1
|
Wang L, Zhou Z, Yang X, Shi S, Zeng X, Cao D. The present state and challenges of active learning in drug discovery. Drug Discov Today 2024; 29:103985. [PMID: 38642700 DOI: 10.1016/j.drudis.2024.103985] [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: 03/03/2024] [Revised: 04/08/2024] [Accepted: 04/15/2024] [Indexed: 04/22/2024]
Abstract
Active learning (AL) is an iterative feedback process that efficiently identifies valuable data within vast chemical space, even with limited labeled data. This characteristic renders it a valuable approach to tackle the ongoing challenges faced in drug discovery, such as the ever-expanding explore space and the limitations of labeled data. Consequently, AL is increasingly gaining prominence in the field of drug development. In this paper, we comprehensively review the application of AL at all stages of drug discovery, including compounds-target interaction prediction, virtual screening, molecular generation and optimization, as well as molecular properties prediction. Additionally, we discuss the challenges and prospects associated with the current applications of AL in drug discovery.
Collapse
Affiliation(s)
- Lei Wang
- Xiangya School of Pharmaceutical Sciences, Central South University, Changsha 410013, Hunan, China
| | - Zhenran Zhou
- Department of Computer Science, Hunan University, Changsha 410082, Hunan, China
| | - Xixi Yang
- Department of Computer Science, Hunan University, Changsha 410082, Hunan, China
| | - Shaohua Shi
- Institute for Advancing Translational Medicine in Bone and Joint Diseases, School of Chinese Medicine, Hong Kong Baptist University, Hong Kong SAR, China
| | - Xiangxiang Zeng
- Department of Computer Science, Hunan University, Changsha 410082, Hunan, China.
| | - Dongsheng Cao
- Xiangya School of Pharmaceutical Sciences, Central South University, Changsha 410013, Hunan, China.
| |
Collapse
|
2
|
Cleves AE, Jain AN, Demeter DA, Buchan ZA, Wilmot J, Hancock EN. From UK-2A to florylpicoxamid: Active learning to identify a mimic of a macrocyclic natural product. J Comput Aided Mol Des 2024; 38:19. [PMID: 38630341 DOI: 10.1007/s10822-024-00555-3] [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: 01/02/2024] [Accepted: 02/26/2024] [Indexed: 04/19/2024]
Abstract
Scaffold replacement as part of an optimization process that requires maintenance of potency, desirable biodistribution, metabolic stability, and considerations of synthesis at very large scale is a complex challenge. Here, we consider a set of over 1000 time-stamped compounds, beginning with a macrocyclic natural-product lead and ending with a broad-spectrum crop anti-fungal. We demonstrate the application of the QuanSA 3D-QSAR method employing an active learning procedure that combines two types of molecular selection. The first identifies compounds predicted to be most active of those most likely to be well-covered by the model. The second identifies compounds predicted to be most informative based on exhibiting low predicted activity but showing high 3D similarity to a highly active nearest-neighbor training molecule. Beginning with just 100 compounds, using a deterministic and automatic procedure, five rounds of 20-compound selection and model refinement identifies the binding metabolic form of florylpicoxamid. We show how iterative refinement broadens the domain of applicability of the successive models while also enhancing predictive accuracy. We also demonstrate how a simple method requiring very sparse data can be used to generate relevant ideas for synthetic candidates.
Collapse
Affiliation(s)
- Ann E Cleves
- BioPharmics Division, Optibrium Limited, Cambridge, CB25 9GL, UK.
| | - Ajay N Jain
- BioPharmics Division, Optibrium Limited, Cambridge, CB25 9GL, UK
| | | | | | | | | |
Collapse
|
3
|
Gorantla R, Kubincová A, Suutari B, Cossins BP, Mey ASJS. Benchmarking Active Learning Protocols for Ligand-Binding Affinity Prediction. J Chem Inf Model 2024; 64:1955-1965. [PMID: 38446131 PMCID: PMC10966646 DOI: 10.1021/acs.jcim.4c00220] [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: 02/07/2024] [Accepted: 02/23/2024] [Indexed: 03/07/2024]
Abstract
Active learning (AL) has become a powerful tool in computational drug discovery, enabling the identification of top binders from vast molecular libraries. To design a robust AL protocol, it is important to understand the influence of AL parameters, as well as the features of the data sets on the outcomes. We use four affinity data sets for different targets (TYK2, USP7, D2R, Mpro) to systematically evaluate the performance of machine learning models [Gaussian process (GP) model and Chemprop model], sample selection protocols, and the batch size based on metrics describing the overall predictive power of the model (R2, Spearman rank, root-mean-square error) as well as the accurate identification of top 2%/5% binders (Recall, F1 score). Both models have a comparable Recall of top binders on large data sets, but the GP model surpasses the Chemprop model when training data are sparse. A larger initial batch size, especially on diverse data sets, increased the Recall of both models as well as overall correlation metrics. However, for subsequent cycles, smaller batch sizes of 20 or 30 compounds proved to be desirable. Furthermore, adding artificial Gaussian noise to the data up to a certain threshold still allowed the model to identify clusters with top-scoring compounds. However, excessive noise (<1σ) did impact the model's predictive and exploitative capabilities.
