{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:25:17Z","timestamp":1783700717659,"version":"3.55.0"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2018,9,8]],"date-time":"2018-09-08T00:00:00Z","timestamp":1536364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81530088"],"award-info":[{"award-number":["81530088"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81473070"],"award-info":[{"award-number":["81473070"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81402764"],"award-info":[{"award-number":["81402764"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81373102"],"award-info":[{"award-number":["81373102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81402763"],"award-info":[{"award-number":["81402763"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Project of Research and Development Program","award":["2016YFE0204900"],"award-info":[{"award-number":["2016YFE0204900"]}]},{"name":"Academic Program Development of Jiangsu Higher Education Institutions"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,4,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Stitching together trans-omics data is a powerful approach to assess the complex mechanisms of cancer occurrence, progression and treatment. However, the integration process suffers from the \u2018block missing\u2019 phenomena when part of individuals lacks some omics data.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We proposed a k-nearest neighbor (kNN) weighted imputation method for trans-omics block missing data (TOBMIkNN) to handle gene-absence individuals in RNA-seq datasets using external information obtained from DNA methylation probe datasets. Referencing to multi-hot deck, mean imputation and missing cases deletion, we assess the relative error, absolute error, inter-omics correlation structure change and variable selection.<\/jats:p>\n                  <jats:p>The proposed method, TOBMIkNN reliably imputed RNA-seq data by borrowing information from DNA methylation data, and showed superiority over the other three methods in imputation error and stability of correlation structure. Our study indicates that TOBMIkNN can be used as an advisable method for trans-omics block missing data imputation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>TOBMIkNN is freely available at https:\/\/github.com\/XuesiDong\/TOBMI.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/bty796","type":"journal-article","created":{"date-parts":[[2018,9,6]],"date-time":"2018-09-06T11:51:26Z","timestamp":1536234686000},"page":"1278-1283","source":"Crossref","is-referenced-by-count":43,"title":["TOBMI: trans-omics block missing data imputation using a k-nearest neighbor weighted approach"],"prefix":"10.1093","volume":"35","author":[{"given":"Xuesi","family":"Dong","sequence":"first","affiliation":[{"name":"Department of Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, China"},{"name":"Department of Epidemiology and Biostatistics, School of Public Health, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, China"},{"name":"China International Cooperation Center for Environment and Human Health, Nanjing Medical University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, China"},{"name":"China International Cooperation Center for Environment and Human Health, Nanjing Medical University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David C","family":"Christiani","sequence":"additional","affiliation":[{"name":"China International Cooperation Center for Environment and Human Health, Nanjing Medical University, Nanjing, China"},{"name":"Department of Environmental Health, Harvard School of Public Health, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongyue","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, China"},{"name":"China International Cooperation Center for Environment and Human Health, Nanjing Medical University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, School of Public Health, Nanjing Medical University, Nanjing, China"},{"name":"China International Cooperation Center for Environment and Human Health, Nanjing Medical University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,9,8]]},"reference":[{"key":"2023012808145107100_bty796-B1","doi-asserted-by":"crossref","first-page":"15.","DOI":"10.1186\/s12859-015-0857-9","article-title":"Methods for the integration of multi-omics data: mathematical aspects","volume":"17 Suppl 2","author":"Bersanelli","year":"2016","journal-title":"BMC Bioinformatics"},{"key":"2023012808145107100_bty796-B2","doi-asserted-by":"crossref","first-page":"e54","DOI":"10.2196\/jmir.1448","article-title":"Missing data approaches in eHealth research: simulation study and a tutorial for nonmathematically inclined researchers","volume":"12","author":"Blankers","year":"2010","journal-title":"J. Med. Internet Res"},{"key":"2023012808145107100_bty796-B3","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1142\/S0219720006002302","article-title":"Iterated local least squares microarray missing value imputation","volume":"4","author":"Cai","year":"2006","journal-title":"J. Bioinformatics Comput. Biol"},{"key":"2023012808145107100_bty796-B4","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1038\/ng.2764","article-title":"The Cancer Genome Atlas Pan-Cancer analysis project","volume":"45","year":"2013","journal-title":"Nat. Genet"},{"key":"2023012808145107100_bty796-B5","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1017\/S0007123412000312","article-title":"We have to be discrete about this: a non-parametric imputation technique for missing categorical data","volume":"43","author":"Cranmer","year":"2013","journal-title":"Br. J. Polit. Sci"},{"key":"2023012808145107100_bty796-B8","doi-asserted-by":"crossref","first-page":"S56","DOI":"10.1038\/nmeth.1436","article-title":"Visualization of omics data for systems biology","volume":"7","author":"Gehlenborg","year":"2010","journal-title":"Nat. Methods"},{"key":"2023012808145107100_bty796-B10","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/s11306-011-0366-4","article-title":"Missing values in mass spectrometry based metabolomics: an undervalued step in the data processing pipeline","volume":"8","author":"Hrydziuszko","year":"2012","journal-title":"Metabolomics"},{"key":"2023012808145107100_bty796-B11","first-page":"1726","volume-title":"Bioinformatics","author":"Imbert","year":"2017"},{"key":"2023012808145107100_bty796-B12","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1038\/nature08987","article-title":"International