Learning Kernels from genetic profiles to discriminate tumor subtypes

Our 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 Al...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Palazzo, Martín, Beauseroy, Pierre, Koile, Daniel, Yankilevich, Patricio
Formato: Objeto de conferencia Resumen
Lenguaje:Inglés
Publicado: 2018
Materias:
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/70649
http://47jaiio.sadio.org.ar/sites/default/files/AGRANDA-09.pdf
Aporte de:
id I19-R120-10915-70649
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
kernel target alignment
multiple kernel learning
somatic mutation
breast cancer
support vector classification
feature selection
spellingShingle Ciencias Informáticas
kernel target alignment
multiple kernel learning
somatic mutation
breast cancer
support vector classification
feature selection
Palazzo, Martín
Beauseroy, Pierre
Koile, Daniel
Yankilevich, Patricio
Learning Kernels from genetic profiles to discriminate tumor subtypes
topic_facet Ciencias Informáticas
kernel target alignment
multiple kernel learning
somatic mutation
breast cancer
support vector classification
feature selection
description Our 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.
format Objeto de conferencia
Resumen
author Palazzo, Martín
Beauseroy, Pierre
Koile, Daniel
Yankilevich, Patricio
author_facet Palazzo, Martín
Beauseroy, Pierre
Koile, Daniel
Yankilevich, Patricio
author_sort Palazzo, Martín
title Learning Kernels from genetic profiles to discriminate tumor subtypes
title_short Learning Kernels from genetic profiles to discriminate tumor subtypes
title_full Learning Kernels from genetic profiles to discriminate tumor subtypes
title_fullStr Learning Kernels from genetic profiles to discriminate tumor subtypes
title_full_unstemmed Learning Kernels from genetic profiles to discriminate tumor subtypes
title_sort learning kernels from genetic profiles to discriminate tumor subtypes
publishDate 2018
url http://sedici.unlp.edu.ar/handle/10915/70649
http://47jaiio.sadio.org.ar/sites/default/files/AGRANDA-09.pdf
work_keys_str_mv AT palazzomartin learningkernelsfromgeneticprofilestodiscriminatetumorsubtypes
AT beauseroypierre learningkernelsfromgeneticprofilestodiscriminatetumorsubtypes
AT koiledaniel learningkernelsfromgeneticprofilestodiscriminatetumorsubtypes
AT yankilevichpatricio learningkernelsfromgeneticprofilestodiscriminatetumorsubtypes
bdutipo_str Repositorios
_version_ 1764820481648623618