{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T21:08:44Z","timestamp":1774472924175,"version":"3.50.1"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T00:00:00Z","timestamp":1686873600000},"content-version":"vor","delay-in-days":15,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Government of Canada\u2019s New Frontiers in Research Fund"},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Interpretable deep learning (DL) models that can provide biological insights, in addition to accurate predictions, are of great interest to the biomedical community. Recently, interpretable DL models that incorporate signaling pathways have been proposed for drug response prediction (DRP). While these models improve interpretability, it is unclear whether this comes at the cost of less accurate DRPs, or a prediction improvement can also be obtained.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We comprehensively and systematically assessed four state-of-the-art interpretable DL models using three pathway collections to assess their ability in making accurate predictions on unseen samples from the same dataset, as well as their generalizability to an independent dataset. Our results showed that models that explicitly incorporate pathway information in the form of a latent layer perform worse compared to models that incorporate this information implicitly. However, in most evaluation setups, the best performance was achieved using a black-box multilayer perceptron, and the performance of a random forests baseline was comparable to those of the interpretable models. Replacing the signaling pathways with randomly generated pathways showed a comparable performance for the majority of the models. Finally, the performance of all models deteriorated when applied to an independent dataset. These results highlight the importance of systematic evaluation of newly proposed models using carefully selected baselines. We provide different evaluation setups and baseline models that can be used to achieve this goal.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Implemented models and datasets are provided at https:\/\/doi.org\/10.5281\/zenodo.7787178 and https:\/\/doi.org\/10.5281\/zenodo.7101665, respectively.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad390","type":"journal-article","created":{"date-parts":[[2023,6,15]],"date-time":"2023-06-15T02:53:34Z","timestamp":1686797614000},"source":"Crossref","is-referenced-by-count":25,"title":["Interpretable deep learning architectures for improving drug response prediction performance: myth or reality?"],"prefix":"10.1093","volume":"39","author":[{"given":"Yihui","family":"Li","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, McGill University , Montreal, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1611-8332","authenticated-orcid":false,"given":"David Earl","family":"Hostallero","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, McGill University , Montreal, QC, Canada"},{"name":"Mila, Quebec AI Institute , Montreal, QC, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5108-4887","authenticated-orcid":false,"given":"Amin","family":"Emad","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, McGill University , Montreal, QC, Canada"},{"name":"Mila, Quebec AI Institute , Montreal, QC, Canada"},{"name":"The Rosalind and Morris Goodman Cancer Institute , Montreal, QC, Canada"}]}],"member":"286","published-online":{"date-parts":[[2023,6,16]]},"reference":[{"key":"2023062809444297300_btad390-B1","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1038\/s41698-020-0122-1","article-title":"Machine learning approaches to drug response prediction: challenges and recent progress","volume":"4","author":"Adam","year":"2020","journal-title":"NPJ Precis Oncol"},{"key":"2023062809444297300_btad390-B2","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1016\/j.tig.2020.03.005","article-title":"Opening the black box: interpretable machine learning for geneticists","volume":"36","author":"Azodi","year":"2020","journal-title":"Trends Genet"},{"key":"2023062809444297300_btad390-B3","article-title":"Artificial intelligence for drug response prediction in disease models","volume":"23","author":"Ballester","year":"2022","journal-title":"Brief Bioinformatics"},{"key":"2023062809444297300_btad390-B4","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1093\/bib\/bbz171","article-title":"Deep learning for drug response prediction in cancer","volume":"22","author":"Baptista","year":"2021","journal-title":"Brief Bioinformatics"},{"key":"2023062809444297300_btad390-B5","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","article-title":"Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI","volume":"58","author":"Barredo Arrieta","year":"2020","journal-title":"Inform Fusion"},{"key":"2023062809444297300_btad390-B6","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1038\/nature11003","article-title":"The Cancer Cell Line Encyclopedia