{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:03:07Z","timestamp":1792785787173,"version":"4.5.0"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"vor","delay-in-days":44,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["82203432"],"award-info":[{"award-number":["82203432"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Innovation Program","doi-asserted-by":"publisher","award":["JCYJ20230807110314029"],"award-info":[{"award-number":["JCYJ20230807110314029"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012151","name":"Sanming Project of Medicine in Shenzhen","doi-asserted-by":"publisher","award":["SZSM202311017"],"award-info":[{"award-number":["SZSM202311017"]}],"id":[{"id":"10.13039\/501100012151","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015549","name":"Science and Technology Development Fund","doi-asserted-by":"publisher","award":["0025\/2023\/RIA1"],"award-info":[{"award-number":["0025\/2023\/RIA1"]}],"id":[{"id":"10.13039\/100015549","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100015549","name":"Science and Technology Development Fund","doi-asserted-by":"publisher","award":["0010\/2023\/AKP"],"award-info":[{"award-number":["0010\/2023\/AKP"]}],"id":[{"id":"10.13039\/100015549","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Education Frontiers Science Centre for Precision Oncology, University of Macau","award":["SP2025-00001-FSCPO"],"award-info":[{"award-number":["SP2025-00001-FSCPO"]}],"id":[{"id":"https:\/\/ror.org\/01r4q9n85","id-type":"ROR","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004733","name":"University of Macau","doi-asserted-by":"publisher","award":["MYRG-GRG2024-00265-FHS"],"award-info":[{"award-number":["MYRG-GRG2024-00265-FHS"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate prediction of anticancer drug response remains challenging because conventional approaches based on chemical structures and baseline molecular profiles do not directly capture drug-induced perturbations or cellular dependencies. Here, we present vulnerability-guided cascaded attention transformer (VCAT), which integrates Connectivity Map (CMap)\/Library of Integrated Network-based Cellular Signatures (LINCS)-derived consensus transcriptional signatures with clustered regularly interspaced short palindromic repeats (CRISPR)-supervised cellular representations through adaptive encoders and dual stream cascaded attention. Across four data splitting strategies, VCAT outperformed conventional machine learning and published deep learning models, achieving the best performance in 11 of 12 classification split metric comparisons. Ablation analyses showed that CRISPR-derived vulnerability features complement baseline gene expression and that the proposed interaction architecture further improves prediction. VCAT also enhanced continuous IC50 prediction and generalized across Cancer Therapeutics Response Portal (CTRP), Profiling Relative Inhibition Simultaneously in Mixtures (PRISM), patient-derived organoids, and hepatocellular carcinoma cohorts. Attention based prioritization and integrated gradients jointly highlighted biologically relevant genes, while knockdown of cytosolic iron-sulfur assembly component 3 (CIAO3), methylenetetrahydrofolate dehydrogenase 2 (MTHFD2), and WD repeat domain 1 (WDR1) increased sorafenib sensitivity in hepatocellular carcinoma cell lines. These findings support integrating drug-induced perturbations with genetic vulnerabilities for accurate, interpretable, and transferable anticancer drug response prediction.<\/jats:p>","DOI":"10.1093\/bib\/bbag559","type":"journal-article","created":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T12:17:59Z","timestamp":1790425079000},"source":"Crossref","is-referenced-by-count":0,"title":["Decoding cellular vulnerabilities for interpretable drug response prediction"],"prefix":"10.1093","volume":"27","author":[{"given":"Chonghao","family":"Chen","sequence":"first","affiliation":[{"name":"Faculty of Health Sciences, University of Macau , Avenida da Universidade, Taipa, Macao SAR 999078 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulei","family":"Du","sequence":"additional","affiliation":[{"name":"Faculty of Health Sciences, University of Macau , Avenida da Universidade, Taipa, Macao SAR 999078 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaxin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Faculty of Health Sciences, University of Macau , Avenida da Universidade, Taipa, Macao SAR 999078 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanfang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of General Surgery, The Seventh Affiliated Hospital of Sun Yat-sen University , No. 628 Zhenyuan