{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:55:59Z","timestamp":1778082959578,"version":"3.51.4"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T00:00:00Z","timestamp":1738627200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T00:00:00Z","timestamp":1738627200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"DOI":"10.1186\/s12859-025-06050-2","type":"journal-article","created":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T06:31:12Z","timestamp":1738650672000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["BioLake: an RNA expression analysis framework for prostate cancer biomarker powered by data lakehouse"],"prefix":"10.1186","volume":"26","author":[{"given":"Qiaowang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaser","family":"Gamallat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jon George","family":"Rokne","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tarek A.","family":"Bismar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reda","family":"Alhajj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,2,4]]},"reference":[{"key":"6050_CR1","doi-asserted-by":"crossref","unstructured":"Smith S, Hogan J, Rittenbruch M, Johnson D, Brereton M. Visual analytics for large-scale bioinformatic data sets. In Proceedings of the annual meeting of the australian special interest group for computer human interaction. 2015;603\u20137.","DOI":"10.1145\/2838739.2838829"},{"issue":"3","key":"6050_CR2","doi-asserted-by":"publisher","first-page":"1001779","DOI":"10.1371\/journal.pmed.1001779","volume":"12","author":"C Sudlow","year":"2015","unstructured":"Sudlow C, Gallacher J, Allen N, Beral V, Burton P, Danesh J, Downey P, Elliott P, Green J, Landray M, et al. UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PLoS Med. 2015;12(3):1001779.","journal-title":"PLoS Med"},{"issue":"12","key":"6050_CR3","doi-asserted-by":"publisher","first-page":"3411","DOI":"10.14778\/3415478.3415560","volume":"13","author":"M Armbrust","year":"2020","unstructured":"Armbrust M, Das T, Sun L, Yavuz B, Zhu S, Murthy M, Torres J, Hovell H, Ionescu A, \u0141uszczak A, et al. Delta lake: high-performance acid table storage over cloud object stores. Proc VLDB Endow. 2020;13(12):3411\u201324.","journal-title":"Proc VLDB Endow"},{"key":"6050_CR4","first-page":"28","volume":"8","author":"M Armbrust","year":"2021","unstructured":"Armbrust M, Ghodsi A, Xin R, Zaharia M. Lakehouse: a new generation of open platforms that unify data warehousing and advanced analytics. Proc CIDR. 2021;8:28.","journal-title":"Proc CIDR"},{"key":"6050_CR5","unstructured":"Segal T, Barnard R. Let the shoemaker make the shoes-an abstraction layer is needed between bioinformatic analysis, tools, data, and equipment: an agenda for the next 5 years. In: Proceedings of the first Asia-pacific bioinformatics conference on bioinformatics 2003. 2003;19:215\u20138."},{"key":"6050_CR6","unstructured":"BioinformaticsFMRP: TCGAbiolinksGUI. http:\/\/tcgabiolinks.fmrp.usp.br:3838\/. Accessed 8 April 2023"},{"key":"6050_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-14-S18-S1","volume":"14","author":"EY Chen","year":"2013","unstructured":"Chen EY, Tan CM, Kou Y, Duan Q, Wang Z, Meirelles GV, Clark NR, Ma\u2019ayan A. Enrichr: interactive and collaborative HTML5 gene list enrichment analysis tool. BMC Bioinform. 2013;14:1\u201314.","journal-title":"BMC Bioinform"},{"issue":"1","key":"6050_CR8","doi-asserted-by":"publisher","first-page":"20560","DOI":"10.1038\/s41598-020-76603-3","volume":"10","author":"J Goedhart","year":"2020","unstructured":"Goedhart J, Luijsterburg MS. Volcanoser is a web app for creating, exploring, labeling and sharing volcano plots. Sci Rep. 2020;10(1):20560.","journal-title":"Sci Rep"},{"key":"6050_CR9","doi-asserted-by":"crossref","unstructured":"Goldman M, Craft B, Hastie M, Repe\u010dka K, McDade F, Kamath A, Banerjee A, Luo Y, Rogers D, Brooks AN, et al. The UCSC Xena platform for public and private cancer genomics data visualization and interpretation. biorxiv, 2018;326470.","DOI":"10.1101\/326470"},{"key":"6050_CR10","doi-asserted-by":"crossref","unstructured":"Li R, Zhu J, Zhong W-D, Jia Z. Pcadb-a comprehensive and interactive database for transcriptomes from prostate cancer population cohorts. BioRxiv. 