Show simple item record

dc.contributor.authorViñas, Ramon
dc.contributor.authorAndrés-Terré, Helena
dc.contributor.authorLiò, Pietro
dc.contributor.authorBryson, Kevin
dc.date.accessioned2021-01-19T00:31:50Z
dc.date.available2021-01-19T00:31:50Z
dc.date.issued2021-01-20
dc.identifier.issn1367-4803
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/316393
dc.description.abstractHigh-throughput gene expression can be used to address a wide range of fundamental biological problems, but datasets of an appropriate size are often unavailable. Moreover, existing transcriptomics simulators have been criticised because they fail to emulate key properties of gene expression data. In this paper, we develop a method based on a conditional generative adversarial network to generate realistic transcriptomics data for E. coli and humans. We assess the performance of our approach across several tissues and cancer types. We show that our model preserves several gene expression properties significantly better than widely used simulators such as SynTReN or GeneNetWeaver. The synthetic data preserves tissue and cancer-specific properties of transcriptomics data. Moreover, it exhibits real gene clusters and ontologies both at local and global scales, suggesting that the model learns to approximate the gene expression manifold in a biologically meaningful way.
dc.description.sponsorshipThe project leading to these results have received funding from “la Caixa” Foundation (ID 100010434), under the agreement LCF/BQ/EU19/11710059.
dc.publisherOxford University Press (OUP)
dc.rightsAll rights reserved
dc.titleAdversarial generation of gene expression data.
dc.typeArticle
prism.publicationNameBioinformatics
dc.identifier.doi10.17863/CAM.63503
dcterms.dateAccepted2021-01-14
rioxxterms.versionofrecord10.1093/bioinformatics/btab035
rioxxterms.versionAM
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserved
rioxxterms.licenseref.startdate2021-01-14
dc.contributor.orcidViñas Torné, Ramon [0000-0003-2411-4478]
dc.contributor.orcidLio, Pietro [0000-0002-0540-5053]
dc.identifier.eissn1367-4811
rioxxterms.typeJournal Article/Review
cam.issuedOnline2021-01-20
cam.orpheus.successMon Feb 01 07:30:33 GMT 2021 - Embargo updated
cam.orpheus.counter1
rioxxterms.freetoread.startdate2022-01-20


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record