Road, Guangming District, Shenzhen, Guangdong 518107 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6486-273X","authenticated-orcid":false,"given":"Di","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of General Surgery, The Seventh Affiliated Hospital of Sun Yat-sen University , No. 628 Zhenyuan Road, Guangming District, Shenzhen, Guangdong 518107 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofan","family":"Ding","sequence":"additional","affiliation":[{"name":"Faculty of Health Sciences, University of Macau , Avenida da Universidade, Taipa, Macao SAR 999078 ,","place":["China"]},{"name":"MOE Frontiers Science Center for Precision Oncology , University of Macau, Avenida da Universidade, Taipa, Macau SAR 999078,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4813-5487","authenticated-orcid":false,"given":"Mian","family":"He","sequence":"additional","affiliation":[{"name":"Department of General Surgery, The Seventh Affiliated Hospital of Sun Yat-sen University , No. 628 Zhenyuan Road, Guangming District, Shenzhen, Guangdong 518107 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,15]]},"reference":[{"key":"2026101511474578900_ref1","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1038\/s41467-019-14050-z","article-title":"Intratumoral heterogeneity and clonal evolution in liver cancer","volume":"11","author":"Losic","year":"2020","journal-title":"Nat Commun"},{"key":"2026101511474578900_ref2","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1038\/s41540-025-00547-5","article-title":"Personalized cancer treatment strategies incorporating irreversible and reversible drug resistance mechanisms","volume":"11","author":"He","year":"2025","journal-title":"npj Syst Biol Appl"},{"key":"2026101511474578900_ref3","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1038\/s41467-020-20294-x","article-title":"Global computational alignment of tumor and cell line transcriptional profiles","volume":"12","author":"Warren","year":"2021","journal-title":"Nat Commun"},{"key":"2026101511474578900_ref4","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The cancer genome atlas pan-cancer analysis project","volume":"45","author":"Weinstein","year":"2013","journal-title":"Nat Genet"},{"key":"2026101511474578900_ref5","doi-asserted-by":"publisher","first-page":"e2","DOI":"10.1017\/pcm.2023.23","article-title":"Heterogeneity in precision oncology","volume":"2","author":"Tomasik","year":"2023","journal-title":"Camb Prisms Precis Med"},{"key":"2026101511474578900_ref6","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1038\/s41392-024-01856-7","article-title":"Exploring treatment options in cancer: tumor treatment strategies","volume":"9","author":"Liu","year":"2024","journal-title":"Signal Transduct Target Ther"},{"key":"2026101511474578900_ref7","doi-asserted-by":"publisher","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":"2026101511474578900_ref8","doi-asserted-by":"publisher","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":"2026101511474578900_ref9","doi-asserted-by":"publisher","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":"2026101511474578900_ref10","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1038\/s43018-019-0018-6","article-title":"Discovering the anticancer potential of non-oncology drugs by systematic viability profiling","volume":"1","author":"Corsello","year":"2020","journal-title":"Nat Cancer"},{"key":"2026101511474578900_ref11","doi-asserted-by":"publisher","first-page":"i911","DOI":"10.1093\/bioinformatics\/btaa822","article-title":"DeepCDR: a hybrid graph convolutional network for predicting cancer drug response","volume":"36","author":"Liu","year":"2020","journal-title":"Bioinformatics"},{"key":"2026101511474578900_ref12","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1186\/s12859-021-04146-z","article-title":"Super.FELT: supervised feature extraction learning using triplet loss for drug response prediction with multi-omics data","volume":"22","author":"Park","year":"2021","journal-title":"BMC Bioinformatics"},{"key":"2026101511474578900_ref13","doi-asserted-by":"publisher","first-page":"bbae088","DOI":"10.1093\/bib\/bbae088","article-title":"PANCDR: precise medicine prediction using an adversarial network for cancer drug response","volume":"25","author":"Kim","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026101511474578900_ref14","doi-asserted-by":"publisher","first-page":"20824","DOI":"10.1038\/s41598-025-91571-2","article-title":"Deep learning-driven drug response prediction and mechanistic insights in cancer genomics","volume":"15","author":"Yu","year":"2025","journal-title":"Sci