{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T22:47:45Z","timestamp":1761518865541},"reference-count":15,"publisher":"Oxford University Press (OUP)","issue":"22","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007,11,15]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Motivation: The \u2018reproducibility\u2019 of mass spectrometry proteomic profiling has become an intensely controversial topic. The mere mention of concern over the \u2018reproducibility\u2019 of data generated from any particular platform can lead to the anxiety over the generalizability of its results and its role in the future of discovery proteomics. In this study, we examine the reproducibility of proteomic profiles generated by surface-enhanced laser desorption\/ionization time-of-flight mass spectrometry (SELDI-TOF-MS) across multiple data-generation sessions. We analyze the problem in terms of the reproducibility of signals, reproducibility of discriminative features and reproducibility of multivariate classification models on profiles for serum samples from early lung cancer and healthy control subjects.<\/jats:p><jats:p>Results: Proteomic profiles in individual data-generation sessions experience within-session variability. We show that combining data from multiple sessions introduces additional (inter-session) noise. While additional noise can affect the discriminative analysis, we show that its average effect on profiles in our study is relatively small. Moreover, for the purposes of prediction on future (previously unseen) data, classifiers trained on multi-session data are able to adapt to inter-session noise and improve their classification accuracy.<\/jats:p><jats:p>Contact: \u00a0milos@cs.pitt.edu<\/jats:p>","DOI":"10.1093\/bioinformatics\/btm415","type":"journal-article","created":{"date-parts":[[2007,9,1]],"date-time":"2007-09-01T00:27:43Z","timestamp":1188606463000},"page":"3065-3072","source":"Crossref","is-referenced-by-count":12,"title":["Intersession reproducibility of mass spectrometry profiles and its effect on accuracy of multivariate classification models"],"prefix":"10.1093","volume":"23","author":[{"given":"Richard","family":"Pelikan","sequence":"first","affiliation":[{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"},{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"},{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"William L.","family":"Bigbee","sequence":"additional","affiliation":[{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Malehorn","sequence":"additional","affiliation":[{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James","family":"Lyons-Weiler","sequence":"additional","affiliation":[{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"},{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"},{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milos","family":"Hauskrecht","sequence":"additional","affiliation":[{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"},{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"},{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"},{"name":"1 Department of Computer Science, 2Intelligent Systems Program, 3Department of Biomedical Informatics, 4University of Pittsburgh Cancer Institute and 5Genomics and Proteomics Core Laboratories, University of Pittsburgh, Pittsburgh, PA 15260, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2007,8,30]]},"reference":[{"key":"2023041208261002600_","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1093\/bioinformatics\/btg484","article-title":"Reproducibility of SELDI-TOF protein patterns in serum: comparing datasets from different experiments","volume":"20","author":"Baggerly","year":"2004","journal-title":"Bioinformatics"},{"key":"2023041208261002600_","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1373\/49.8.1272","article-title":"Point: proteomic patterns in biological fluids: do they represent the future of cancer diagnostics?","volume":"49","author":"Diamandis","year":"2003","journal-title":"Clin. Chem."},{"key":"2023041208261002600_","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611970319","volume-title":"The Jackknife, the Bootstrap, and Other Resampling Plans","author":"Efron","year":"1982"},{"key":"2023041208261002600_","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2346-5","volume-title":"Permutation Tests: A Practical Guide to Resampling Methods for Testing Hypotheses","author":"Good","year":"1994"},{"key":"2023041208261002600_","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1177\/117693510500100106","article-title":"The need for review and understanding of seldi\/maldi mass spectroscopy data prior to analysis","volume":"1","author":"Grizzle","year":"2005","journal-title":"Cancer Inform."},{"key":"2023041208261002600_","doi-asserted-by":"crossref","first-page":"227","DOI":"10.2165\/00822942-200504040-00003","article-title":"Feature selection for classification of seldi\u2013tof\u2013ms proteomic profiles","volume":"4","author":"Hauskrecht","year":"2005","journal-title":"Appl. Bioinformatics"},{"key":"2023041208261002600_","author":"Hauskrecht","year":"2007","journal-title":"Fundamentals of Data Mining in Genomics and Proteomics"},{"key":"2023041208261002600_","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1023\/A:1024068626366","article-title":"Inference for the generalization error","volume":"52","author":"Nadeau","year":"2003","journal-title":"Mach. Learn"},{"key":"2023041208261002600_","volume-title":"Serum Proteomic Profiling and Analysis","author":"Pelikan","year":"2004"},{"key":"2023041208261002600_","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1016\/S0140-6736(02)07746-2","article-title":"Use of proteomic patterns in serum to identify ovarian cancer","volume":"359","author":"Petricoin","year":"2002","journal-title":"Lancet"},{"key":"2023041208261002600_","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1385\/CP:2:1:91","article-title":"Assessment of protein stability in cerebrospinal fluid using surface-enhanced laser desorption\/ionization time-of-flight mass spectrometry protein profiling","volume":"2","author":"Ranganathan","year":"2006","journal-title":"Clin. Proteomics"},{"key":"2023041208261002600_","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1038\/nrc1550","article-title":"Bias as a threat to the validity of cancer molecular-marker research","volume":"5","author":"Ransohoff","year":"2005","journal-title":"Nat. Rev. Cancer"},{"key":"2023041208261002600_","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1373\/clinchem.2004.038950","article-title":"Evaluation of serum protein profiling by surface-enhanced laser desorption\/ionization time-of-flight mass spectrometry for the detection of prostate cancer: I. Assessment of platform reproducibility","volume":"51","author":"Semmes","year":"2005","journal-title":"Clin. Chem."},{"key":"2023041208261002600_","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The Nature of Statistical Learning Theory","author":"Vapnik","year":"1995"},{"key":"2023041208261002600_","doi-asserted-by":"crossref","first-page":"5882","DOI":"10.1158\/0008-5472.CAN-04-0746","article-title":"Three biomarkers identified from serum proteomic analysis for the detection of early stage ovarian cancer","volume":"64","author":"Zhang","year":"2004","journal-title":"Cancer Res."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/23\/22\/3065\/49857454\/bioinformatics_23_22_3065.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/23\/22\/3065\/49857454\/bioinformatics_23_22_3065.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,13]],"date-time":"2023-05-13T23:56:46Z","timestamp":1684022206000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/23\/22\/3065\/207192"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,8,30]]},"references-count":15,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2007,11,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btm415","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2007,11,15]]},"published":{"date-parts":[[2007,8,30]]}}}