{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T04:39:16Z","timestamp":1793507956857,"version":"4.5.0"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"S24","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2019,12,20]],"date-time":"2019-12-20T00:00:00Z","timestamp":1576800000000},"content-version":"vor","delay-in-days":19,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"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><jats:sec>\n<jats:title>Background<\/jats:title>\n<jats:p>With the rise of metabolomics, the development of methods to address analytical challenges in the analysis of metabolomics data is of great importance. Missing values (MVs) are pervasive, yet the treatment of MVs can have a substantial impact on downstream statistical analyses. The MVs problem in metabolomics is quite challenging and can arise because the metabolite is not biologically present in the sample, or is present in the sample but at a concentration below the lower limit of detection (LOD), or is present in the sample but undetected due to technical issues related to sample pre-processing steps. The former is considered missing not at random (MNAR) while the latter is an example of missing at random (MAR). Typically, such MVs are substituted by a minimum value, which may lead to severely biased results in downstream analyses.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Results<\/jats:title>\n<jats:p>We develop a Bayesian model, called BayesMetab, that systematically accounts for missing values based on a Markov chain Monte Carlo (MCMC) algorithm that incorporates data augmentation by allowing MVs to be due to either truncation below the LOD or other technical reasons unrelated to its abundance. Based on a variety of performance metrics (power for detecting differential abundance, area under the curve, bias and MSE for parameter estimates), our simulation results indicate that BayesMetab outperformed other imputation algorithms when there is a mixture of missingness due to MAR and MNAR. Further, our approach was competitive with other methods tailored specifically to MNAR in situations where missing data were completely MNAR. Applying our approach to an analysis of metabolomics data from a mouse myocardial infarction revealed several statistically significant metabolites not previously identified that were of direct biological relevance to the study.<\/jats:p>\n<\/jats:sec><jats:sec>\n<jats:title>Conclusions<\/jats:title>\n<jats:p>Our findings demonstrate that BayesMetab has improved performance in imputing the missing values and performing statistical inference compared to other current methods when missing values are due to a mixture of MNAR and MAR. Analysis of real metabolomics data strongly suggests this mixture is likely to occur in practice, and thus, it is important to consider an imputation model that accounts for a mixture of missing data types.<\/jats:p>\n<\/jats:sec>","DOI":"10.1186\/s12859-019-3250-2","type":"journal-article","created":{"date-parts":[[2019,12,20]],"date-time":"2019-12-20T08:05:23Z","timestamp":1576829123000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["BayesMetab: treatment of missing values in metabolomic studies using a Bayesian modeling approach"],"prefix":"10.1186","volume":"20","author":[{"given":"Jasmit","family":"Shah","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guy N.","family":"Brock","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeremy","family":"Gaskins","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,12,20]]},"reference":[{"key":"3250_CR1","doi-asserted-by":"crossref","unstructured":"Xi B, Gu H, Baniasadi H, Raftery D. Statistical analysis and modeling of mass spectrometry-based metabolomics data. In: Mass spectrometry in metabolomics: Springer; 2014. p. 333\u201353.","DOI":"10.1007\/978-1-4939-1258-2_22"},{"issue":"5","key":"3250_CR2","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1080\/10705511.2016.1186549","volume":"23","author":"D McNeish","year":"2016","unstructured":"McNeish D. On using Bayesian methods to address small sample problems. Struct Equ Model Multidiscip J. 2016;23(5):750\u201373.","journal-title":"Struct Equ Model Multidiscip J"},{"issue":"12","key":"3250_CR3","doi-asserted-by":"publisher","first-page":"1222","DOI":"10.1093\/aje\/153.12.1222","volume":"153","author":"DB Dunson","year":"2001","unstructured":"Dunson DB. Commentary: practical advantages of Bayesian analysis of epidemiologic data. Am J Epidemiol. 