enables predictive modelling of anticancer drug sensitivity","volume":"483","author":"Barretina","year":"2012","journal-title":"Nature"},{"key":"2023062809444297300_btad390-B7","first-page":"1721","author":"Caruana","year":"2015"},{"key":"2023062809444297300_btad390-B8","first-page":"371","article-title":"Interpretable deep models for ICU outcome prediction","volume":"2016","author":"Che","year":"2016","journal-title":"AMIA Annu Symp Proc"},{"key":"2023062809444297300_btad390-B9","article-title":"How much can deep learning improve prediction of the responses to drugs in cancer cell lines?","volume":"23","author":"Chen","year":"2022","journal-title":"Brief Bioinformatics"},{"key":"2023062809444297300_btad390-B10","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1038\/nbt.2877","article-title":"A community effort to assess and improve drug sensitivity prediction algorithms","volume":"32","author":"Costello","year":"2014","journal-title":"Nat Biotechnol"},{"key":"2023062809444297300_btad390-B11","doi-asserted-by":"crossref","first-page":"4497","DOI":"10.1021\/acs.jcim.0c00331","article-title":"Pathway-guided deep neural network toward interpretable and predictive modeling of drug sensitivity","volume":"60","author":"Deng","year":"2020","journal-title":"J Chem Inform Model"},{"key":"2023062809444297300_btad390-B12","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad177","article-title":"MARSY: a multitask deep-learning framework for prediction of drug combination synergy scores","volume":"39","author":"El Khili","year":"2023","journal-title":"Bioinformatics"},{"key":"2023062809444297300_btad390-B13","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1186\/s13059-017-1282-3","article-title":"Knowledge-guided gene prioritization reveals new insights into the mechanisms of chemoresistance","volume":"18","author":"Emad","year":"2017","journal-title":"Genome Biol"},{"key":"2023062809444297300_btad390-B14","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1186\/s12859-017-1559-2","article-title":"Reactome pathway analysis: a high-performance in-memory approach","volume":"18","author":"Fabregat","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2023062809444297300_btad390-B15","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1093\/bib\/bbz153","article-title":"Improving drug response prediction by integrating multiple data sources: matrix factorization, kernel and network-based approaches","volume":"22","author":"Guvenc Paltun","year":"2021","journal-title":"Brief Bioinformatics"},{"key":"2023062809444297300_btad390-B16","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s13321-015-0068-4","article-title":"InChI, the IUPAC international chemical identifier","volume":"7","author":"Heller","year":"2015","journal-title":"J Cheminform"},{"key":"2023062809444297300_btad390-B17","doi-asserted-by":"crossref","first-page":"3609","DOI":"10.1093\/bioinformatics\/btac383","article-title":"Looking at the BiG picture: incorporating bipartite graphs in drug response prediction","volume":"38","author":"Hostallero","year":"2022","journal-title":"Bioinformatics"},{"key":"2023062809444297300_btad390-B18","doi-asserted-by":"crossref","DOI":"10.1016\/j.gpb.2023.01.006","article-title":"Preclinical-to-clinical anti-cancer drug response prediction and biomarker identification using TINDL","author":"Hostallero","year":"2023","journal-title":"Genom Proteom Bioinformatics"},{"key":"2023062809444297300_btad390-B19","doi-asserted-by":"crossref","first-page":"e1007607","DOI":"10.1371\/journal.pcbi.1007607","article-title":"Tissue-guided LASSO for prediction of clinical drug response using preclinical samples","volume":"16","author":"Huang","year":"2020","journal-title":"PLoS Comput Biol"},{"key":"2023062809444297300_btad390-B20","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1186\/s13321-020-00450-7","article-title":"A review of computational drug repositioning: strategies, approaches, opportunities, challenges, and directions","volume":"12","author":"Jarada","year":"2020","journal-title":"J Cheminform"},{"key":"2023062809444297300_btad390-B21","doi-asserted-by":"crossref","first-page":"3858","DOI":"10.1021\/acs.jcim.1c00706","article-title":"HiDRA: hierarchical network for drug response prediction with attention","volume":"61","author":"Jin","year":"2021","journal-title":"J Chem Inf Model"},{"key":"2023062809444297300_btad390-B22","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1093\/nar\/28.1.27","article-title":"KEGG: Kyoto Encyclopedia of Genes and Genomes","volume":"28","author":"Kanehisa","year":"2000","journal-title":"Nucleic Acids Res"},{"key":"2023062809444297300_btad390-B23","doi-asserted-by":"crossref","first-page":"D1388","DOI":"10.1093\/nar\/gkaa971","article-title":"PubChem in 2021: new data content and improved web interfaces","volume":"49","author":"Kim","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2023062809444297300_btad390-B24","doi-asserted-by":"crossref","first-page":"672","DOI":"10.1016\/j.ccell.2020.09.014","article-title":"Predicting