Collapse
Affiliation(s)
- Rohan Gorantla
- School
of Informatics, University of Edinburgh, Edinburgh EH8 9AB, U.K.
- EaStCHEM
School of Chemistry, University of Edinburgh, Edinburgh EH9 3FJ, U.K.
- Exscientia, Schrödinger Building, Oxford OX4 4GE, U.K.
| | | | | | | | | |
Collapse
|
4
|
Alexandrov V, Vilenchik M, Kantidze O, Tsutskiridze N, Kharchilava D, Lhewa P, Shishkin A, Gankin Y, Kirpich A. Novel Efficient Multistage Lead Optimization Pipeline Experimentally Validated for DYRK1B Selective Inhibitors. J Med Chem 2022; 65:13784-13792. [PMID: 36239428 PMCID: PMC9619999 DOI: 10.1021/acs.jmedchem.2c00988] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
![]()
In addition to general challenges in drug discovery such as the
identification of lead compounds in time- and cost-effective ways,
specific challenges also exist. Particularly, it is necessary to develop
pharmacological inhibitors that effectively discriminate between closely
related molecular targets. DYRK1B kinase is considered a valuable
target for cancer-specific mono- or combination chemotherapy; however,
the inhibition of its closely related DYRK1A kinase is not beneficial.
Existing inhibitors target both kinases with essentially the same
efficiency, and the unavailability of the DYRK1B crystal structure
makes the discovery of DYRK1B-specific inhibitors even more challenging.
Here, we propose a novel multi-stage compound discovery pipeline aimed
at in silico identification of both potent and selective
small molecules from a large set of initial candidates. The method
uses structure-based docking and ligand-based quantitative structure–activity
relationship modeling. This approach allowed us to identify lead and
runner-up small-molecule compounds targeting DYRK1B with high efficiency
and specificity.
Collapse
Affiliation(s)
- Vadim Alexandrov
- Liquid Algo LLC, Hopewell Junction, New York12533, United States
| | - Maria Vilenchik
- Felicitex Therapeutics, Natick, Massachusetts01760, United States
| | - Omar Kantidze
- Quantori LLC, Cambridge, Massachusetts02142, United States
| | - Nika Tsutskiridze
- Quantori LLC, Cambridge, Massachusetts02142, United States.,Tbilisi State Medical University, Tbilisi0186, Georgia
| | - Daviti Kharchilava
- Quantori LLC, Cambridge, Massachusetts02142, United States.,Tbilisi State Medical University, Tbilisi0186, Georgia
| | - Pema Lhewa
- Department of Population Health Sciences, School of Public Health, Georgia State University, Atlanta, Georgia30303, United States
| | - Aleksandr Shishkin
- Department of Population Health Sciences, School of Public Health, Georgia State University, Atlanta, Georgia30303, United States
| | - Yuriy Gankin
- Quantori LLC, Cambridge, Massachusetts02142, United States
| | - Alexander Kirpich
- Department of Population Health Sciences, School of Public Health, Georgia State University, Atlanta, Georgia30303, United States
| |
Collapse
|
5
|
Mohr B, Shmilovich K, Kleinwächter IS, Schneider D, Ferguson AL, Bereau T. Data-driven discovery of cardiolipin-selective small molecules by computational active learning. Chem Sci 2022; 13:4498-4511. [PMID: 35656132 PMCID: PMC9019913 DOI: 10.1039/d2sc00116k] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2022] [Accepted: 02/24/2022] [Indexed: 12/23/2022] Open
Abstract
Subtle variations in the lipid composition of mitochondrial membranes can have a profound impact on mitochondrial function. The inner mitochondrial membrane contains the phospholipid cardiolipin, which has been demonstrated to act as a biomarker for a number of diverse pathologies. Small molecule dyes capable of selectively partitioning into cardiolipin membranes enable visualization and quantification of the cardiolipin content. Here we present a data-driven approach that combines a deep learning-enabled active learning workflow with coarse-grained molecular dynamics simulations and alchemical free energy calculations to discover small organic compounds able to selectively permeate cardiolipin-containing membranes. By employing transferable coarse-grained models we efficiently navigate the all-atom design space corresponding to small organic molecules with molecular weight less than ≈500 Da. After direct simulation of only 0.42% of our coarse-grained search space we identify molecules with considerably increased levels of cardiolipin selectivity compared to a widely used cardiolipin probe 10-N-nonyl acridine orange. Our accumulated simulation data enables us to derive interpretable design rules linking coarse-grained structure to cardiolipin selectivity. The findings are corroborated by fluorescence anisotropy measurements of two compounds conforming to our defined design rules. Our findings highlight the potential of coarse-grained representations and multiscale modelling for materials discovery and design.
