{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:37:24Z","timestamp":1782491844352,"version":"3.54.5"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,11,4]],"date-time":"2019-11-04T00:00:00Z","timestamp":1572825600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2019,11,4]],"date-time":"2019-11-04T00:00:00Z","timestamp":1572825600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100011201","name":"FP7 Science in Society","doi-asserted-by":"publisher","award":["283775"],"award-info":[{"award-number":["283775"]}],"id":[{"id":"10.13039\/100011201","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2019,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n              <jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Transcriptomic data is often used to build statistical models which are predictive of a given phenotype, such as disease status. Genes work together in pathways and it is widely thought that pathway representations will be more robust to noise in the gene expression levels. We aimed to test this hypothesis by constructing models based on either genes alone, or based on sample specific scores for each pathway, thus transforming the data to a \u2018pathway space\u2019. We progressively degraded the raw data by addition of noise and examined the ability of the models to maintain predictivity.<\/jats:p>\n              <\/jats:sec>\n              <jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>Models in the pathway space indeed had higher predictive robustness than models in the gene space. This result was independent of the workflow, parameters, classifier and data set used. Surprisingly, randomised pathway mappings produced models of similar accuracy and robustness to true mappings, suggesting that the success of pathway space models is not conferred by the specific definitions of the pathway. Instead, predictive models built on the true pathway mappings led to prediction rules with fewer influential pathways than those built on randomised pathways. The extent of this effect was used to differentiate pathway collections coming from a variety of widely used pathway databases.<\/jats:p>\n              <\/jats:sec>\n              <jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Prediction models based on pathway scores are more robust to degradation of gene expression information than the equivalent models based on ungrouped genes. While models based on true pathway scores are not more robust or accurate than those based on randomised pathways, true pathways produced simpler prediction rules, emphasizing a smaller number of pathways.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12859-019-3163-0","type":"journal-article","created":{"date-parts":[[2019,11,4]],"date-time":"2019-11-04T11:03:45Z","timestamp":1572865425000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Predictive modelling using pathway scores: robustness and significance of pathway collections"],"prefix":"10.1186","volume":"20","author":[{"given":"Marcelo P.","family":"Segura-Lepe","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hector C.","family":"Keun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3372-8423","authenticated-orcid":false,"given":"Timothy M. D.","family":"Ebbels","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,11,4]]},"reference":[{"issue":"3","key":"3163_CR1","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1038\/10343","volume":"22","author":"S Tavazoie","year":"1999","unstructured":"Tavazoie S, Hughes JD, Campbell MJ, Cho RJ, Church GM. Systematic determination of genetic network architecture. Nat Genet. 1999;22(3):281\u20135.","journal-title":"Nat Genet"},{"issue":"3","key":"3163_CR2","doi-asserted-by":"publisher","first-page":"798","DOI":"10.1089\/cmb.2006.13.798","volume":"13","author":"N Raghavan","year":"2006","unstructured":"Raghavan N, Amaratunga D, Cabrera J, Nie A, Qin J, McMillian M. On methods for gene function scoring as a means of facilitating the interpretation of microarray results. J Comput Biol. 2006;13(3):798\u2013809.","journal-title":"J Comput Biol"},{"issue":"11","key":"3163_CR3","doi-asserted-by":"publisher","first-page":"e1000217","DOI":"10.1371\/journal.pcbi.1000217","volume":"4","author":"E Lee","year":"2008","unstructured":"Lee E, Chuang HY, Kim JW, Ideker T, Lee D. Inferring pathway activity toward precise disease classification. PLoS Comput Biol. 2008;4(11):e1000217.","journal-title":"PLoS Comput Biol"},{"issue":"5","key":"3163_CR4","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1093\/bib\/bbp016","volume":"10","author":"S Baek","year":"2009","unstructured":"Baek S, Tsai CA, Chen JJ. Development of biomarker classifiers from high-dimensional data. Brief Bioinform. 