Learning Kernels from genetic profiles to discriminate tumor subtypes

dc.creatorPalazzo, Martín
dc.creatorBeauseroy, Pierre
dc.creatorKoile, Daniel
dc.creatorYankilevich, Patricio
dc.date2018-09
dc.date2018-11-09T15:28:30Z
dc.identifierhttp://sedici.unlp.edu.ar/handle/10915/70649
dc.identifierhttp://47jaiio.sadio.org.ar/sites/default/files/AGRANDA-09.pdf
dc.identifierissn:2451-7569
dc.descriptionOur work aims to perform the feature selection step on Multiple Kernel Learning by optimizing the Kernel Target Alignment score. It begins by building feature-wise gaussian kernel functions. Then by a constrained linear combination of the feature-wise kernels, we aim to increase the Kernel Target Alignment to obtain a new optimized custom kernel. The linear combination results in a sparse solution where only few kernels survive to improve KTA and consequently a reduced feature subset is obtained. Reducing considerably the original gene set allow to study deeper the selected genes for clinical purposes. The higher the KTA obtained, the better the feature selection, since we want to build custom kernels to use them for classification purposes later. The final kernel after optimizing the KTA is built by a linear combination of ‘Ki’ kernels, each one associated to a μi coefficient. The μ vector is computed during the optimization process.
dc.descriptionSociedad Argentina de Informática e Investigación Operativa
dc.formatapplication/pdf
dc.format88-90
dc.languageen
dc.rightshttp://creativecommons.org/licenses/by-sa/3.0/
dc.rightsCreative Commons Attribution-ShareAlike 3.0 Unported (CC BY-SA 3.0)
dc.subjectCiencias Informáticas
dc.subjectkernel target alignment
dc.subjectmultiple kernel learning
dc.subjectsomatic mutation
dc.subjectbreast cancer
dc.subjectsupport vector classification
dc.subjectfeature selection
dc.titleLearning Kernels from genetic profiles to discriminate tumor subtypes
dc.typeObjeto de conferencia
dc.typeResumen


Este ítem pertenece a la siguiente institución