Collapse
Affiliation(s)
- Bernadette Mohr
- Van't Hoff Institute for Molecular Sciences and Informatics Institute, University of Amsterdam Amsterdam 1098 XH The Netherlands
| | - Kirill Shmilovich
- Pritzker School of Molecular Engineering, University of Chicago Chicago Illinois 60637 USA
| | - Isabel S Kleinwächter
- Department of Chemistry - Biochemistry, Johannes Gutenberg University Mainz 55128 Mainz Germany
| | - Dirk Schneider
- Department of Chemistry - Biochemistry, Johannes Gutenberg University Mainz 55128 Mainz Germany
| | - Andrew L Ferguson
- Pritzker School of Molecular Engineering, University of Chicago Chicago Illinois 60637 USA
| | - Tristan Bereau
- Van't Hoff Institute for Molecular Sciences and Informatics Institute, University of Amsterdam Amsterdam 1098 XH The Netherlands .,Max Planck Institute for Polymer Research 55128 Mainz Germany
| |
Collapse
|
6
|
Cleves AE, Johnson SR, Jain AN. Synergy and Complementarity between Focused Machine Learning and Physics-Based Simulation in Affinity Prediction. J Chem Inf Model 2021; 61:5948-5966. [PMID: 34890185 DOI: 10.1021/acs.jcim.1c01382] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
We present results on the extent to which physics-based simulation (exemplified by FEP+) and focused machine learning (exemplified by QuanSA) are complementary for ligand affinity prediction. For both methods, predictions of activity for LFA-1 inhibitors from a medicinal chemistry lead optimization project were accurate within the applicable domain of each approach. A hybrid model that combined predictions by both approaches by simple averaging performed better than either method, with respect to both ranking and absolute pKi values. Two publicly available FEP+ benchmarks, covering 16 diverse biological targets, were used to test the generality of the synergy. By identifying training data specifically focused on relevant ligands, accurate QuanSA models were derived using ligand activity data known at the time of the original series publications. Results across the 16 benchmark targets demonstrated significant improvements both for ranking and for absolute pKi values using hybrid predictions that combined the FEP+ and QuanSA predicted affinity values. The results argue for a combined approach for affinity prediction that makes use of physics-driven methods as well as those driven by machine learning, each applied carefully on appropriate compounds, with hybrid prediction strategies being employed where possible.
Collapse
Affiliation(s)
- Ann E Cleves
- Applied Science, BioPharmics LLC, Santa Rosa, California 95404, United States
| | - Stephen R Johnson
- Computer-Assisted Drug-Design, Bristol-Myers Squibb Company, Princeton, New Jersey 08648, United States
| | - Ajay N Jain
- Research and Development, BioPharmics LLC, Santa Rosa, California 95404, United States
| |
Collapse
|
7
|
Mao J, Akhtar J, Zhang X, Sun L, Guan S, Li X, Chen G, Liu J, Jeon HN, Kim MS, No KT, Wang G. Comprehensive strategies of machine-learning-based quantitative structure-activity relationship models. iScience 2021; 24:103052. [PMID: 34553136 PMCID: PMC8441174 DOI: 10.1016/j.isci.2021.103052] [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] [Indexed: 11/21/2022] Open
Abstract
Early quantitative structure-activity relationship (QSAR) technologies have unsatisfactory versatility and accuracy in fields such as drug discovery because they are based on traditional machine learning and interpretive expert features. The development of Big Data and deep learning technologies significantly improve the processing of unstructured data and unleash the great potential of QSAR. Here we discuss the integration of wet experiments (which provide experimental data and reliable verification), molecular dynamics simulation (which provides mechanistic interpretation at the atomic/molecular levels), and machine learning (including deep learning) techniques to improve QSAR models. We first review the history of traditional QSAR and point out its problems. We then propose a better QSAR model characterized by a new iterative framework to integrate machine learning with disparate data input. Finally, we discuss the application of QSAR and machine learning to many practical research fields, including drug development and clinical trials.
Collapse
Affiliation(s)
- Jiashun Mao
- The Interdisciplinary Graduate Program in Integrative Biotechnology and Translational Medicine, Yonsei University, Incheon 21983, Republic of Korea
- Department of Biology, School of Life Sciences, Southern University of Science and Technology, 1088 Xueyuan Avenue, Shenzhen, Guangdong 518055, China
- Guangdong Provincial Key Laboratory of Computational Science and Material Design, Shenzhen, Guangdong 518055 China
| | - Javed Akhtar
- Department of Biology, School of Life Sciences, Southern University of Science and Technology, 1088 Xueyuan Avenue, Shenzhen, Guangdong 518055, China
- Guangdong Provincial Key Laboratory of Cell Microenvironment and Disease Research, Shenzhen, Guangdong 518055, China
| | - Xiao Zhang
- Shanghai Rural Commercial Bank Co., Ltd, Shanghai 200002, China
| | - Liang Sun
- Department of Physics, City University of Hong Kong, 83 Tat Chee Avenue, Kowloon, Hong Kong, China
| | - Shenghui Guan
- Department of Biology, School of Life Sciences, Southern University of Science and Technology, 1088 Xueyuan Avenue, Shenzhen, Guangdong 518055, China
- Guangdong Provincial Key Laboratory of Computational Science and Material Design, Shenzhen, Guangdong 518055 China
| | - Xinyu Li
- School of Life and Health Sciences and Warshel Institute for Computational Biology, The Chinese University of Hong Kong, Shenzhen 518172, China
| | - Guangming Chen
- Department of Biology, School of Life Sciences, Southern University of Science and Technology, 1088 Xueyuan Avenue, Shenzhen, Guangdong 518055, China
