{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T17:48:08Z","timestamp":1786470488608,"version":"build-2736575974"},"reference-count":25,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T00:00:00Z","timestamp":1786406400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>\n                    Drug sensitivity prediction is an important issue within the precision medicine field. IC50, which is the molar drug dose needed to decrease the viability of cells by half compared to the drug-free control, is the main pharmacodynamics parameter used for drug sensitivity analysis in large-scale pharmacogenomics screenings. Computational estimation of IC50s based on molecular and genomic factors significantly reduces costs associated with experiments for measuring cell viability and allows for accelerating the process of drug discovery. Traditional methods of IC50 calculation do not allow integrating the three-dimensional chemical structure of drugs and the biological context of particular cell lines, resulting in suboptimal model performance when using different pharmacogenomics data sources. In this work, we propose an innovative dual-branch approach based on Graph Isomorphism Network (GIN) drug representations coupled with a Multilayer Perceptron (MLP) for 50-dimensional ssGSEA pathway activities calculated from CCLE gene expression. After training on cell-line-drug pair combinations from the Genomics of Drug Sensitivity in Cancer 2 (GDSC2) dataset across various cancers, the proposed GIN+Pathway MLP model attains an R\n                    <jats:sup>2<\/jats:sup>\n                    of 0.8553 and a Pearson Correlation Coefficient (PCC) of 0.9249 on the testing split of the same dataset. In a variant ablation study of six variants, we find that eliminating the pathway MLP component lowers the R\n                    <jats:sup>2<\/jats:sup>\n                    value by more than 0.15, thus proving the importance of biological features in the two-branch model. The performance of our proposed model exceeds benchmark scores for models such as GraphDRP (PCC\u2009=\u20090.870, R\n                    <jats:sup>2<\/jats:sup>\n                    \u2009=\u20090.756) and DeepCDR (PCC\u2009=\u20090.847, R\n                    <jats:sup>2<\/jats:sup>\n                    \u2009=\u20090.720) when tested on the same GDSC2 dataset.\n                  <\/jats:p>","DOI":"10.1371\/journal.pone.0354669","type":"journal-article","created":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T17:23:21Z","timestamp":1786469001000},"page":"e0354669","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Drug sensitivity prediction across cancer types using graph isomorphism networks and biological pathway features: A dual-branch deep learning approach"],"prefix":"10.1371","volume":"21","author":[{"given":"Shuang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanzhong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feifei","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuya","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3336-4509","authenticated-orcid":true,"given":"Weikai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,11]]},"reference":[{"issue":"2","key":"pone.0354669.ref001","doi-asserted-by":"crossref","first-page":"174","DOI":"10.1016\/j.autrev.2014.10.016","article-title":"Autoimmune thyroid disorders","volume":"14","author":"A Antonelli","year":"2015","journal-title":"Autoimmun Rev"},{"key":"pone.0354669.ref002","doi-asserted-by":"crossref","first-page":"113993","DOI":"10.1016\/j.biopha.2022.113993","article-title":"Disorders of cancer metabolism: the therapeutic potential of cannabinoids","volume":"157","author":"D Sun","year":"2023","journal-title":"Biomed Pharmacother"},{"key":"pone.0354669.ref003","first-page":"1263","article-title":"Neural message passing for quantum chemistry.","volume-title":"International Conference on Machine Learning","author":"J Gilmer","year":"2017"},{"key":"pone.0354669.ref004","doi-asserted-by":"crossref","first-page":"164","DOI":"10.2174\/1574893616666210708143556","article-title":"Cervical cancer metastasis and recurrence risk prediction based on deep convolutional neural network","volume":"17","author":"Z Ye","year":"2022","journal-title":"Curr Bioinform"},{"key":"pone.0354669.ref005","doi-asserted-by":"crossref","first-page":"676","DOI":"10.1016\/j.omtn.2020.07.003","article-title":"An improved anticancer drug-response prediction based on an ensemble method integrating matrix completion and ridge regression","volume":"21","author":"C Liu","year":"2020","journal-title":"Mol Ther Nucleic Acids"},{"issue":"4","key":"pone.0354669.ref006","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0061318","article-title":"Machine learning prediction of cancer cell sensitivity to drugs based on genomic and chemical properties","volume":"8","author":"MP Menden","year":"2013","journal-title":"PLoS One"},{"issue":"3","key":"pone.0354669.ref007","doi-asserted-by":"crossref","DOI":"10.1186\/gb-2014-15-3-r47","article-title":"Clinical drug response can be predicted using baseline gene expression levels and in vitro drug sensitivity in cell lines","volume":"15","author":"P Geeleher","year":"2014","journal-title":"Genome Biol"},{"issue":"14","key":"pone.0354669.ref008","doi-asserted-by":"crossref","first-page":"6799","DOI":"10.3390\/ijms26146799","article-title":"LSA-DDI: learning stereochemistry-aware drug interactions via 3D feature fusion