{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:38:39Z","timestamp":1783701519523,"version":"3.55.0"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T00:00:00Z","timestamp":1719532800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100018710","name":"National Center of Competence in Research AntiResist","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018710","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"publisher","award":["180541"],"award-info":[{"award-number":["180541"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Basel Research Centre for Child Health Postdoctoral Excellence Programme","award":["#PEP-2021\u20131008"],"award-info":[{"award-number":["#PEP-2021\u20131008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>In many biomedical applications, we are confronted with paired groups of samples, such as treated versus control. The aim is to detect discriminating features, i.e. biomarkers, based on high-dimensional (omics-) data. This problem can be phrased more generally as a two-sample problem requiring statistical significance testing to establish differences, and interpretations to identify distinguishing features. The multivariate maximum mean discrepancy (MMD) test quantifies group-level differences, whereas statistically significantly associated features are usually found by univariate feature selection. Currently, few general-purpose methods simultaneously perform multivariate feature selection and two-sample testing.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We introduce a sparse, interpretable, and optimized MMD test (SpInOpt-MMD) that enables two-sample testing and feature selection in the same experiment. SpInOpt-MMD is a versatile method and we demonstrate its application to a variety of synthetic and real-world data types including images, gene expression measurements, and text data. SpInOpt-MMD is effective in identifying relevant features in small sample sizes and outperforms other feature selection methods such as SHapley Additive exPlanations and univariate association analysis in several experiments.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The code and links to our public data are available at https:\/\/github.com\/BorgwardtLab\/spinoptmmd.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae251","type":"journal-article","created":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T09:35:08Z","timestamp":1719567308000},"page":"i501-i510","source":"Crossref","is-referenced-by-count":2,"title":["Biomarker identification by interpretable maximum mean discrepancy"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8996-7167","authenticated-orcid":false,"given":"Michael F","family":"Adamer","sequence":"first","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , Basel 4056, Switzerland"},{"name":"Swiss Institute for Bioinformatics (SIB), Amphip\u00f4le, Quartier UNIL-Sorge , Lausanne 1015, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3176-1032","authenticated-orcid":false,"given":"Sarah C","family":"Br\u00fcningk","sequence":"additional","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , Basel 4056, Switzerland"},{"name":"Swiss Institute for Bioinformatics (SIB), Amphip\u00f4le, Quartier UNIL-Sorge , Lausanne 1015, Switzerland"},{"name":"Department of Health Sciences and Technology, ETH Zurich , Zurich 8008, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dexiong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , Basel 4056, Switzerland"},{"name":"Swiss Institute for Bioinformatics (SIB), Amphip\u00f4le, Quartier UNIL-Sorge , Lausanne 1015, Switzerland"},{"name":"Department of Machine Learning and Systems Biology, Max Planck Institute of Biochemistry , Martinsried 82152, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7221-2393","authenticated-orcid":false,"given":"Karsten","family":"Borgwardt","sequence":"additional","affiliation":[{"name":"Department of Biosystems Science and Engineering, ETH Zurich , Basel 4056, Switzerland"},{"name":"Swiss Institute for Bioinformatics (SIB), Amphip\u00f4le, Quartier UNIL-Sorge , Lausanne 1015, Switzerland"},{"name":"Department of Machine Learning and Systems Biology, Max Planck Institute of Biochemistry , Martinsried 82152, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,6,28]]},"reference":[{"key":"2024062809080329700_btae251-B1","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1016\/j.neurobiolaging.2008.01.010","article-title":"A meta-analysis of hippocampal atrophy rates in Alzheimer\u2019s disease","volume":"30","author":"Barnes","year":"2009","journal-title":"Neurobiol Aging"},{"key":"2024062809080329700_btae251-B2","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1023\/A:1011429418057","article-title":"Detecting group differences: mining contrast sets","volume":"5","author":"Bay","year":"2001","journal-title":"Data Min Knowl Discov"},{"key":"2024062809080329700_btae251-B3","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J R Stat Soc: Ser B (Methodol)"},{"key":"2024062809080329700_btae251-B4","doi-asserted-by":"crossref","first-page":"e49","DOI":"10.1093\/bioinformatics\/btl242","article-title":"Integrating structured biological data by kernel maximum mean discrepancy","volume":"22","author":"Borgwardt","year":"2006","journal-title":"Bioinformatics"},{"key":"2024062809080329700_btae251-B5","first-page":"730","author":"Br\u00fcningk","year":"2021"},{"key":"2024062809080329700_btae251-B6","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1007\/s10278-013-9622-7","article-title":"The cancer imaging archive (TCIA): maintaining and operating a public information repository","volume":"26","author":"Clark","year":"2013","journal-title":"J Digit