Explainable machine learning predictions of dual-target compounds reveal characteristic structural features

Abstract Compounds with defined multi-target activity play an increasingly important role in drug discovery. Structural features that might be signatures of such compounds have mostly remained elusive thus far. We have explored the potential of explainable machine learning to uncover structural moti...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Christian Feldmann, Maren Philipps, Jürgen Bajorath
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/e417e0653e004604a6e4ace6cc0f33c4
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:e417e0653e004604a6e4ace6cc0f33c4
record_format dspace
spelling oai:doaj.org-article:e417e0653e004604a6e4ace6cc0f33c42021-11-08T10:55:12ZExplainable machine learning predictions of dual-target compounds reveal characteristic structural features10.1038/s41598-021-01099-42045-2322https://doaj.org/article/e417e0653e004604a6e4ace6cc0f33c42021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-01099-4https://doaj.org/toc/2045-2322Abstract Compounds with defined multi-target activity play an increasingly important role in drug discovery. Structural features that might be signatures of such compounds have mostly remained elusive thus far. We have explored the potential of explainable machine learning to uncover structural motifs that are characteristic of dual-target compounds. For a pharmacologically relevant target pair-based test system designed for our study, accurate prediction models were derived and the influence of molecular representation features of test compounds was quantified to explain the predictions. The analysis revealed small numbers of specific features whose presence in dual-target and absence in single-target compounds determined accurate predictions. These features formed coherent substructures in dual-target compounds. From computational analysis of specific feature contributions, structural motifs emerged that were confirmed to be signatures of different dual-target activities. Our findings demonstrate the ability of explainable machine learning to bridge between predictions and intuitive chemical analysis and reveal characteristic substructures of dual-target compounds.Christian FeldmannMaren PhilippsJürgen BajorathNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Christian Feldmann
Maren Philipps
Jürgen Bajorath
Explainable machine learning predictions of dual-target compounds reveal characteristic structural features
description Abstract Compounds with defined multi-target activity play an increasingly important role in drug discovery. Structural features that might be signatures of such compounds have mostly remained elusive thus far. We have explored the potential of explainable machine learning to uncover structural motifs that are characteristic of dual-target compounds. For a pharmacologically relevant target pair-based test system designed for our study, accurate prediction models were derived and the influence of molecular representation features of test compounds was quantified to explain the predictions. The analysis revealed small numbers of specific features whose presence in dual-target and absence in single-target compounds determined accurate predictions. These features formed coherent substructures in dual-target compounds. From computational analysis of specific feature contributions, structural motifs emerged that were confirmed to be signatures of different dual-target activities. Our findings demonstrate the ability of explainable machine learning to bridge between predictions and intuitive chemical analysis and reveal characteristic substructures of dual-target compounds.
format article
author Christian Feldmann
Maren Philipps
Jürgen Bajorath
author_facet Christian Feldmann
Maren Philipps
Jürgen Bajorath
author_sort Christian Feldmann
title Explainable machine learning predictions of dual-target compounds reveal characteristic structural features
title_short Explainable machine learning predictions of dual-target compounds reveal characteristic structural features
title_full Explainable machine learning predictions of dual-target compounds reveal characteristic structural features
title_fullStr Explainable machine learning predictions of dual-target compounds reveal characteristic structural features
title_full_unstemmed Explainable machine learning predictions of dual-target compounds reveal characteristic structural features
title_sort explainable machine learning predictions of dual-target compounds reveal characteristic structural features
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/e417e0653e004604a6e4ace6cc0f33c4
work_keys_str_mv AT christianfeldmann explainablemachinelearningpredictionsofdualtargetcompoundsrevealcharacteristicstructuralfeatures
AT marenphilipps explainablemachinelearningpredictionsofdualtargetcompoundsrevealcharacteristicstructuralfeatures
AT jurgenbajorath explainablemachinelearningpredictionsofdualtargetcompoundsrevealcharacteristicstructuralfeatures
_version_ 1718442575672639488