- Guangdong Provincial Key Laboratory of Cell Microenvironment and Disease Research, Shenzhen, Guangdong 518055, China
| | - Jiaxin Liu
- Biotechnology, College of Life Science and Biotechnology, Yonsei University, Seoul 03722, Republic of Korea
| | - Hyeon-Nae Jeon
- Biotechnology, College of Life Science and Biotechnology, Yonsei University, Seoul 03722, Republic of Korea
| | - Min Sung Kim
- Biotechnology, College of Life Science and Biotechnology, Yonsei University, Seoul 03722, Republic of Korea
| | - Kyoung Tai No
- The Interdisciplinary Graduate Program in Integrative Biotechnology and Translational Medicine, Yonsei University, Incheon 21983, Republic of Korea
| | - Guanyu Wang
- Department of Biology, School of Life Sciences, Southern University of Science and Technology, 1088 Xueyuan Avenue, Shenzhen, Guangdong 518055, China
- Guangdong Provincial Key Laboratory of Computational Science and Material Design, Shenzhen, Guangdong 518055 China
- Guangdong Provincial Key Laboratory of Cell Microenvironment and Disease Research, Shenzhen, Guangdong 518055, China
| |
Collapse
|
8
|
Titov IY, Stroylov VS, Rusina P, Svitanko IV. Preliminary modelling as the first stage of targeted organic synthesis. RUSSIAN CHEMICAL REVIEWS 2021. [DOI: 10.1070/rcr5012] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
The review aims to present a classification and applicability analysis of methods for preliminary molecular modelling for targeted organic, catalytic and biocatalytic synthesis. The following three main approaches are considered as a primary classification of the methods: modelling of the target – ligand coordination without structural information on both the target and the resulting complex; calculations based on experimentally obtained structural information about the target; and dynamic simulation of the target – ligand complex and the reaction mechanism with calculation of the free energy of the reaction. The review is meant for synthetic chemists to be used as a guide for building an algorithm for preliminary modelling and synthesis of structures with specified properties.
The bibliography includes 353 references.
Collapse
|
9
|
Piroozmand F, Mohammadipanah F, Sajedi H. Spectrum of deep learning algorithms in drug discovery. Chem Biol Drug Des 2021; 96:886-901. [PMID: 33058458 DOI: 10.1111/cbdd.13674] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2019] [Revised: 02/11/2020] [Accepted: 02/19/2020] [Indexed: 12/16/2022]
Abstract
Deep learning (DL) algorithms are a subset of machine learning algorithms with the aim of modeling complex mapping between a set of elements and their classes. In parallel to the advance in revealing the molecular bases of diseases, a notable innovation has been undertaken to apply DL in data/libraries management, reaction optimizations, differentiating uncertainties, molecule constructions, creating metrics from qualitative results, and prediction of structures or interactions. From source identification to lead discovery and medicinal chemistry of the drug candidate, drug delivery, and modification, the challenges can be subjected to artificial intelligence algorithms to aid in the generation and interpretation of data. Discovery and design approach, both demand automation, large data management and data fusion by the advance in high-throughput mode. The application of DL can accelerate the exploration of drug mechanisms, finding novel indications for existing drugs (drug repositioning), drug development, and preclinical and clinical studies. The impact of DL in the workflow of drug discovery, design, and their complementary tools are highlighted in this review. Additionally, the type of DL algorithms used for this purpose, and their pros and cons along with the dominant directions of future research are presented.
Collapse
Affiliation(s)
- Firoozeh Piroozmand
- Pharmaceutical Biotechnology Lab, Department of Microbiology, School of Biology and Center of Excellence in Phylogeny of Living Organisms, College of Science, University of Tehran, Tehran, Iran
| | - Fatemeh Mohammadipanah
- Pharmaceutical Biotechnology Lab, Department of Microbiology, School of Biology and Center of Excellence in Phylogeny of Living Organisms, College of Science, University of Tehran, Tehran, Iran
| | - Hedieh Sajedi
- Department of Computer Science, School of Mathematics, Statistics and Computer Science, College of Science, University of Tehran, Tehran, Iran
| |
Collapse
|
10
|
Reker D. Practical considerations for active machine learning in drug discovery. DRUG DISCOVERY TODAY. TECHNOLOGIES 2020; 32-33:73-79. [PMID: 33386097 DOI: 10.1016/j.ddtec.2020.06.001] [Citation(s) in RCA: 23] [Impact Index Per Article: 5.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/15/2020] [Revised: 06/01/2020] [Accepted: 06/10/2020] [Indexed: 02/01/2023]
Abstract
Active machine learning enables the automated selection of the most valuable next experiments to improve predictive modelling and hasten active retrieval in drug discovery. Although a long established theoretical concept and introduced to drug discovery approximately 15 years ago, the deployment of active learning technology in the discovery pipelines across academia and industry remains slow. With the recent re-discovered enthusiasm for artificial intelligence as well as improved flexibility of laboratory automation, active learning is expected to surge and become a key technology for molecular optimizations. This review recapitulates key findings from previous active learning studies to highlight the challenges and opportunities of applying adaptive machine learning to drug discovery. Specifically, considerations regarding implementation, infrastructural integration, and expected benefits are discussed. By focusing on these practical aspects of active learning, this review aims at providing insights for scientists planning to implement active learning workflows in their discovery pipelines.