Imag"},{"key":"2024062809080329700_btae251-B7","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1186\/1471-2105-7-126","article-title":"A two-sample bayesian t-test for microarray data","volume":"7","author":"Fox","year":"2006","journal-title":"BMC Bioinf"},{"key":"2024062809080329700_btae251-B8","first-page":"1","article-title":"Kernel measures of conditional dependence","volume":"20","author":"Fukumizu","year":"2007","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024062809080329700_btae251-B9","first-page":"1","article-title":"A kernel method for the two-sample-problem","volume":"19","author":"Gretton","year":"2006","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024062809080329700_btae251-B10","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J Mach Learn Res"},{"key":"2024062809080329700_btae251-B11","first-page":"1","article-title":"Optimal kernel choice for large-scale two-sample tests","volume":"25","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024062809080329700_btae251-B12"},{"key":"2024062809080329700_btae251-B13","first-page":"1","article-title":"Interpretable distribution features with maximum testing power","volume":"29","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024062809080329700_btae251-B14","author":"Kirby","year":"2006"},{"key":"2024062809080329700_btae251-B15","volume-title":"Applied linear statistical models","author":"Kutner","year":"2005"},{"key":"2024062809080329700_btae251-B16","first-page":"461","article-title":"Efficient two-sample designs for microarray experiments with biological replications","volume":"4","author":"Landgrebe","year":"2004","journal-title":"In Silico Biol"},{"key":"2024062809080329700_btae251-B17","author":"Liu"},{"key":"2024062809080329700_btae251-B18","author":"Lopez-Paz","year":"2016"},{"key":"2024062809080329700_btae251-B19","year":"199"},{"key":"2024062809080329700_btae251-B20","doi-asserted-by":"crossref","first-page":"236","DOI":"10.3389\/fonc.2017.00236","article-title":"The role of atrx in glioma biology","volume":"7","author":"Nandakumar","year":"2017","journal-title":"Front Oncol"},{"key":"2024062809080329700_btae251-B134","author":"Pedano"},{"key":"2024062809080329700_btae251-B21","first-page":"32:1\u201312","article-title":"Pytorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024062809080329700_btae251-B22","doi-asserted-by":"crossref","first-page":"5951","DOI":"10.1007\/s00521-019-04082-3","article-title":"Ensemble feature selection for high-dimensional data: a stability analysis across multiple domains","volume":"32","author":"Pes","year":"2020","journal-title":"Neural Comput Appl"},{"key":"2024062809080329700_btae251-B23","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1038\/nbt.3192","article-title":"Spatial reconstruction of single-cell gene expression data","volume":"33","author":"Satija","year":"2015","journal-title":"Nat Biotechnol"},{"key":"2024062809080329700_btae251-B24","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1126\/science.270.5235.467","article-title":"Quantitative monitoring of gene expression patterns with a complementary dna microarray","volume":"270","author":"Schena","year":"1995","journal-title":"Science"},{"key":"2024062809080329700_btae251-B25","doi-asserted-by":"crossref","first-page":"i490","DOI":"10.1093\/bioinformatics\/btm216","article-title":"Gene selection via the bahsic family of algorithms","volume":"23","author":"Song","year":"2007","journal-title":"Bioinformatics"},{"key":"2024062809080329700_btae251-B26","first-page":"1393","article-title":"Feature selection via dependence maximization","volume":"13","author":"Song","year":"2012","journal-title":"J Mach Learn Res"},{"key":"2024062809080329700_btae251-B27","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1089\/cmb.2009.0175","article-title":"A robust bayesian two-sample test for detecting intervals of differential gene expression in microarray time series","volume":"17","author":"Stegle","year":"2010","journal-title":"J Comput Biol"},{"key":"2024062809080329700_btae251-B28","first-page":"1","author":"Sutherland","year":"2017"},{"key":"2024062809080329700_btae251-B29","doi-asserted-by":"crossref","first-page":"7629","DOI":"10.1073\/pnas.1507583112","article-title":"Statistical learning and selective inference","volume":"112","author":"Taylor","year":"2015","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024062809080329700_btae251-B30","doi-asserted-by":"crossref","first-page":"5233","DOI":"10.1038\/s41598-019-41695-z","article-title":"From louvain to leiden: guaranteeing well-connected communities","volume":"9","author":"Traag","year":"2019","journal-title":"Sci Rep"},{"key":"2024062809080329700_btae251-B31","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"van Griethuysen","year":"2017","journal-title":"Cancer Res"},{"key":"2024062809080329700_btae251-B33","year":"2022"},{"key":"2024062809080329700_btae251-B32","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1038\/s41591-021-01619-9","article-title":"Direct antimicrobial resistance prediction from clinical maldi-tof mass spectra using machine learning","volume":"28","author":"Weis","year":"2022","journal-title":"Nat Med"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/Supplement_1\/i501\/58354949\/btae251.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/Supplement_1\/i501\/58354949\/btae251.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T09:35:40Z","timestamp":1719567340000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/40\/Supplement_1\/i501\/7700883"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,28]]},"references-count":34,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2024,6,28]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae251","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,7]]},"published":{"date-parts":[[2024,6,28]]}}}