» Articles » PMID: 34769065

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

Overview
Journal Int J Mol Sci
Publisher MDPI
Date 2021 Nov 13
PMID 34769065
Citations 7
Authors
Affiliations
Soon will be listed here.
Abstract

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.

Citing Articles

Accurate prediction of protein-ligand interactions by combining physical energy functions and graph-neural networks.

Hong Y, Ha J, Sim J, Lim C, Oh K, Chandrasekaran R J Cheminform. 2024; 16(1):121.

PMID: 39497201 PMC: 11536843. DOI: 10.1186/s13321-024-00912-2.


DrugGym: A testbed for the economics of autonomous drug discovery.

Retchin M, Wang Y, Takaba K, Chodera J bioRxiv. 2024; .

PMID: 38854082 PMC: 11160604. DOI: 10.1101/2024.05.28.596296.


Integrating QSAR modelling and deep learning in drug discovery: the emergence of deep QSAR.

Tropsha A, Isayev O, Varnek A, Schneider G, Cherkasov A Nat Rev Drug Discov. 2023; 23(2):141-155.

PMID: 38066301 DOI: 10.1038/s41573-023-00832-0.


HIt Discovery using docking ENriched by GEnerative Modeling (HIDDEN GEM): A novel computational workflow for accelerated virtual screening of ultra-large chemical libraries.

Popov K, Wellnitz J, Maxfield T, Tropsha A Mol Inform. 2023; 43(1):e202300207.

PMID: 37802967 PMC: 11156482. DOI: 10.1002/minf.202300207.


Optimizing interactions to protein binding sites by integrating docking-scoring strategies into generative AI methods.

Sauer S, Matter H, Hessler G, Grebner C Front Chem. 2022; 10:1012507.

PMID: 36339033 PMC: 9629386. DOI: 10.3389/fchem.2022.1012507.


References
1.
Kim S, Chen J, Cheng T, Gindulyte A, He J, He S . PubChem in 2021: new data content and improved web interfaces. Nucleic Acids Res. 2020; 49(D1):D1388-D1395. PMC: 7778930. DOI: 10.1093/nar/gkaa971. View

2.
Krishnan S, Bung N, Bulusu G, Roy A . Accelerating Drug Design against Novel Proteins Using Deep Learning. J Chem Inf Model. 2021; 61(2):621-630. DOI: 10.1021/acs.jcim.0c01060. View

3.
Gentile F, Agrawal V, Hsing M, Ton A, Ban F, Norinder U . Deep Docking: A Deep Learning Platform for Augmentation of Structure Based Drug Discovery. ACS Cent Sci. 2020; 6(6):939-949. PMC: 7318080. DOI: 10.1021/acscentsci.0c00229. View

4.
Zhang M, Wilkinson B . Drug discovery beyond the 'rule-of-five'. Curr Opin Biotechnol. 2007; 18(6):478-88. DOI: 10.1016/j.copbio.2007.10.005. View

5.
Yoshimori A, Kawasaki E, Kanai C, Tasaka T . Strategies for Design of Molecular Structures with a Desired Pharmacophore Using Deep Reinforcement Learning. Chem Pharm Bull (Tokyo). 2020; 68(3):227-233. DOI: 10.1248/cpb.c19-00625. View