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 3 条
  • [1] 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)
  • [2] 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
  • [3] 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
    Eurtivong, Chatchakorn
    Zimmer, Collin
    Schirmeister, Tanja
    Butkinaree, Chutikarn
    Saruengkhanphasit, Rungroj
    Niwetmarin, Worawat
    Ruchirawat, Somsak
    Bhambra, Avninder S. S.
    MOLECULAR DIVERSITY, 2024, 28 (02) : 531 - 551