On the interpretation of high throughput MS based metabolomics fingerprints with Random Forest

David P. Enot; Manfred Beckmann; John Draper

doi:10.1007/11875741_22

On the interpretation of high throughput MS based metabolomics fingerprints with Random Forest

David P. Enot
, Manfred Beckmann
, John Draper

Institute of Biological, Environmental, and Rural Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (ISBN)

6 Citations (Scopus)

Abstract

We discuss application of a machine learning method, Random Forest (RF), for the extraction of relevant biological knowledge from metabolomics fingerprinting experiments. The importance of RF margins and variable significance as well as prediction accuracy is discussed to provide insight into model generalisability and explanatory power. A method is described for detection of relevant features while conserving the redundant structure of the fingerprint data. The methodology is illustrated using two datasets from electrospray ionisation mass spectrometry from 27 Arabidopsis genotypes and a set of transgenic potato lines.

Original language	English
Title of host publication	Second International Symposium, CompLife 2006, Cambridge, UK, September 27-29, 2006. Proceedings
Publisher	Springer Nature
Pages	226-235
Number of pages	10
ISBN (Electronic)	978-3-540-45768-8
ISBN (Print)	978-3-540-45767-1
DOIs	https://doi.org/10.1007/11875741_22
Publication status	Published - 2006
Event	International Symposium, CompLife - Cambridge, United Kingdom of Great Britain and Northern Ireland Duration: 27 Sept 2006 → 29 Sept 2006

Conference

Conference	International Symposium, CompLife
Country/Territory	United Kingdom of Great Britain and Northern Ireland
City	Cambridge
Period	27 Sept 2006 → 29 Sept 2006

Access to Document

10.1007/11875741_22

Permanent link

Persistent link

Cite this

@inproceedings{9596308824b44c0293d6ad93cd82a466,

title = "On the interpretation of high throughput MS based metabolomics fingerprints with Random Forest",

abstract = "We discuss application of a machine learning method, Random Forest (RF), for the extraction of relevant biological knowledge from metabolomics fingerprinting experiments. The importance of RF margins and variable significance as well as prediction accuracy is discussed to provide insight into model generalisability and explanatory power. A method is described for detection of relevant features while conserving the redundant structure of the fingerprint data. The methodology is illustrated using two datasets from electrospray ionisation mass spectrometry from 27 Arabidopsis genotypes and a set of transgenic potato lines.",

author = "Enot, \{David P.\} and Manfred Beckmann and John Draper",

note = "Enot, D.P., Beckmann, M., Draper, J. (2006). On the interpretation of high throughput MS based metabolomics fingerprints with Random Forest. Proceedings, 2nd International Symposium on Computational Life Science - CompLife 06, 4216, 226-235; International Symposium, CompLife ; Conference date: 27-09-2006 Through 29-09-2006",

year = "2006",

doi = "10.1007/11875741\_22",

language = "English",

isbn = "978-3-540-45767-1",

pages = "226--235",

booktitle = "Second International Symposium, CompLife 2006, Cambridge, UK, September 27-29, 2006. Proceedings",

publisher = "Springer Nature",

address = "Switzerland",

}

Enot, DP, Beckmann, M & Draper, J 2006, On the interpretation of high throughput MS based metabolomics fingerprints with Random Forest. in Second International Symposium, CompLife 2006, Cambridge, UK, September 27-29, 2006. Proceedings. Springer Nature, pp. 226-235, International Symposium, CompLife, Cambridge, United Kingdom of Great Britain and Northern Ireland, 27 Sept 2006. https://doi.org/10.1007/11875741_22

On the interpretation of high throughput MS based metabolomics fingerprints with Random Forest. / Enot, David P.; Beckmann, Manfred; Draper, John.
Second International Symposium, CompLife 2006, Cambridge, UK, September 27-29, 2006. Proceedings. Springer Nature, 2006. p. 226-235.

Research output: Chapter in Book/Report/Conference proceeding › Conference Proceeding (ISBN)

TY - GEN

T1 - On the interpretation of high throughput MS based metabolomics fingerprints with Random Forest

AU - Enot, David P.

AU - Beckmann, Manfred

AU - Draper, John

N1 - Enot, D.P., Beckmann, M., Draper, J. (2006). On the interpretation of high throughput MS based metabolomics fingerprints with Random Forest. Proceedings, 2nd International Symposium on Computational Life Science - CompLife 06, 4216, 226-235

PY - 2006

Y1 - 2006

N2 - We discuss application of a machine learning method, Random Forest (RF), for the extraction of relevant biological knowledge from metabolomics fingerprinting experiments. The importance of RF margins and variable significance as well as prediction accuracy is discussed to provide insight into model generalisability and explanatory power. A method is described for detection of relevant features while conserving the redundant structure of the fingerprint data. The methodology is illustrated using two datasets from electrospray ionisation mass spectrometry from 27 Arabidopsis genotypes and a set of transgenic potato lines.

AB - We discuss application of a machine learning method, Random Forest (RF), for the extraction of relevant biological knowledge from metabolomics fingerprinting experiments. The importance of RF margins and variable significance as well as prediction accuracy is discussed to provide insight into model generalisability and explanatory power. A method is described for detection of relevant features while conserving the redundant structure of the fingerprint data. The methodology is illustrated using two datasets from electrospray ionisation mass spectrometry from 27 Arabidopsis genotypes and a set of transgenic potato lines.

U2 - 10.1007/11875741_22

DO - 10.1007/11875741_22

M3 - Conference Proceeding (ISBN)

SN - 978-3-540-45767-1

SP - 226

EP - 235

BT - Second International Symposium, CompLife 2006, Cambridge, UK, September 27-29, 2006. Proceedings

PB - Springer Nature

T2 - International Symposium, CompLife

Y2 - 27 September 2006 through 29 September 2006

ER -

On the interpretation of high throughput MS based metabolomics fingerprints with Random Forest

Abstract

Conference

Access to Document

Permanent link

Fingerprint

Cite this