V-Dock: Fast Generation of Novel Drug-like Molecules Using Machine-Learning-Based Docking Score and Molecular Optimization

被引:11
|
作者
Choi, Jieun [1 ]
Lee, Juyong [1 ,2 ]
机构
[1] Kangwon Natl Univ, Dept Chem, Div Chem & Biochem, Chunchon 24341, South Korea
[2] Arontier Co, Seoul 06735, South Korea
基金
新加坡国家研究基金会;
关键词
protein-ligand docking; computer-aided drug discovery; docking score prediction; quantitative estimation of drug-likeness (QED); conformational space annealing (CSA); Lipinski's rule of five; V-dock; MolFinder; deep learning; molecular property optimization; DESIGN; DISCOVERY;
D O I
10.3390/ijms222111635
中图分类号
Q5 [生物化学]; Q7 [分子生物学];
学科分类号
071010 ; 081704 ;
摘要
We propose a computational workflow to design novel drug-like molecules by combining the global optimization of molecular properties and protein-ligand docking with machine learning. However, most existing methods depend heavily on experimental data, and many targets do not have sufficient data to train reliable activity prediction models. To overcome this limitation, protein-ligand docking calculations must be performed using the limited data available. Such docking calculations during molecular generation require considerable computational time, preventing extensive exploration of the chemical space. To address this problem, we trained a machine-learning-based model that predicted the docking energy using SMILES to accelerate the molecular generation process. Docking scores could be accurately predicted using only a SMILES string. We combined this docking score prediction model with the global molecular property optimization approach, MolFinder, to find novel molecules exhibiting the desired properties with high values of predicted docking scores. We named this design approach V-dock. Using V-dock, we efficiently generated many novel molecules with high docking scores for a target protein, a similarity to the reference molecule, and desirable drug-like and bespoke properties, such as QED. The predicted docking scores of the generated molecules were verified by correlating them with the actual docking scores.
引用
收藏
页数:18
相关论文
共 14 条
  • [1] Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions
    Peter Ertl
    Ansgar Schuffenhauer
    Journal of Cheminformatics, 1
  • [2] Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions
    Ertl, Peter
    Schuffenhauer, Ansgar
    JOURNAL OF CHEMINFORMATICS, 2009, 1
  • [3] Quantum-based machine learning and AI models to generate force field parameters for drug-like small molecules
    Mudedla, Sathish Kumar
    Braka, Abdennour
    Wu, Sangwook
    FRONTIERS IN MOLECULAR BIOSCIENCES, 2022, 9
  • [4] Efficient and enhanced sampling of drug-like chemical space for virtual screening and molecular design using modern machine learning methods
    Goel, Manan
    Aggarwal, Rishal
    Sridharan, Bhuvanesh
    Pal, Pradeep Kumar
    Priyakumar, U. Deva
    WILEY INTERDISCIPLINARY REVIEWS-COMPUTATIONAL MOLECULAR SCIENCE, 2023, 13 (02)
  • [5] Machine Learning-Based Drug Repositioning of Novel Human Aromatase Inhibitors Utilizing Molecular Docking and Molecular Dynamic Simulation
    Bodun, Damilola Samuel
    Abdulwahab, Adeniyi Ayinde
    Adegbenro, Temitope Ibukunoluwa
    Chidinma, Emidun Olayinka
    Osunnaya, Samuel Aduramurewa
    Alonge, Mary Oluwatominsin
    Diyaolu, Zainab Olaide
    Abdulazeez, Muhammad Temitope
    Abolade, Rachael Oluwakamiye
    JOURNAL OF COMPUTATIONAL BIOPHYSICS AND CHEMISTRY, 2025, 24 (03): : 371 - 387
  • [6] Virtual screening approach to identifying influenza virus neuraminidase inhibitors using molecular docking combined with machine-learning-based scoring function
    Zhang, Li
    Ai, Hai-Xin
    Li, Shi-Meng
    Qi, Meng-Yuan
    Zhao, Jian
    Zhao, Qi
    Liu, Hong-Sheng
    ONCOTARGET, 2017, 8 (47) : 83142 - 83154
  • [7] Machine Learning-Based Drug Repositioning of Novel Janus Kinase 2 Inhibitors Utilizing Molecular Docking and Molecular Dynamic Simulation
    Yasir, Muhammad
    Park, Jinyoung
    Han, Eun-Taek
    Park, Won Sun
    Han, Jin-Hee
    Kwon, Yong-Soo
    Lee, Hee-Jae
    Chun, Wanjoo
    JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2023, 63 (21) : 6487 - 6500
  • [8] Machine Learning-Based Drug Repositioning of Novel Janus Kinase 2 Inhibitors Utilizing Molecular Docking and Molecular Dynamic Simulation
    Department of Pharmacology, Kangwon National University School of Medicine, Chuncheon
    24341, Korea, Republic of
    不详
    24341, Korea, Republic of
    不详
    24341, Korea, Republic of
    不详
    24341, Korea, Republic of
    J. Chem. Inf. Model., 1600, 21 (6487-6500): : 6487 - 6500
  • [9] Discovery of Cobimetinib as a novel A-FABP inhibitor using machine learning and molecular docking-based virtual screening
    Yang, Shilun
    Li, Simeng
    Chang, Junlei
    RSC ADVANCES, 2022, 12 (21) : 13500 - 13510
  • [10] A structure-based virtual high-throughput screening, molecular docking, molecular dynamics and MM/PBSA study identified novel putative drug-like dual inhibitors of trypanosomal cruzain and rhodesain cysteine proteases
    Chatchakorn Eurtivong
    Collin Zimmer
    Tanja Schirmeister
    Chutikarn Butkinaree
    Rungroj Saruengkhanphasit
    Worawat Niwetmarin
    Somsak Ruchirawat
    Avninder S. Bhambra
    Molecular Diversity, 2024, 28 : 531 - 551