Cargando…

A subcomponent-guided deep learning method for interpretable cancer drug response prediction

Accurate prediction of cancer drug response (CDR) is a longstanding challenge in modern oncology that underpins personalized treatment. Current computational methods implement CDR prediction by modeling responses between entire drugs and cell lines, without the consideration that response outcomes m...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Xuan, Zhang, Wen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10470940/
https://www.ncbi.nlm.nih.gov/pubmed/37603576
http://dx.doi.org/10.1371/journal.pcbi.1011382
_version_ 1785099794575785984
author Liu, Xuan
Zhang, Wen
author_facet Liu, Xuan
Zhang, Wen
author_sort Liu, Xuan
collection PubMed
description Accurate prediction of cancer drug response (CDR) is a longstanding challenge in modern oncology that underpins personalized treatment. Current computational methods implement CDR prediction by modeling responses between entire drugs and cell lines, without the consideration that response outcomes may primarily attribute to a few finer-level ‘subcomponents’, such as privileged substructures of the drug or gene signatures of the cancer cell, thus producing predictions that are hard to explain. Herein, we present SubCDR, a subcomponent-guided deep learning method for interpretable CDR prediction, to recognize the most relevant subcomponents driving response outcomes. Technically, SubCDR is built upon a line of deep neural networks that enables a set of functional subcomponents to be extracted from each drug and cell line profile, and breaks the CDR prediction down to identifying pairwise interactions between subcomponents. Such a subcomponent interaction form can offer a traceable path to explicitly indicate which subcomponents contribute more to the response outcome. We verify the superiority of SubCDR over state-of-the-art CDR prediction methods through extensive computational experiments on the GDSC dataset. Crucially, we found many predicted cases that demonstrate the strength of SubCDR in finding the key subcomponents driving responses and exploiting these subcomponents to discover new therapeutic drugs. These results suggest that SubCDR will be highly useful for biomedical researchers, particularly in anti-cancer drug design.
format Online
Article
Text
id pubmed-10470940
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-104709402023-09-01 A subcomponent-guided deep learning method for interpretable cancer drug response prediction Liu, Xuan Zhang, Wen PLoS Comput Biol Research Article Accurate prediction of cancer drug response (CDR) is a longstanding challenge in modern oncology that underpins personalized treatment. Current computational methods implement CDR prediction by modeling responses between entire drugs and cell lines, without the consideration that response outcomes may primarily attribute to a few finer-level ‘subcomponents’, such as privileged substructures of the drug or gene signatures of the cancer cell, thus producing predictions that are hard to explain. Herein, we present SubCDR, a subcomponent-guided deep learning method for interpretable CDR prediction, to recognize the most relevant subcomponents driving response outcomes. Technically, SubCDR is built upon a line of deep neural networks that enables a set of functional subcomponents to be extracted from each drug and cell line profile, and breaks the CDR prediction down to identifying pairwise interactions between subcomponents. Such a subcomponent interaction form can offer a traceable path to explicitly indicate which subcomponents contribute more to the response outcome. We verify the superiority of SubCDR over state-of-the-art CDR prediction methods through extensive computational experiments on the GDSC dataset. Crucially, we found many predicted cases that demonstrate the strength of SubCDR in finding the key subcomponents driving responses and exploiting these subcomponents to discover new therapeutic drugs. These results suggest that SubCDR will be highly useful for biomedical researchers, particularly in anti-cancer drug design. Public Library of Science 2023-08-21 /pmc/articles/PMC10470940/ /pubmed/37603576 http://dx.doi.org/10.1371/journal.pcbi.1011382 Text en © 2023 Liu, Zhang https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Liu, Xuan
Zhang, Wen
A subcomponent-guided deep learning method for interpretable cancer drug response prediction
title A subcomponent-guided deep learning method for interpretable cancer drug response prediction
title_full A subcomponent-guided deep learning method for interpretable cancer drug response prediction
title_fullStr A subcomponent-guided deep learning method for interpretable cancer drug response prediction
title_full_unstemmed A subcomponent-guided deep learning method for interpretable cancer drug response prediction
title_short A subcomponent-guided deep learning method for interpretable cancer drug response prediction
title_sort subcomponent-guided deep learning method for interpretable cancer drug response prediction
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10470940/
https://www.ncbi.nlm.nih.gov/pubmed/37603576
http://dx.doi.org/10.1371/journal.pcbi.1011382
work_keys_str_mv AT liuxuan asubcomponentguideddeeplearningmethodforinterpretablecancerdrugresponseprediction
AT zhangwen asubcomponentguideddeeplearningmethodforinterpretablecancerdrugresponseprediction
AT liuxuan subcomponentguideddeeplearningmethodforinterpretablecancerdrugresponseprediction
AT zhangwen subcomponentguideddeeplearningmethodforinterpretablecancerdrugresponseprediction