{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T18:49:25Z","timestamp":1774896565193,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014100","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000}}],"reference-count":39,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","award":["2020.0239"],"award-info":[{"award-number":["2020.0239"]}],"id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Cellular signaling is driven by complex, dynamic phosphorylation networks that control growth and survival, and their dysregulation underlies diseases such as cancer. Although modern mass spectrometry enables large-scale quantification of phosphoproteomic responses over time, these measurements remain descriptive and cannot by themselves predict how signaling will evolve under perturbations. Here, we extend a biologically informed recurrent neural network framework (LEMBAS), to learn time-resolved phosphoproteomic trajectories. We introduce two interpretable modules; a phosphosite mapping that links signaling nodes to measured phosphorylation sites and a monotonic time mapping that aligns continuous experimental times to discrete signaling steps. Using synthetic benchmarks and an EGF-stimulation dataset with inhibitor treatments, the model accurately interpolates unseen time points and predicts drug-induced phosphoproteomic responses in a zero-shot setting, outperforming na\u00efve and fully connected baselines. Importantly, the model identifies both canonical and non-canonical signaling effects, including modulation of the transcription factor FOXO3:S7 (from the PI3K\/AKT pathway) by drugs affecting PTPN11 (from the RAS\/ERK pathway). By combining mechanistic priors with deep learning, our framework provides a scalable approach to interpret and predict dynamic drug responses from phosphoproteomic data.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014100","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T17:36:00Z","timestamp":1773855360000},"page":"e1014100","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Zero-shot prediction of drug responses using biologically informed neural networks trained on phosphoproteomic timeseries"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2781-3872","authenticated-orcid":true,"given":"Konstantinos","family":"Antonopoulos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5711-376X","authenticated-orcid":true,"given":"Olof","family":"Nordenstorm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9476-4516","authenticated-orcid":true,"given":"Avlant","family":"Nilsson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"issue":"5","key":"pcbi.1014100.ref001","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/j.cell.2011.02.013","article-title":"Hallmarks of cancer: the next generation","volume":"144","author":"D Hanahan","year":"2011","journal-title":"Cell"},{"issue":"11","key":"pcbi.1014100.ref002","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1016\/j.trecan.2016.10.006","article-title":"mTOR Signaling Confers Resistance to Targeted Cancer Drugs","volume":"2","author":"Y Guri","year":"2016","journal-title":"Trends Cancer"},{"issue":"8","key":"pcbi.1014100.ref003","doi-asserted-by":"crossref","first-page":"109157","DOI":"10.1016\/j.celrep.2021.109157","article-title":"A systematic analysis of signaling reactivation and drug resistance","volume":"35","author":"BN Kholodenko","year":"2021","journal-title":"Cell Rep"},{"key":"pcbi.1014100.ref004","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/j.semcancer.2021.06.019","article-title":"Attacking the PI3K\/Akt\/mTOR signaling pathway for targeted therapeutic treatment in human cancer","volume":"85","author":"L Yu","year":"2022","journal-title":"Semin Cancer Biol"},{"issue":"4","key":"pcbi.1014100.ref005","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1016\/j.cell.2016.03.029","article-title":"Oncogenic KRAS Regulates Tumor Cell Signaling via Stromal Reciprocation","volume":"165","author":"CJ Tape","year":"2016","journal-title":"Cell"},{"key":"pcbi.1014100.ref006","doi-asserted-by":"crossref","first-page":"105091","DOI":"10.1016\/j.phrs.2020.105091","article-title":"Investigation of cancer drug resistance mechanisms by phosphoproteomics","volume":"160","author":"JC Boulos","year":"2020","journal-title":"Pharmacol Res"},{"issue":"5","key":"pcbi.1014100.ref007","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1080\/17460441.2017.1304377","article-title":"Harnessing the power of proteomics for identification of oncogenic, druggable signalling pathways in cancer","volume":"12","author":"HC Murray","year":"2017","journal-title":"Expert Opin Drug Discov"},{"issue":"8052","key":"pcbi.1014100.ref008","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1038\/s41586-025-08584-0","article-title":"Mass-spectrometry-based