{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T00:02:56Z","timestamp":1774137776597,"version":"3.50.1"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T00:00:00Z","timestamp":1769299200000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Sabanci University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,2,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Combinatorial drug therapy holds great promise for tackling complex diseases, but the vast number of possible drug combinations makes exhaustive experimental testing infeasible. Computational models have been developed to guide experimental screens by assigning synergy scores to drug pair\u2013cell line combinations, where they take input structural and chemical information on drugs and molecular features of cell lines. The premise of these models is that they leverage this biological and chemical information to predict synergy measurements.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In this study, we demonstrate that replacing drug and cell line representations with simple one-hot encodings results in comparable or even slightly improved performance across diverse published drug combination models. This unexpected finding suggests that current models use these representations primarily as identifiers and exploit covariation in the synergy labels. Our synthetic data experiments show that models can learn from the true features; however, when drugs and cell lines recur across drug\u2013drug\u2013cell triplets, this repeating structure impairs feature-based learning. While the current synergy prediction models can aid in prioritizing drug pairs within a panel of tested drugs and cell lines, our results highlight the need for better strategies to learn from intended features and to generalize to unseen drugs and cell lines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The scripts to run the experiments are available at: https:\/\/github.com\/tastanlab\/ohe<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag040","type":"journal-article","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T12:52:34Z","timestamp":1769086354000},"source":"Crossref","is-referenced-by-count":0,"title":["One-hot news: drug synergy models shortcut molecular features"],"prefix":"10.1093","volume":"42","author":[{"given":"Emine Beyza","family":"\u00c7and\u0131r","sequence":"first","affiliation":[{"name":"Sabanci University Faculty of Engineering and Natural Sciences, , Istanbul, 34956,","place":["Turkey"]},{"name":"Sabanci University Center of Excellence in Data Analytics, , Istanbul, 34956,","place":["Turkey"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4356-8846","authenticated-orcid":false,"given":"Halil \u0130brahim","family":"Kuru","sequence":"additional","affiliation":[{"name":"Bilkent University Department of Computer Engineering, , Ankara, 06800,","place":["Turkey"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8196-5565","authenticated-orcid":false,"given":"Magnus","family":"Rattray","sequence":"additional","affiliation":[{"name":"University of Manchester Division of Informatics, Imaging and Data Sciences, , Manchester, M13 9PL,","place":["United Kingdom"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8613-6619","authenticated-orcid":false,"given":"A Erc\u00fcment","family":"\u00c7i\u00e7ek","sequence":"additional","affiliation":[{"name":"Bilkent University Department of Computer Engineering, , Ankara, 06800,","place":["Turkey"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7058-5372","authenticated-orcid":false,"given":"Oznur","family":"Tastan","sequence":"additional","affiliation":[{"name":"Sabanci University Faculty of Engineering and Natural Sciences, , Istanbul, 34956,","place":["Turkey"]},{"name":"Sabanci University Center of Excellence in Data Analytics, , Istanbul, 34956,","place":["Turkey"]}]}],"member":"286","published-online":{"date-parts":[[2026,1,24]]},"reference":[{"key":"2026032119465823800_btag040-B1","doi-asserted-by":"crossref","first-page":"102827","DOI":"10.1016\/j.sbi.2024.102827","article-title":"New methods for drug synergy prediction: a mini-review","volume":"86","author":"Abbasi","year":"2024","journal-title":"Curr Opin Struct Biol"},{"key":"2026032119465823800_btag040-B2","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1038\/nbt.2284","article-title":"Combinatorial drug therapy for cancer in the post-genomic era","volume":"30","author":"Al-Lazikani","year":"2012","journal-title":"Nat Biotechnol"},{"key":"2026032119465823800_btag040-B3","doi-asserted-by":"crossref","first-page":"e0303597","DOI":"10.1371\/journal.pone.0303597","article-title":"Lstm-driven drug design using selfies for target-focused de novo generation of HIV-1 protease inhibitor candidates for aids treatment","volume":"19","author":"Albrijawi","year":"2024","journal-title":"PLoS