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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61388963%3A_____%2F24%3A00581097" target="_blank" >RIV/61388963:_____/24:00581097 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/61989592:15310/24:73627556

Výsledek na webu

<a href="https://doi.org/10.1039/D3RA08147H" target="_blank" >https://doi.org/10.1039/D3RA08147H</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1039/d3ra08147h" target="_blank" >10.1039/d3ra08147h</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10403 - Physical chemistry

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

RSC Advances

ISSN

2046-2069

e-ISSN

2046-2069

Svazek periodika

14

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

13

Strana od-do

1341-1353

Kód UT WoS článku

001135725900001

EID výsledku v databázi Scopus

2-s2.0-85183320570