Biology subjects

Yesylevskyy, S.

Publications and source records attributed to Yesylevskyy, S..

7 recordsLinked to original sources

bioRxiv2025

Sampling and ranking of protein conformations using machine learning techniques do not improve quality of rigid protein-protein docking

Rigid docking remains the most popular method of predicting protein-protein interactions in cases when experimental 3D structures of the complexes are not available. The docking often relies on known unbound (Apo) protein structures, which may differ significantly from their bound (Holo) forms. Modern machine learning (ML) based conformational sampling techniques allow generating ensembles of functionally relevant protein structures, which may be closer to their Holo forms and thus could improve the outcomes of the classical rigid protein-protein docking. Here, we sampled conformations of the protein subunits in 30 complexes from the novel PINDER dataset with two state-of-the-art ML-based techniques and evaluated their docking performance using several physics-based, data-based, and ML-based scoring functions. We showed that such conformational sampling rarely produces structures that are closer to the Holo conformations than the corresponding Apo ones. Moreover, even when such conformations are generated, none of the tested scoring functions were able to prioritize and rank them correctly. Our work highlights critical limitations in the current ML-enhanced rigid protein-protein docking workflows and emphasizes the need for new approaches that can better utilize the potential of modern techniques for conformational generation and scoring.

biophysics↗

bioRxiv2025

Leveraging Large Language Models for Literature-Driven Prioritization of Protein Binding Pockets

We present a novel approach for the identification and prioritization of protein binding pockets for small molecules by combining geometric pocket detection with Large Language Models (LLMs). Our method leverages Fpocket to generate candidate pockets, which are then validated against published experimental data extracted from research articles using LLM with a series of prompts fine-tuned to identify and extract residue-level information associated with experimentally confirmed binding sites. We developed a curated benchmark dataset of diverse proteins and associated literature to train and evaluate the LLMs performance in paper relevance assessment and pocket extraction. The extracted information is then mapped onto protein structures and used to filter and merge the geometry-based predictions, generating a refined volumetric representation of biologically relevant pockets. This hybrid pipeline offers an efficient, accurate and automated method for identifying functional binding pockets, addressing a significant bottleneck in the high-throughput drug discovery workflows. The developed benchmark dataset and methodology are freely available at https://github.com/MelnychenkoM/LLM-benchmark-dataset.

biophysics↗

bioRxiv2024

MolAR: memory-safe library for analysis of MD simulations written in Rust

Transition to the memory safe natively compiled programming languages is a major software development trend in recent years, which eliminates memory-related security exploits, enables a fearless concurrency and parallelization, and drastically improves ergonomics and speed of software development. Modern memory-safe programing languages, such as Rust, are currently not used for developing molecular modeling and simulation software despite such obvious benefits as faster development cycle, better performance and smaller amount of bugs. In this work we present MolAR -the first memory-safe library for analysis of MD simulations written in Rust. MolAR is intended to explore the advantages and challenges of implementing molecular analysis software in the memory-safe natively compiled language and to develop specific memory-safe abstractions for this kind of software. MolAR demonstrates an excellent performance in benchmarks outperforming popular molecular analysis libraries, which makes it attractive for implementing computationally intensive analysis tasks. MolAR is freely available under Artistic License 2.0 at https://github.com/yesint/molar.

biophysics↗

bioRxiv2024

ArtiDock: fast and accurate machine learning approach to protein-ligand docking based on multimodal data augmentation

Classical protein-ligand docking has been a cornerstone technique in computational drug discovery for decades, but has reached an accuracy and performance plateau. Recently introduced Machine Learning (ML) based docking methods offer a promising paradigm shift, but their practical adoption is hampered by accuracy-to-speed trade-offs, inadequate benchmarking standards, and questionable chemical validity of predicted poses. In this study, we introduce ArtiDock - an ML-based docking technique optimized for high-throughput virtual screening applications. To evaluate ArtiDock, we developed a dedicated performance and accuracy benchmark for pocket-specific rigid protein-ligand docking, which mimics realistic industrial drug discovery scenarios and is based on the novel PLINDER dataset. We demonstrate that ArtiDock is 29-38% more accurate in comparison to leading open-source and commercial classical docking techniques such as AutoDock, Vina, and Glide, while providing a low computational cost. ArtiDock notably excels in challenging docking scenarios involving unbound protein structures and binding sites containing ions and structured water molecules. Our results show that ArtiDock could be considered as a method of choice in high-throughput virtual screening scenarios.

bioinformatics↗

bioRxiv2022

3DProtDTA: the deep learning model for drug-target affinity prediction based on the 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 was 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 a potential for further improvement.

pharmacology and toxicology↗

bioRxiv2019

Curvature increases permeability of the plasma membrane for ions, water and the anti-cancer drugs cisplatin and gemcitabine

In this work the permeability of a model asymmetric plasma membrane, for ions, water and the anti-cancer drugs cisplatin and gemcitabine is studied by means of all-atom molecular dynamics simulations. It is shown that permeability of the membranes increases from one to three orders of magnitude upon membrane bending depending on the compound and the sign of curvature. Our results show that the membrane curvature is an important factor which should be considered during evaluation of drug translocation.\n\nTOC GRAPHICS O_FIG_DISPLAY_L [Figure 1] M_FIG_DISPLAY C_FIG_DISPLAY

biophysics↗

bioRxiv2018

Permeation of cisplatin through the membranes of normal and cancer cells: a molecular dynamics study

In this work, realistic models of membranes of normal and cancer cells are developed. A special focus is given to their cholesterol content. It is shown that the loss of lipid asymmetry in the membranes of cancer cells leads to a decrease of their permeability to cisplatin by one order of magnitude in comparison to the membranes of normal cells. The change of cholesterol molar ratio from 0% to 33% also decreases the permeability of the membrane by approximately one order of magnitude. The permeability of pure DOPC membrane is 5-6 orders of magnitude higher than one of the membrane with realistic lipid composition, which makes it as an inadequate model for the studies of drug permeability.

biophysics↗