{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T04:19:39Z","timestamp":1786681179311,"version":"build-2736575974"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100012957","name":"Friedrich-Schiller-Universit\u00e4t Jena","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100012957","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>The Genotype-Tissue Expression (GTEx) project provides a valuable resource for investigating gene regulation across various human tissues. However, its cross-sectional design introduces technical artifacts and batch effects related to donor demographics and tissue processing. These confounders obscure biological signals and distort multi-tissue analyses. We present GTEx_Pro, a Nextflow-based pipeline for preprocessing GTEx v8 transcriptomic data, enhancing multi-tissue comparability. It integrates TMM\u2009+\u2009CPM normalization and SVA batch effect correction to improve biological signal recovery while reducing systematic variations across 54 GTEx tissues. Designed for scalability and reproducibility, GTEx_Pro facilitates accurate multi-tissue transcriptomic analysis, and a similar framework can be adapted to other large-scale transcriptome datasets.<\/jats:p>","DOI":"10.1038\/s41598-025-20697-0","type":"journal-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T20:06:43Z","timestamp":1758658003000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["GTEx pro enables accurate multi-tissue gene expression analysis using robust normalization and batch correction"],"prefix":"10.1038","volume":"15","author":[{"given":"D.","family":"Jothi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,23]]},"reference":[{"issue":"6","key":"20697_CR1","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1038\/ng.2653","volume":"45","author":"J Lonsdale","year":"2013","unstructured":"Lonsdale, J. et al. The Genotype-Tissue expression (GTEx) project. Nat. Genet. 45(6), 580\u2013585 (2013).","journal-title":"Nat. Genet."},{"issue":"1","key":"20697_CR2","doi-asserted-by":"publisher","first-page":"24799","DOI":"10.1038\/srep24799","volume":"6","author":"I Kosti","year":"2016","unstructured":"Kosti, I. et al. Cross-tissue analysis of gene and protein expression in normal and cancer tissues. Sci. Rep. 6(1), 24799 (2016).","journal-title":"Sci. Rep."},{"issue":"6","key":"20697_CR3","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1093\/bioinformatics\/bts034","volume":"28","author":"JT Leek","year":"2012","unstructured":"Leek, J. T. et al. The Sva package for removing batch effects and other unwanted variation in high-throughput experiments. Bioinformatics 28(6), 882\u2013883 (2012).","journal-title":"Bioinformatics"},{"issue":"3","key":"20697_CR4","doi-asserted-by":"publisher","first-page":"R25","DOI":"10.1186\/gb-2010-11-3-r25","volume":"11","author":"MD Robinson","year":"2010","unstructured":"Robinson, M. D. & Oshlack, A. A scaling normalization method for differential expression analysis of RNA-seq data. Genome Biol. 11(3), R25 (2010).","journal-title":"Genome Biol."},{"issue":"1","key":"20697_CR5","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1186\/s12864-024-10364-5","volume":"25","author":"R Cuevas-Diaz Duran","year":"2024","unstructured":"Cuevas-Diaz Duran, R., Wei, H. & Wu, J. Data normalization for addressing the challenges in the analysis of single-cell transcriptomic datasets. BMC Genom. 25(1), 444 (2024).","journal-title":"BMC Genom."},{"issue":"3","key":"20697_CR6","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1175\/1520-0493(2001)129<0540:EDAASM>2.0.CO;2","volume":"129","author":"KL Elmore","year":"2001","unstructured":"Elmore, K. L. & Richman, M. B. Euclidean distance as a similarity metric for principal component analysis. Mon. Weather Rev. 129(3), 540\u2013549 (2001).","journal-title":"Mon. Weather Rev."},{"key":"20697_CR7","doi-asserted-by":"crossref","unstructured":"Yao, F. & Coquery, J. L\u00ea Cao, K.-A. Independent principal component analysis for biologically meaningful dimension reduction of large biological data sets. BMC Bioinform. 13(1), 24 (2012).","DOI":"10.1186\/1471-2105-13-24"},{"issue":"2","key":"20697_CR8","first-page":"PAMI","volume":"1","author":"DL Davies","year":"1979","unstructured":"Davies, D. L. & Bouldin, D. W. A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. 