A systematic evaluation of deep learning methods for the prediction of drug synergy in cancer

dc.commentsCEB56224por
dc.contributor.authorBaptista, Delorapor
dc.contributor.authorFerreira, Pedro G.por
dc.contributor.authorRocha, Miguelpor
dc.date.accessioned2023-05-03T15:38:42Z
dc.date.available2023-05-03T15:38:42Z
dc.date.issued2023-03
dc.date.updated2023-05-02T19:13:08Z
dc.description.abstractOne of the main obstacles to the successful treatment of cancer is the phenomenon of drug resistance. A common strategy to overcome resistance is the use of combination therapies. However, the space of possibilities is huge and efficient search strategies are required. Machine Learning (ML) can be a useful tool for the discovery of novel, clinically relevant anti-cancer drug combinations. In particular, deep learning (DL) has become a popular choice for modeling drug combination effects. Here, we set out to examine the impact of different methodological choices on the performance of multimodal DL-based drug synergy prediction methods, including the use of different input data types, preprocessing steps and model architectures. Focusing on the NCI ALMANAC dataset, we found that feature selection based on prior biological knowledge has a positive impactâlimiting gene expression data to cancer or drug response-specific genes improved performance. Drug features appeared to be more predictive of drug response, with a 41% increase in coefficient of determination (R2) and 26% increase in Spearman correlation relative to a baseline model that used only cell line and drug identifiers. Molecular fingerprint-based drug representations performed slightly better than learned representationsâECFP4 fingerprints increased R2 by 5.3% and Spearman correlation by 2.8% w.r.t the best learned representations. In general, fully connected feature-encoding subnetworks outperformed other architectures. DL outperformed other ML methods by more than 35% (R2) and 14% (Spearman). Additionally, an ensemble combining the top DL and ML models improved performance by about 6.5% (R2) and 4% (Spearman). Using a state-of-the-art interpretability method, we showed that DL models can learn to associate drug and cell line features with drug response in a biologically meaningful way. The strategies explored in this study will help to improve the development of computational methods for the rational design of effective drug combinations for cancer therapy.por
dc.description.publicationversioninfo:eu-repo/semantics/publishedVersion
dc.description.sponsorshipThis study was supported by the Portuguese Foundation for Science and Technology (FCT), through a PhD scholarship (SFRH/BD/130913/2017 awarded to DB) and under the scope of the strategic funding of UIDB/04469/ 2020 unit. Tpor
dc.distributioninternationalpor
dc.identifier.citationBaptista, Delora; Ferreira, Pedro G.; Rocha, Miguel, A systematic evaluation of deep learning methods for the prediction of drug synergy in cancerrrrr. PLoS Computational Biology, 19(3), e1010200, 2023por
dc.identifier.doi10.1371/journal.pcbi.1010200por
dc.identifier.issn1553-734Xpor
dc.identifier.pmid36952569por
dc.identifier.urihttps://hdl.handle.net/1822/84253
dc.language.isoengpor
dc.peerreviewedyespor
dc.publisherPublic Library of Science (PLOS)por
dc.relationinfo:eu-repo/grantAgreement/FCT/POR_NORTE/SFRH%2FBD%2F130913%2F2017/PTpor
dc.relationinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04469%2F2020/PTpor
dc.relation.publisherversionhttps://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1010200por
dc.rightsopenAccesspor
dc.subject.wosScience & Technologypor
dc.titleA systematic evaluation of deep learning methods for the prediction of drug synergy in cancerpor
dc.typearticle
dspace.entity.typePublicationen
oaire.citationConferencePlaceUnited States
oaire.citationIssue3por
oaire.citationStartPagee1010200por
oaire.citationVolume19por
sdum.journalPLoS Computational Biologypor

Ficheiros

Pacote original

A mostrar 1 - 1 de 1
A carregar...
Nome:
document_56224_1.pdf
Tamanho:
1.86 MB
Formato:
Adobe Portable Document Format