2001;153(12):1222\u20136.","journal-title":"Am J Epidemiol"},{"issue":"2","key":"3250_CR4","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1037\/met0000065","volume":"22","author":"S Depaoli","year":"2017","unstructured":"Depaoli S, Van de Schoot R. Improving transparency and replication in Bayesian statistics: the WAMBS-checklist. Psychol Methods. 2017;22(2):240.","journal-title":"Psychol Methods"},{"issue":"3","key":"3250_CR5","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1080\/10705511.2014.937849","volume":"22","author":"S Depaoli","year":"2015","unstructured":"Depaoli S, Clifton JP. A Bayesian approach to multilevel structural equation modeling with continuous and dichotomous outcomes. Struct Equ Model Multidiscip J. 2015;22(3):327\u201351.","journal-title":"Struct Equ Model Multidiscip J"},{"issue":"2","key":"3250_CR6","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/s10648-014-9287-x","volume":"28","author":"DM McNeish","year":"2016","unstructured":"McNeish DM, Stapleton LM. The effect of small sample size on two-level model estimates: a review and illustration. Educ Psychol Rev. 2016;28(2):295\u2013314.","journal-title":"Educ Psychol Rev"},{"issue":"6","key":"3250_CR7","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1515\/sagmb-2013-0021","volume":"12","author":"SL Taylor","year":"2013","unstructured":"Taylor SL, Leiserowitz GS, Kim K. Accounting for undetected compounds in statistical analyses of mass spectrometry \u2018omic studies. Stat Appl Genet Mol Biol. 2013;12(6):703\u201322.","journal-title":"Stat Appl Genet Mol Biol"},{"key":"3250_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/9781119013563","volume-title":"Statistical analysis with missing data","author":"RJ Little","year":"2002","unstructured":"Little RJ, Rubin DB. Statistical analysis with missing data; 2002."},{"issue":"16","key":"3250_CR9","doi-asserted-by":"publisher","first-page":"2028","DOI":"10.1093\/bioinformatics\/btp362","volume":"25","author":"Yuliya Karpievitch","year":"2009","unstructured":"Karpievitch Y, Stanley J, Taverner T, Huang J, Adkins JN, Ansong C, Heffron F, Metz TO, Qian W-J, Yoon H: A statistical framework for protein quantitation in bottom-up MS-based proteomics. Bioinformatics 2009, 25(16):2028\u20132034.","journal-title":"Bioinformatics"},{"issue":"16","key":"3250_CR10","doi-asserted-by":"publisher","first-page":"S5","DOI":"10.1186\/1471-2105-13-S16-S5","volume":"13","author":"YV Karpievitch","year":"2012","unstructured":"Karpievitch YV, Dabney AR, Smith RD. Normalization and missing value imputation for label-free LC-MS analysis. BMC bioinformatics. 2012;13(16):S5.","journal-title":"BMC bioinformatics"},{"key":"3250_CR11","doi-asserted-by":"publisher","DOI":"10.1201\/9781420011180","volume-title":"Missing data in longitudinal studies: strategies for Bayesian modeling and sensitivity analysis: chapman and hall\/CRC","author":"MJ Daniels","year":"2008","unstructured":"Daniels MJ, Hogan JW. Missing data in longitudinal studies: strategies for Bayesian modeling and sensitivity analysis: chapman and hall\/CRC; 2008."},{"issue":"398","key":"3250_CR12","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1080\/01621459.1987.10478458","volume":"82","author":"MA Tanner","year":"1987","unstructured":"Tanner MA, Wong WH. The calculation of posterior distributions by data augmentation. J Am Stat Assoc. 1987;82(398):528\u201340.","journal-title":"J Am Stat Assoc"},{"issue":"2","key":"3250_CR13","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1093\/biomet\/asr013","volume":"98","author":"A. Bhattacharya","year":"2011","unstructured":"Bhattacharya A, Dunson DB. Sparse Bayesian infinite factor models. Biometrika. 