{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T15:38:04Z","timestamp":1760888284382},"reference-count":32,"publisher":"Oxford University Press (OUP)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,1,15]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Motivation: The analysis of high-resolution proton nuclear magnetic resonance (NMR) spectrometry can assist human experts to implicate metabolites expressed by diseased biofluids. Here, we explore an intermediate representation, between spectral trace and classifier, able to furnish a communicative interface between expert and machine. This representation permits equivalent, or better, classification accuracies than either principal component analysis (PCA) or multi-dimensional scaling (MDS). In the training phase, the peaks in each trace are detected and clustered in order to compile a common dictionary, which could be visualized and adjusted by an expert. The dictionary is used to characterize each trace with a fixed-length feature vector, termed Bag of Peaks, ready to be classified with classical supervised methods.<\/jats:p><jats:p>Results: Our small-scale study, concerning Type I diabetes in Sardinian children, provides a preliminary indication of the effectiveness of the Bag of Peaks approach over standard PCA and MDS. Consistently, higher classification accuracies are obtained once a sufficient number of peaks (&amp;gt;10) are included in the dictionary. A large-scale simulation of noisy spectra further confirms this advantage. Finally, suggestions for metabolite-peak loci that may be implicated in the disease are obtained by applying standard feature selection techniques.<\/jats:p><jats:p>Availability: Matlab code to compute the Bag of Peaks representation may be found at http:\/\/economia.uniss.it\/docenti\/bicego\/BagOfPeaks\/BagOfPeaks.zip<\/jats:p><jats:p>Contact: \u00a0gjb@crs4.it<\/jats:p>","DOI":"10.1093\/bioinformatics\/btn599","type":"journal-article","created":{"date-parts":[[2008,11,19]],"date-time":"2008-11-19T03:17:57Z","timestamp":1227064677000},"page":"258-264","source":"Crossref","is-referenced-by-count":10,"title":["Bag of Peaks: interpretation of NMR spectrometry"],"prefix":"10.1093","volume":"25","author":[{"given":"Gavin","family":"Brelstaff","sequence":"first","affiliation":[{"name":"1 Biocomputing, CRS4, 09100 Pula (CA), Sardinia, 2DEIR, University of Sassari, via Torre Tonda 34, 07100 Sassari, 3ICB-CNR, 07040 Li Punti, Sassari and 4Porto Conte Ricerche, Loc. Tramariglio, Alghero, Italy"}]},{"given":"Manuele","family":"Bicego","sequence":"additional","affiliation":[{"name":"1 Biocomputing, CRS4, 09100 Pula (CA), Sardinia, 2DEIR, University of Sassari, via Torre Tonda 34, 07100 Sassari, 3ICB-CNR, 07040 Li Punti, Sassari and 4Porto Conte Ricerche, Loc. Tramariglio, Alghero, Italy"}]},{"given":"Nicola","family":"Culeddu","sequence":"additional","affiliation":[{"name":"1 Biocomputing, CRS4, 09100 Pula (CA), Sardinia, 2DEIR, University of Sassari, via Torre Tonda 34, 07100 Sassari, 3ICB-CNR, 07040 Li Punti, Sassari and 4Porto Conte Ricerche, Loc. Tramariglio, Alghero, Italy"}]},{"given":"Matilde","family":"Chessa","sequence":"additional","affiliation":[{"name":"1 Biocomputing, CRS4, 09100 Pula (CA), Sardinia, 2DEIR, University of Sassari, via Torre Tonda 34, 07100 Sassari, 3ICB-CNR, 07040 Li Punti, Sassari and 4Porto Conte Ricerche, Loc. Tramariglio, Alghero, Italy"}]}],"member":"286","published-online":{"date-parts":[[2008,11,18]]},"reference":[{"key":"2023013109591897300_B1","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural Network for Pattern Recognition.","author":"Bishop","year":"1995"},{"key":"2023013109591897300_B2","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1002\/cmr.a.20043","article-title":"Exponential parameter estimation (in NMR) using Bayesian probability theory.","volume":"27","author":"Bretthorst","year":"2005","journal-title":"Concepts Magn. Reson. A"},{"key":"2023013109591897300_B3","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1207\/s15327906mbr0102_10","article-title":"The screen test for the number of factors.","volume":"1","author":"Cattell","year":"1966","journal-title":"Multivariate Behav. Res."},{"key":"2023013109591897300_B4","volume-title":"Multidimensional Scaling.","author":"Cox","year":"1994"},{"key":"2023013109591897300_B5","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1023\/A:1013625426931","article-title":"Latent semantic kernels.","volume":"18","author":"Cristianini","year":"2002","journal-title":"J. Intell. Inf. Syst."},{"key":"2023013109591897300_B6","article-title":"Visual categorization with bags of keypoints.","volume-title":"Proceedings of the Workshop Pattern Recognition and Machine Learning in Computer Vision.","author":"Csurka","year":"2004"},{"key":"2023013109591897300_B7","first-page":"224","article-title":"A cluster separation measure.","volume-title":"IEEE Trans. Pattern Anal. Mach. Intell.","author":"Davies","year":"1979"},{"key":"2023013109591897300_B8","article-title":"Prtools4, a matlab toolbox for pattern recognition.","author":"Duin","year":"2004"},{"key":"2023013109591897300_B9","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198556473.001.0001","volume-title":"Principles of Nuclear Magnetic Resonance in One and Two Dimensions.","author":"Ernst","year":"1990"},{"key":"2023013109591897300_B10","doi-asserted-by":"crossref","first-page":"783","DOI":"10.2307\/2408678","article-title":"Confidence limits on phylogenies: an approach