Collapse
Affiliation(s)
- Daniel Reker
- Koch Institute for Integrative Cancer Research and MIT-IBM Watson AI Lab, Massachusetts Institute of Technology, Cambridge, MA, USA; Division of Gastroenterology, Hepatology and Endoscopy, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
| |
Collapse
|
11
|
Vucicevic J, Nikolic K, Mitchell JB. Rational Drug Design of Antineoplastic Agents Using 3D-QSAR, Cheminformatic, and Virtual Screening Approaches. Curr Med Chem 2019; 26:3874-3889. [DOI: 10.2174/0929867324666170712115411] [Citation(s) in RCA: 15] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/27/2017] [Revised: 06/06/2017] [Accepted: 06/13/2017] [Indexed: 01/07/2023]
Abstract
Background:Computer-Aided Drug Design has strongly accelerated the development of novel antineoplastic agents by helping in the hit identification, optimization, and evaluation.Results:Computational approaches such as cheminformatic search, virtual screening, pharmacophore modeling, molecular docking and dynamics have been developed and applied to explain the activity of bioactive molecules, design novel agents, increase the success rate of drug research, and decrease the total costs of drug discovery. Similarity, searches and virtual screening are used to identify molecules with an increased probability to interact with drug targets of interest, while the other computational approaches are applied for the design and evaluation of molecules with enhanced activity and improved safety profile.Conclusion:In this review are described the main in silico techniques used in rational drug design of antineoplastic agents and presented optimal combinations of computational methods for design of more efficient antineoplastic drugs.
Collapse
Affiliation(s)
- Jelica Vucicevic
- Department of Pharmaceutical Chemistry, Faculty of Pharmacy, University of Belgrade, Vojvode Stepe 450, 11000 Belgrade, Serbia
| | - Katarina Nikolic
- Department of Pharmaceutical Chemistry, Faculty of Pharmacy, University of Belgrade, Vojvode Stepe 450, 11000 Belgrade, Serbia
| | - John B.O. Mitchell
- EaStCHEM School of Chemistry and Biomedical Sciences Research Complex, University of St Andrews, St Andrews KY16 9ST, United Kingdom
| |
Collapse
|
12
|
Miyao T, Funatsu K. Iterative Screening Methods for Identification of Chemical Compounds with Specific Values of Various Properties. J Chem Inf Model 2019; 59:2626-2641. [PMID: 31058504 DOI: 10.1021/acs.jcim.9b00093] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
Abstract
Identification of chemical compounds having desirable properties is a central goal of screening campaigns. Iterative screening is a means of surveying a set of compounds, during which their property values are determined and used as feedback for regression models. Quantitative models that assess the relationships between chemical structures and property/activity are repeatedly updated through this type of cycle, and the efficient sampling of compounds for the subsequent test is a key factor in the early identification of target compounds. Nevertheless, methodological approaches to comparisons and to establishing the degree of extrapolation of sampled compounds, including the effects of applicability domains, are still required. In the present study, we conducted a series of virtual experiments to assess the characteristics of different iterative screening methods. Genetic algorithm-based partial least-squares regression, support vector regression, Bayesian optimization with Gaussian Process (GP), and batch-based Bayesian optimization with GP (GP_batch) were all compared, based on the analysis of one million compounds extracted from the ZINC database. Our results show that, irrespective of the diversity of the initial set of compounds, it was possible to identify a compound having the desired property value using the appropriate screening method. However, overall, the GP_batch method was found to be preferable when evaluating properties either which are difficult to predict or for which a key factor is present in the set of molecular descriptors.
Collapse
Affiliation(s)
- Tomoyuki Miyao
- Data Science Center and Graduate School of Science and Technology , Nara Institute of Science and Technology , 8916-5 Takayama-cho , Ikoma , Nara 630-0192 , Japan
| | - Kimito Funatsu
- Data Science Center and Graduate School of Science and Technology , Nara Institute of Science and Technology , 8916-5 Takayama-cho , Ikoma , Nara 630-0192 , Japan.,Department of Chemical System Engineering, School of Engineering , The University of Tokyo , 7-3-1 Hongo , Bunkyo-ku , Tokyo 113-8656 , Japan
| |
Collapse
|
13
|
Cleves AE, Jain AN. Quantitative surface field analysis: learning causal models to predict ligand binding affinity and pose. J Comput Aided Mol Des 2018; 32:731-757. [PMID: 29934750 PMCID: PMC6096883 DOI: 10.1007/s10822-018-0126-x] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2018] [Accepted: 06/14/2018] [Indexed: 12/27/2022]
Abstract
We introduce the QuanSA method for inducing physically meaningful field-based models of ligand binding pockets based on structure-activity data alone. The method is closely related to the QMOD approach, substituting a learned scoring field for a pocket constructed of molecular fragments. The problem of mutual ligand alignment is addressed in a general way, and optimal model parameters and ligand poses are identified through multiple-instance machine learning. We provide algorithmic details along with performance results on sixteen structure-activity data sets covering many pharmaceutically relevant targets. In particular, we show how models initially induced from small data sets can extrapolatively identify potent new ligands with novel underlying scaffolds with very high specificity. Further, we show that combining predictions from QuanSA models with those from physics-based simulation approaches is synergistic. QuanSA predictions yield binding affinities, explicit estimates of ligand strain, associated ligand pose families, and estimates of structural novelty and confidence. The method is applicable for fine-grained lead optimization as well as potent new lead identification.