1(2), PAMI (1979).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"20697_CR9","doi-asserted-by":"publisher","first-page":"15534","DOI":"10.1038\/s41598-020-72664-6","volume":"10","author":"Y Zhao","year":"2020","unstructured":"Zhao, Y., Wong, L. & Goh, W. W. B. How to do quantile normalization correctly for gene expression data analyses. Sci. Rep. 10(1), 15534 (2020).","journal-title":"Sci. Rep."},{"issue":"1","key":"20697_CR10","doi-asserted-by":"publisher","first-page":"7233","DOI":"10.1038\/s41598-019-43829-9","volume":"9","author":"M Ryaboshapkina","year":"2019","unstructured":"Ryaboshapkina, M. & Hammar, M. Tissue-specific genes as an underutilized resource in drug discovery. Sci. Rep. 9(1), 7233 (2019).","journal-title":"Sci. Rep."},{"key":"20697_CR11","doi-asserted-by":"crossref","unstructured":"Danino, R., Nachman, I. & Sharan, R. Batch correction of single-cell sequencing data via an autoencoder architecture. Bioinf. Adv.  4(1) (2023).","DOI":"10.1093\/bioadv\/vbad186"},{"issue":"1","key":"20697_CR12","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1093\/bioinformatics\/btp616","volume":"26","author":"MD Robinson","year":"2010","unstructured":"Robinson, M. D., McCarthy, D. J. & Smyth, G. K. EdgeR: a bioconductor package for differential expression analysis of digital gene expression data. Bioinformatics 26(1), 139\u2013140 (2010).","journal-title":"Bioinformatics"},{"key":"20697_CR13","unstructured":"Bolstad, B. preprocessCore: A collection of pre-processing functions. R package version 1.48.0. (2023)."},{"issue":"4","key":"20697_CR14","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1207\/s15327906mbr2704_2","volume":"27","author":"A Buja","year":"1992","unstructured":"Buja, A. & Eyuboglu, N. Remarks on parallel analysis. Multivar. Behav. Res. 27(4), 509\u2013540 (1992).","journal-title":"Multivar. Behav. Res."},{"issue":"6509","key":"20697_CR15","doi-asserted-by":"publisher","first-page":"eaba3066","DOI":"10.1126\/science.aba3066","volume":"369","author":"M Oliva","year":"2020","unstructured":"Oliva, M. et al. The impact of sex on gene expression across human tissues. Science 369(6509), eaba3066 (2020).","journal-title":"Science"},{"key":"20697_CR16","unstructured":"Blighe, K. L.A., PCAtools: Everything Principal Components Analysis. R package version 2.18.0.(2024)."},{"key":"20697_CR17","doi-asserted-by":"crossref","unstructured":"Inc., P. T. Collaborative Data Science (Plotly Technologies Inc., 2015).","DOI":"10.1016\/S1365-6937(15)30382-8"},{"key":"20697_CR18","unstructured":"Walesiak, M. D.A., The choice of variable normalization method in cluster analysis. Int. Bus. Inform. Manage. Association (IBIMA) 325\u2013340 (2020)."},{"key":"20697_CR19","doi-asserted-by":"crossref","unstructured":"Wickham, H. ggplot2: Elegant Graphics for Data Analysis(Springer International Publishing, 2016).","DOI":"10.1007\/978-3-319-24277-4_9"},{"key":"20697_CR20","doi-asserted-by":"crossref","unstructured":"Makowski, D. B. S. et al. Methods and algorithms for correlation analysis in {R}. J. Open. Source Softw. 5, 2306 (2020).","DOI":"10.21105\/joss.02306"},{"key":"20697_CR21","unstructured":"Kolde, R. pheatmap: Pretty Heatmaps. R package version 1.0.12. (2018)."},{"issue":"4","key":"20697_CR22","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1038\/nbt.3820","volume":"35","author":"P Di Tommaso","year":"2017","unstructured":"Di Tommaso, P. et al. Nextflow enables reproducible computational workflows. Nat. Biotechnol. 35(4), 316\u2013319 (2017).","journal-title":"Nat. Biotechnol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20697-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20697-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20697-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T20:06:45Z","timestamp":1758658005000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-20697-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,23]]},"references-count":22,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["20697"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-20697-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,23]]},"assertion":[{"value":"5 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"32684"}}