using the bootstrap.","volume":"39","author":"Felsenstein","year":"1985","journal-title":"Evolution"},{"key":"2023013109591897300_B11","volume-title":"Introduction to Statistical Pattern Recognition.","author":"Fukanaga","year":"1990","edition":"2nd edn"},{"key":"2023013109591897300_B12","volume-title":"Clustering Algorithms.","author":"Hartigan","year":"1975"},{"key":"2023013109591897300_B13","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-21606-5","volume-title":"The Elements of Statistical Learning.","author":"Hastie","year":"2001"},{"key":"2023013109591897300_B14","volume-title":"Algorithms for Clustering Data.","author":"Jain","year":"1988"},{"key":"2023013109591897300_B15","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/331499.331504","article-title":"Data clustering: a review.","volume":"31","author":"Jain","year":"1999","journal-title":"ACM Comput. Surv."},{"key":"2023013109591897300_B16","first-page":"137","article-title":"Text categorization with support vector machines: learning with many relevant features.","volume-title":"Proceedings of the European Conf. Machine Learning.","author":"Joachims","year":"1998"},{"key":"2023013109591897300_B17","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-1904-8","volume-title":"Principal Component Analysis.","author":"Jollife","year":"1986"},{"key":"2023013109591897300_B18","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.pharmthera.2005.06.008","article-title":"Metabonic modeling of drug toxicity.","volume":"109","author":"Keun","year":"2006","journal-title":"J. Pharmacol. Ther."},{"key":"2023013109591897300_B19","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/S0004-3702(97)00043-X","article-title":"Wrappers for feature subset selection.","volume":"97","author":"Kohavi","year":"1997","journal-title":"Artif. Intell."},{"key":"2023013109591897300_B20","first-page":"296","article-title":"Multidimensional scaling and other methods for discovering structure.","volume-title":"Statistical Methods for Digital Computers.","author":"Kruskal","year":"1997"},{"key":"2023013109591897300_B21","first-page":"2169","article-title":"Beyond bags of features: spatial pyramid matching for recognizing natural scene categories.","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.","author":"Lazebnik","year":"2006"},{"key":"2023013109591897300_B22","article-title":"Intelligent bucketing for metabonomics - part 1.","volume-title":"Metabolic Profiling: Pathways in Discovery.","author":"Lefebvre","year":"2004"},{"key":"2023013109591897300_B23","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/S0041-008X(02)00079-0","article-title":"Contemporary issues in toxicology - the role of metabonomics in toxicology and its evaluation by the COMET project.","volume":"187","author":"Lindon","year":"2003","journal-title":"Toxicol. Appl. Pharmacol."},{"key":"2023013109591897300_B24","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/S0079-6565(00)00036-4","article-title":"Pattern recognition methods and applications in biomedical magnetic resonance.","volume":"39","author":"Lindon","year":"2001","journal-title":"Prog. Nucl. Magn. Reson. Spectrosc."},{"key":"2023013109591897300_B25","volume-title":"The Handbook of Metabonomics and Metabolomics.","author":"Lindon","year":"2007"},{"key":"2023013109591897300_B26","article-title":"Text classification using string kernels.","volume-title":"Advances in Neural Information Processing Systems.","author":"Lodhi","year":"2001"},{"key":"2023013109591897300_B27","volume-title":"Learning with Kernels.","author":"Sch\u00f6lkopf","year":"2002"},{"key":"2023013109591897300_B28","volume-title":"NMR Spectroscopy: Data Acquisition.","author":"Schorn","year":"2002"},{"key":"2023013109591897300_B29","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1002\/nbm.700","article-title":"NMR spectral quantitation by principal component analysis.","volume":"14","author":"Stoyanova","year":"2001","journal-title":"NMR Biomed."},{"key":"2023013109591897300_B30","volume-title":"Pattern Recognition.","author":"Theodoridis","year":"1999"},{"key":"2023013109591897300_B31","doi-asserted-by":"crossref","first-page":"3034","DOI":"10.1093\/bioinformatics\/bth357","article-title":"Sample classification from protein mass spectrometry, by \u2018peak probability contrasts\u2019.","volume":"20","author":"Tibshirani","year":"2004","journal-title":"Bioinformatics"},{"key":"2023013109591897300_B32","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s11263-006-9794-4","article-title":"Local features and kernels for classifcation of texture and object categories: a comprehensive study.","volume":"73","author":"Zhang","year":"2007","journal-title":"Int. J. Comput. Vis."}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/25\/2\/258\/48981897\/bioinformatics_25_2_258.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/25\/2\/258\/48981897\/bioinformatics_25_2_258.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T14:53:35Z","timestamp":1709391215000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/25\/2\/258\/218735"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,11,18]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2009,1,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btn599","relation":{},"ISSN":["1367-4811","1367-4803"],"issn-type":[{"value":"1367-4811","type":"electronic"},{"value":"1367-4803","type":"print"}],"subject":[],"published-other":{"date-parts":[[2009,1,15]]},"published":{"date-parts":[[2008,11,18]]}}}