{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:38:04Z","timestamp":1776109084341,"version":"3.50.1"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T00:00:00Z","timestamp":1632355200000},"content-version":"vor","delay-in-days":22,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["CRU 306 P-C"],"award-info":[{"award-number":["CRU 306 P-C"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["296 P8"],"award-info":[{"award-number":["296 P8"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["CRC 1286 Z2"],"award-info":[{"award-number":["CRC 1286 Z2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Recent technological advances have resulted in an unprecedented increase in publicly available biomedical data, yet the reuse of the data is often precluded by experimental bias and a lack of annotation depth and consistency. Missing annotations makes it impossible for researchers to find datasets specific to their needs.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Findings<\/jats:title>\n                  <jats:p>Here, we investigate RNA-sequencing metadata prediction based on gene expression values. We present a deep-learning\u2013based domain adaptation algorithm for the automatic annotation of RNA-sequencing metadata. We show, in multiple experiments, that our model is better at integrating heterogeneous training data compared with existing linear regression\u2013based approaches, resulting in improved tissue type classification. By using a model architecture similar to Siamese networks, the algorithm can learn biases from datasets with few samples.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Using our novel domain adaptation approach, we achieved metadata annotation accuracies up to 15.7% better than a previously published method. Using the best model, we provide a list of &amp;gt;10,000 novel tissue and sex label annotations for 8,495 unique SRA samples. Our approach has the potential to revive idle datasets by automated annotation making them more searchable.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/gigascience\/giab064","type":"journal-article","created":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T01:49:21Z","timestamp":1632361761000},"source":"Crossref","is-referenced-by-count":6,"title":["Bias-invariant RNA-sequencing metadata annotation"],"prefix":"10.1093","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4344-7024","authenticated-orcid":false,"given":"Hannes","family":"Wartmann","sequence":"first","affiliation":[{"name":"Institute of Medical Systems Biology, Center for Biomedical AI, University Medical Center Hamburg-Eppendorf , 20251 Hamburg,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sven","family":"Heins","sequence":"additional","affiliation":[{"name":"Institute of Medical Systems Biology, Center for Biomedical AI, University Medical Center Hamburg-Eppendorf , 20251 Hamburg,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karin","family":"Kloiber","sequence":"additional","affiliation":[{"name":"Institute of Medical Systems Biology, Center for Biomedical AI, University Medical Center Hamburg-Eppendorf , 20251 Hamburg,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4366-5662","authenticated-orcid":false,"given":"Stefan","family":"Bonn","sequence":"additional","affiliation":[{"name":"Institute of Medical Systems Biology, Center for Biomedical AI, University Medical Center Hamburg-Eppendorf , 20251 Hamburg,","place":["Germany"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"issue":"1","key":"2024111606492963500_bib2","doi-asserted-by":"publisher","DOI":"10.1002\/wrna.1364","article-title":"RNA-Seq methods for transcriptome analysis","volume":"8","author":"Hrdlickova","year":"2017","journal-title":"Wiley Interdiscip Rev RNA"},{"issue":"6","key":"2024111606492963500_bib3","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1038\/nrg.2016.49","article-title":"Coming of age: ten years of next-generation sequencing technologies","volume":"17","author":"Goodwin","year":"2016","journal-title":"Nat Rev Genet"},{"issue":"1","key":"2024111606492963500_bib4","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1038\/nrg2484","article-title":"RNA-Seq: a revolutionary tool for transcriptomics","volume":"10","author":"Wang","year":"2009","journal-title":"Nat Rev Genet"},{"issue":"2","key":"2024111606492963500_bib5","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1038\/ejhg.2012.129","article-title":"RNA-Seq and human complex diseases: recent accomplishments and future perspectives","volume":"21","author":"Costa","year":"2013","journal-title":"Eur J Hum Genet"},{"issue":"11","key":"2024111606492963500_bib6","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1038\/nbt.2702","article-title":"Reproducibility of high-throughput mRNA and small RNA sequencing across laboratories","volume":"31","author":"\u2019t\u00a0Hoen","year":"2013","journal-title":"Nat Biotechnol"},{"issue":"9","key":"2024111606492963500_bib7","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1038\/nbt.3000","article-title":"Detecting and correcting systematic variation in large-scale RNA sequencing data","volume":"32","author":"Li","year":"2014","journal-title":"Nat