Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines

Abstract Computational models for drug sensitivity prediction have the potential to significantly improve personalized cancer medicine. Drug sensitivity assays, combined with profiling of cancer cell lines and drugs become increasingly available for training such models. Multiple methods were propos...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Krzysztof Koras, Ewa Kizling, Dilafruz Juraeva, Eike Staub, Ewa Szczurek
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/5ca6b6ee38d84c60b90d71aa1aaab0aa
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5ca6b6ee38d84c60b90d71aa1aaab0aa
record_format dspace
spelling oai:doaj.org-article:5ca6b6ee38d84c60b90d71aa1aaab0aa2021-12-02T18:49:36ZInterpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines10.1038/s41598-021-94564-z2045-2322https://doaj.org/article/5ca6b6ee38d84c60b90d71aa1aaab0aa2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-94564-zhttps://doaj.org/toc/2045-2322Abstract Computational models for drug sensitivity prediction have the potential to significantly improve personalized cancer medicine. Drug sensitivity assays, combined with profiling of cancer cell lines and drugs become increasingly available for training such models. Multiple methods were proposed for predicting drug sensitivity from cancer cell line features, some in a multi-task fashion. So far, no such model leveraged drug inhibition profiles. Importantly, multi-task models require a tailored approach to model interpretability. In this work, we develop DEERS, a neural network recommender system for kinase inhibitor sensitivity prediction. The model utilizes molecular features of the cancer cell lines and kinase inhibition profiles of the drugs. DEERS incorporates two autoencoders to project cell line and drug features into 10-dimensional hidden representations and a feed-forward neural network to combine them into response prediction. We propose a novel interpretability approach, which in addition to the set of modeled features considers also the genes and processes outside of this set. Our approach outperforms simpler matrix factorization models, achieving R  $$=$$ =  0.82 correlation between true and predicted response for the unseen cell lines. The interpretability analysis identifies 67 biological processes that drive the cell line sensitivity to particular compounds. Detailed case studies are shown for PHA-793887, XMD14-99 and Dabrafenib.Krzysztof KorasEwa KizlingDilafruz JuraevaEike StaubEwa SzczurekNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-16 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Krzysztof Koras
Ewa Kizling
Dilafruz Juraeva
Eike Staub
Ewa Szczurek
Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines
description Abstract Computational models for drug sensitivity prediction have the potential to significantly improve personalized cancer medicine. Drug sensitivity assays, combined with profiling of cancer cell lines and drugs become increasingly available for training such models. Multiple methods were proposed for predicting drug sensitivity from cancer cell line features, some in a multi-task fashion. So far, no such model leveraged drug inhibition profiles. Importantly, multi-task models require a tailored approach to model interpretability. In this work, we develop DEERS, a neural network recommender system for kinase inhibitor sensitivity prediction. The model utilizes molecular features of the cancer cell lines and kinase inhibition profiles of the drugs. DEERS incorporates two autoencoders to project cell line and drug features into 10-dimensional hidden representations and a feed-forward neural network to combine them into response prediction. We propose a novel interpretability approach, which in addition to the set of modeled features considers also the genes and processes outside of this set. Our approach outperforms simpler matrix factorization models, achieving R  $$=$$ =  0.82 correlation between true and predicted response for the unseen cell lines. The interpretability analysis identifies 67 biological processes that drive the cell line sensitivity to particular compounds. Detailed case studies are shown for PHA-793887, XMD14-99 and Dabrafenib.
format article
author Krzysztof Koras
Ewa Kizling
Dilafruz Juraeva
Eike Staub
Ewa Szczurek
author_facet Krzysztof Koras
Ewa Kizling
Dilafruz Juraeva
Eike Staub
Ewa Szczurek
author_sort Krzysztof Koras
title Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines
title_short Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines
title_full Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines
title_fullStr Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines
title_full_unstemmed Interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines
title_sort interpretable deep recommender system model for prediction of kinase inhibitor efficacy across cancer cell lines
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/5ca6b6ee38d84c60b90d71aa1aaab0aa
work_keys_str_mv AT krzysztofkoras interpretabledeeprecommendersystemmodelforpredictionofkinaseinhibitorefficacyacrosscancercelllines
AT ewakizling interpretabledeeprecommendersystemmodelforpredictionofkinaseinhibitorefficacyacrosscancercelllines
AT dilafruzjuraeva interpretabledeeprecommendersystemmodelforpredictionofkinaseinhibitorefficacyacrosscancercelllines
AT eikestaub interpretabledeeprecommendersystemmodelforpredictionofkinaseinhibitorefficacyacrosscancercelllines
AT ewaszczurek interpretabledeeprecommendersystemmodelforpredictionofkinaseinhibitorefficacyacrosscancercelllines
_version_ 1718377562049085440