Show simple item record

dc.contributor.authorZhang, Xiaokang
dc.contributor.authorJonassen, Inge
dc.date.accessioned2020-03-31T13:32:59Z
dc.date.available2020-03-31T13:32:59Z
dc.date.issued2019
dc.PublishedZhang X, Jonassen I: A Comparative Analysis of Feature Selection Methods for Biomarker Discovery in Study of Toxicant-Treated Atlantic Cod (Gadus Morhua) Liver. In: Bach K, Ruocco M. Nordic Artificial Intelligence Research and Development. NAIS 2019. Communications in Computer and Information Science, vol 1056, p. 114-123. Springer.eng
dc.identifier.isbn978-3-030-35664-4en_US
dc.identifier.urihttps://hdl.handle.net/1956/21642
dc.description.abstractUnivariate and multivariate feature selection methods can be used for biomarker discovery in analysis of toxicant exposure. Among the univariate methods, differential expression analysis (DEA) is often applied for its simplicity and interpretability. A characteristic of methods for DEA is that they treat genes individually, disregarding the correlation that exists between them. On the other hand, some multivariate feature selection methods are proposed for biomarker discovery. Provided with various biomarker discovery methods, how to choose the most suitable method for a specific dataset becomes a problem. In this paper, we present a framework for comparison of potential biomarker discovery methods: three methods that stem from different theories are compared by how stable they are and how well they can improve the classification accuracy. The three methods we have considered are: Significance Analysis of Microarrays (SAM) which identifies the differentially expressed genes; minimum Redundancy Maximum Relevance (mRMR) based on information theory; and Characteristic Direction (GeoDE) inspired by a graphical perspective. Tested on the gene expression data from two experiments exposing the cod fish to two different toxicants (MeHg and PCB 153), different methods stand out in different cases, so a decision upon the most suitable method should be made based on the dataset under study and the research interest.en_US
dc.language.isoengeng
dc.publisherSpringeren_US
dc.relation.urihttps://link.springer.com/chapter/10.1007/978-3-030-35664-4_11
dc.subjectFeature selectioneng
dc.subjectStabilityeng
dc.subjectClassificationeng
dc.subjectBiomarker discoveryeng
dc.titleA Comparative Analysis of Feature Selection Methods for Biomarker Discovery in Study of Toxicant-Treated Atlantic Cod (Gadus Morhua) Liveren_US
dc.typeChapter
dc.typeConference object
dc.typePeer reviewed
dc.date.updated2020-02-11T22:14:58Z
dc.description.versionacceptedVersionen_US
dc.rights.holderCopyright 2019 Springer Nature Switzerlanden_US
dc.identifier.doihttps://doi.org/10.1007/978-3-030-35664-4
dc.identifier.cristin1752763
dc.relation.projectNorges forskningsråd: 248840


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record