Biotechnol"},{"key":"2024111606492963500_bib8","first-page":"1521","article-title":"Unbiased look at dataset bias","volume-title":"2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011), Colorado Springs","author":"Torralba","year":"2011"},{"issue":"12","key":"2024111606492963500_bib9","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1186\/gm208","article-title":"Overcoming bias and systematic errors in next generation sequencing data","volume":"2","author":"Taub","year":"2010","journal-title":"Genome Med"},{"issue":"7","key":"2024111606492963500_bib10","doi-asserted-by":"crossref","first-page":"e1002195","DOI":"10.1371\/journal.pbio.1002195","article-title":"Big data: astronomical or genomical?","volume":"13","author":"Stephens","year":"2015","journal-title":"PLoS Biol"},{"issue":"6","key":"2024111606492963500_bib11","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1038\/ng.2653","article-title":"The genotype-tissue expression (GTEx) project","volume":"45","author":"Lonsdale","year":"2013","journal-title":"Nat Genet"},{"issue":"suppl1","key":"2024111606492963500_bib12","first-page":"D19","article-title":"The Sequence Read Archive","volume":"39","author":"Leinonen","year":"2010","journal-title":"Nucleic Acids Res"},{"issue":"S2","key":"2024111606492963500_bib13","doi-asserted-by":"crossref","first-page":"S1","DOI":"10.1186\/1471-2105-10-S2-S1","article-title":"Ontology-driven indexing of public datasets for translational bioinformatics","volume":"10","author":"Shah","year":"2009","journal-title":"BMC Bioinformatics"},{"issue":"3","key":"2024111606492963500_bib14","first-page":"403","article-title":"Ontology-based annotations and semantic relations in large-scale (epi) genomics data","volume":"18","author":"Galeota","year":"2017","journal-title":"Brief Bioinform"},{"issue":"18","key":"2024111606492963500_bib15","doi-asserted-by":"crossref","first-page":"2914","DOI":"10.1093\/bioinformatics\/btx334","article-title":"MetaSRA: normalized human sample-specific metadata for the Sequence Read Archive","volume":"33","author":"Bernstein","year":"2017","journal-title":"Bioinformatics"},{"issue":"12","key":"2024111606492963500_bib16","doi-asserted-by":"crossref","first-page":"959","DOI":"10.15252\/msb.20177728","article-title":"The landscape of human mutually exclusive splicing","volume":"13","author":"Hatje","year":"2017","journal-title":"Mol Syst Biol"},{"issue":"1","key":"2024111606492963500_bib17","first-page":"101913","article-title":"CellO: Comprehensive and hierarchical cell type classification of human cells with the Cell Ontology","volume":"24","author":"Bernstein","year":"2021","journal-title":"Science"},{"issue":"1","key":"2024111606492963500_bib18","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1186\/s12859-020-3427-8","article-title":"Standard machine learning approaches outperform deep representation learning on phenotype prediction from transcriptomics data","volume":"21","author":"Smith","year":"2020","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"2024111606492963500_bib19","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1038\/s41598-018-19635-0","article-title":"Robust phenotype prediction from gene expression data using differential shrinkage of co-regulated genes","volume":"8","author":"Zarringhalam","year":"2018","journal-title":"Sci Rep"},{"issue":"1","key":"2024111606492963500_bib20","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1186\/s12859-017-1984-2","article-title":"A biological network-based regularized artificial neural network model for robust phenotype prediction from gene expression data","volume":"18","author":"Kang","year":"2017","journal-title":"BMC Bioinformatics"},{"issue":"9","key":"2024111606492963500_bib21","doi-asserted-by":"crossref","first-page":"e54","DOI":"10.1093\/nar\/gky102","article-title":"Improving the value of public RNA-seq expression data by phenotype prediction","volume":"46","author":"Ellis","year":"2018","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"2024111606492963500_bib22","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1038\/s41467-019-14018-z","article-title":"Realistic in silico generation and augmentation of single-cell RNA-seq data using generative adversarial networks","volume":"11","author":"Marouf","year":"2020","journal-title":"Nat Commun"},{"issue":"30","key":"2024111606492963500_bib23","doi-asserted-by":"crossref","first-page":"eaba2619","DOI":"10.1126\/sciadv.aba2619","article-title":"Deep learning\u2013based cell composition analysis from tissue expression profiles","volume":"6","author":"Menden","year":"2020","journal-title":"Sci Adv"},{"issue":"5","key":"2024111606492963500_bib24","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.1021\/acs.molpharmaceut.5b00982","article-title":"Applications of deep learning in biomedicine","volume":"13","author":"Mamoshina","year":"2016","journal-title":"Mol Pharm"},{"issue":"9","key":"2024111606492963500_bib25","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1038\/nbt.4233","article-title":"Deep learning in biomedicine","volume":"36","author":"Wainberg","year":"2018","journal-title":"Nat Biotechnol"},{"key":"2024111606492963500_bib26","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-58347-1_1","article-title":"Domain