Collapse
Affiliation(s)
- Ann E Cleves
- Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, USA
| | - Ajay N Jain
- Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, USA.
| |
Collapse
|
14
|
Nikolic K, Mavridis L, Djikic T, Vucicevic J, Agbaba D, Yelekci K, Mitchell JBO. Drug Design for CNS Diseases: Polypharmacological Profiling of Compounds Using Cheminformatic, 3D-QSAR and Virtual Screening Methodologies. Front Neurosci 2016; 10:265. [PMID: 27375423 PMCID: PMC4901078 DOI: 10.3389/fnins.2016.00265] [Citation(s) in RCA: 52] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/22/2016] [Accepted: 05/25/2016] [Indexed: 11/13/2022] Open
Abstract
HIGHLIGHTSMany CNS targets are being explored for multi-target drug design New databases and cheminformatic methods enable prediction of primary pharmaceutical target and off-targets of compounds QSAR, virtual screening and docking methods increase the potential of rational drug design
The diverse cerebral mechanisms implicated in Central Nervous System (CNS) diseases together with the heterogeneous and overlapping nature of phenotypes indicated that multitarget strategies may be appropriate for the improved treatment of complex brain diseases. Understanding how the neurotransmitter systems interact is also important in optimizing therapeutic strategies. Pharmacological intervention on one target will often influence another one, such as the well-established serotonin-dopamine interaction or the dopamine-glutamate interaction. It is now accepted that drug action can involve plural targets and that polypharmacological interaction with multiple targets, to address disease in more subtle and effective ways, is a key concept for development of novel drug candidates against complex CNS diseases. A multi-target therapeutic strategy for Alzheimer‘s disease resulted in the development of very effective Multi-Target Designed Ligands (MTDL) that act on both the cholinergic and monoaminergic systems, and also retard the progression of neurodegeneration by inhibiting amyloid aggregation. Many compounds already in databases have been investigated as ligands for multiple targets in drug-discovery programs. A probabilistic method, the Parzen-Rosenblatt Window approach, was used to build a “predictor” model using data collected from the ChEMBL database. The model can be used to predict both the primary pharmaceutical target and off-targets of a compound based on its structure. Several multi-target ligands were selected for further study, as compounds with possible additional beneficial pharmacological activities. Based on all these findings, it is concluded that multipotent ligands targeting AChE/MAO-A/MAO-B and also D1-R/D2-R/5-HT2A-R/H3-R are promising novel drug candidates with improved efficacy and beneficial neuroleptic and procognitive activities in treatment of Alzheimer's and related neurodegenerative diseases. Structural information for drug targets permits docking and virtual screening and exploration of the molecular determinants of binding, hence facilitating the design of multi-targeted drugs. The crystal structures and models of enzymes of the monoaminergic and cholinergic systems have been used to investigate the structural origins of target selectivity and to identify molecular determinants, in order to design MTDLs.
Collapse
Affiliation(s)
- Katarina Nikolic
- Department of Pharmaceutical Chemistry, Faculty of Pharmacy, University of Belgrade Belgrade, Serbia
| | - Lazaros Mavridis
- School of Biological and Chemical Sciences, Queen Mary University of London London, UK
| | - Teodora Djikic
- Department of Bioinformatics and Genetics, Faculty of Engineering and Natural Sciences, Kadir Has University Istanbul, Turkey
| | - Jelica Vucicevic
- Department of Pharmaceutical Chemistry, Faculty of Pharmacy, University of Belgrade Belgrade, Serbia
| | - Danica Agbaba
- Department of Pharmaceutical Chemistry, Faculty of Pharmacy, University of Belgrade Belgrade, Serbia
| | - Kemal Yelekci
- Department of Bioinformatics and Genetics, Faculty of Engineering and Natural Sciences, Kadir Has University Istanbul, Turkey
| | - John B O Mitchell
- EaStCHEM School of Chemistry and Biomedical Sciences Research Complex, University of St Andrews St Andrews, UK
| |
Collapse
|
15
|
Reker D, Schneider P, Schneider G. Multi-objective active machine learning rapidly improves structure-activity models and reveals new protein-protein interaction inhibitors. Chem Sci 2016; 7:3919-3927. [PMID: 30155037 PMCID: PMC6013791 DOI: 10.1039/c5sc04272k] [Citation(s) in RCA: 42] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2015] [Accepted: 02/27/2016] [Indexed: 11/21/2022] Open
Abstract
Active machine learning puts artificial intelligence in charge of a sequential, feedback-driven discovery process. We present the application of a multi-objective active learning scheme for identifying small molecules that inhibit the protein-protein interaction between the anti-cancer target CXC chemokine receptor 4 (CXCR4) and its endogenous ligand CXCL-12 (SDF-1). Experimental design by active learning was used to retrieve informative active compounds that continuously improved the adaptive structure-activity model. The balanced character of the compound selection function rapidly delivered new molecular structures with the desired inhibitory activity and at the same time allowed us to focus on informative compounds for model adjustment. The results of our study validate active learning for prospective ligand finding by adaptive, focused screening of large compound repositories and virtual compound libraries.