Rep"},{"key":"2026101511474578900_ref15","doi-asserted-by":"publisher","first-page":"564","DOI":"10.1016\/j.cell.2017.06.010","article-title":"Defining a cancer dependency map","volume":"170","author":"Tsherniak","year":"2017","journal-title":"Cell"},{"key":"2026101511474578900_ref16","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1016\/j.cell.2017.10.049","article-title":"A next generation connectivity map: L1000 platform and the first 1,000,000 profiles","volume":"171","author":"Subramanian","year":"2017","journal-title":"Cell"},{"key":"2026101511474578900_ref17","doi-asserted-by":"publisher","first-page":"1176","DOI":"10.1038\/s43018-024-00789-y","article-title":"Building a translational cancer dependency map for the cancer genome atlas","volume":"5","author":"Shi","year":"2024","journal-title":"Nat Cancer"},{"key":"2026101511474578900_ref18","doi-asserted-by":"publisher","first-page":"D1265","DOI":"10.1093\/nar\/gkad976","article-title":"DrugBank 6.0: the DrugBank knowledgebase for 2024","volume":"52","author":"Knox","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026101511474578900_ref19","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1136\/gutjnl-2018-316408","article-title":"Molecular predictors of prevention of recurrence in HCC with sorafenib as adjuvant treatment and prognostic factors in the phase 3 STORM trial","volume":"68","author":"Pinyol","year":"2019","journal-title":"Gut"},{"key":"2026101511474578900_ref20","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.ccell.2024.03.004","article-title":"Pharmacogenomic profiling of intra-tumor heterogeneity using a large organoid biobank of liver cancer","volume":"42","author":"Yang","year":"2024","journal-title":"Cancer Cell"},{"key":"2026101511474578900_ref21","doi-asserted-by":"publisher","first-page":"36812","DOI":"10.1038\/srep36812","article-title":"Logic models to predict continuous outputs based on binary inputs with an application to personalized cancer therapy","volume":"6","author":"Knijnenburg","year":"2016","journal-title":"Sci Rep"},{"key":"2026101511474578900_ref22","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s42004-026-01916-9","article-title":"Benchmarking deep learning models for predicting anticancer drug potency (IC50) with insights for medicinal chemists","volume":"9","author":"Garai","year":"2026","journal-title":"Commun Chem"},{"key":"2026101511474578900_ref23","doi-asserted-by":"publisher","first-page":"e487","DOI":"10.1002\/cpz1.487","article-title":"Getting started with LINCS datasets and tools","volume":"2","author":"Xie","year":"2022","journal-title":"Curr Protoc"},{"key":"2026101511474578900_ref24","doi-asserted-by":"publisher","first-page":"e2106682118","DOI":"10.1073\/pnas.2106682118","article-title":"Predicting patient response with models trained on cell lines and patient-derived xenografts by nonlinear transfer learning","volume":"118","author":"Mourragui","year":"2021","journal-title":"Proc Natl Acad Sci"},{"key":"2026101511474578900_ref25","doi-asserted-by":"publisher","first-page":"15545","DOI":"10.1073\/pnas.0506580102","article-title":"Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles","volume":"102","author":"Subramanian","year":"2005","journal-title":"Proc Natl Acad Sci"},{"key":"2026101511474578900_ops-bib-reference-jmuxlq9hk5n5ssda","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2025.103101","article-title":"DRExplainer: Quantifiable interpretability in drug response prediction with directed graph convolutional network","volume":"163","author":"Shi","journal-title":"Artificial Intelligence in Medicine"},{"key":"2026101511474578900_ops-bib-reference-hmuxlrqvkd5co61g","doi-asserted-by":"publisher","DOI":"10.1038\/s42003-026-09957-5","article-title":"GCNPath : introspecting drug response prediction with pathway-guided graph convolution networks","volume":"9","author":"Yoon","journal-title":"Communications Biology"},{"key":"2026101511474578900_ref26","doi-asserted-by":"publisher","DOI":"10.31083\/j.fbl2901035","article-title":"Downregulation of MTHFD2 inhibits proliferation and enhances chemosensitivity in hepatocellular carcinoma via PI3K\/AKT pathway","volume":"29","author":"Wang","year":"2024","journal-title":"Front Biosci-Landmark"},{"key":"2026101511474578900_ref27","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1186\/s12957-024-03417-2","article-title":"Cytoskeletal gene alterations linked to sorafenib resistance in hepatocellular carcinoma","volume":"22","author":"Xiao","year":"2024","journal-title":"World J Surg Oncol"},{"key":"2026101511474578900_ref28","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1038\/s41392-020-0111-4","article-title":"Silencing MYH9 blocks HBx-induced GSK3\u03b2 ubiquitination and degradation to inhibit tumor stemness in