{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T08:43:57Z","timestamp":1790671437920,"version":"4.1.0"},"reference-count":14,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2018,9,10]],"date-time":"2018-09-10T00:00:00Z","timestamp":1536537600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"LIbrary of Integrated Network-Based Cellular Signatures","award":["U54HL127366"],"award-info":[{"award-number":["U54HL127366"]}]},{"name":"Big Data to Knowledge","award":["5U01HG008699"],"award-info":[{"award-number":["5U01HG008699"]}]}],"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>Facilitated by technological improvements, pharmacologic and genetic perturbational datasets have grown in recent years to include millions of experiments. Sharing and publicly distributing these diverse data creates many opportunities for discovery, but in recent years the unprecedented size of data generated and its complex associated metadata have also created data storage and integration challenges.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We present the GCTx file format and a suite of open-source packages for the efficient storage, serialization and analysis of dense two-dimensional matrices. We have extensively used the format in the Connectivity Map to assemble and share massive datasets currently comprising 1.3 million experiments, and we anticipate that the format\u2019s generalizability, paired with code libraries that we provide, will lower barriers for integrated cross-assay analysis and algorithm development.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Software packages (available in Python, R, Matlab and Java) are freely available at https:\/\/github.com\/cmap. Additional instructions, tutorials and datasets are available at clue.io\/code.<\/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\/bty784","type":"journal-article","created":{"date-parts":[[2018,9,8]],"date-time":"2018-09-08T03:56:01Z","timestamp":1536378961000},"page":"1427-1429","source":"Crossref","is-referenced-by-count":53,"title":["The GCTx format and cmap{Py, R, M, J} packages: resources for optimized storage and integrated traversal of annotated dense matrices"],"prefix":"10.1093","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9541-0058","authenticated-orcid":false,"given":"Oana M","family":"Enache","sequence":"first","affiliation":[{"name":"The Broad Institute, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David L","family":"Lahr","sequence":"additional","affiliation":[{"name":"The Broad Institute, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ted E","family":"Natoli","sequence":"additional","affiliation":[{"name":"The Broad Institute, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lev","family":"Litichevskiy","sequence":"additional","affiliation":[{"name":"The Broad Institute, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Wadden","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Corey","family":"Flynn","sequence":"additional","affiliation":[{"name":"MediaSilo, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua","family":"Gould","sequence":"additional","affiliation":[{"name":"The Broad Institute, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacob K","family":"Asiedu","sequence":"additional","affiliation":[{"name":"The Broad Institute, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajiv","family":"Narayan","sequence":"additional","affiliation":[{"name":"The Broad Institute, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aravind","family":"Subramanian","sequence":"additional","affiliation":[{"name":"The Broad Institute, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,9,10]]},"reference":[{"key":"2023012808252185900_bty784-B1","doi-asserted-by":"crossref","first-page":"1622","DOI":"10.1074\/mcp.M116.058354","article-title":"Reduced-representation phosphosignatures measured by quantitative targeted MS capture cellular states and enable large-scale comparison of drug-induced phenotypes","volume":"15","author":"Abelin","year":"2016","journal-title":"Mol. Cell. Proteomics"},{"key":"2023012808252185900_bty784-B2","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1038\/nprot.2016.105","article-title":"Cell Painting, a high-content image-based assay for morphological profiling using multiplexed fluorescent dyes","volume":"11","author":"Bray","year":"2016","journal-title":"Nat. Protoc"},{"key":"2023012808252185900_bty784-B3","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1038\/nm.4306","article-title":"The Drug Repurposing Hub: a next-generation drug library and information resource","volume":"23","author":"Corsello","year":"2017","journal-title":"Nat. Med"},{"key":"2023012808252185900_bty784-B4","doi-asserted-by":"crossref","first-page":"14863","DOI":"10.1073\/pnas.95.25.14863","article-title":"Cluster analysis and display of genome-wide expression patterns","volume":"95","author":"Eisen","year":"1998","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"2023012808252185900_bty784-B5","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0092-8674(00)00015-5","article-title":"Functional discovery via a compendium of expression profiles","volume":"102","author":"Hughes","year":"2000","journal-title":"Cell"},{"key":"2023012808252185900_bty784-B6","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.cels.2017.11.001","article-title":"The library of integrated network-based cellular signatures NIH program: system-level cataloging of human cells response to perturbations","volume":"6","author":"Keenan","year":"2018","journal-title":"Cell Syst."},{"key":"2023012808252185900_bty784-B7","doi-asserted-by":"crossref","first-page":"1929","DOI":"10.1126\/science.1132939","article-title":"The Connectivity Map: using gene-expression signatures to connect small molecules, genes, and disease","volume":"313","author":"Lamb","year":"2006","journal-title":"Science"},{"key":"2023012808252185900_bty784-B8","doi-asserted-by":"crossref","first-page":"1739","DOI":"10.1093\/bioinformatics\/btr260","article-title":"Molecular signatures database (MSigDB) 3.0","volume":"27","author":"Liberzon","year":"2011","journal-title":"Bioinformatics"},{"key":"2023012808252185900_bty784-B9","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1038\/nmeth.1600","article-title":"Adaptive informatics for multifactorial and high-content biological data","volume":"8","author":"Millard","year":"2011","journal-title":"Nat. Methods"},{"key":"2023012808252185900_bty784-B10","doi-asserted-by":"crossref","first-page":"1580","DOI":"10.1093\/bioinformatics\/btt175","article-title":"CellH5: a format for data exchange in high-content screening","volume":"29","author":"Sommer","year":"2013","journal-title":"Bioinformatics"},{"key":"2023012808252185900_bty784-B11","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1016\/j.cell.2017.10.049","article-title":"A next generation connectivity map: l 1000 platform and the first 1, 000, 000 profiles","volume":"171","author":"Subramanian","year":"2017","journal-title":"Cell"},{"key":"2023012808252185900_bty784-B12"},{"key":"2023012808252185900_bty784-B13","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1177\/1087057114522514","article-title":"Metadata standard and data exchange specifications to describe, model, and integrate complex and diverse high-throughput screening data from the library of integrated network-based cellular signatures (LINCS)","volume":"19","author":"Vempati","year":"2014","journal-title":"J. Biomol. Screen"},{"key":"2023012808252185900_bty784-B14","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1126\/science.275.5298.343","article-title":"An information-intensive approach to the molecular pharmacology of cancer","volume":"275","author":"Weinstein","year":"1997","journal-title":"Science"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/8\/1427\/48941730\/bioinformatics_35_8_1427.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/8\/1427\/48941730\/bioinformatics_35_8_1427.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,28]],"date-time":"2023-01-28T08:41:42Z","timestamp":1674895302000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/8\/1427\/5094509"}},"subtitle":[],"editor":[{"given":"Janet","family":"Kelso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2018,9,10]]},"references-count":14,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2019,4,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty784","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":[[2018,9,10]]}}}