and contrastive cross-attention","volume":"26","author":"S Wang","year":"2025","journal-title":"Int J Mol Sci"},{"issue":"9","key":"pone.0354669.ref009","article-title":"Flat-lattice-CNN: A model for Chinese medical-named-entity recognition","volume":"20","author":"S Wang","year":"2025","journal-title":"PLoS One"},{"key":"pone.0354669.ref010","article-title":"DeepCDR: a hybrid graph convolutional network for predicting cancer drug response","volume":"36","author":"Q Liu","year":"2020","journal-title":"Bioinformatics"},{"issue":"12","key":"pone.0354669.ref011","doi-asserted-by":"crossref","first-page":"1582","DOI":"10.3390\/pharmaceutics16121582","article-title":"Precisely tailoring molecular structure of doxorubicin prodrugs to enable stable nanoassembly, rapid activation, and potent antitumor effect","volume":"16","author":"C Feng","year":"2024","journal-title":"Pharmaceutics"},{"issue":"3","key":"pone.0354669.ref012","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1016\/j.jgg.2025.08.001","article-title":"tsRNADisease: a manually curated database of tsRNAs associated with human disease","volume":"53","author":"H Yang","year":"2026","journal-title":"J Genet Genomics"},{"issue":"5","key":"pone.0354669.ref013","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/s10822-022-00442-9","article-title":"Evolution of support vector machine and regression modeling in chemoinformatics and drug discovery","volume":"36","author":"R Rodr\u00edguez-P\u00e9rez","year":"2022","journal-title":"J Comput Aided Mol Des"},{"issue":"6","key":"pone.0354669.ref014","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1016\/j.cels.2015.12.004","article-title":"The Molecular Signatures Database (MSigDB) hallmark gene set collection","volume":"1","author":"A Liberzon","year":"2015","journal-title":"Cell Syst"},{"issue":"6","key":"pone.0354669.ref015","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1038\/s12276-025-01465-6","article-title":"Extracellular vesicles derived from lung M2 macrophages enhance group 2 innate lymphoid cells function in allergic airway inflammation","volume":"57","author":"K Lv","year":"2025","journal-title":"Exp Mol Med"},{"issue":"1","key":"pone.0354669.ref016","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1186\/s12915-025-02457-8","article-title":"MCLRP: enhanced prediction of anticancer drug response through low-rank matrix completion and transcriptomic profiling","volume":"24","author":"K Wang","year":"2025","journal-title":"BMC Biol"},{"key":"pone.0354669.ref017","doi-asserted-by":"crossref","first-page":"126501","DOI":"10.1016\/j.ijpharm.2025.126501","article-title":"Advances in metal ion-mediated macromolecular drug delivery","volume":"689","author":"K Li","year":"2026","journal-title":"Int J Pharm"},{"key":"pone.0354669.ref018","doi-asserted-by":"crossref","first-page":"8359","DOI":"10.1007\/s13369-025-10647-3","article-title":"Smart city electricity load forecasting using greylag goose optimization-enhanced time series analysis","volume":"51","author":"ESM El-Kenawy","year":"2026","journal-title":"Arab J Sci Eng"},{"issue":"1","key":"pone.0354669.ref019","doi-asserted-by":"crossref","first-page":"8597","DOI":"10.1038\/s41598-026-39632-y","article-title":"Optimizing solar and wind forecasting with iHow optimization algorithm and multi-scale attention networks","volume":"16","author":"M Radwan","year":"2026","journal-title":"Sci Rep"},{"key":"pone.0354669.ref020","doi-asserted-by":"crossref","first-page":"104462","DOI":"10.1016\/j.jnca.2026.104462","article-title":"Hybrid Al-Biruni and Puma Optimization (BERPO) for boosting the classification of Quality-of-Service (QoS) in 5G networks","volume":"250","author":"AA Alhussan","year":"2026","journal-title":"J Netw Comput Appl"},{"key":"pone.0354669.ref021","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/s10462-026-11504-x","article-title":"Glider snake optimizer (GSO): a nature-inspired metaheuristic algorithm for global and engineering optimization problems","volume":"59","author":"ESM El-kenawy","year":"2026","journal-title":"Artif Intell Rev"},{"key":"pone.0354669.ref022","article-title":"PubChem 2023 update","volume":"51","author":"S Kim","year":"2023","journal-title":"Nucleic Acids Res"},{"issue":"7757","key":"pone.0354669.ref023","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1038\/s41586-019-1186-3","article-title":"Next-generation characterisation of the cancer cell line encyclopedia","volume":"569","author":"M Ghandi","year":"2019","journal-title":"Nature"},{"issue":"2","key":"pone.0354669.ref024","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1021\/c160017a018","article-title":"The generation of a unique machine description for chemical structures-a technique developed at chemical abstracts service","volume":"5","author":"HL Morgan","year":"1965","journal-title":"J Chem Doc"},{"key":"pone.0354669.ref025","author":"K Xu","year":"2018"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0354669","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T17:23:26Z","timestamp":1786469006000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0354669"}},"subtitle":[],"editor":[{"given":"Satyaki","family":"Roy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,11]]},"references-count":25,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,11]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0354669","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,11]]}}}