Collapse
Affiliation(s)
- D Reker
- Department of Chemistry and Applied Biosciences , ETH Zürich , Vladimir-Prelog Weg 4 , 8093 Zürich , Switzerland .
| | - P Schneider
- Department of Chemistry and Applied Biosciences , ETH Zürich , Vladimir-Prelog Weg 4 , 8093 Zürich , Switzerland .
| | - G Schneider
- Department of Chemistry and Applied Biosciences , ETH Zürich , Vladimir-Prelog Weg 4 , 8093 Zürich , Switzerland .
| |
Collapse
|
16
|
Cleves AE, Jain AN. Extrapolative prediction using physically-based QSAR. J Comput Aided Mol Des 2016; 30:127-52. [PMID: 26860112 PMCID: PMC4796382 DOI: 10.1007/s10822-016-9896-1] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/14/2015] [Accepted: 01/21/2016] [Indexed: 11/25/2022]
Abstract
Surflex-QMOD integrates chemical structure and activity data to produce physically-realistic models for binding affinity prediction
. Here, we apply QMOD to a 3D-QSAR benchmark dataset and show broad applicability to a diverse set of targets. Testing new ligands within the QMOD model employs automated flexible molecular alignment, with the model itself defining the optimal pose for each ligand. QMOD performance was compared to that of four approaches that depended on manual alignments (CoMFA, two variations of CoMSIA, and CMF). QMOD showed comparable performance to the other methods on a challenging, but structurally limited, test set. The QMOD models were also applied to test a large and structurally diverse dataset of ligands from ChEMBL, nearly all of which were synthesized years after those used for model construction. Extrapolation across diverse chemical structures was possible because the method addresses the ligand pose problem and provides structural and geometric means to quantitatively identify ligands within a model’s applicability domain. Predictions for such ligands for the four tested targets were highly statistically significant based on rank correlation. Those molecules predicted to be highly active (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\hbox {pK}_i \ge 7.5$$\end{document}pKi≥7.5) had a mean experimental \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\hbox {pK}_i$$\end{document}pKi of 7.5, with potent and structurally novel ligands being identified by QMOD for each target.
Collapse
Affiliation(s)
- Ann E Cleves
- Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, CA, USA
| | - Ajay N Jain
- Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, CA, USA.
| |
Collapse
|
17
|
Liu S, Wang L, Mobley DL. Is ring breaking feasible in relative binding free energy calculations? J Chem Inf Model 2015; 55:727-35. [PMID: 25835054 DOI: 10.1021/acs.jcim.5b00057] [Citation(s) in RCA: 41] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
Our interest is relative binding free energy (RBFE) calculations based on molecular simulations. These are promising tools for lead optimization in drug discovery, computing changes in binding free energy due to modifications of a lead compound. However, in the "alchemical" framework for RBFE calculations, some types of mutations have the potential to introduce error into the computed binding free energies. Here we explore the magnitude of this error in several different model binding calculations. We find that some of the calculations involving ring breaking have significant errors, and these errors are especially large in bridged ring systems. Since the error is a function of ligand strain, which is unpredictable in advance, we believe that ring breaking should be avoided when possible.
Collapse
Affiliation(s)
- Shuai Liu
- †Department of Pharmaceutical Sciences and Department of Chemistry, University of California, Irvine, 147 Bison Modular, Irvine, California 92697, United States
| | - Lingle Wang
- ‡Schrödinger, Inc., 120 West 45th Street, New York, New York 10036, United States
| | - David L Mobley
- †Department of Pharmaceutical Sciences and Department of Chemistry, University of California, Irvine, 147 Bison Modular, Irvine, California 92697, United States
| |
Collapse
|
18
|
Reker D, Schneider G. Active-learning strategies in computer-assisted drug discovery. Drug Discov Today 2015; 20:458-65. [DOI: 10.1016/j.drudis.2014.12.004] [Citation(s) in RCA: 100] [Impact Index Per Article: 11.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2014] [Revised: 11/13/2014] [Accepted: 12/02/2014] [Indexed: 12/20/2022]
|
19
|
Cherkasov A, Muratov EN, Fourches D, Varnek A, Baskin II, Cronin M, Dearden J, Gramatica P, Martin YC, Todeschini R, Consonni V, Kuz'min VE, Cramer R, Benigni R, Yang C, Rathman J, Terfloth L, Gasteiger J, Richard A, Tropsha A. QSAR modeling: where have you been? Where are you going to? J Med Chem 2014; 57:4977-5010. [PMID: 24351051 PMCID: PMC4074254 DOI: 10.1021/jm4004285] [Citation(s) in RCA: 1040] [Impact Index Per Article: 104.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/08/2023]
Abstract
Quantitative structure-activity relationship modeling is one of the major computational tools employed in medicinal chemistry. However, throughout its entire history it has drawn both praise and criticism concerning its reliability, limitations, successes, and failures. In this paper, we discuss (i) the development and evolution of QSAR; (ii) the current trends, unsolved problems, and pressing challenges; and (iii) several novel and emerging applications of QSAR modeling. Throughout this discussion, we provide guidelines for QSAR development, validation, and application, which are summarized in best practices for building rigorously validated and externally predictive QSAR models. We hope that this Perspective will help communications between computational and experimental chemists toward collaborative development and use of QSAR models. We also believe that the guidelines presented here will help journal editors and reviewers apply more stringent scientific standards to manuscripts reporting new QSAR studies, as well as encourage the use of high quality, validated QSARs for regulatory decision making.
