From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification

<p>Abstract</p> <p>Background</p> <p>Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level....

Full description

Bibliographic Details
Main Authors: Dawyndt Peter, Waegeman Willem, Slabbinck Bram, De Vos Paul, De Baets Bernard
Format: Article
Language:English
Published: BMC 2010-01-01
Series:BMC Bioinformatics
Online Access:http://www.biomedcentral.com/1471-2105/11/69
_version_ 1819123547943993344
author Dawyndt Peter
Waegeman Willem
Slabbinck Bram
De Vos Paul
De Baets Bernard
author_facet Dawyndt Peter
Waegeman Willem
Slabbinck Bram
De Vos Paul
De Baets Bernard
author_sort Dawyndt Peter
collection DOAJ
description <p>Abstract</p> <p>Background</p> <p>Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification.</p> <p>Results</p> <p>In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model.</p> <p>Conclusions</p> <p>FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the resolution of FAME data for the discrimination of bacterial species. Summarized, by phylogenetic learning we are able to situate and evaluate FAME-based bacterial species classification in a more informative context.</p>
first_indexed 2024-12-22T07:10:06Z
format Article
id doaj.art-de67914e2e224b7c90e07c936f217d5f
institution Directory Open Access Journal
issn 1471-2105
language English
last_indexed 2024-12-22T07:10:06Z
publishDate 2010-01-01
publisher BMC
record_format Article
series BMC Bioinformatics
spelling doaj.art-de67914e2e224b7c90e07c936f217d5f2022-12-21T18:34:33ZengBMCBMC Bioinformatics1471-21052010-01-011116910.1186/1471-2105-11-69From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classificationDawyndt PeterWaegeman WillemSlabbinck BramDe Vos PaulDe Baets Bernard<p>Abstract</p> <p>Background</p> <p>Machine learning techniques have shown to improve bacterial species classification based on fatty acid methyl ester (FAME) data. Nonetheless, FAME analysis has a limited resolution for discrimination of bacteria at the species level. In this paper, we approach the species classification problem from a taxonomic point of view. Such a taxonomy or tree is typically obtained by applying clustering algorithms on FAME data or on 16S rRNA gene data. The knowledge gained from the tree can then be used to evaluate FAME-based classifiers, resulting in a novel framework for bacterial species classification.</p> <p>Results</p> <p>In view of learning in a taxonomic framework, we consider two types of trees. First, a FAME tree is constructed with a supervised divisive clustering algorithm. Subsequently, based on 16S rRNA gene sequence analysis, phylogenetic trees are inferred by the NJ and UPGMA methods. In this second approach, the species classification problem is based on the combination of two different types of data. Herein, 16S rRNA gene sequence data is used for phylogenetic tree inference and the corresponding binary tree splits are learned based on FAME data. We call this learning approach 'phylogenetic learning'. Supervised Random Forest models are developed to train the classification tasks in a stratified cross-validation setting. In this way, better classification results are obtained for species that are typically hard to distinguish by a single or flat multi-class classification model.</p> <p>Conclusions</p> <p>FAME-based bacterial species classification is successfully evaluated in a taxonomic framework. Although the proposed approach does not improve the overall accuracy compared to flat multi-class classification, it has some distinct advantages. First, it has better capabilities for distinguishing species on which flat multi-class classification fails. Secondly, the hierarchical classification structure allows to easily evaluate and visualize the resolution of FAME data for the discrimination of bacterial species. Summarized, by phylogenetic learning we are able to situate and evaluate FAME-based bacterial species classification in a more informative context.</p>http://www.biomedcentral.com/1471-2105/11/69
spellingShingle Dawyndt Peter
Waegeman Willem
Slabbinck Bram
De Vos Paul
De Baets Bernard
From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification
BMC Bioinformatics
title From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification
title_full From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification
title_fullStr From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification
title_full_unstemmed From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification
title_short From learning taxonomies to phylogenetic learning: Integration of 16S rRNA gene data into FAME-based bacterial classification
title_sort from learning taxonomies to phylogenetic learning integration of 16s rrna gene data into fame based bacterial classification
url http://www.biomedcentral.com/1471-2105/11/69
work_keys_str_mv AT dawyndtpeter fromlearningtaxonomiestophylogeneticlearningintegrationof16srrnagenedataintofamebasedbacterialclassification
AT waegemanwillem fromlearningtaxonomiestophylogeneticlearningintegrationof16srrnagenedataintofamebasedbacterialclassification
AT slabbinckbram fromlearningtaxonomiestophylogeneticlearningintegrationof16srrnagenedataintofamebasedbacterialclassification
AT devospaul fromlearningtaxonomiestophylogeneticlearningintegrationof16srrnagenedataintofamebasedbacterialclassification
AT debaetsbernard fromlearningtaxonomiestophylogeneticlearningintegrationof16srrnagenedataintofamebasedbacterialclassification