adaptation for visual applications: A comprehensive survey","author":"Csurka","year":"2017"},{"key":"2024111606492963500_bib27","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-58347-1_2","article-title":"A deeper look at dataset bias","author":"Tommasi","year":"2017"},{"issue":"1","key":"2024111606492963500_bib28","doi-asserted-by":"crossref","first-page":"2734","DOI":"10.1038\/s41598-020-59516-z","article-title":"Variability in estimated gene expression among commonly used RNA-seq pipelines","volume":"10","author":"Arora","year":"2020","journal-title":"Sci Rep"},{"key":"2024111606492963500_bib44_1631556094188"},{"issue":"24","key":"2024111606492963500_bib29","doi-asserted-by":"crossref","first-page":"4033","DOI":"10.1093\/bioinformatics\/btw575","article-title":"Rail-RNA: scalable analysis of RNA-seq splicing and coverage","volume":"33","author":"Nellore","year":"2017","journal-title":"Bioinformatics"},{"key":"2024111606492963500_bib33","doi-asserted-by":"crossref","unstructured":"Wartmann H, Heins S, Kloiber K, et al. \u00a0Supporting data for \u201cBias invariant RNA-seq metadata annotation.\". GigaScience Database. 2021, 10.5524\/100920.","DOI":"10.1101\/2020.11.26.399568"},{"key":"2024111606492963500_bib30","author":"Project GTEx, 13.09.2019"},{"key":"2024111606492963500_bib45_1631560717500"},{"issue":"2","key":"2024111606492963500_bib31","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1007\/s10888-011-9188-x","article-title":"The origins of the Gini index: extracts from Variabilit\u00e0 e Mutabilit\u00e0 (1912) by Corrado Gini","volume":"10","author":"Ceriani","year":"2012","journal-title":"J Econ Inequal"},{"issue":"1","key":"2024111606492963500_bib32","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1186\/s12864-017-3661-2","article-title":"Detect tissue heterogeneity in gene expression data with BioQC","volume":"18","author":"Zhang","year":"2017","journal-title":"BMC Genomics"},{"issue":"7553","key":"2024111606492963500_bib34","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2024111606492963500_bib35","first-page":"539","article-title":"Learning a similarity metric discriminatively, with application to face verification","volume-title":"Computer Vision and Pattern Recognition, 2005 (CVPR 2005)","author":"Chopra","year":"2005"},{"key":"2024111606492963500_bib36","first-page":"815","article-title":"Facenet: A unified embedding for face recognition and clustering","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Schroff","year":"2015"},{"key":"2024111606492963500_bib1","article-title":"Git repository for \u201cBias invariant RNA-seq metadata annotation.\u201d","author":"Wartmann","year":"2021"},{"key":"2024111606492963500_bib46_1631561366438"},{"key":"2024111606492963500_bib37","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045244","article-title":"Dlid: Deep learning for domain adaptation by interpolating between domains","volume-title":"ICML Workshop on challenges in representation learning","author":"Chopra","year":"2013"},{"issue":"1","key":"2024111606492963500_bib38","first-page":"2030","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J Mach Learn Res"},{"key":"2024111606492963500_bib39","first-page":"7167","article-title":"Adversarial discriminative domain adaptation","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Tzeng","year":"2017"},{"key":"2024111606492963500_bib40","doi-asserted-by":"publisher","DOI":"10.1145\/3422622","article-title":"Generative adversarial nets","volume-title":"Adv Neural Inform Process Syst","author":"Goodfellow","year":"2014"},{"key":"2024111606492963500_bib41","article-title":"Few-shot adversarial domain adaptation","volume-title":"Adv Neural Inform Process Syst","author":"Motiian","year":"2017"},{"issue":"3","key":"2024111606492963500_bib42","doi-asserted-by":"crossref","first-page":"16004","DOI":"10.1038\/nmicrobiol.2016.4","article-title":"MERS coronavirus induces apoptosis in kidney and lung by upregulating Smad7 and FGF2","volume":"1","author":"Yeung","year":"2016","journal-title":"Nat Microbiol"},{"issue":"2","key":"2024111606492963500_bib43","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.cell.2015.03.001","article-title":"KPC1-mediated ubiquitination and proteasomal processing of NF-kB1 p105 to p50 restricts tumor growth","volume":"161","author":"Kravtsova-Ivantsiv","year":"2015","journal-title":"Cell"}],"container-title":["GigaScience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/gigascience\/article-pdf\/10\/9\/giab064\/60691036\/giab064.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/gigascience\/article-pdf\/10\/9\/giab064\/60691036\/giab064.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,16]],"date-time":"2024-11-16T06:50:45Z","timestamp":1731739845000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/gigascience\/article\/doi\/10.1093\/gigascience\/giab064\/6374210"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":46,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2021,9,22]]}},"URL":"https:\/\/doi.org\/10.1093\/gigascience\/giab064","relation":{},"ISSN":["2047-217X"],"issn-type":[{"value":"2047-217X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,9]]},"published":{"date-parts":[[2021,9]]},"article-number":"giab064"}}