Augmenting a training dataset of the generative diffusion model for molecular docking with artificial binding pockets

0581097 - ÚOCHB 2025 RIV GB eng J - Článek v odborném periodiku
Voitsitskyi, T. - Bdzhola, V. - Stratiichuk, R. - Koleiev, I. - Ostrovsky, Z. - Vozniak, V. - Khropachov, I. - Henitsoi, P. - Popryho, L. - Zhytar, R. - Yesylevskyy, Semen - Nafiiev, A. - Starosyla, S.
Augmenting a training dataset of the generative diffusion model for molecular docking with artificial binding pockets.
RSC Advances. Roč. 14, č. 2 (2024), s. 1341-1353. E-ISSN 2046-2069
Institucionální podpora: RVO:61388963
Klíčová slova: database * collection
Impakt faktor: 3.9, rok: 2022
Způsob publikování: Open access
https://doi.org/10.1039/D3RA08147H

This study introduces the PocketCFDM generative diffusion model, aimed at improving the prediction of small molecule poses in the protein binding pockets. The model utilizes a novel data augmentation technique, involving the creation of numerous artificial binding pockets that mimic the statistical patterns of non-bond interactions found in actual protein-ligand complexes. An algorithmic method was developed to assess and replicate these interaction patterns in the artificial binding pockets built around small molecule conformers. It is shown that the integration of artificial binding pockets into the training process significantly enhanced the model's performance. Notably, PocketCFDM surpassed DiffDock in terms of non-bond interaction and steric clash numbers, and the inference speed. Future developments and optimizations of the model are discussed. The inference code and final model weights of PocketCFDM are accessible publicly via the GitHub repository: https://github.com/vtarasv/pocket-cfdm.git.
Trvalý link: https://hdl.handle.net/11104/0349647