Feature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics

Abstract Machine learning is widely applied in drug discovery research to predict molecular properties and aid in the identification of active compounds. Herein, we introduce a new approach that uses model-internal information from compound activity predictions to uncover relationships between targe...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Raquel Rodríguez-Pérez, Jürgen Bajorath
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/bc252408c3dc491e81bac622c5fb9155
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bc252408c3dc491e81bac622c5fb9155
record_format	dspace
spelling	oai:doaj.org-article:bc252408c3dc491e81bac622c5fb91552021-12-02T16:24:50ZFeature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics10.1038/s41598-021-93771-y2045-2322https://doaj.org/article/bc252408c3dc491e81bac622c5fb91552021-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-93771-yhttps://doaj.org/toc/2045-2322Abstract Machine learning is widely applied in drug discovery research to predict molecular properties and aid in the identification of active compounds. Herein, we introduce a new approach that uses model-internal information from compound activity predictions to uncover relationships between target proteins. On the basis of a large-scale analysis generating and comparing machine learning models for more than 200 proteins, feature importance correlation analysis is shown to detect similar compound binding characteristics. Furthermore, rather unexpectedly, the analysis also reveals functional relationships between proteins that are independent of active compounds and binding characteristics. Feature importance correlation analysis does not depend on specific representations, algorithms, or metrics and is generally applicable as long as predictive models can be derived. Moreover, the approach does not require or involve explainable or interpretable machine learning, but only access to feature weights or importance values. On the basis of our findings, the approach represents a new facet of machine learning in drug discovery with potential for practical applications.Raquel Rodríguez-PérezJürgen BajorathNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Raquel Rodríguez-Pérez Jürgen Bajorath Feature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics
description	Abstract Machine learning is widely applied in drug discovery research to predict molecular properties and aid in the identification of active compounds. Herein, we introduce a new approach that uses model-internal information from compound activity predictions to uncover relationships between target proteins. On the basis of a large-scale analysis generating and comparing machine learning models for more than 200 proteins, feature importance correlation analysis is shown to detect similar compound binding characteristics. Furthermore, rather unexpectedly, the analysis also reveals functional relationships between proteins that are independent of active compounds and binding characteristics. Feature importance correlation analysis does not depend on specific representations, algorithms, or metrics and is generally applicable as long as predictive models can be derived. Moreover, the approach does not require or involve explainable or interpretable machine learning, but only access to feature weights or importance values. On the basis of our findings, the approach represents a new facet of machine learning in drug discovery with potential for practical applications.
format	article
author	Raquel Rodríguez-Pérez Jürgen Bajorath
author_facet	Raquel Rodríguez-Pérez Jürgen Bajorath
author_sort	Raquel Rodríguez-Pérez
title	Feature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics
title_short	Feature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics
title_full	Feature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics
title_fullStr	Feature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics
title_full_unstemmed	Feature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics
title_sort	feature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/bc252408c3dc491e81bac622c5fb9155
work_keys_str_mv	AT raquelrodriguezperez featureimportancecorrelationfrommachinelearningindicatesfunctionalrelationshipsbetweenproteinsandsimilarcompoundbindingcharacteristics AT jurgenbajorath featureimportancecorrelationfrommachinelearningindicatesfunctionalrelationshipsbetweenproteinsandsimilarcompoundbindingcharacteristics
_version_	1718384135013138432

Feature importance correlation from machine learning indicates functional relationships between proteins and similar compound binding characteristics

Ejemplares similares