{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Urzua-Traslavina CG"],"funding":["European Research Council","Dutch Research Council (NWO)"],"pagination":["1464"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC7935959"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["12(1)"],"pubmed_abstract":["The interpretation of high throughput sequencing data is limited by our incomplete functional understanding of coding and non-coding transcripts. Reliably predicting the function of such transcripts can overcome this limitation. Here we report the use of a consensus independent component analysis and guilt-by-association approach to predict over 23,000 functional groups comprised of over 55,000 coding and non-coding transcripts using publicly available transcriptomic profiles. We show that, compared to using Principal Component Analysis, Independent Component Analysis-derived transcriptional components enable more confident functionality predictions, improve predictions when new members are added to the gene sets, and are less affected by gene multi-functionality. Predictions generated usi"],"journal":["Nature communications"],"pubmed_title":["Improving gene function predictions using independent transcriptional components."],"pmcid":["PMC7935959"],"funding_grant_id":["682421","16025"],"pubmed_authors":["Leeuwenburgh VC","de Vries EGE","Bhattacharya A","Fehrmann RSN","Loipfinger S","Urzua-Traslavina CG","van Vugt MATM"],"additional_accession":[]},"is_claimable":false,"name":"Improving gene function predictions using independent transcriptional components.","description":"The interpretation of high throughput sequencing data is limited by our incomplete functional understanding of coding and non-coding transcripts. Reliably predicting the function of such transcripts can overcome this limitation. Here we report the use of a consensus independent component analysis and guilt-by-association approach to predict over 23,000 functional groups comprised of over 55,000 coding and non-coding transcripts using publicly available transcriptomic profiles. We show that, compared to using Principal Component Analysis, Independent Component Analysis-derived transcriptional components enable more confident functionality predictions, improve predictions when new members are added to the gene sets, and are less affected by gene multi-functionality. Predictions generated usi","dates":{"release":"2021-01-01T00:00:00Z","publication":"2021 Mar","modification":"2025-04-22T02:06:10.962Z","creation":"2025-04-05T20:14:53.29Z"},"accession":"S-EPMC7935959","cross_references":{"pubmed":["33674610"],"doi":["10.1038/s41467-021-21671-w"]}}