Cargando…

Differentiating Inhibitors of Closely Related Protein Kinases with Single- or Multi-Target Activity via Explainable Machine Learning and Feature Analysis

Protein kinases are major drug targets. Most kinase inhibitors are directed against the adenosine triphosphate (ATP) cofactor binding site, which is largely conserved across the human kinome. Hence, such kinase inhibitors are often thought to be promiscuous. However, experimental evidence and activi...

Descripción completa

Detalles Bibliográficos
Autores principales: Feldmann, Christian, Bajorath, Jürgen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9032434/
https://www.ncbi.nlm.nih.gov/pubmed/35454147
http://dx.doi.org/10.3390/biom12040557
_version_ 1784692643183198208
author Feldmann, Christian
Bajorath, Jürgen
author_facet Feldmann, Christian
Bajorath, Jürgen
author_sort Feldmann, Christian
collection PubMed
description Protein kinases are major drug targets. Most kinase inhibitors are directed against the adenosine triphosphate (ATP) cofactor binding site, which is largely conserved across the human kinome. Hence, such kinase inhibitors are often thought to be promiscuous. However, experimental evidence and activity data for publicly available kinase inhibitors indicate that this is not generally the case. We have investigated whether inhibitors of closely related human kinases with single- or multi-kinase activity can be differentiated on the basis of chemical structure. Therefore, a test system consisting of two distinct kinase triplets has been devised for which inhibitors with reported triple-kinase activities and corresponding single-kinase activities were assembled. Machine learning models derived on the basis of chemical structure distinguished between these multi- and single-kinase inhibitors with high accuracy. A model-independent explanatory approach was applied to identify structural features determining accurate predictions. For both kinase triplets, the analysis revealed decisive features contained in multi-kinase inhibitors. These features were found to be absent in corresponding single-kinase inhibitors, thus providing a rationale for successful machine learning. Mapping of features determining accurate predictions revealed that they formed coherent and chemically meaningful substructures that were characteristic of multi-kinase inhibitors compared with single-kinase inhibitors.
format Online
Article
Text
id pubmed-9032434
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90324342022-04-23 Differentiating Inhibitors of Closely Related Protein Kinases with Single- or Multi-Target Activity via Explainable Machine Learning and Feature Analysis Feldmann, Christian Bajorath, Jürgen Biomolecules Article Protein kinases are major drug targets. Most kinase inhibitors are directed against the adenosine triphosphate (ATP) cofactor binding site, which is largely conserved across the human kinome. Hence, such kinase inhibitors are often thought to be promiscuous. However, experimental evidence and activity data for publicly available kinase inhibitors indicate that this is not generally the case. We have investigated whether inhibitors of closely related human kinases with single- or multi-kinase activity can be differentiated on the basis of chemical structure. Therefore, a test system consisting of two distinct kinase triplets has been devised for which inhibitors with reported triple-kinase activities and corresponding single-kinase activities were assembled. Machine learning models derived on the basis of chemical structure distinguished between these multi- and single-kinase inhibitors with high accuracy. A model-independent explanatory approach was applied to identify structural features determining accurate predictions. For both kinase triplets, the analysis revealed decisive features contained in multi-kinase inhibitors. These features were found to be absent in corresponding single-kinase inhibitors, thus providing a rationale for successful machine learning. Mapping of features determining accurate predictions revealed that they formed coherent and chemically meaningful substructures that were characteristic of multi-kinase inhibitors compared with single-kinase inhibitors. MDPI 2022-04-08 /pmc/articles/PMC9032434/ /pubmed/35454147 http://dx.doi.org/10.3390/biom12040557 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Feldmann, Christian
Bajorath, Jürgen
Differentiating Inhibitors of Closely Related Protein Kinases with Single- or Multi-Target Activity via Explainable Machine Learning and Feature Analysis
title Differentiating Inhibitors of Closely Related Protein Kinases with Single- or Multi-Target Activity via Explainable Machine Learning and Feature Analysis
title_full Differentiating Inhibitors of Closely Related Protein Kinases with Single- or Multi-Target Activity via Explainable Machine Learning and Feature Analysis
title_fullStr Differentiating Inhibitors of Closely Related Protein Kinases with Single- or Multi-Target Activity via Explainable Machine Learning and Feature Analysis
title_full_unstemmed Differentiating Inhibitors of Closely Related Protein Kinases with Single- or Multi-Target Activity via Explainable Machine Learning and Feature Analysis
title_short Differentiating Inhibitors of Closely Related Protein Kinases with Single- or Multi-Target Activity via Explainable Machine Learning and Feature Analysis
title_sort differentiating inhibitors of closely related protein kinases with single- or multi-target activity via explainable machine learning and feature analysis
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9032434/
https://www.ncbi.nlm.nih.gov/pubmed/35454147
http://dx.doi.org/10.3390/biom12040557
work_keys_str_mv AT feldmannchristian differentiatinginhibitorsofcloselyrelatedproteinkinaseswithsingleormultitargetactivityviaexplainablemachinelearningandfeatureanalysis
AT bajorathjurgen differentiatinginhibitorsofcloselyrelatedproteinkinaseswithsingleormultitargetactivityviaexplainablemachinelearningandfeatureanalysis