Výsledky vyhledávání - "Druchok, Maksym"

Report

Machine learning-assisted search for novel coagulants: when machine learning can be efficient even if data availability is low

Autor: Rovenchak, Andrij, Druchok, Maksym

Publikováno v: J. Comput. Chem. 45, No. 13, 937-952 (2024)

Design of new drugs is a challenging process: a candidate molecule should satisfy multiple conditions to act properly and make the least side-effect -- perfect candidates selectively attach to and influence only targets, leaving off-targets intact. T

Externí odkaz: http://arxiv.org/abs/2401.01811

Zobrazit plný text záznamu

Report

One-dimensionally confined ammonia molecules: A theoretical study

Autor: Druchok, Maksym, Krasnov, Volodymyr, Krokhmalskii, Taras, Derzhko, Oleg

Publikováno v: Journal of Molecular Liquids, Volume 387, 1 October 2023, 122633

We examine a single-file chain of ammonia molecules in a carbon nanotube. To this end, we use i) molecular dynamics simulations (combined with the charges for ammonia nitrogen and hydrogen obtained from quantum chemistry) and ii) lattice-model calcul

Externí odkaz: http://arxiv.org/abs/2307.06186

Zobrazit plný text záznamu

Report

Towards a quasiphase transition in the single-file chain of water molecules: Simple lattice model

Autor: Druchok, Maksym, Krasnov, Volodymyr, Krokhmalskii, Taras, Bufalo, Tatiana Cardoso e, de Souza, Sergio Martins, Rojas, Onofre, Derzhko, Oleg

Publikováno v: J. Chem. Phys. 158, 104304 (2023)

Recently, X.Ma et al. [Phys. Rev. Lett. 118, 027402 (2017)] have suggested that water molecules encapsulated in (6,5) single-wall carbon nanotube experience a temperature-induced quasiphase transition around 150 K interpreted as changes in the water

Externí odkaz: http://arxiv.org/abs/2302.09362

Zobrazit plný text záznamu

Report

High throughput screening with machine learning

Autor: Gurbych, Oleksandr, Druchok, Maksym, Yarish, Dzvenymyra, Garkot, Sofiya

This study assesses the efficiency of several popular machine learning approaches in the prediction of molecular binding affinity: CatBoost, Graph Attention Neural Network, and Bidirectional Encoder Representations from Transformers. The models were

Externí odkaz: http://arxiv.org/abs/2012.08275

Zobrazit plný text záznamu