Standard

Predictive modeling of antibacterial activity of ionic liquids by machine learning methods. / Makarov, D.m.; Fadeeva, Yu.a.; Сафонова, Евгения Алексеевна; Shmukler, L.e.

в: Computational Biology and Chemistry, Том 101, 107775, 01.12.2022.

Результаты исследований: Научные публикации в периодических изданияхстатьяРецензирование

Harvard

APA

Makarov, D. M., Fadeeva, Y. A., Сафонова, Е. А., & Shmukler, L. E. (2022). Predictive modeling of antibacterial activity of ionic liquids by machine learning methods. Computational Biology and Chemistry, 101, [107775]. https://doi.org/10.1016/j.compbiolchem.2022.107775

Vancouver

Author

Makarov, D.m. ; Fadeeva, Yu.a. ; Сафонова, Евгения Алексеевна ; Shmukler, L.e. / Predictive modeling of antibacterial activity of ionic liquids by machine learning methods. в: Computational Biology and Chemistry. 2022 ; Том 101.

BibTeX

@article{2d09ea4cd7254408a2de707a6078528f,
title = "Predictive modeling of antibacterial activity of ionic liquids by machine learning methods",
abstract = "Structural variation and different bioactivity of ionic liquids (ILs) make them highly promising for the development of novel biocides. Application of computational methods to the evaluation of potential antibacterial activity of chemical compounds is a useful, time- and cost-saving tool replacing numerous experimental syntheses. In the present study, quantitative structure–activity relationship (QSAR) modeling is applied to develop models (based on more than 800 data points) aiming to predict the minimal inhibitory concentration (MIC) of ILs against three types of human pathogens – Staphylococcus aureus, Escherichia coli and Pseudomonas aeruginosa. The random forest model with the AlvaDesc descriptors in general demonstrates the best performance for all the three types of bacteria and is suggested as a final model. To interpret the final model and determine the most significant descriptors, a SHapley Additive exPlanation (SHAP) method was applied. Six amino acid ILs, which were synthesized for the first time, and five halogenide ionic liquids purchased, all based on 1-alkyl-3methylimidozolium cations with different alkyl chain lengths, C10, C12 and C14, are tested in vitro and used to validate the developed QSAR models. The data sets and developed model are available free of charge at http://ochem.eu/article/147386.",
keywords = "Antibacterial activity, Ionic Liquids, OCHEM, QSAR",
author = "D.m. Makarov and Yu.a. Fadeeva and Сафонова, {Евгения Алексеевна} and L.e. Shmukler",
note = "Publisher Copyright: {\textcopyright} 2022 Elsevier Ltd",
year = "2022",
month = dec,
day = "1",
doi = "10.1016/j.compbiolchem.2022.107775",
language = "English",
volume = "101",
journal = "Computational Biology and Chemistry",
issn = "1476-9271",
publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Predictive modeling of antibacterial activity of ionic liquids by machine learning methods

AU - Makarov, D.m.

AU - Fadeeva, Yu.a.

AU - Сафонова, Евгения Алексеевна

AU - Shmukler, L.e.

N1 - Publisher Copyright: © 2022 Elsevier Ltd

PY - 2022/12/1

Y1 - 2022/12/1

N2 - Structural variation and different bioactivity of ionic liquids (ILs) make them highly promising for the development of novel biocides. Application of computational methods to the evaluation of potential antibacterial activity of chemical compounds is a useful, time- and cost-saving tool replacing numerous experimental syntheses. In the present study, quantitative structure–activity relationship (QSAR) modeling is applied to develop models (based on more than 800 data points) aiming to predict the minimal inhibitory concentration (MIC) of ILs against three types of human pathogens – Staphylococcus aureus, Escherichia coli and Pseudomonas aeruginosa. The random forest model with the AlvaDesc descriptors in general demonstrates the best performance for all the three types of bacteria and is suggested as a final model. To interpret the final model and determine the most significant descriptors, a SHapley Additive exPlanation (SHAP) method was applied. Six amino acid ILs, which were synthesized for the first time, and five halogenide ionic liquids purchased, all based on 1-alkyl-3methylimidozolium cations with different alkyl chain lengths, C10, C12 and C14, are tested in vitro and used to validate the developed QSAR models. The data sets and developed model are available free of charge at http://ochem.eu/article/147386.

AB - Structural variation and different bioactivity of ionic liquids (ILs) make them highly promising for the development of novel biocides. Application of computational methods to the evaluation of potential antibacterial activity of chemical compounds is a useful, time- and cost-saving tool replacing numerous experimental syntheses. In the present study, quantitative structure–activity relationship (QSAR) modeling is applied to develop models (based on more than 800 data points) aiming to predict the minimal inhibitory concentration (MIC) of ILs against three types of human pathogens – Staphylococcus aureus, Escherichia coli and Pseudomonas aeruginosa. The random forest model with the AlvaDesc descriptors in general demonstrates the best performance for all the three types of bacteria and is suggested as a final model. To interpret the final model and determine the most significant descriptors, a SHapley Additive exPlanation (SHAP) method was applied. Six amino acid ILs, which were synthesized for the first time, and five halogenide ionic liquids purchased, all based on 1-alkyl-3methylimidozolium cations with different alkyl chain lengths, C10, C12 and C14, are tested in vitro and used to validate the developed QSAR models. The data sets and developed model are available free of charge at http://ochem.eu/article/147386.

KW - Antibacterial activity

KW - Ionic Liquids

KW - OCHEM

KW - QSAR

UR - https://www.mendeley.com/catalogue/9da001bd-0c31-335d-a6e7-4dd1543a4cd0/

UR - http://www.scopus.com/inward/record.url?scp=85140034455&partnerID=8YFLogxK

U2 - 10.1016/j.compbiolchem.2022.107775

DO - 10.1016/j.compbiolchem.2022.107775

M3 - Article

VL - 101

JO - Computational Biology and Chemistry

JF - Computational Biology and Chemistry

SN - 1476-9271

M1 - 107775

ER -

ID: 99470163