Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets

Abstract Protein kinases are receiving wide research interest, from drug perspective, due to their important roles in human body. Available kinase-inhibitor data, including crystallized structures, revealed many details about the mechanism of inhibition and binding modes. The understanding and analy...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ibrahim Abdelbaky, Hilal Tayara, Kil To Chong
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/f0877084a5104e888bb76bd9c90bee5b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f0877084a5104e888bb76bd9c90bee5b
record_format	dspace
spelling	oai:doaj.org-article:f0877084a5104e888bb76bd9c90bee5b2021-12-02T15:23:08ZPrediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets10.1038/s41598-020-80758-42045-2322https://doaj.org/article/f0877084a5104e888bb76bd9c90bee5b2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-80758-4https://doaj.org/toc/2045-2322Abstract Protein kinases are receiving wide research interest, from drug perspective, due to their important roles in human body. Available kinase-inhibitor data, including crystallized structures, revealed many details about the mechanism of inhibition and binding modes. The understanding and analysis of these binding modes are expected to support the discovery of kinase-targeting drugs. The huge amounts of data made it possible to utilize computational techniques, including machine learning, to help in the discovery of kinase-targeting drugs. Machine learning gave reasonable predictions when applied to differentiate between the binding modes of kinase inhibitors, promoting a wider application in that domain. In this study, we applied machine learning supported by feature selection techniques to classify kinase inhibitors according to their binding modes. We represented inhibitors as a large number of molecular descriptors, as features, and systematically reduced these features in a multi-step manner while trying to attain high classification accuracy. Our predictive models could satisfy both goals by achieving high accuracy while utilizing at most 5% of the modeling features. The models could differentiate between binding mode types with MCC values between 0.67 and 0.92, and balanced accuracy values between 0.78 and 0.97 for independent test sets.Ibrahim AbdelbakyHilal TayaraKil To ChongNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ibrahim Abdelbaky Hilal Tayara Kil To Chong Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets
description	Abstract Protein kinases are receiving wide research interest, from drug perspective, due to their important roles in human body. Available kinase-inhibitor data, including crystallized structures, revealed many details about the mechanism of inhibition and binding modes. The understanding and analysis of these binding modes are expected to support the discovery of kinase-targeting drugs. The huge amounts of data made it possible to utilize computational techniques, including machine learning, to help in the discovery of kinase-targeting drugs. Machine learning gave reasonable predictions when applied to differentiate between the binding modes of kinase inhibitors, promoting a wider application in that domain. In this study, we applied machine learning supported by feature selection techniques to classify kinase inhibitors according to their binding modes. We represented inhibitors as a large number of molecular descriptors, as features, and systematically reduced these features in a multi-step manner while trying to attain high classification accuracy. Our predictive models could satisfy both goals by achieving high accuracy while utilizing at most 5% of the modeling features. The models could differentiate between binding mode types with MCC values between 0.67 and 0.92, and balanced accuracy values between 0.78 and 0.97 for independent test sets.
format	article
author	Ibrahim Abdelbaky Hilal Tayara Kil To Chong
author_facet	Ibrahim Abdelbaky Hilal Tayara Kil To Chong
author_sort	Ibrahim Abdelbaky
title	Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets
title_short	Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets
title_full	Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets
title_fullStr	Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets
title_full_unstemmed	Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets
title_sort	prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/f0877084a5104e888bb76bd9c90bee5b
work_keys_str_mv	AT ibrahimabdelbaky predictionofkinaseinhibitorsbindingmodeswithmachinelearningandreduceddescriptorsets AT hilaltayara predictionofkinaseinhibitorsbindingmodeswithmachinelearningandreduceddescriptorsets AT kiltochong predictionofkinaseinhibitorsbindingmodeswithmachinelearningandreduceddescriptorsets
_version_	1718387361351467008

Prediction of kinase inhibitors binding modes with machine learning and reduced descriptor sets

Ejemplares similares