hepatocellular carcinoma","volume":"5","author":"Lin","year":"2020","journal-title":"Signal Transduct Target Ther"},{"key":"2026101511474578900_ref29","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1038\/s41386-020-0752-6","article-title":"Signature-based approaches for informed drug repurposing: targeting CNS disorders","volume":"46","author":"Shukla","year":"2021","journal-title":"Neuropsychopharmacol"},{"key":"2026101511474578900_ref30","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/j.ccell.2023.12.016","article-title":"A comprehensive clinically informed map of dependencies in cancer cells and framework for target prioritization","volume":"42","author":"Pacini","year":"2024","journal-title":"Cancer Cell"},{"key":"2026101511474578900_ref31","doi-asserted-by":"publisher","first-page":"btad390","DOI":"10.1093\/bioinformatics\/btad390","article-title":"Interpretable deep learning architectures for improving drug response prediction performance: myth or reality?","volume":"39","author":"Li","year":"2023","journal-title":"Bioinformatics"},{"key":"2026101511474578900_ref32","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1038\/s41392-020-0187-x","article-title":"The mechanisms of sorafenib resistance in hepatocellular carcinoma: theoretical basis and therapeutic aspects","volume":"5","author":"Tang","year":"2020","journal-title":"Signal Transduct Target Ther"},{"key":"2026101511474578900_ref33","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.3390\/cancers12061576","article-title":"Sorafenib resistance in hepatocellular carcinoma: the relevance of genetic heterogeneity","volume":"12","author":"Cabral","year":"2020","journal-title":"Cancers"},{"key":"2026101511474578900_ref34","doi-asserted-by":"publisher","first-page":"17624","DOI":"10.1038\/s41598-021-97005-z","article-title":"Evaluation of connectivity map shows limited reproducibility in drug repositioning","volume":"11","author":"Lim","year":"2021","journal-title":"Sci Rep"},{"key":"2026101511474578900_ref35","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1038\/s41551-025-01481-x","article-title":"Combinatorial prediction of therapeutic perturbations using causally inspired neural networks","volume":"10","author":"Gonzalez","year":"2025","journal-title":"Nat Biomed Eng"},{"key":"2026101511474578900_ref36","doi-asserted-by":"publisher","first-page":"1470","DOI":"10.1038\/s41592-024-02201-0","article-title":"scGPT: toward building a foundation model for single-cell multi-omics using generative AI","volume":"21","author":"Cui","year":"2024","journal-title":"Nat Methods"},{"key":"2026101511474578900_ref37","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1038\/s43588-025-00887-6","article-title":"Predicting drug responses of unseen cell types through transfer learning with foundation models","volume":"6","author":"Wang","year":"2026","journal-title":"Nat Comput Sci"},{"key":"2026101511474578900_ref38","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)"},{"key":"2026101511474578900_ref39","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1038\/s42256-025-01165-w","article-title":"Modelling drug-induced cellular perturbation responses with a biologically informed dual-branch transformer","volume":"8","author":"Guo","year":"2026","journal-title":"Nat Mach Intell"},{"key":"2026101511474578900_ref40","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1038\/s41592-025-02748-6","article-title":"GeneAgent: self-verification language agent for gene-set analysis using domain databases","volume":"22","author":"Wang","year":"2025","journal-title":"Nat Methods"},{"key":"2026101511474578900_ref41","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1186\/s13059-025-03844-8","article-title":"Natural language processing of gene descriptions for overrepresentation analysis with GeneTEA","volume":"26","author":"Boyle","year":"2025","journal-title":"Genome Biol"},{"key":"2026101511474578900_ref42","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1038\/s44386-025-00034-1","article-title":"A review of deep learning approaches for drug synergy prediction in cancer","volume":"2","author":"Li","year":"2025","journal-title":"Npj Drug Discov"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag559\/71972768\/bbag559.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/5\/bbag559\/71972768\/bbag559.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T15:47:56Z","timestamp":1792079276000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag559\/8918432"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":44,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag559","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9,1]]},"article-number":"bbag559"}}