM, Biggin PC. Learning protein-ligand binding affinity with atomic environment vectors. J Cheminform 2021; 13:59. [PMID: 34391475 PMCID: PMC8364054 DOI: 10.1186/s13321-021-00536-w] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2021] [Accepted: 07/21/2021] [Indexed: 12/03/2022] Open
Abstract
Scoring functions for the prediction of protein-ligand binding affinity have seen renewed interest in recent years when novel machine learning and deep learning methods started to consistently outperform classical scoring functions. Here we explore the use of atomic environment vectors (AEVs) and feed-forward neural networks, the building blocks of several neural network potentials, for the prediction of protein-ligand binding affinity. The AEV-based scoring function, which we term AEScore, is shown to perform as well or better than other state-of-the-art scoring functions on binding affinity prediction, with an RMSE of 1.22 pK units and a Pearson’s correlation coefficient of 0.83 for the CASF-2016 benchmark. However, AEScore does not perform as well in docking and virtual screening tasks, for which it has not been explicitly trained. Therefore, we show that the model can be combined with the classical scoring function AutoDock Vina in the context of \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\Delta$$\end{document}Δ-learning, where corrections to the AutoDock Vina scoring function are learned instead of the protein-ligand binding affinity itself. Combined with AutoDock Vina, \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\Delta$$\end{document}Δ-AEScore has an RMSE of 1.32 pK units and a Pearson’s correlation coefficient of 0.80 on the CASF-2016 benchmark, while retaining the docking and screening power of the underlying classical scoring function.
Collapse
Affiliation(s)
- Rocco Meli
- Department of Biochemistry, University of Oxford, Oxford, UK
| | | | | | | | - Philip C Biggin
- Department of Biochemistry, University of Oxford, Oxford, UK.
| |
Collapse
|
48
|
Sánchez-Cruz N, Medina-Franco JL, Mestres J, Barril X. Extended connectivity interaction features: improving binding affinity prediction through chemical description. Bioinformatics 2021; 37:1376-1382. [PMID: 33226061 DOI: 10.1093/bioinformatics/btaa982] [Citation(s) in RCA: 50] [Impact Index Per Article: 16.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/18/2020] [Revised: 10/27/2020] [Accepted: 11/10/2020] [Indexed: 12/22/2022] Open
Abstract
MOTIVATION Machine-learning scoring functions (SFs) have been found to outperform standard SFs for binding affinity prediction of protein-ligand complexes. A plethora of reports focus on the implementation of increasingly complex algorithms, while the chemical description of the system has not been fully exploited. RESULTS Herein, we introduce Extended Connectivity Interaction Features (ECIF) to describe protein-ligand complexes and build machine-learning SFs with improved predictions of binding affinity. ECIF are a set of protein-ligand atom-type pair counts that take into account each atom's connectivity to describe it and thus define the pair types. ECIF were used to build different machine-learning models to predict protein-ligand affinities (pKd/pKi). The models were evaluated in terms of 'scoring power' on the Comparative Assessment of Scoring Functions 2016. The best models built on ECIF achieved Pearson correlation coefficients of 0.857 when used on its own, and 0.866 when used in combination with ligand descriptors, demonstrating ECIF descriptive power. AVAILABILITY AND IMPLEMENTATION Data and code to reproduce all the results are freely available at https://github.com/DIFACQUIM/ECIF. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Norberto Sánchez-Cruz
- Department of Pharmacy, School of Chemistry, Universidad Nacional Autónoma de México, Mexico City 04510, Mexico
| | - José L Medina-Franco
- Department of Pharmacy, School of Chemistry, Universidad Nacional Autónoma de México, Mexico City 04510, Mexico
| | - Jordi Mestres
- Research Group on Systems Pharmacology, Research Program on Biomedical Informatics (GRIB), IMIM Hospital del Mar Medical Research Institute and University Pompeu Fabra, Parc de Recerca Biomedica (PRBB), 08003 Barcelona, Catalonia, Spain
- Chemotargets SL, Parc Cientific de Barcelona (PCB), 08028 Barcelona, Catalonia, Spain
| | - Xavier Barril
- Institut de Biomedicina de la Universitat de Barcelona (IBUB) and Facultat de Farmacia, Universitat de Barcelona, 08028 Barcelona, Spain
- Catalan Institution for Research and Advanced Studies (ICREA), 08010 Barcelona, Spain
| |
Collapse
|
49
|
Jiang Z, Xu J, Yan A, Wang L. A comprehensive comparative assessment of 3D molecular similarity tools in ligand-based virtual screening. Brief Bioinform 2021; 22:6304389. [PMID: 34151363 DOI: 10.1093/bib/bbab231] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/18/2020] [Revised: 05/10/2021] [Accepted: 05/27/2021] [Indexed: 12/19/2022] Open
Abstract
