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

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.

3DProtDTA: a deep learning model for drug-target affinity prediction based on residue-level protein graphs.

Accurate prediction of the drug-target affinity (DTA) in silico is of critical importance for modern drug discovery. Computational methods of DTA prediction, applied in the early stages of drug development, are able to speed it up and cut its cost significantly. A wide range of approaches based on machine learning were recently proposed for DTA assessment. The most promising of them are based on deep learning techniques and graph neural networks to encode molecular structures. The recent breakthrough in protein structure prediction made by AlphaFold made an unprecedented amount of proteins without experimentally defined structures accessible for computational DTA prediction. In this work, we propose a new deep learning DTA model 3DProtDTA, which utilises AlphaFold structure predictions in conjunction with the graph representation of proteins. The model is superior to its rivals on common benchmarking datasets and has potential for further improvement.

Identification of Novel Antistaphylococcal Hit Compounds Targeting Sortase A.

Staphylococcus aureus (S. aureus) is a causative agent of many hospital- and community-acquired infections with the tendency to develop resistance to all known antibiotics. Therefore, the development of novel antistaphylococcal agents is of urgent need. Sortase A is considered a promising molecular target for the development of antistaphylococcal agents. The main aim of this study was to identify novel sortase A inhibitors. In order to find novel antistaphylococcal agents, we performed phenotypic screening of a library containing 15512 compounds against S. aureus ATCC43300. The molecular docking of hits was performed using the DOCK program and 10 compounds were selected for in vitro enzymatic activity inhibition assay. Two inhibitors were identified, N,N-diethyl-N'-(5-nitro-2-(quinazolin-2-yl)phenyl)propane-1,3-diamine (1) and acridin-9-yl-(1H-benzoimidazol-5-yl)-amine (2), which decrease sortase A activity with IC50 values of 160.3 µM and 207.01 µM, respectively. It was found that compounds 1 and 2 possess antibacterial activity toward 29 tested multidrug resistant S. aureus strains with MIC values ranging from 78.12 to 312.5 mg/L. These compounds can be used for further structural optimization and biological research.