2021;2021\u201306.","DOI":"10.1101\/2021.06.29.449134"},{"issue":"1","key":"6050_CR11","doi-asserted-by":"publisher","first-page":"7580","DOI":"10.1038\/s41598-019-43935-8","volume":"9","author":"NA Mahi","year":"2019","unstructured":"Mahi NA, Najafabadi MF, Pilarczyk M, Kouril M, Medvedovic M. GREIN: an interactive web platform for re-analyzing GEO RNA-seq data. Sci Rep. 2019;9(1):7580.","journal-title":"Sci Rep"},{"key":"6050_CR12","unstructured":"Bioinformatics\u2014SRPlot. https:\/\/www.bioinformatics.com.cn\/srplot. Accessed 26 June 2023"},{"issue":"W1","key":"6050_CR13","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1093\/nar\/gkx247","volume":"45","author":"Z Tang","year":"2017","unstructured":"Tang Z, Li C, Kang B, Gao G, Li C, Zhang Z. Gepia: a web server for cancer and normal gene expression profiling and interactive analyses. Nucl Acids Res. 2017;45(W1):98\u2013102.","journal-title":"Nucl Acids Res"},{"issue":"D1","key":"6050_CR14","doi-asserted-by":"publisher","first-page":"956","DOI":"10.1093\/nar\/gkx1090","volume":"46","author":"SV Vasaikar","year":"2018","unstructured":"Vasaikar SV, Straub P, Wang J, Zhang B. Linkedomics: analyzing multi-omics data within and across 32 cancer types. Nucl Acids Res. 2018;46(D1):956\u201363.","journal-title":"Nucl Acids Res"},{"issue":"8","key":"6050_CR15","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1093\/nar\/gkv1507","volume":"44","author":"A Colaprico","year":"2016","unstructured":"Colaprico A, Silva TC, Olsen C, Garofano L, Cava C, Garolini D, Sabedot TS, Malta TM, Pagnotta SM, Castiglioni I, et al. Tcgabiolinks: an R\/Bioconductor package for integrative analysis of TCGA data. Nucl Acids Res. 2016;44(8):71\u201371.","journal-title":"Nucl Acids Res"},{"issue":"6","key":"6050_CR16","doi-asserted-by":"publisher","first-page":"2044","DOI":"10.1093\/bib\/bby067","volume":"20","author":"A McDermaid","year":"2019","unstructured":"McDermaid A, Monier B, Zhao J, Liu B, Ma Q. Interpretation of differential gene expression results of RNA-seq data: review and integration. Brief Bioinform. 2019;20(6):2044\u201354.","journal-title":"Brief Bioinform"},{"key":"6050_CR17","doi-asserted-by":"crossref","unstructured":"Dao T-C, Bednarik R, Vrzakova H. Heatmap rendering from large-scale distributed datasets using cloud computing. In: Proceedings of the symposium on eye tracking research and applications. 2014;215\u20138.","DOI":"10.1145\/2578153.2578187"},{"key":"6050_CR18","first-page":"1055","volume":"3","author":"H Abdi","year":"2007","unstructured":"Abdi H. Z-scores. Encycl Meas Stat. 2007;3:1055\u20138.","journal-title":"Encycl Meas Stat"},{"key":"6050_CR19","doi-asserted-by":"crossref","unstructured":"Spearman C. The proof and measurement of association between two things. 1961.","DOI":"10.1037\/11491-005"},{"issue":"suppl-1","key":"6050_CR20","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1093\/nar\/gkh036","volume":"32","author":"Consortium GO","year":"2004","unstructured":"Consortium GO. The gene ontology (go) database and informatics resource. Nucl Acids Res. 2004;32(suppl-1):258\u201361.","journal-title":"Nucl Acids Res"},{"key":"6050_CR21","doi-asserted-by":"crossref","unstructured":"Kanehisa M. The kegg database. In: \u2018In Silico\u2019simulation of biological processes: novartis foundation symposium 2002;247, vol. 247, pp. 91\u2013103. Wiley Online Library","DOI":"10.1002\/0470857897.ch8"},{"issue":"43","key":"6050_CR22","doi-asserted-by":"publisher","first-page":"15545","DOI":"10.1073\/pnas.0506580102","volume":"102","author":"A Subramanian","year":"2005","unstructured":"Subramanian A, Tamayo P, Mootha VK, Mukherjee S, Ebert BL, Gillette MA, Paulovich A, Pomeroy SL, Golub TR, Lander ES, et al. Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles. Proc Natl Acad Sci. 2005;102(43):15545\u201350.","journal-title":"Proc Natl Acad Sci"},{"issue":"5","key":"6050_CR23","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1089\/omi.2011.0118","volume":"16","author":"G Yu","year":"2012","unstructured":"Yu G, Wang L-G, Han Y, He Q-Y. clusterprofiler: an r package for comparing biological themes among gene clusters. Omics J Integrat Biol. 2012;16(5):284\u20137.","journal-title":"Omics J Integrat Biol"},{"issue":"15","key":"6050_CR24","doi-asserted-by":"publisher","first-page":"2156","DOI":"10.1093\/bioinformatics\/btr330","volume":"27","author":"P Danecek","year":"2011","unstructured":"Danecek P, Auton A, Abecasis G, Albers CA, Banks E, DePristo MA, Handsaker RE, Lunter G, Marth GT, Sherry ST, et al. The variant call format and VCFtools. Bioinformatics. 