An approach for feature selection with data modelling in LC-MS metabolomics

I. Plyushchenko; D. Shakhmatov; T. Bolotnik; T. Baygildiev; P.N. Nesterenko; I. Rodin

doi:10.1039/d0ay00204f

An approach for feature selection with data modelling in LC-MS metabolomics

I. Plyushchenko, D. Shakhmatov, T. Bolotnik, T. Baygildiev, P.N. Nesterenko, I. Rodin

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

© The Royal Society of Chemistry.The data processing workflow for LC-MS based metabolomics study is suggested with signal drift correction, univariate analysis, supervised learning, feature selection and unsupervised modelling. The proposed approach requires only an annotation-free peak table and produces an extremely reduced set of the most relevant features together with validation via Receiver Operating Characteristic analysis for selected predictors, cross-validation and unsupervised projection. The presented study was initially optimised by its own experimental set and then was successfully tested by using 36 datasets from 21 publicly available metabolomics projects. The suggested workflow can be used for classification purposes in high dimensional metabolomics studies and as a first step in exploratory analysis, data projection, biomarker selection, data integration and fusion. This journal is

Original language	English
Pages (from-to)	3582-3591
Journal	Analytical Methods
Volume	12
Issue number	28
DOIs	https://doi.org/10.1039/d0ay00204f
Publication status	Published - 28 Jul 2020
Externally published	Yes

Funding

This work was funded by the Russian Foundation for Basic Research (RFBR), according to the research project No. 19-33-90071. The authors thank George Varziev (CEO, InterAnalyt – General Distributor of Shimadzu – Russia) for providing the LC-MS instrument. In addition, the authors would like to thank Oleg Mayboroda (Dr Leiden University Medical Center), Boris Sarvin (Ph.D. candidate, Israel Institute of Technology), Andrey Stavrianidi (Ph.D., Lomonosov Moscow State University), Eliz-aveta Fedorova (Ph.D. candidate, IPCE RAS) and two anonymous reviewers for their useful comments regarding the manuscript.

Funders	Funder number
Russian Foundation for Basic Research	19-33-90071

Access to Document

10.1039/d0ay00204f

Persistent URL (handle)

Copy link address

Cite this

@article{a1aabe6c2d95450f93fa549948ee64d8,

title = "An approach for feature selection with data modelling in LC-MS metabolomics",

abstract = "{\textcopyright} The Royal Society of Chemistry.The data processing workflow for LC-MS based metabolomics study is suggested with signal drift correction, univariate analysis, supervised learning, feature selection and unsupervised modelling. The proposed approach requires only an annotation-free peak table and produces an extremely reduced set of the most relevant features together with validation via Receiver Operating Characteristic analysis for selected predictors, cross-validation and unsupervised projection. The presented study was initially optimised by its own experimental set and then was successfully tested by using 36 datasets from 21 publicly available metabolomics projects. The suggested workflow can be used for classification purposes in high dimensional metabolomics studies and as a first step in exploratory analysis, data projection, biomarker selection, data integration and fusion. This journal is",

author = "I. Plyushchenko and D. Shakhmatov and T. Bolotnik and T. Baygildiev and P.N. Nesterenko and I. Rodin",

year = "2020",

month = jul,

day = "28",

doi = "10.1039/d0ay00204f",

language = "English",

volume = "12",

pages = "3582--3591",

journal = "Analytical Methods",

issn = "1759-9660",

publisher = "Royal Society of Chemistry",

number = "28",

}

TY - JOUR

T1 - An approach for feature selection with data modelling in LC-MS metabolomics

AU - Plyushchenko, I.

AU - Shakhmatov, D.

AU - Bolotnik, T.

AU - Baygildiev, T.

AU - Nesterenko, P.N.

AU - Rodin, I.

PY - 2020/7/28

Y1 - 2020/7/28

N2 - © The Royal Society of Chemistry.The data processing workflow for LC-MS based metabolomics study is suggested with signal drift correction, univariate analysis, supervised learning, feature selection and unsupervised modelling. The proposed approach requires only an annotation-free peak table and produces an extremely reduced set of the most relevant features together with validation via Receiver Operating Characteristic analysis for selected predictors, cross-validation and unsupervised projection. The presented study was initially optimised by its own experimental set and then was successfully tested by using 36 datasets from 21 publicly available metabolomics projects. The suggested workflow can be used for classification purposes in high dimensional metabolomics studies and as a first step in exploratory analysis, data projection, biomarker selection, data integration and fusion. This journal is

AB - © The Royal Society of Chemistry.The data processing workflow for LC-MS based metabolomics study is suggested with signal drift correction, univariate analysis, supervised learning, feature selection and unsupervised modelling. The proposed approach requires only an annotation-free peak table and produces an extremely reduced set of the most relevant features together with validation via Receiver Operating Characteristic analysis for selected predictors, cross-validation and unsupervised projection. The presented study was initially optimised by its own experimental set and then was successfully tested by using 36 datasets from 21 publicly available metabolomics projects. The suggested workflow can be used for classification purposes in high dimensional metabolomics studies and as a first step in exploratory analysis, data projection, biomarker selection, data integration and fusion. This journal is

U2 - 10.1039/d0ay00204f

DO - 10.1039/d0ay00204f

M3 - Article

SN - 1759-9660

VL - 12

SP - 3582

EP - 3591

JO - Analytical Methods

JF - Analytical Methods

IS - 28

ER -

An approach for feature selection with data modelling in LC-MS metabolomics

Abstract

Funding

Access to Document

Persistent URL (handle)

Fingerprint

Cite this