2009;10(5):537\u201346.","journal-title":"Brief Bioinform"},{"issue":"4","key":"3163_CR5","doi-asserted-by":"publisher","first-page":"e34796","DOI":"10.1371\/journal.pone.0034796","volume":"7","author":"C Staiger","year":"2012","unstructured":"Staiger C, Cadot S, Kooter R, Dittrich M, Muller T, Klau GW, Wessels LF. A critical evaluation of network and pathway-based classifiers for outcome prediction in breast cancer. PLoS One. 2012;7(4):e34796.","journal-title":"PLoS One"},{"key":"3163_CR6","doi-asserted-by":"publisher","first-page":"289","DOI":"10.3389\/fgene.2013.00289","volume":"4","author":"C Staiger","year":"2013","unstructured":"Staiger C, Cadot S, Gyorffy B, Wessels LF, Klau GW. Current composite-feature classification methods do not outperform simple single-genes classifiers in breast cancer prognosis. Front Genet. 2013;4:289.","journal-title":"Front Genet"},{"issue":"12","key":"3163_CR7","doi-asserted-by":"publisher","first-page":"i311","DOI":"10.1093\/bioinformatics\/btv255","volume":"31","author":"A Allahyar","year":"2015","unstructured":"Allahyar A, de Ridder J. FERAL: network-based classifier with application to breast cancer outcome prediction. Bioinformatics. 2015;31(12):i311\u20139.","journal-title":"Bioinformatics"},{"issue":"16","key":"3163_CR8","doi-asserted-by":"publisher","first-page":"e151","DOI":"10.1093\/nar\/gkx642","volume":"45","author":"N Alcaraz","year":"2017","unstructured":"Alcaraz N, List M, Batra R, Vandin F, Ditzel HJ, Baumbach J. De novo pathway-based biomarker identification. Nucleic Acids Res. 2017;45(16):e151.","journal-title":"Nucleic Acids Res"},{"key":"3163_CR9","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1186\/1745-6150-7-21","volume":"7","author":"S Kim","year":"2012","unstructured":"Kim S, Kon M, DeLisi C. Pathway-based classification of cancer subtypes. Biol Direct. 2012;7:21.","journal-title":"Biol Direct"},{"key":"3163_CR10","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1186\/1471-2105-6-225","volume":"6","author":"J Tomfohr","year":"2005","unstructured":"Tomfohr J, Lu J, Kepler TB. Pathway level analysis of gene expression using singular value decomposition. BMC Bioinformatics. 2005;6:225.","journal-title":"BMC Bioinformatics"},{"issue":"7074","key":"3163_CR11","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1038\/nature04296","volume":"439","author":"AH Bild","year":"2006","unstructured":"Bild AH, Yao G, Chang JT, Wang Q, Potti A, Chasse D, Joshi MB, Harpole D, Lancaster JM, Berchuck A, et al. Oncogenic pathway signatures in human cancers as a guide to targeted therapies. Nature. 2006;439(7074):353\u20137.","journal-title":"Nature"},{"issue":"19","key":"3163_CR12","doi-asserted-by":"publisher","first-page":"2373","DOI":"10.1093\/bioinformatics\/btl401","volume":"22","author":"SW Kong","year":"2006","unstructured":"Kong SW, Pu WT, Park PJ. A multivariate approach for integrating genome-wide expression data and biological knowledge. Bioinformatics. 2006;22(19):2373\u201380.","journal-title":"Bioinformatics"},{"key":"3163_CR13","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1186\/1471-2105-12-322","volume":"12","author":"JA Miller","year":"2011","unstructured":"Miller JA, Cai C, Langfelder P, Geschwind DH, Kurian SM, Salomon DR, Horvath S. Strategies for aggregating gene expression data: the collapseRows R function. BMC Bioinformatics. 2011;12:322.","journal-title":"BMC Bioinformatics"},{"issue":"Suppl 7","key":"3163_CR14","doi-asserted-by":"crossref","first-page":"S26","DOI":"10.1186\/1471-2164-13-S7-S26","volume":"13","author":"S Hwang","year":"2012","unstructured":"Hwang S. Comparison and evaluation of pathway-level aggregation methods of gene expression data. BMC Genomics. 2012;13(Suppl 7):S26.","journal-title":"BMC Genomics"},{"issue":"8","key":"3163_CR15","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.tibtech.2005.05.011","volume":"23","author":"RK Curtis","year":"2005","unstructured":"Curtis RK, Oresic M, Vidal-Puig A. Pathways to the analysis of microarray data. Trends Biotechnol. 2005;23(8):429\u201335.","journal-title":"Trends Biotechnol"},{"issue":"7269","key":"3163_CR16","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1038\/nature08460","volume":"462","author":"DA Barbie","year":"2009","unstructured":"Barbie DA, Tamayo P, Boehm JS, Kim SY, Moody SE, Dunn IF, Schinzel AC, Sandy P, Meylan E, Scholl C, et al. Systematic RNA interference reveals that oncogenic KRAS-driven cancers require TBK1. Nature. 