Model selection for within-batch effect correction in UPLC-MS metabolomics using quality control - Support vector regression

Fecha de publicación: 05/10/2018

Autores de IIS La Fe

Ángel Sánchez Illana

Autor
Daniel Cuesta Garcia

Autor
Máximo Vento Torres

Autor
José Luis Ruiz Cerdá

Autor
Guillermo Quintas Soriano

Autor
Julia Kuligowski

Autor

Participantes ajenos a IIS La Fe

Perez-Guaita, D
Sanjuan-Herraez, JD

Grupos

Perinatología

Leader

Máximo Vento Torres
Unidad Mixta de Investigación en Nanomedicina y Sensores

Leader

Ramón Martínez Máñez

Abstract

Ultra performance liquid chromatography-mass spectrometry (UPLC-MS) is increasingly being used for untargeted metabolomics in biomedical research. Complex matrices and a large number of samples per analytical batch lead to gradual changes in the instrumental response (i.e. within-batch effects) that reduce the repeatability and reproducibility and limit the power to detect biological responses. A strategy for within-batch effect correction based on the use of quality control (QC) samples and Support Vector Regression (QC-SVRC) with a radial basis function kernel was recently proposed. QC-SVRC requires the optimization of three hyperparameters that determine the accuracy of the within-batch effects elimination: the tolerance threshold (epsilon), the penalty term (C) and the kernel width (gamma). This work compares three widely used strategies for QC-SVRC hyperparameter optimization (grid search, random search and particle swarm optimization) using a UPLC-MS data set containing 193 urine injections as model example. Results show that QC-SVRC is robust to hyperparameter selection and that a pre-selection of C and e, followed by optimization of g is competitive in terms of accuracy, precision and number of function evaluations with full grid analysis, random search and particle swarm optimization. The QC-SVRC optimization procedure can be regarded as a useful non-parametric tool for efficiently complementing alternative approaches such as QC-robust splines correction (RSC). (c) 2018 Elsevier B.V. All rights reserved.

Datos de la publicación

ISSN/ISSNe:: 0003-2670, 1873-4324
Tipo:: Article
Páginas:: 62-68
DOI:: 10.1016/j.aca.2018.04.055
Factor de Impacto:: 1,467 SCImago ℠
Cuartil:: Q1 SCImago ℠

Documentos

No hay documentos

Métricas

Filiaciones

Sanchez-Illana, A:: Instituto de Investigación. Hosp La Fe, Hlth Res Inst, Neonatal Res Unit, Valencia, Spain
Perez-Guaita, D:: Monash Univ, Ctr Biospect, Clayton, Vic, Australia
Cuesta-Garcia, D:: Instituto de Investigación. Hosp La Fe, Hlth Res Inst, Neonatal Res Unit, Valencia, Spain
Sanjuan-Herraez, JD:: Leitat Technol Ctr, Hlth & Biomed, Barcelona, Spain
Vento, M:: Univ & Polytech Hosp La Fe, Div Neonatol, Valencia, Spain
Ruiz-Cerda, JL:: Hosp Univ & Politecn La Fe, Urol Serv, Valencia, Spain
Quintas, G:: Leitat Technol Ctr, Hlth & Biomed, Barcelona, Spain

Instituto de Investigación. Hosp La Fe, Hlth Res Inst, Analyt Unit, Valencia, Spain
Kuligowski, J:: Instituto de Investigación. Hosp La Fe, Hlth Res Inst, Neonatal Res Unit, Valencia, Spain