2011;27(15):2156\u20138.","journal-title":"Bioinformatics"},{"issue":"16","key":"6050_CR25","doi-asserted-by":"publisher","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","volume":"25","author":"H Li","year":"2009","unstructured":"Li H, Handsaker B, Wysoker A, Fennell T, Ruan J, Homer N, Marth G, Abecasis G, Durbin R, Subgroup GPDP. The sequence alignment\/map format and SAMtools. bioinformatics. 2009;25(16):2078\u20139.","journal-title":"bioinformatics"},{"key":"6050_CR26","doi-asserted-by":"crossref","unstructured":"Nothaft FA, Massie M, Danford T, Zhang Z, Laserson U, Yeksigian C, Kottalam J, Ahuja A, Hammerbacher J, Linderman M, et al. Rethinking data-intensive science using scalable analytics systems. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data. 2015;631\u201346.","DOI":"10.1145\/2723372.2742787"},{"key":"6050_CR27","doi-asserted-by":"crossref","unstructured":"Vohra D, Vohra D. Apache parquet. Practical Hadoop Ecosystem: A Definitive Guide to Hadoop-Related Frameworks and Tools. 2016;325\u201335.","DOI":"10.1007\/978-1-4842-2199-0_8"},{"key":"6050_CR28","doi-asserted-by":"crossref","unstructured":"Abadi DJ, Madden SR, Hachem N. Column-stores versus row-stores: how different are they really? In: Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data, 2008;pp. 967\u2013980.","DOI":"10.1145\/1376616.1376712"},{"key":"6050_CR29","unstructured":"Glow: An open-source toolkit for large-scale genomic analysis. https:\/\/projectglow.io"},{"key":"6050_CR30","doi-asserted-by":"crossref","unstructured":"Santos RJ, Bernardino J. Real-time data warehouse loading methodology. In: Proceedings of the 2008 International Symposium on Database Engineering & Applications, 2008;pp. 49\u201358","DOI":"10.1145\/1451940.1451949"},{"key":"6050_CR31","doi-asserted-by":"crossref","unstructured":"Li P, Pronovost C, Wilson W, Tait B, Zhou J, Ding C, Criswell J. Beating opt with statistical clairvoyance and variable size caching. In: Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems, 2019;pp. 243\u2013256.","DOI":"10.1145\/3297858.3304067"},{"issue":"4","key":"6050_CR32","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/MC.2004.1297303","volume":"37","author":"N Megiddo","year":"2004","unstructured":"Megiddo N, Modha DS. Outperforming LRU with an adaptive replacement cache algorithm. Computer. 2004;37(4):58\u201365.","journal-title":"Computer"},{"issue":"1","key":"6050_CR33","doi-asserted-by":"publisher","first-page":"26241","DOI":"10.1038\/s41598-024-78021-1","volume":"14","author":"MA Khan","year":"2024","unstructured":"Khan MA, Mazhar T, Mateen Yaqoob M, Badruddin Khan M, Jilani Saudagar AK, Ghadi YY, Khattak UF, Shahid M. Optimal feature selection for heart disease prediction using modified Artificial Bee colony (M-ABC) and K-nearest neighbors (KNN). Sci Rep. 2024;14(1):26241.","journal-title":"Sci Rep"},{"issue":"1","key":"6050_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s43926-024-00078-1","volume":"4","author":"T Mazhar","year":"2024","unstructured":"Mazhar T, Shah SFA, Inam SA, Awotunde JB, Saeed MM, Hamam H. Analysis of integration of IoMT with blockchain: issues, challenges and solutions. Discover Internet of Things. 2024;4(1):1\u201336.","journal-title":"Discover Internet of Things"},{"key":"6050_CR35","doi-asserted-by":"crossref","unstructured":"Aoun M, Mazhar T, Nadeem MA, Shahzad T, Rehman SU, Rehman AU. A novel encryption scheme for secure communication based on rna. CSI Transactions on ICT, 2024;1\u201310.","DOI":"10.1007\/s40012-024-00398-1"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-025-06050-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-025-06050-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-025-06050-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,4]],"date-time":"2025-02-04T06:31:23Z","timestamp":1738650683000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-025-06050-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,4]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["6050"],"URL":"https:\/\/doi.org\/10.1186\/s12859-025-06050-2","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,4]]},"assertion":[{"value":"22 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 January 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 February 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":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Materials availability"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"37"}}