{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:37:26Z","timestamp":1780418246042,"version":"3.54.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1009465","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T00:00:00Z","timestamp":1634256000000}}],"reference-count":34,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2021,10,5]],"date-time":"2021-10-05T00:00:00Z","timestamp":1633392000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Drug treatment induces cell type specific transcriptional programs, and as the number of combinations of drugs and cell types grows, the cost for exhaustive screens measuring the transcriptional drug response becomes intractable. We developed DeepCellState, a deep learning autoencoder-based framework, for predicting the induced transcriptional state in a cell type after drug treatment, based on the drug response in another cell type. Training the method on a large collection of transcriptional drug perturbation profiles, prediction accuracy improves significantly over baseline and alternative deep learning approaches when applying the method to two cell types, with improved accuracy when generalizing the framework to additional cell types. Treatments with drugs or whole drug families not seen during training are predicted with similar accuracy, and the same framework can be used for predicting the results from other interventions, such as gene knock-downs. Finally, analysis of the trained model shows that the internal representation is able to learn regulatory relationships between genes in a fully data-driven manner.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1009465","type":"journal-article","created":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T04:50:23Z","timestamp":1633495823000},"page":"e1009465","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":18,"title":["DeepCellState: An autoencoder-based framework for predicting cell type specific transcriptional states induced by drug treatment"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3477-7101","authenticated-orcid":true,"given":"Ramzan","family":"Umarov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3664-6722","authenticated-orcid":true,"given":"Yu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1225-4908","authenticated-orcid":true,"given":"Erik","family":"Arner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,10,5]]},"reference":[{"issue":"1","key":"pcbi.1009465.ref001","doi-asserted-by":"crossref","first-page":"1186","DOI":"10.1038\/s41467-017-01383-w","article-title":"Common and cell-type specific responses to anti-cancer drugs revealed by high throughput transcript profiling","volume":"8","author":"M Niepel","year":"2017","journal-title":"Nat Commun"},{"key":"pcbi.1009465.ref002","first-page":"32","article-title":"Cell-specific prediction and application of drug-induced gene expression profiles","volume":"23","author":"R Hodos","year":"2018","journal-title":"Pac Symp Biocomput Pac Symp Biocomput"},{"issue":"33","key":"pcbi.1009465.ref003","doi-asserted-by":"crossref","first-page":"14621","DOI":"10.1073\/pnas.1000138107","article-title":"Discovery of drug mode of action and drug repositioning from transcriptional responses","volume":"107","author":"F Iorio","year":"2010","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"7\u20138","key":"pcbi.1009465.ref004","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1016\/j.drudis.2012.07.014","article-title":"Transcriptional data: a new gateway to drug repositioning?","volume":"18","author":"F Iorio","year":"2013","journal-title":"Drug Discov Today."