proteomics: from single cells to clinical applications","volume":"638","author":"T Guo","year":"2025","journal-title":"Nature"},{"issue":"8","key":"pcbi.1014100.ref009","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1080\/14789450.2021.1976152","article-title":"Phosphoproteomics: a valuable tool for uncovering molecular signaling in cancer cells","volume":"18","author":"JS Gerritsen","year":"2021","journal-title":"Expert Rev Proteomics"},{"issue":"19","key":"pcbi.1014100.ref010","doi-asserted-by":"crossref","first-page":"2772","DOI":"10.1093\/bioinformatics\/btu382","article-title":"Predicting dynamic signaling network response under unseen perturbations","volume":"30","author":"F Zhu","year":"2014","journal-title":"Bioinformatics"},{"key":"pcbi.1014100.ref011","article-title":"Beyond the black box with biologically informed neural networks","author":"DA Selby","year":"2025","journal-title":"Nat Rev Genet"},{"issue":"133","key":"pcbi.1014100.ref012","doi-asserted-by":"crossref","first-page":"20170237","DOI":"10.1098\/rsif.2017.0237","article-title":"How to deal with parameters for whole-cell modelling","volume":"14","author":"AC Babtie","year":"2017","journal-title":"J R Soc Interface"},{"issue":"17","key":"pcbi.1014100.ref013","doi-asserted-by":"crossref","first-page":"3073","DOI":"10.1093\/bioinformatics\/btz020","article-title":"Benchmark problems for dynamic modeling of intracellular processes","volume":"35","author":"H Hass","year":"2019","journal-title":"Bioinformatics"},{"issue":"15","key":"pcbi.1014100.ref014","doi-asserted-by":"crossref","first-page":"3216","DOI":"10.1021\/bi902202q","article-title":"Logic-based models for the analysis of cell signaling networks","volume":"49","author":"MK Morris","year":"2010","journal-title":"Biochemistry"},{"issue":"1","key":"pcbi.1014100.ref015","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1186\/1478-811X-11-43","article-title":"Modeling approaches for qualitative and semi-quantitative analysis of cellular signaling networks","volume":"11","author":"R Samaga","year":"2013","journal-title":"Cell Commun Signal"},{"issue":"141","key":"pcbi.1014100.ref016","doi-asserted-by":"crossref","first-page":"20170387","DOI":"10.1098\/rsif.2017.0387","article-title":"Opportunities and obstacles for deep learning in biology and medicine","volume":"15","author":"T Ching","year":"2018","journal-title":"J R Soc Interface"},{"issue":"6","key":"pcbi.1014100.ref017","article-title":"Machine learning alternative to systems biology should not solely depend on data","volume":"23","author":"HC Yeo","year":"2022","journal-title":"Brief Bioinform"},{"issue":"1","key":"pcbi.1014100.ref018","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1038\/s41698-025-00822-y","article-title":"Towards an interpretable deep learning model of cancer","volume":"9","author":"A Nilsson","year":"2025","journal-title":"NPJ Precis Oncol"},{"issue":"1","key":"pcbi.1014100.ref019","doi-asserted-by":"crossref","first-page":"3069","DOI":"10.1038\/s41467-022-30684-y","article-title":"Artificial neural networks enable genome-scale simulations of intracellular signaling","volume":"13","author":"A Nilsson","year":"2022","journal-title":"Nat Commun"},{"issue":"12","key":"pcbi.1014100.ref020","doi-asserted-by":"crossref","first-page":"966","DOI":"10.1038\/nmeth.4077","article-title":"OmniPath: guidelines and gateway for literature-curated signaling pathway resources","volume":"13","author":"D T\u00fcrei","year":"2016","journal-title":"Nat Methods"},{"key":"pcbi.1014100.ref021","doi-asserted-by":"crossref","unstructured":"Cremers CG, Nguyen LK. Network rewiring, adaptive resistance and combating strategies in breast cancer. CDR [Internet]. 2019 [cited 2025 May 5]. Available from: https:\/\/www.oaepublish.com\/articles\/cdr.2019.60","DOI":"10.20517\/cdr.2019.60"},{"issue":"45","key":"pcbi.1014100.ref022","doi-asserted-by":"crossref","first-page":"5599","DOI":"10.1038\/onc.2015.26","article-title":"Adaptive stress signaling in targeted cancer therapy resistance","volume":"34","author":"E Pazarentzos","year":"2015","journal-title":"Oncogene"},{"key":"pcbi.1014100.ref023","doi-asserted-by":"crossref","unstructured":"Feng S, Sanford JA, Weber T, Hutchinson-Bunch CM, Dakup PP, Paurus VL. A phosphoproteomics data resource for systems-level modeling of kinase signaling networks. 2023.","DOI":"10.1101\/2023.08.03.551714"},{"key":"pcbi.1014100.ref024","doi-asserted-by":"crossref","unstructured":"Nordenstorm O, Baghdassarian H, Lauffenburger DA, Nilsson A. Biologically informed neural network models are robust to spurious interactions via self-pruning [Internet]. 