{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/discriminating-sample-groups-with-multi-way","title":"Discriminating sample groups with multi-way data","arxiv_id":"1606.08046","date":"2016-06-26","proceeding":null,"authors":["Tianmeng Lyu","Eric F. Lock","Lynn E. Eberly"],"abstract":"High-dimensional linear classifiers, such as the support vector machine (SVM)\nand distance weighted discrimination (DWD), are commonly used in biomedical\nresearch to distinguish groups of subjects based on a large number of features.\nHowever, their use is limited to applications where a single vector of features\nis measured for each subject. In practice data are often multi-way, or measured\nover multiple dimensions. For example, metabolite abundance may be measured\nover multiple regions or tissues, or gene expression may be measured over\nmultiple time points, for the same subjects. We propose a framework for linear\nclassification of high-dimensional multi-way data, in which coefficients can be\nfactorized into weights that are specific to each dimension. More generally,\nthe coefficients for each measurement in a multi-way dataset are assumed to\nhave low-rank structure. This framework extends existing classification\ntechniques, and we have implemented multi-way versions of SVM and DWD. We\ndescribe informative simulation results, and apply multi-way DWD to data for\ntwo very different clinical research studies. The first study uses metabolite\nmagnetic resonance spectroscopy data over multiple brain regions to compare\npatients with and without spinocerebellar ataxia, the second uses publicly\navailable gene expression time-course data to compare treatment responses for\npatients with multiple sclerosis. Our method improves performance and\nsimplifies interpretation over naive applications of full rank linear\nclassification to multi-way data. An R package is available at\nhttps://github.com/lockEF/MultiwayClassification .","url_abs":"http://arxiv.org/abs/1606.08046v1","url_pdf":"http://arxiv.org/pdf/1606.08046v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"discriminating-sample-groups-with-multi-way","repo_url":"https://github.com/lockEF/MultiwayClassification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[{"method_slug":"svm","method_name":"SVM"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}