Three-dimensional (3D) molecular similarity, one major ligand-based virtual screening (VS) method, has been widely used in the drug discovery process. A variety of 3D molecular similarity tools have been developed in recent decades. In this study, we assessed a panel of 15 3D molecular similarity programs against the DUD-E and LIT-PCBA datasets, including commercial ROCS and Phase, in terms of screening power and scaffold-hopping power. The results revealed that (1) SHAFTS, LS-align, Phase Shape_Pharm and LIGSIFT showed the best VS capability in terms of screening power. Some 3D similarity tools available to academia can yield relatively better VS performance than commercial ROCS and Phase software. (2) Current 3D similarity VS tools exhibit a considerable ability to capture actives with new chemotypes in terms of scaffold hopping. (3) Multiple conformers relative to single conformations will generally improve VS performance for most 3D similarity tools, with marginal improvement observed in area under the receiving operator characteristic curve values, enrichment factor in the top 1% and hit rate in the top 1% values showed larger improvement. Moreover, redundancy and complementarity analyses of hit lists from different query seeds and different 3D similarity VS tools showed that the combination of different query seeds and/or different 3D similarity tools in VS campaigns retrieved more (and more diverse) active molecules. These findings provide useful information for guiding choices of the optimal 3D molecular similarity tools for VS practices and designing possible combination strategies to discover more diverse active compounds.
Collapse
Affiliation(s)
- Zhenla Jiang
- South China University of Technology, Guangzhou 510006, China
| | - Jianrong Xu
- Shanghai Jiao Tong University School of Medicine and Shanghai University of Traditional Chinese Medicine, Guangzhou 510006, China
| | - Aixia Yan
- Beijing University of Chemical Technology, Guangzhou 510006, China
| | - Ling Wang
- South China University of Technology, Guangzhou 510006, China
| |
Collapse
|
50
|
Wang E, Fu W, Jiang D, Sun H, Wang J, Zhang X, Weng G, Liu H, Tao P, Hou T. VAD-MM/GBSA: A Variable Atomic Dielectric MM/GBSA Model for Improved Accuracy in Protein-Ligand Binding Free Energy Calculations. J Chem Inf Model 2021; 61:2844-2856. [PMID: 34014672 DOI: 10.1021/acs.jcim.1c00091] [Citation(s) in RCA: 24] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/21/2022]
Abstract
The molecular mechanics/generalized Born surface area (MM/GBSA) has been widely used in end-point binding free energy prediction in structure-based drug design (SBDD). However, in practice, it is usually being treated as a disputed method mostly because of its system dependence. Here, combining with machine-learning optimization, we developed a novel version of MM/GBSA, named variable atomic dielectric MM/GBSA (VAD-MM/GBSA), by assigning variable dielectric constants directly to the protein/ligand atoms. The new strategy exhibits markedly improved accuracy in binding affinity calculations for various protein-ligand systems and is promising to be used in the postprocessing of structure-based virtual screening. Moreover, VAD-MM/GBSA outperformed prime MM/GBSA in Schrödinger software and showed remarkable predictive performance for specific protein targets, such as POL polyprotein, human immunodeficiency virus type 1 (HIV-1) protease, etc. Our study showed that the VAD-MM/GBSA method with little extra computational overhead provides a potential replacement of the MM/GBSA in AMBER software. An online web server of VAD-MMGBSA has been developed and is now available at http://cadd.zju.edu.cn/vdgb.
Collapse
Affiliation(s)
- Ercheng Wang
- Innovation Institute for Artificial Intelligence in Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang 310058, China
| | - Weitao Fu
- Innovation Institute for Artificial Intelligence in Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang 310058, China
| | - Dejun Jiang
- College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China
| | - Huiyong Sun
- Innovation Institute for Artificial Intelligence in Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang 310058, China
| | - Junmei Wang
- Department of Pharmaceutical Sciences, University of Pittsburgh, Pittsburgh, Pennsylvania 15261, United States
| | - Xujun Zhang
- Innovation Institute for Artificial Intelligence in Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang 310058, China
| | - Gaoqi Weng
- Innovation Institute for Artificial Intelligence in Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang 310058, China
| | - Hui Liu
- Innovation Institute for Artificial Intelligence in Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang 310058, China
| | - Peng Tao
- Department of Pharmaceutical Sciences, University of Pittsburgh, Pittsburgh, Pennsylvania 15261, United States
| | - Tingjun Hou
- Innovation Institute for Artificial Intelligence in Medicine, College of Pharmaceutical Sciences, Zhejiang University, Hangzhou, Zhejiang 310058, China
| |
Collapse
|