},{"issue":"1","key":"pcbi.1009465.ref005","doi-asserted-by":"crossref","first-page":"4307","DOI":"10.1038\/s41467-018-06500-x","article-title":"DRUG-seq for miniaturized high-throughput transcriptome profiling in drug discovery.","volume":"9","author":"C Ye","year":"2018","journal-title":"Nat Commun"},{"issue":"6","key":"pcbi.1009465.ref006","doi-asserted-by":"crossref","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":"A Subramanian","year":"2017","journal-title":"Cell"},{"issue":"5795","key":"pcbi.1009465.ref007","doi-asserted-by":"crossref","first-page":"1929","DOI":"10.1126\/science.1132939","article-title":"The Connectivity Map: using gene-expression signatures to connect small molecules, genes, and disease","volume":"313","author":"J Lamb","year":"2006","journal-title":"Science"},{"issue":"1","key":"pcbi.1009465.ref008","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1038\/s41467-018-07931-2","article-title":"Single-cell RNA-seq denoising using a deep count autoencoder","volume":"10","author":"G Eraslan","year":"2019","journal-title":"Nat Commun."},{"issue":"1","key":"pcbi.1009465.ref009","doi-asserted-by":"crossref","first-page":"16329","DOI":"10.1038\/s41598-018-34688-x","article-title":"AutoImpute: Autoencoder based imputation of single-cell RNA-seq data","volume":"8","author":"D Talwar","year":"2018","journal-title":"Sci Rep"},{"key":"pcbi.1009465.ref010","first-page":"219","article-title":"A DEEP LEARNING APPROACH FOR CANCER DETECTION AND RELEVANT GENE IDENTIFICATION","volume":"22","author":"P Danaee","year":"2017","journal-title":"Pac Symp Biocomput Pac Symp Biocomput"},{"issue":"1","key":"pcbi.1009465.ref011","first-page":"mSystems.00025","article-title":"ADAGE-Based Integration of Publicly Available Pseudomonas aeruginosa Gene Expression Data with Denoising Autoencoders Illuminates Microbe-Host Interactions","volume":"1","author":"J Tan","year":"2016","journal-title":"mSystems"},{"issue":"S9","key":"pcbi.1009465.ref012","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1186\/s12864-017-4226-0","article-title":"A deep auto-encoder model for gene expression prediction","volume":"18","author":"R Xie","year":"2017","journal-title":"BMC Genomics"},{"issue":"19","key":"pcbi.1009465.ref013","doi-asserted-by":"crossref","first-page":"3743","DOI":"10.1093\/bioinformatics\/btz158","article-title":"Dr.VAE: improving drug response prediction via modeling of drug perturbation effects","volume":"35","author":"L Ramp\u00e1\u0161ek","year":"2019","journal-title":"Bioinforma Oxf Engl"},{"issue":"S1","key":"pcbi.1009465.ref014","doi-asserted-by":"crossref","first-page":"S9","DOI":"10.1186\/s12859-015-0852-1","article-title":"Learning a hierarchical representation of the yeast transcriptomic machinery using an autoencoder model","volume":"17","author":"L Chen","year":"2016","journal-title":"BMC Bioinformatics"},{"issue":"8","key":"pcbi.1009465.ref015","doi-asserted-by":"crossref","first-page":"715","DOI":"10.1038\/s41592-019-0494-8","article-title":"scGen predicts single-cell perturbation responses.","volume":"16","author":"M Lotfollahi","year":"2019","journal-title":"Nat Methods"},{"key":"pcbi.1009465.ref016","unstructured":"Nguyen TT, Nguyen CM, Nguyen DT, Nguyen DT, Nahavandi S. Deep learning for deepfakes creation and detection. ArXiv Prepr ArXiv190911573. 2019;1."},{"key":"pcbi.1009465.ref017","doi-asserted-by":"crossref","first-page":"10096","DOI":"10.1109\/ACCESS.2016.2611583","article-title":"Deep Dictionary Learning","volume":"4","author":"S Tariyal","year":"2016","journal-title":"IEEE Access"},{"key":"pcbi.1009465.ref018","first-page":"448","volume-title":"Proceedings of the Twelth International Conference on Artificial Intelligence and Statistics","author":"R Salakhutdinov","year":"2009"},{"key":"pcbi.1009465.ref019","doi-asserted-by":"crossref","unstructured":"Vincent P, Larochelle H, Bengio Y, Manzagol P-A. Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on Machine learning. 2008. p. 1096\u2013103.","DOI":"10.1145\/1390156.1390294"},{"key":"pcbi.1009465.ref020","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.isci.2019.04.039","article-title":"Perturbational Gene-Expression Signatures for Combinatorial Drug Discovery","volume":"15","author":"C-T Huang","year":"2019","journal-title":"iScience"},{"issue":"1","key":"pcbi.1009465.ref021","doi-asserted-by":"crossref","first-page":"17603","DOI":"10.1038\/s41598-019-54180-4","article-title":"A framework for identification of on- and off-target transcriptional responses to drug treatment","volume":"9","author":"Y Huang","year":"2019","journal-title":"Sci