drug response and synergy using a deep learning model of human cancer cells","volume":"38","author":"Kuenzi","year":"2020","journal-title":"Cancer Cell"},{"key":"2023062809444297300_btad390-B25","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"2023062809444297300_btad390-B26","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1007\/978-3-319-54024-5_5","volume-title":"Transparent Data Mining for Big and Small Data","author":"Malioutov","year":"2017"},{"key":"2023062809444297300_btad390-B27","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1038\/nchembio.1986","article-title":"Correlating chemical sensitivity and basal gene expression reveals mechanism of action","volume":"12","author":"Rees","year":"2016","journal-title":"Nat Chem Biol"},{"key":"2023062809444297300_btad390-B28","doi-asserted-by":"crossref","first-page":"D674","DOI":"10.1093\/nar\/gkn653","article-title":"PID: the Pathway Interaction Database","volume":"37","author":"Schaefer","year":"2009","journal-title":"Nucleic Acids Res"},{"key":"2023062809444297300_btad390-B29","first-page":"10220","article-title":"CXPlain: causal explanations for model interpretation under uncertainty","volume":"32","author":"Schwab","year":"2019"},{"key":"2023062809444297300_btad390-B30","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab294","article-title":"Drug sensitivity prediction from cell line-based pharmacogenomics data: guidelines for developing machine learning models","volume":"22","author":"Sharifi-Noghabi","year":"2021","journal-title":"Brief Bioinformatics"},{"key":"2023062809444297300_btad390-B31","first-page":"4844","author":"Shrikumar","year":"2017"},{"key":"2023062809444297300_btad390-B32","first-page":"3558","author":"Snow","year":"2021"},{"key":"2023062809444297300_btad390-B33","doi-asserted-by":"crossref","first-page":"D607","DOI":"10.1093\/nar\/gky1131","article-title":"STRING v11: protein-protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets","volume":"47","author":"Szklarczyk","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023062809444297300_btad390-B34","doi-asserted-by":"crossref","first-page":"D380","DOI":"10.1093\/nar\/gkv1277","article-title":"STITCH 5: augmenting protein-chemical interaction networks with tissue and affinity data","volume":"44","author":"Szklarczyk","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2023062809444297300_btad390-B35","doi-asserted-by":"crossref","first-page":"3128","DOI":"10.1038\/s41598-021-82612-7","article-title":"Explainable drug sensitivity prediction through cancer pathway enrichment","volume":"11","author":"Tang","year":"2021","journal-title":"Sci Rep"},{"key":"2023062809444297300_btad390-B36","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1038\/s41573-019-0024-5","article-title":"Applications of machine learning in drug discovery and development","volume":"18","author":"Vamathevan","year":"2019","journal-title":"Nat Rev Drug Discov"},{"key":"2023062809444297300_btad390-B37","doi-asserted-by":"crossref","first-page":"D955","DOI":"10.1093\/nar\/gks1111","article-title":"Genomics of drug sensitivity in cancer (GDSC): a resource for therapeutic biomarker discovery in cancer cells","volume":"41","author":"Yang","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2023062809444297300_btad390-B38","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab291","article-title":"Comparative analysis of molecular fingerprints in prediction of drug combination effects","volume":"22","author":"Zagidullin","year":"2021","journal-title":"Brief Bioinformatics"},{"key":"2023062809444297300_btad390-B39","doi-asserted-by":"crossref","first-page":"639349","DOI":"10.3389\/fbinf.2021.639349","article-title":"Predicting anticancer drug response with deep learning constrained by signaling pathways","volume":"1","author":"Zhang","year":"2021","journal-title":"Front Bioinformatics"},{"key":"2023062809444297300_btad390-B40","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab006","article-title":"Benchmarking network-based gene prioritization methods for cerebral small vessel disease","volume":"22","author":"Zhang","year":"2021","journal-title":"Brief Bioinform"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad390\/50628666\/btad390.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/6\/btad390\/50729804\/btad390.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/6\/btad390\/50729804\/btad390.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T22:42:48Z","timestamp":1702593768000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad390\/7199590"}},"subtitle":[],"editor":[{"given":"Anthony","family":"Mathelier","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad390","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.10.03.510614","asserted-by":"object"}]},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,6,1]]},"published":{"date-parts":[[2023,6,1]]},"article-number":"btad390"}}