2009;462(7269):108\u201312.","journal-title":"Nature"},{"issue":"3","key":"3163_CR17","doi-asserted-by":"publisher","first-page":"202","DOI":"10.1016\/j.mrrev.2008.04.006","volume":"659","author":"M Vinken","year":"2008","unstructured":"Vinken M, Doktorova T, Ellinger-Ziegelbauer H, Ahr HJ, Lock E, Carmichael P, Roggen E, van Delft J, Kleinjans J, Castell J, et al. The carcinoGENOMICS project: critical selection of model compounds for the development of omics-based in vitro carcinogenicity screening assays. Mutat Res. 2008;659(3):202\u201310.","journal-title":"Mutat Res"},{"issue":"5439","key":"3163_CR18","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1126\/science.286.5439.531","volume":"286","author":"TR Golub","year":"1999","unstructured":"Golub TR, Slonim DK, Tamayo P, Huard C, Gaasenbeek M, Mesirov JP, Coller H, Loh ML, Downing JR, Caligiuri MA, et al. Molecular classification of cancer: class discovery and class prediction by gene expression monitoring. Science. 1999;286(5439):531\u20137.","journal-title":"Science"},{"issue":"10","key":"3163_CR19","doi-asserted-by":"publisher","first-page":"e1002240","DOI":"10.1371\/journal.pcbi.1002240","volume":"7","author":"D Venet","year":"2011","unstructured":"Venet D, Dumont JE, Detours V. Most random gene expression signatures are significantly associated with breast cancer outcome. PLoS Comput Biol. 2011;7(10):e1002240.","journal-title":"PLoS Comput Biol"},{"issue":"Suppl 10","key":"3163_CR20","doi-asserted-by":"publisher","first-page":"S15","DOI":"10.1186\/1471-2105-13-S10-S15","volume":"13","author":"M Holec","year":"2012","unstructured":"Holec M, Klema J, Zelezny F, Tolar J. Comparative evaluation of set-level techniques in predictive classification of gene expression samples. BMC Bioinformatics. 2012;13(Suppl 10):S15.","journal-title":"BMC Bioinformatics"},{"key":"3163_CR21","doi-asserted-by":"publisher","first-page":"193","DOI":"10.4137\/CIN.S10375","volume":"11","author":"M Burton","year":"2012","unstructured":"Burton M, Thomassen M, Tan Q, Kruse TA. Prediction of breast cancer metastasis by gene expression profiles: a comparison of metagenes and single genes. Cancer Inform. 2012;11:193\u2013217.","journal-title":"Cancer Inform"},{"issue":"43","key":"3163_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 U S A. 2005;102(43):15545\u201350.","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"3","key":"3163_CR23","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1093\/bib\/bbq085","volume":"12","author":"AL Boulesteix","year":"2011","unstructured":"Boulesteix AL, Sauerbrei W. Added predictive value of high-throughput molecular data to clinical data and its validation. Brief Bioinform. 2011;12(3):215\u201329.","journal-title":"Brief Bioinform"},{"issue":"3","key":"3163_CR24","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1093\/bioinformatics\/btg405","volume":"20","author":"L Gautier","year":"2004","unstructured":"Gautier L, Cope L, Bolstad BM, Irizarry RA. affy--analysis of Affymetrix GeneChip data at the probe level. Bioinformatics. 2004;20(3):307\u201315.","journal-title":"Bioinformatics"},{"issue":"Database issue","key":"3163_CR25","doi-asserted-by":"publisher","first-page":"D623","DOI":"10.1093\/nar\/gkn698","volume":"37","author":"A Kamburov","year":"2009","unstructured":"Kamburov A, Wierling C, Lehrach H, Herwig R. ConsensusPathDB--a database for integrating human functional interaction networks. Nucleic Acids Res. 2009;37(Database issue):D623\u20138.","journal-title":"Nucleic Acids Res"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-019-3163-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-019-3163-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-019-3163-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,3]],"date-time":"2020-11-03T00:08:24Z","timestamp":1604362104000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-019-3163-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,4]]},"references-count":25,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["3163"],"URL":"https:\/\/doi.org\/10.1186\/s12859-019-3163-0","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,11,4]]},"assertion":[{"value":"16 January 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"TMDE is an Associate Editor member of the Editorial Board of BMC Bioinformatics. The authors declare that they have no further competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"543"}}