Rep"},{"issue":"24","key":"pcbi.1009465.ref022","doi-asserted-by":"crossref","first-page":"6807","DOI":"10.1158\/0008-5472.CAN-18-0989","article-title":"The NCI Transcriptional Pharmacodynamics Workbench: A Tool to Examine Dynamic Expression Profiling of Therapeutic Response in the NCI-60 Cell Line Panel","volume":"78","author":"A Monks","year":"2018","journal-title":"Cancer Res"},{"issue":"1","key":"pcbi.1009465.ref023","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1038\/s41467-020-20249-2","article-title":"Multi-domain translation between single-cell imaging and sequencing data using autoencoders","volume":"12","author":"KD Yang","year":"2021","journal-title":"Nat Commun."},{"key":"pcbi.1009465.ref024","unstructured":"Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-Image Translation with Conditional Adversarial Networks. ArXiv161107004 Cs [Internet]. 2018 Nov 26 [cited 2021 Feb 8]; Available from: http:\/\/arxiv.org\/abs\/1611.07004"},{"key":"pcbi.1009465.ref025","unstructured":"Amodio M, Krishnaswamy S. MAGAN: Aligning Biological Manifolds. ArXiv180300385 Cs [Internet]. 2018 Feb 9 [cited 2021 Jan 21]; Available from: http:\/\/arxiv.org\/abs\/1803.00385"},{"issue":"1","key":"pcbi.1009465.ref026","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.cels.2017.06.003","article-title":"Unsupervised Extraction of Stable Expression Signatures from Public Compendia with an Ensemble of Neural Networks","volume":"5","author":"J Tan","year":"2017","journal-title":"Cell Syst"},{"issue":"12","key":"pcbi.1009465.ref027","article-title":"ChIP-Atlas: a data-mining suite powered by full integration of public ChIP-seq data","volume":"19","author":"S Oki","year":"2018","journal-title":"EMBO Rep"},{"issue":"D1","key":"pcbi.1009465.ref028","doi-asserted-by":"crossref","first-page":"D419","DOI":"10.1093\/nar\/gky1038","article-title":"PANTHER version 14: more genomes, a new PANTHER GO-slim and improvements in enrichment analysis tools","volume":"47","author":"H Mi","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1009465.ref029","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1038\/s41540-017-0022-3","article-title":"Comparing structural and transcriptional drug networks reveals signatures of drug activity and toxicity in transcriptional responses","volume":"3","author":"F Sirci","year":"2017","journal-title":"NPJ Syst Biol Appl"},{"issue":"11","key":"pcbi.1009465.ref030","doi-asserted-by":"crossref","first-page":"1139","DOI":"10.1038\/s41592-019-0576-7","article-title":"Exploring single-cell data with deep multitasking neural networks.","volume":"16","author":"M Amodio","year":"2019","journal-title":"Nat Methods"},{"key":"pcbi.1009465.ref031","unstructured":"Mirsky Y, Lee W. The Creation and Detection of Deepfakes: A Survey. ArXiv200411138 Cs Eess [Internet]. 2020 Sep 13 [cited 2020 Dec 12]; Available from: http:\/\/arxiv.org\/abs\/2004.11138"},{"key":"pcbi.1009465.ref032","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"AL Maas","year":"2013","journal-title":"In: Proc icml"},{"key":"pcbi.1009465.ref033","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. ArXiv Prepr ArXiv14126980. 2014;"},{"key":"pcbi.1009465.ref034","unstructured":"Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al. Tensorflow: A system for large-scale machine learning. In: 12th {USENIX} symposium on operating systems design and implementation ({OSDI} 16). 2016. p. 265\u201383."}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1009465","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T00:00:00Z","timestamp":1634256000000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,15]],"date-time":"2021-10-15T18:50:51Z","timestamp":1634323851000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1009465"}},"subtitle":[],"editor":[{"given":"Magnus","family":"Rattray","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,10,5]]},"references-count":34,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,10,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1009465","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1009465","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,5]]}}}