One"},{"key":"2026032119465823800_btag040-B4","author":"Beery","year":"2018"},{"key":"2026032119465823800_btag040-B5","author":"Bri\u00e8re","year":"2025"},{"key":"2026032119465823800_btag040-B6","doi-asserted-by":"crossref","first-page":"1989","DOI":"10.1038\/s41467-023-37572-z","article-title":"Improving the generalizability of protein-ligand binding predictions with ai-bind","volume":"14","author":"Chatterjee","year":"2023","journal-title":"Nat Commun"},{"key":"2026032119465823800_btag040-B7","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1038\/s42256-021-00338-7","article-title":"Ai for radiographic covid-19 detection selects shortcuts over signal","volume":"3","author":"DeGrave","year":"2021","journal-title":"Nat Mach Intell"},{"key":"2026032119465823800_btag040-B8","article-title":"Marsy: a multitask","volume":"39","author":"El Khili","year":"2023","journal-title":"Bioinformatics"},{"key":"2026032119465823800_btag040-B9","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","article-title":"Shortcut learning in deep neural networks","volume":"2","author":"Geirhos","year":"2020","journal-title":"Nat Mach Intell"},{"key":"2026032119465823800_btag040-B10","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.jash.2010.03.001","article-title":"Combination therapy in hypertension","volume":"4","author":"Gradman","year":"2010","journal-title":"J Am Soc Hypertens"},{"key":"2026032119465823800_btag040-B11","doi-asserted-by":"crossref","first-page":"bbab293","DOI":"10.1093\/bib\/bbab293","article-title":"Machine learning approaches for drug combination therapies","volume":"22","author":"G\u00fcven\u00e7 Paltun","year":"2021","journal-title":"Brief Bioinform"},{"key":"2026032119465823800_btag040-B12","author":"Hermann","year":"2023"},{"key":"2026032119465823800_btag040-B13","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1016\/j.cell.2016.06.017","article-title":"A landscape of pharmacogenomic interactions in cancer","volume":"166","author":"Iorio","year":"2016","journal-title":"Cell"},{"key":"2026032119465823800_btag040-B14","author":"Kokhlikyan","year":"2020"},{"key":"2026032119465823800_btag040-B15","doi-asserted-by":"crossref","first-page":"2334","DOI":"10.1109\/TCBB.2021.3086702","article-title":"MatchMaker: a deep learning framework for drug synergy prediction","volume":"19","author":"Kuru","year":"2022","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"2026032119465823800_btag040-B16","author":"Landrum","year":"2016"},{"key":"2026032119465823800_btag040-B17","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae604","article-title":"Dual-view jointly learning improves","volume":"40","author":"Li","year":"2024","journal-title":"Bioinformatics"},{"key":"2026032119465823800_btag040-B18","first-page":"285","article-title":"The problem of synergism and antagonism of combined drugs","volume":"3","author":"Loewe","year":"1953","journal-title":"Arzneimittelforschung"},{"key":"2026032119465823800_btag040-B19","doi-asserted-by":"crossref","first-page":"btae693","DOI":"10.1093\/bioinformatics\/btae693","article-title":"Accurate and transferable drug\u2013target interaction prediction with druglamp","volume":"40","author":"Luo","year":"2024","journal-title":"Bioinformatics"},{"key":"2026032119465823800_btag040-B20","doi-asserted-by":"crossref","first-page":"38022","DOI":"10.18632\/oncotarget.16723","article-title":"Combination therapy in combating cancer","volume":"8","author":"Mokhtari","year":"2017","journal-title":"Oncotarget"},{"key":"2026032119465823800_btag040-B21","doi-asserted-by":"crossref","first-page":"1568","DOI":"10.1016\/S0140-6736(98)08513-4","article-title":"Comparison of combination therapy with single-drug therapy in early rheumatoid arthritis: a randomised trial","volume":"353","author":"M\u00f6tt\u00f6nen","year":"1999","journal-title":"Lancet"},{"key":"2026032119465823800_btag040-B22","doi-asserted-by":"crossref","first-page":"2108","DOI":"10.1016\/j.jid.2018.06.175","article-title":"Automated classification of skin lesions: from pixels to practice","volume":"138","author":"Narla","year":"2018","journal-title":"J Invest Dermatol"},{"key":"2026032119465823800_btag040-B23","author":"Nori","year":"2024"},{"key":"2026032119465823800_btag040-B24","author":"Ong","year":"2023"},{"key":"2026032119465823800_btag040-B25","doi-asserted-by":"crossref","first-page":"bbaf667","DOI":"10.1093\/bib\/bbaf667","article-title":"Benchmarking community drug response prediction models: datasets, models, tools, and metrics for cross-dataset generalization analysis","volume":"27","author":"Partin","year":"2026","journal-title":"Brief Bioinform"},{"key":"2026032119465823800_btag040-B26","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1093\/bioinformatics\/btx806","article-title":"Deepsynergy: predicting anti-cancer drug synergy with deep learning","volume":"34","author":"Preuer","year":"2018","journal-title":"Bioinformatics"},{"key":"2026032119465823800_btag040-B27","volume-title":"Deep Learning for the Life Sciences","author":"Ramsundar","year":"2019"},{"key":"2026032119465823800_btag040-B28","doi-asserted-by":"crossref","first-page":"3499","DOI":"10.1158\/0008-5472.CAN-12-1370","article-title":"CellMiner: a web-based suite of genomic and pharmacologic tools to explore transcript and drug patterns in the nci-60 cell line set","volume":"72","author":"Reinhold","year":"2012","journal-title":"Cancer Res"},{"key":"2026032119465823800_btag040-B29","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.1038\/s42256-022-00580-7","article-title":"Large-scale chemical language representations capture molecular structure and properties","volume":"4","author":"Ross","year":"2022","journal-title":"Nat Mach Intell"},{"key":"2026032119465823800_btag040-B30","doi-asserted-by":"crossref","first-page":"e1013541","DOI":"10.1371\/journal.pcbi.1013541","article-title":"Rnatranslator: modeling protein-conditional rna design as sequence-to-sequence natural language translation","volume":"21","author":"Shukueian Tabrizi","year":"2025","journal-title":"PLoS Comput Biol"},{"key":"2026032119465823800_btag040-B31","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1016\/j.cell.2017.10.049","article-title":"A next generation connectivity map: l 1000 platform and the first 1,000,000 profiles","volume":"171","author":"Subramanian","year":"2017","journal-title":"Cell"},{"key":"2026032119465823800_btag040-B32","author":"Sundararajan","year":"2017"},{"key":"2026032119465823800_btag040-B33","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1128\/CMR.05041-11","article-title":"Combination therapy for treatment of infections with gram-negative bacteria","volume":"25","author":"Tamma","year":"2012","journal-title":"Clin Microbiol Rev"},{"key":"2026032119465823800_btag040-B34","doi-asserted-by":"publisher","author":"Tasnina","year":"2025","DOI":"10.1093\/bib\/bbaf676"},{"key":"2026032119465823800_btag040-B35","doi-asserted-by":"crossref","first-page":"7596","DOI":"10.1038\/s41467-024-52055-5","article-title":"Leveraging multiple data types for improved compound-kinase bioactivity prediction","volume":"15","author":"Theisen","year":"2024","journal-title":"Nat Commun"},{"key":"2026032119465823800_btag040-B36","doi-asserted-by":"crossref","first-page":"110438","DOI":"10.1016\/j.compbiomed.2025.110438","article-title":"Drug-target interaction\/affinity prediction: deep learning models and advances review","volume":"196","author":"Vefghi","year":"2025","journal-title":"Comput Biol Med"},{"key":"2026032119465823800_btag040-B37","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab390","article-title":"Deepdds: deep graph neural","volume":"23","author":"Wang","year":"2022","journal-title":"Brief Bioinform"},{"key":"2026032119465823800_btag040-B38","doi-asserted-by":"crossref","first-page":"7861","DOI":"10.1038\/s41467-023-43597-1","article-title":"Zerobind: a protein-specific zero-shot predictor with subgraph matching for drug-target interactions","volume":"14","author":"Wang","year":"2023","journal-title":"Nat Commun"},{"key":"2026032119465823800_btag040-B39","article-title":"Deep learning for predicting","volume":"4","author":"Wang","year":"2024","journal-title":"Clinical and Translational Dis"},{"key":"2026032119465823800_btag040-B40","doi-asserted-by":"crossref","first-page":"844","DOI":"10.3390\/molecules28020844","article-title":"Deml: drug synergy and interaction prediction using ensemble-based multi-task learning","volume":"28","author":"Wang","year":"2023","journal-title":"Molecules"},{"key":"2026032119465823800_btag040-B41","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1186\/s13321-023-00690-3","article-title":"Dffndds: prediction of synergistic drug combinations with dual feature fusion networks","volume":"15","author":"Xu","year":"2023","journal-title":"J Cheminform"},{"key":"2026032119465823800_btag040-B42","doi-asserted-by":"crossref","first-page":"e1002683","DOI":"10.1371\/journal.pmed.1002683","article-title":"Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study","volume":"15","author":"Zech","year":"2018","journal-title":"PLoS Med"},{"key":"2026032119465823800_btag040-B43","doi-asserted-by":"crossref","first-page":"e1010951","DOI":"10.1371\/journal.pcbi.1010951","article-title":"Mgae-dc: predicting the synergistic effects of drug combinations through multi-channel graph autoencoders","volume":"19","author":"Zhang","year":"2023","journal-title":"PLoS Comput Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag040\/66568794\/btag040.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/3\/btag040\/66568794\/btag040.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/3\/btag040\/66568794\/btag040.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T23:47:08Z","timestamp":1774136828000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag040\/8440676"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2026,1,24]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,2,28]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag040","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,3]]},"published":{"date-parts":[[2026,1,24]]},"article-number":"btag040"}}