Machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations

Abstract Compounds with defined multi-target activity (promiscuity) play an increasingly important role in drug discovery. However, the molecular basis of multi-target activity is currently only little understood. In particular, it remains unclear whether structural features exist that generally cha...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Christian Feldmann, Jürgen Bajorath
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/83b7d8f712e044dbb9f8249f70d76be9
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:83b7d8f712e044dbb9f8249f70d76be9
record_format dspace
spelling oai:doaj.org-article:83b7d8f712e044dbb9f8249f70d76be92021-12-02T15:51:16ZMachine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations10.1038/s41598-021-87042-z2045-2322https://doaj.org/article/83b7d8f712e044dbb9f8249f70d76be92021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87042-zhttps://doaj.org/toc/2045-2322Abstract Compounds with defined multi-target activity (promiscuity) play an increasingly important role in drug discovery. However, the molecular basis of multi-target activity is currently only little understood. In particular, it remains unclear whether structural features exist that generally characterize promiscuous compounds and set them apart from compounds with single-target activity. We have devised a test system using machine learning to systematically examine structural features that might characterize compounds with multi-target activity. Using this system, more than 860,000 diagnostic predictions were carried out. The analysis provided compelling evidence for the presence of structural characteristics of promiscuous compounds that were dependent on given target combinations, but not generalizable. Feature weighting and mapping identified characteristic substructures in test compounds. Taken together, these findings are relevant for the design of compounds with desired multi-target activity.Christian FeldmannJürgen BajorathNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-7 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Christian Feldmann
Jürgen Bajorath
Machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations
description Abstract Compounds with defined multi-target activity (promiscuity) play an increasingly important role in drug discovery. However, the molecular basis of multi-target activity is currently only little understood. In particular, it remains unclear whether structural features exist that generally characterize promiscuous compounds and set them apart from compounds with single-target activity. We have devised a test system using machine learning to systematically examine structural features that might characterize compounds with multi-target activity. Using this system, more than 860,000 diagnostic predictions were carried out. The analysis provided compelling evidence for the presence of structural characteristics of promiscuous compounds that were dependent on given target combinations, but not generalizable. Feature weighting and mapping identified characteristic substructures in test compounds. Taken together, these findings are relevant for the design of compounds with desired multi-target activity.
format article
author Christian Feldmann
Jürgen Bajorath
author_facet Christian Feldmann
Jürgen Bajorath
author_sort Christian Feldmann
title Machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations
title_short Machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations
title_full Machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations
title_fullStr Machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations
title_full_unstemmed Machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations
title_sort machine learning reveals that structural features distinguishing promiscuous and non-promiscuous compounds depend on target combinations
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/83b7d8f712e044dbb9f8249f70d76be9
work_keys_str_mv AT christianfeldmann machinelearningrevealsthatstructuralfeaturesdistinguishingpromiscuousandnonpromiscuouscompoundsdependontargetcombinations
AT jurgenbajorath machinelearningrevealsthatstructuralfeaturesdistinguishingpromiscuousandnonpromiscuouscompoundsdependontargetcombinations
_version_ 1718385645225771008