Collapse
Affiliation(s)
- Artem Cherkasov
- Vancouver Prostate Centre, University of British Columbia, Vancouver, BC, V6H3Z6, Canada
| | - Eugene N. Muratov
- Laboratory for Molecular Modeling, UNC Eshelman School of Pharmacy, University of North Carolina, Chapel Hill, NC, 27599, USA
- Department of Molecular Structure and Cheminformatics, A.V. Bogatsky Physical-Chemical Institute National Academy of Sciences of Ukraine, Odessa, 65080, Ukraine
| | - Denis Fourches
- Laboratory for Molecular Modeling, UNC Eshelman School of Pharmacy, University of North Carolina, Chapel Hill, NC, 27599, USA
| | - Alexandre Varnek
- Department of Chemistry, L. Pasteur University of Strasbourg, Strasbourg, 67000, France
| | - Igor I. Baskin
- Department of Physics, Lomonosov Moscow State University, Moscow, 119991, Russia
| | - Mark Cronin
- School of Pharmacy and Biomolecular Sciences, Liverpool John Moores University, Liverpool L33AF, UK
| | - John Dearden
- School of Pharmacy and Biomolecular Sciences, Liverpool John Moores University, Liverpool L33AF, UK
| | - Paola Gramatica
- Department of Structural and Functional Biology, University of Insubria, Varese, 21100, Italy
| | | | - Roberto Todeschini
- Milano Chemometrics and QSAR Research Group, University of Milano-Bicocca, Milan, 20126, Italy
| | - Viviana Consonni
- Milano Chemometrics and QSAR Research Group, University of Milano-Bicocca, Milan, 20126, Italy
| | - Victor E. Kuz'min
- Department of Molecular Structure and Cheminformatics, A.V. Bogatsky Physical-Chemical Institute National Academy of Sciences of Ukraine, Odessa, 65080, Ukraine
| | | | - Romualdo Benigni
- Environment and Health Department, Istituto Superiore di Sanita’, Rome, 00161, Italy
| | | | - James Rathman
- Altamira LLC, Columbus OH 43235, USA
- Department of Chemical and Biomolecular Engineering, the Ohio State University, Columbus, OH 43215, USA
| | | | | | - Ann Richard
- National Center for Computational Toxicology, U.S. Environmental Protection Agency, Research Triangle Park, NC, 27519, USA
| | - Alexander Tropsha
- Laboratory for Molecular Modeling, UNC Eshelman School of Pharmacy, University of North Carolina, Chapel Hill, NC, 27599, USA
| |
Collapse
|
20
|
Zhan W, Li D, Che J, Zhang L, Yang B, Hu Y, Liu T, Dong X. Integrating docking scores, interaction profiles and molecular descriptors to improve the accuracy of molecular docking: Toward the discovery of novel Akt1 inhibitors. Eur J Med Chem 2014; 75:11-20. [DOI: 10.1016/j.ejmech.2014.01.019] [Citation(s) in RCA: 38] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/04/2013] [Revised: 01/08/2014] [Accepted: 01/13/2014] [Indexed: 11/30/2022]
|
21
|
Varela R, Cleves AE, Spitzer R, Jain AN. A structure-guided approach for protein pocket modeling and affinity prediction. J Comput Aided Mol Des 2013; 27:917-34. [PMID: 24214361 PMCID: PMC3851759 DOI: 10.1007/s10822-013-9688-9] [Citation(s) in RCA: 7] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/29/2013] [Accepted: 10/25/2013] [Indexed: 11/25/2022]
Abstract
Binding affinity prediction is frequently addressed using computational models constructed solely with molecular structure and activity data. We present a hybrid structure-guided strategy that combines molecular similarity, docking, and multiple-instance learning such that information from protein structures can be used to inform models of structure-activity relationships. The Surflex-QMOD approach has been shown to produce accurate predictions of binding affinity by constructing an interpretable physical model of a binding site with no experimental binding site structural information. We introduce a method to integrate protein structure information into the model induction process in order to construct more robust physical models. The structure-guided models accurately predict binding affinities over a broad range of compounds while producing more accurate representations of the protein pockets and ligand binding modes. Structure-guidance for the QMOD method yielded significant performance improvements, both for affinity and pose prediction, especially in cases where predictions were made on ligands very different from those used for model induction.
Collapse
Affiliation(s)
| | - Ann E. Cleves
- Helen Diller Family Comprehensive Cancer Center, University of California, San Francisco, San Francisco, CA USA
| | | | - Ajay N. Jain
- Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco, San Francisco, CA USA
| |
Collapse
|