network of cancer genome projects","volume":"464","year":"2010","journal-title":"Nature"},{"key":"2023012808145107100_bty796-B17","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1029\/95WR02966","article-title":"A nearest neighbor bootstrap for resampling hydrologic time series","volume":"32","author":"Lall","year":"1996","journal-title":"Water Resour. Res"},{"key":"2023012808145107100_bty796-B18","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1038\/nature12213","article-title":"Mutational heterogeneity in cancer and the search for new cancer-associated genes","volume":"499","author":"Lawrence","year":"2013","journal-title":"Nature"},{"key":"2023012808145107100_bty796-B19","first-page":"1.","article-title":"Comparison of next-generation sequencing systems","volume":"2012","author":"Liu","year":"2012","journal-title":"J. Biomed. Biotechnol"},{"key":"2023012808145107100_bty796-B20","doi-asserted-by":"crossref","first-page":"R112.","DOI":"10.1186\/gb-2011-12-11-r112","article-title":"Evaluation of genomic high-throughput sequencing data generated on Illumina HiSeq and genome analyzer systems","volume":"12","author":"Minoche","year":"2011","journal-title":"Genome Biol"},{"key":"2023012808145107100_bty796-B21","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1016\/j.tree.2008.06.014","article-title":"Missing inaction: the dangers of ignoring missing data","volume":"23","author":"Nakagawa","year":"2008","journal-title":"Trends Ecol. Evol"},{"key":"2023012808145107100_bty796-B22","doi-asserted-by":"crossref","first-page":"2088","DOI":"10.1093\/bioinformatics\/btg287","article-title":"A Bayesian missing value estimation method for gene expression profile data","volume":"19","author":"Oba","year":"2003","journal-title":"Bioinformatics"},{"key":"2023012808145107100_bty796-B23","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1038\/nrm3314","article-title":"Innovation: metabolomics: the apogee of the omics trilogy","volume":"13","author":"Patti","year":"2012","journal-title":"Nat. Rev. Mol. Cell Biol"},{"key":"2023012808145107100_bty796-B24","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1038\/nrg3868","article-title":"Methods of integrating data to uncover genotype-phenotype interactions","volume":"16","author":"Ritchie","year":"2015","journal-title":"Nat. Rev. Genet"},{"key":"2023012808145107100_bty796-B25","doi-asserted-by":"crossref","first-page":"137","DOI":"10.2174\/1573409910666140410110241","article-title":"Assessing the validity of QSARs for ready biodegradability of chemicals: an applicability domain perspective","volume":"10","author":"Sahigara","year":"2014","journal-title":"Curr. Comput. Aided Drug Des"},{"key":"2023012808145107100_bty796-B26","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1177\/096228029900800102","article-title":"Multiple imputation: a primer","volume":"8","author":"Schafer","year":"1999","journal-title":"Stat. Methods Med. Res"},{"key":"2023012808145107100_bty796-B27","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1038\/nrg796","article-title":"Candidate-gene approaches for studying complex genetic traits: practical considerations","volume":"3","author":"Tabor","year":"2002","journal-title":"Nat. Rev. Genet"},{"key":"2023012808145107100_bty796-B28","first-page":"312","article-title":"Effects of imputation on correlation: implications for analysis of mass spectrometry data from multiple biological matrices","volume":"18","author":"Taylor","year":"2017","journal-title":"Brief. Bioinform"},{"key":"2023012808145107100_bty796-B29","doi-asserted-by":"crossref","first-page":"520","DOI":"10.1093\/bioinformatics\/17.6.520","article-title":"Missing value estimation methods for DNA microarrays","volume":"17","author":"Troyanskaya","year":"2001","journal-title":"Bioinformatics"},{"key":"2023012808145107100_bty796-B30","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1111\/j.1541-0420.2011.01558.x","article-title":"A hot-deck multiple imputation procedure for gaps in longitudinal recurrent event histories","volume":"67","author":"Wang","year":"2011","journal-title":"Biometrics"},{"key":"2023012808145107100_bty796-B31","doi-asserted-by":"crossref","first-page":"66.","DOI":"10.1186\/s13073-014-0066-6","article-title":"Pan-cancer patterns of DNA methylation","volume":"6","author":"Witte","year":"2014","journal-title":"Genome Med"},{"key":"2023012808145107100_bty796-B33","doi-asserted-by":"crossref","first-page":"2612.","DOI":"10.1038\/ncomms3612","article-title":"Inferring tumour purity and stromal and immune cell admixture from expression data","volume":"4","author":"Yoshihara","year":"2013","journal-title":"Nat. Commun"},{"key":"2023012808145107100_bty796-B34","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1016\/j.tibtech.2015.12.013","article-title":"Trans-omics: how to reconstruct biochemical networks across multiple \u2018omic\u2019 layers","volume":"34","author":"Yugi","year":"2016","journal-title":"Trends Biotechnol"},{"key":"2023012808145107100_bty796-B35","first-page":"1774","article-title":"Efficient kNN classification with different numbers of nearest neighbors","volume-title":"IEEE Trans. Neural Netw. Learn. Syst","author":"Zhang","year":"2017"},{"key":"2023012808145107100_bty796-B36","doi-asserted-by":"crossref","first-page":"e1001301.","DOI":"10.1371\/journal.pbio.1001301","article-title":"Stitching together multiple data dimensions reveals interacting metabolomic and transcriptomic networks that modulate cell regulation","volume":"10","author":"Zhu","year":"2012","journal-title":"PLoS Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/8\/1278\/48941001\/bioinformatics_35_8_1278.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/8\/1278\/48941001\/bioinformatics_35_8_1278.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T08:37:17Z","timestamp":1674895037000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/8\/1278\/5092930"}},"subtitle":[],"editor":[{"given":"John","family":"Hancock","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2018,9,8]]},"references-count":28,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2019,4,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty796","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2019,4,15]]},"published":{"date-parts":[[2018,9,8]]}}}