2025. Available from: https:\/\/www.biorxiv.org\/content\/10.1101\/2025.10.24.684155v2.full","DOI":"10.1101\/2025.10.24.684155"},{"key":"pcbi.1014100.ref025","unstructured":"Jin H. Implicit bias of gradient descent for mean squared error regression with two-layer wide neural networks. 2023;25:1\u201310."},{"key":"pcbi.1014100.ref026","article-title":"Why Machine Learning Models Systematically Underestimate Extreme Values","author":"YS Ting","year":"2025","journal-title":"The Open Journal of Astrophysics [Internet]"},{"issue":"2","key":"pcbi.1014100.ref027","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1074\/jbc.M111.284224","article-title":"Phosphorylation of FOXO3a on Ser-7 by p38 promotes its nuclear localization in response to doxorubicin","volume":"287","author":"K-K Ho","year":"2012","journal-title":"J Biol Chem"},{"issue":"6","key":"pcbi.1014100.ref028","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1038\/cdd.2011.179","article-title":"FOXO3a regulates reactive oxygen metabolism by inhibiting mitochondrial gene expression","volume":"19","author":"EC Ferber","year":"2012","journal-title":"Cell Death Differ"},{"issue":"8","key":"pcbi.1014100.ref029","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1038\/nrd2926","article-title":"Targeting the phosphoinositide 3-kinase pathway in cancer","volume":"8","author":"P Liu","year":"2009","journal-title":"Nat Rev Drug Discov"},{"key":"pcbi.1014100.ref030","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1016\/j.csbj.2022.12.010","article-title":"Phosphoproteomics data-driven signalling network inference: does it work?","volume":"21","author":"LO Sriraja","year":"2023","journal-title":"Comput Struct Biotech J"},{"key":"pcbi.1014100.ref031","doi-asserted-by":"crossref","first-page":"174","DOI":"10.3389\/fnins.2013.00174","article-title":"The consequences of subtracting the mean pattern in fMRI multivariate correlation analyses","volume":"7","author":"L Garrido","year":"2013","journal-title":"Front Neurosci"},{"issue":"1","key":"pcbi.1014100.ref032","doi-asserted-by":"crossref","first-page":"9646","DOI":"10.1038\/s41467-024-53982-z","article-title":"SSEmb: A joint embedding of protein sequence and structure enables robust variant effect predictions","volume":"15","author":"LM Blaabjerg","year":"2024","journal-title":"Nat Commun"},{"key":"pcbi.1014100.ref033","doi-asserted-by":"crossref","unstructured":"Rosen Y, Roohani Y, Agrawal A, Samotorcan L, Consortium TS, Quake SR, et al. Universal Cell Embeddings: A Foundation Model for Cell Biology [Internet]. Cell Biology; 2023 [cited 2025 Sep 3]. Available from: http:\/\/biorxiv.org\/lookup\/doi\/10.1101\/2023.11.28.568918","DOI":"10.1101\/2023.11.28.568918"},{"issue":"1","key":"pcbi.1014100.ref034","doi-asserted-by":"crossref","first-page":"2269","DOI":"10.1038\/s41467-023-38035-1","article-title":"DeepFLR facilitates false localization rate control in phosphoproteomics","volume":"14","author":"Y Zong","year":"2023","journal-title":"Nat Commun"},{"key":"pcbi.1014100.ref035","doi-asserted-by":"crossref","first-page":"101679","DOI":"10.1016\/j.imu.2025.101679","article-title":"Challenges in AI-driven multi-omics data analysis for Oncology: Addressing dimensionality, sparsity, transparency and ethical considerations","volume":"57","author":"M Ouhmouk","year":"2025","journal-title":"Inform Med Unlocked"},{"key":"pcbi.1014100.ref036","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1016\/j.csbj.2024.12.030","article-title":"AI-driven multi-omics integration for multi-scale predictive modeling of genotype-environment-phenotype relationships","volume":"27","author":"Y Wu","year":"2025","journal-title":"Comput Struct Biotechnol J"},{"issue":"25","key":"pcbi.1014100.ref037","doi-asserted-by":"crossref","first-page":"7045","DOI":"10.1016\/j.cell.2024.11.015","article-title":"How to build the virtual cell with artificial intelligence: Priorities and opportunities","volume":"187","author":"C Bunne","year":"2024","journal-title":"Cell"},{"key":"pcbi.1014100.ref038","doi-asserted-by":"crossref","unstructured":"Zhang Y, Lu J, Shai O. Improve Network Embeddings with Regularization. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management [Internet]. Torino Italy: ACM; 2018 [cited 2025 Sep 15]. p. 1643\u20136. Available from: https:\/\/dl.acm.org\/doi\/10.1145\/3269206.3269320","DOI":"10.1145\/3269206.3269320"},{"key":"pcbi.1014100.ref039","author":"S Feng","year":"2023","journal-title":"Available from"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014100","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:46:58Z","timestamp":1774892818000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014100"}},"subtitle":[],"editor":[{"given":"Marc R","family":"Birtwistle","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":39,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014100","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]}}}