Machine learning accelerates pharmacophore-based virtual screening of MAO inhibitors

2024
journal article
article
dc.abstract.enNowadays, an efficient and robust virtual screening procedure is crucial in the drug discovery process, especially when performed on large and chemically diverse databases. Virtual screening methods, like molecular docking and classic QSAR models, are limited in their ability to handle vast numbers of compounds and to learn from scarce data, respectively. In this study, we introduce a universal methodology that uses a machine learning-based approach to predict docking scores without the need for time-consuming molecular docking procedures. The developed protocol yielded 1000 times faster binding energy predictions than classical docking-based screening. The proposed predictive model learns from docking results, allowing users to choose their preferred docking software without relying on insufficient and incoherent experimental activity data. The methodology described employs multiple types of molecular fingerprints and descriptors to construct an ensemble model that further reduces prediction errors and is capable of delivering highly precise docking score values for monoamine oxidase ligands, enabling faster identification of promising compounds. An extensive pharmacophore-constrained screening of the ZINC database resulted in a selection of 24 compounds that were synthesized and evaluated for their biological activity. A preliminary screen discovered weak inhibitors of MAO-A with a percentage efficiency index close to a known drug at the lowest tested concentration. The approach presented here can be successfully applied to other biological targets as target-specific knowledge is not incorporated at the screening phase.
dc.affiliationWydział Chemii : Zakład Krystalochemii i Krystalofizyki
dc.affiliationSzkoła Doktorska Nauk Ścisłych i Przyrodniczych
dc.contributor.authorCieślak, Marcin - 257266
dc.contributor.authorDanel, Tomasz - 231736
dc.contributor.authorKrzysztyńska-Kuleta, Olga - 167054
dc.contributor.authorKalinowska-Tłuścik, Justyna - SAP12019196
dc.date.accession2024-04-18
dc.date.accessioned2024-04-18T13:03:44Z
dc.date.available2024-04-18T13:03:44Z
dc.date.issued2024
dc.date.openaccess0
dc.description.accesstimew momencie opublikowania
dc.description.versionostateczna wersja wydawcy
dc.description.volume14
dc.identifier.articleid8228
dc.identifier.doi10.1038/s41598-024-58122-7
dc.identifier.issn2045-2322
dc.identifier.urihttps://ruj.uj.edu.pl/handle/item/329477
dc.identifier.weblinkhttps://www.nature.com/articles/s41598-024-58122-7
dc.languageeng
dc.language.containereng
dc.rightsUdzielam licencji. Uznanie autorstwa 4.0 Międzynarodowa
dc.rights.licenceCC-BY
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/legalcode.pl
dc.share.typeotwarte czasopismo
dc.subject.enmachine learning
dc.subject.envirtual screening
dc.subject.enmonoamine oxidase inhibitors
dc.subject.enmolecular descriptors
dc.subject.enmolecular docking
dc.subtypeArticle
dc.titleMachine learning accelerates pharmacophore-based virtual screening of MAO inhibitors
dc.title.journalScientific Reports
dc.typeJournalArticle
dspace.entity.typePublicationen
dc.abstract.en
Nowadays, an efficient and robust virtual screening procedure is crucial in the drug discovery process, especially when performed on large and chemically diverse databases. Virtual screening methods, like molecular docking and classic QSAR models, are limited in their ability to handle vast numbers of compounds and to learn from scarce data, respectively. In this study, we introduce a universal methodology that uses a machine learning-based approach to predict docking scores without the need for time-consuming molecular docking procedures. The developed protocol yielded 1000 times faster binding energy predictions than classical docking-based screening. The proposed predictive model learns from docking results, allowing users to choose their preferred docking software without relying on insufficient and incoherent experimental activity data. The methodology described employs multiple types of molecular fingerprints and descriptors to construct an ensemble model that further reduces prediction errors and is capable of delivering highly precise docking score values for monoamine oxidase ligands, enabling faster identification of promising compounds. An extensive pharmacophore-constrained screening of the ZINC database resulted in a selection of 24 compounds that were synthesized and evaluated for their biological activity. A preliminary screen discovered weak inhibitors of MAO-A with a percentage efficiency index close to a known drug at the lowest tested concentration. The approach presented here can be successfully applied to other biological targets as target-specific knowledge is not incorporated at the screening phase.
dc.affiliation
Wydział Chemii : Zakład Krystalochemii i Krystalofizyki
dc.affiliation
Szkoła Doktorska Nauk Ścisłych i Przyrodniczych
dc.contributor.author
Cieślak, Marcin - 257266
dc.contributor.author
Danel, Tomasz - 231736
dc.contributor.author
Krzysztyńska-Kuleta, Olga - 167054
dc.contributor.author
Kalinowska-Tłuścik, Justyna - SAP12019196
dc.date.accession
2024-04-18
dc.date.accessioned
2024-04-18T13:03:44Z
dc.date.available
2024-04-18T13:03:44Z
dc.date.issued
2024
dc.date.openaccess
0
dc.description.accesstime
w momencie opublikowania
dc.description.version
ostateczna wersja wydawcy
dc.description.volume
14
dc.identifier.articleid
8228
dc.identifier.doi
10.1038/s41598-024-58122-7
dc.identifier.issn
2045-2322
dc.identifier.uri
https://ruj.uj.edu.pl/handle/item/329477
dc.identifier.weblink
https://www.nature.com/articles/s41598-024-58122-7
dc.language
eng
dc.language.container
eng
dc.rights
Udzielam licencji. Uznanie autorstwa 4.0 Międzynarodowa
dc.rights.licence
CC-BY
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/legalcode.pl
dc.share.type
otwarte czasopismo
dc.subject.en
machine learning
dc.subject.en
virtual screening
dc.subject.en
monoamine oxidase inhibitors
dc.subject.en
molecular descriptors
dc.subject.en
molecular docking
dc.subtype
Article
dc.title
Machine learning accelerates pharmacophore-based virtual screening of MAO inhibitors
dc.title.journal
Scientific Reports
dc.type
JournalArticle
dspace.entity.typeen
Publication

* The migration of download and view statistics prior to the date of April 8, 2024 is in progress.

Views
46
Views per month
Views per city
Krakow
21
Downloads
cieslak_danel_krzysztynska-kuleta_kalinowska-tluscik_machine_learning_accelerates_2024.pdf
5
s41598-024-58122-7.pdf
1