2011:291\u2013306.","journal-title":"Biometrika"},{"key":"3250_CR14","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.csda.2015.04.009","volume":"90","author":"G Tutz","year":"2015","unstructured":"Tutz G, Ramzan S. Improved methods for the imputation of missing data by nearest neighbor methods. Comput Stat Data Anal. 2015;90:84\u201399.","journal-title":"Comput Stat Data Anal"},{"issue":"1","key":"3250_CR15","doi-asserted-by":"publisher","first-page":"e1005973","DOI":"10.1371\/journal.pcbi.1005973","volume":"14","author":"R Wei","year":"2018","unstructured":"Wei R, Wang J, Jia E, Chen T, Ni Y, Jia W. GSimp: a Gibbs sampler based left-censored missing value imputation approach for metabolomics studies. PLoS Comput Biol. 2018;14(1):e1005973.","journal-title":"PLoS Comput Biol"},{"issue":"1","key":"3250_CR16","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1186\/s12859-017-1547-6","volume":"18","author":"JS Shah","year":"2017","unstructured":"Shah JS, Rai SN, DeFilippis AP, Hill BG, Bhatnagar A, Brock GN. Distribution based nearest neighbor imputation for truncated high dimensional data with applications to pre-clinical and clinical metabolomics studies. BMC bioinformatics. 2017;18(1):114.","journal-title":"BMC bioinformatics"},{"issue":"4","key":"3250_CR17","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1161\/CIRCHEARTFAILURE.114.001151","volume":"7","author":"BE Sansbury","year":"2014","unstructured":"Sansbury BE, DeMartino AM, Xie Z, Brooks AC, Brainard RE, Watson LJ, DeFilippis AP, Cummins TD, Harbeson MA, Brittian KR. Metabolomic analysis of pressure-overloaded and infarcted mouse hearts. Circ Heart Fail. 2014;7(4):634\u201342.","journal-title":"Circ Heart Fail"},{"issue":"1","key":"3250_CR18","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1093\/bioinformatics\/btq613","volume":"27","author":"S Oh","year":"2010","unstructured":"Oh S, Kang DD, Brock GN, Tseng GC. Biological impact of missing-value imputation on downstream analyses of gene expression profiles. Bioinformatics. 2010;27(1):78\u201386.","journal-title":"Bioinformatics"},{"key":"3250_CR19","unstructured":"The Metabolomics Workbench [http:\/\/www.metabolomicsworkbench.org]. Accessed 10 March 2016."},{"issue":"5","key":"3250_CR20","doi-asserted-by":"publisher","first-page":"1650","DOI":"10.1016\/j.csda.2008.03.023","volume":"53","author":"RS Parrish","year":"2009","unstructured":"Parrish RS, Spencer HJ III, Xu P. Distribution modeling and simulation of gene expression data. Comput Stat Data Anal. 2009;53(5):1650\u201360.","journal-title":"Comput Stat Data Anal"},{"issue":"1","key":"3250_CR21","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1038\/s41598-017-19120-0","volume":"8","author":"R Wei","year":"2018","unstructured":"Wei R, Wang J, Su M, Jia E, Chen S, Chen T, Ni Y. Missing value imputation approach for mass spectrometry-based metabolomics data. Sci Rep. 2018;8(1):663.","journal-title":"Sci Rep"},{"issue":"6","key":"3250_CR22","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1111\/dgd.12140","volume":"56","author":"DR Warner","year":"2014","unstructured":"Warner DR, Mukhopadhyay P, Brock G, Webb CL, Michele Pisano M, Greene RM. Micro RNA expression profiling of the developing murine upper lip. Develop Growth Differ. 2014;56(6):434\u201347.","journal-title":"Develop Growth Differ"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-019-3250-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-019-3250-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-019-3250-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,12,19]],"date-time":"2020-12-19T00:05:18Z","timestamp":1608336318000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-019-3250-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":22,"journal-issue":{"issue":"S24","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["3250"],"URL":"https:\/\/doi.org\/10.1186\/s12859-019-3250-2","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12]]},"assertion":[{"value":"20 December 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable as no human subjects.","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":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"673"}}