High Dimensional Classification with combined Adaptive Sparse PLS and Logistic Regression

Motivation: The high dimensionality of genomic data calls for the development of specific classification methodologies, especially to prevent over-optimistic predictions. This challenge can be tackled by compression and variable selection, which combined constitute a powerful framework for classification, as well as data visualization and interpretation. However, current proposed combinations lead to unstable and non convergent methods due to inappropriate computational frameworks. We hereby propose a computationally stable and convergent approach for classification in high dimensional based on sparse Partial Least Squares (sparse PLS). Results: We start by proposing a new solution for the sparse PLS problem that is based on proximal operators for the case of univariate responses. Then we develop an adaptive version of the sparse PLS for classification, called logit-SPLS, which combines iterative optimization of logistic regression and sparse PLS to ensure computational convergence and stability. Our results are confirmed on synthetic and experimental data. In particular we show how crucial convergence and stability can be when cross-validation is involved for calibration purposes. Using gene expression data we explore the prediction of breast cancer relapse. We also propose a multicategorial version of our method, used to predict cell-types based on single-cell expression data.Availability: Our approach is implemented in the plsgenomics R-package.

Mots clés

Computational statistics Classification Dimension reduction Variable selection Single cell analysis

Domaines

Méthodologie [stat.ME] Applications [stat.AP] Bio-Informatique, Biologie Systémique [q-bio.QM]

Fichier principal

article_logit_spls_2017.pdf (1.17 Mo)

Fig1.pdf (10.43 Ko)

Fig2.pdf (52.3 Ko)

Fig3.pdf (410.55 Ko)

Fig4.pdf (286.87 Ko)

overlap_genes_stab_sel.pdf (28.58 Ko)

simulations_choice_K.pdf (13.47 Ko)

Origine	Fichiers produits par l'(les) auteur(s)

Origine	Fichiers produits par l'(les) auteur(s)

Origine	Fichiers produits par l'(les) auteur(s)

Origine	Fichiers produits par l'(les) auteur(s)

Origine	Fichiers produits par l'(les) auteur(s)

Origine	Fichiers produits par l'(les) auteur(s)

Origine	Fichiers produits par l'(les) auteur(s)

Ghislain DURIF : Connectez-vous pour contacter le contributeur

https://hal.science/hal-01587360

Soumis le : jeudi 14 septembre 2017-10:28:03

Dernière modification le : mardi 12 novembre 2024-15:20:07

Dates et versions

hal-01587360 , version 1 (14-09-2017)

Identifiants

HAL Id : hal-01587360 , version 1
ARXIV : 1502.05933
DOI : 10.1093/bioinformatics/btx571

Citer

Ghislain Durif, Laurent Modolo, Jakob Michaelsson, Jeff E. Mold, Sophie Lambert-Lacroix, et al.. High Dimensional Classification with combined Adaptive Sparse PLS and Logistic Regression. Bioinformatics, 2018, 34 (3), pp.485-493. ⟨10.1093/bioinformatics/btx571⟩. ⟨hal-01587360⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

ENS-LYON UGA IMAG CNRS INRIA UNIV-LYON1 INSMI LJK LJK_GI TIMC-IMAG TIMC-IMAG-BCM BIOENVIS INRIA2 LJK-GI-THOTH LBBE UDL ANR

2447 Consultations

1019 Téléchargements