Enhancement of Plant Metabolite Fingerprinting by Machine Learning

dc.contributor.authorScott, Ian M
dc.contributor.authorVermeer, Cornelia P
dc.contributor.authorLiakata, Maria
dc.contributor.authorCorol, Delia I
dc.contributor.authorWard, Jane L
dc.contributor.authorLin, Wanchang
dc.contributor.authorJohnson, Helen E
dc.contributor.authorWhitehead, Lynne
dc.contributor.authorKular, Baldeep
dc.contributor.authorBaker, John
dc.contributor.authorWalsh, Sean
dc.contributor.authorDave, Anuja
dc.date.accessioned2015-12-08T22:36:04Z
dc.date.issued2010
dc.date.updated2016-02-24T11:26:52Z
dc.description.abstractMetabolite fingerprinting of Arabidopsis (Arabidopsis thaliana) mutants with known or predicted metabolic lesions was performed by 1H-nuclear magnetic resonance, Fourier transform infrared, and flow injection electrospray-mass spectrometry. Fingerprinting enabled processing of five times more plants than conventional chromatographic profiling and was competitive for discriminating mutants, other than those affected in only low-abundance metabolites. Despite their rapidity and complexity, fingerprints yielded metabolomic insights (e.g. that effects of single lesions were usually not confined to individual pathways). Among fingerprint techniques, 1H-nuclear magnetic resonance discriminated the most mutant phenotypes from the wild type and Fourier transform infrared discriminated the fewest. To maximize information from fingerprints, data analysis was crucial. One-third of distinctive phenotypes might have been overlooked had data models been confined to principal component analysis score plots. Among several methods tested, machine learning (ML) algorithms, namely support vector machine or random forest (RF) classifiers, were unsurpassed for phenotype discrimination. Support vector machines were often the best performing classifiers, but RFs yielded some particularly informative measures. First, RFs estimated margins between mutant phenotypes, whose relations could then be visualized by Sammon mapping or hierarchical clustering. Second, RFs provided importance scores for the features within fingerprints that discriminated mutants. These scores correlated with analysis of variance F values (as did Kruskal-Wallis tests, true and false-positive measures, mutual information, and the Relief feature selection algorithm). ML classifiers, as models trained on one data set to predict another, were ideal for focused metabolomic queries, such as the distinctiveness and consistency of mutant phenotypes. Accessible software for use of ML in plant physiology is highlighted.
dc.identifier.issn0032-0889
dc.identifier.urihttp://hdl.handle.net/1885/35096
dc.publisherAmerican Society of Plant Biologists
dc.sourcePlant Physiology
dc.subjectKeywords: algorithm; Arabidopsis; article; artificial intelligence; cluster analysis; infrared spectroscopy; mass spectrometry; metabolism; metabolomics; nuclear magnetic resonance spectroscopy; phenotype; principal component analysis; Algorithms; Arabidopsis; Arti
dc.titleEnhancement of Plant Metabolite Fingerprinting by Machine Learning
dc.typeJournal article
local.bibliographicCitation.lastpage1520
local.bibliographicCitation.startpage1506
local.contributor.affiliationScott, Ian M , Aberystwyth University
local.contributor.affiliationVermeer, Cornelia P, Aberystwyth University
local.contributor.affiliationLiakata, Maria, Aberystwyth University
local.contributor.affiliationCorol, Delia I, National Centre for Plant and Microbial Metabolomics
local.contributor.affiliationWard, Jane L, National Centre for Plant and Microbial Metabolomics
local.contributor.affiliationLin, Wanchang, Aberystwyth University
local.contributor.affiliationJohnson, Helen E , Aberystwyth University
local.contributor.affiliationWhitehead, Lynne, College of Medicine, Biology and Environment, ANU
local.contributor.affiliationKular, Baldeep, John Innes Centre
local.contributor.affiliationBaker, John, National Centre for Plant and Microbial Metabolomics,
local.contributor.affiliationWalsh, Sean, The Sainsbury Laboratory
local.contributor.affiliationDave, Anuja, Univeristy of York
local.contributor.authoremailu4548816@anu.edu.au
local.contributor.authoruidWhitehead, Lynne, u4548816
local.description.embargo2037-12-31
local.description.notesImported from ARIES
local.identifier.absfor060101 - Analytical Biochemistry
local.identifier.absseo970106 - Expanding Knowledge in the Biological Sciences
local.identifier.ariespublicationu4956746xPUB120
local.identifier.citationvolume153
local.identifier.doi10.1104/pp.109.150524
local.identifier.scopusID2-s2.0-77955681638
local.identifier.thomsonID000280566000006
local.identifier.uidSubmittedByu4956746
local.type.statusPublished Version

Downloads

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
01_Scott_Enhancement_of_Plant_2010.pdf
Size:
871 KB
Format:
Adobe Portable Document Format
Back to topicon-arrow-up-solid
 
APRU
IARU
 
edX
Group of Eight Member

Acknowledgement of Country

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.


Contact ANUCopyrightDisclaimerPrivacyFreedom of Information

+61 2 6125 5111 The Australian National University, Canberra

TEQSA Provider ID: PRV12002 (Australian University) CRICOS Provider Code: 00120C ABN: 52 234 063 906