Deep learning models for bacteria taxonomic classification of metagenomic data

Giosue' Lo Bosco, Salvatore Gaglio, Laura La Paglia, Massimo La Rosa, Antonino Fiannaca, Alfonso Urso, Salvatore Gaglio, Riccardo Rizzo, Alfonso Urso, Riccardo Rizzo

Risultato della ricerca: Article

7 Citazioni (Scopus)

Abstract

Background: An open challenge in translational bioinformatics is the analysis of sequenced metagenomes from various environmental samples. Of course, several studies demonstrated the 16S ribosomal RNA could be considered as a barcode for bacteria classification at the genus level, but till now it is hard to identify the correct composition of metagenomic data from RNA-seq short-read data. 16S short-read data are generated using two next generation sequencing technologies, i.e. whole genome shotgun (WGS) and amplicon (AMP); typically, the former is filtered to obtain short-reads belonging to a 16S shotgun (SG), whereas the latter take into account only some specific 16S hypervariable regions. The above mentioned two sequencing technologies, SG and AMP, are used alternatively, for this reason in this work we propose a deep learning approach for taxonomic classification of metagenomic data, that can be employed for both of them.Results: To test the proposed pipeline, we simulated both SG and AMP short-reads, from 1000 16S full-length sequences. Then, we adopted a k-mer representation to map sequences as vectors into a numerical space. Finally, we trained two different deep learning architecture, i.e., convolutional neural network (CNN) and deep belief network (DBN), obtaining a trained model for each taxon. We tested our proposed methodology to find the best parameters configuration, and we compared our results against the classification performances provided by a reference classifier for bacteria identification, known as RDP classifier. We outperformed the RDP classifier at each taxonomic level with both architectures. For instance, at the genus level, both CNN and DBN reached 91.3% of accuracy with AMP short-reads, whereas RDP classifier obtained 83.8% with the same data.Conclusions: In this work, we proposed a 16S short-read sequences classification technique based on k-mer representation and deep learning architecture, in which each taxon (from phylum to genus) generates a classification model. Experimental results confirm the proposed pipeline as a valid approach for classifying bacteria sequences; for this reason, our approach could be integrated into the most common tools for metagenomic analysis. According to obtained results, it can be successfully used for classifying both SG and AMP data.
Lingua originaleEnglish
pagine (da-a)61-76
Numero di pagine16
RivistaBMC Bioinformatics
Volume19
Stato di pubblicazionePublished - 2018

Fingerprint

Metagenomics
Firearms
Bacteria
Learning
Classifiers
Classifier
Belief Networks
Bayesian networks
Genus
Pipelines
Sequencing
Metagenome
16S Ribosomal RNA
Technology
Neural networks
Model
Neural Networks
Bioinformatics
Computational Biology
RNA

All Science Journal Classification (ASJC) codes

  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics

Cita questo

Lo Bosco, G., Gaglio, S., La Paglia, L., La Rosa, M., Fiannaca, A., Urso, A., ... Rizzo, R. (2018). Deep learning models for bacteria taxonomic classification of metagenomic data. BMC Bioinformatics, 19, 61-76.

Deep learning models for bacteria taxonomic classification of metagenomic data. / Lo Bosco, Giosue'; Gaglio, Salvatore; La Paglia, Laura; La Rosa, Massimo; Fiannaca, Antonino; Urso, Alfonso; Gaglio, Salvatore; Rizzo, Riccardo; Urso, Alfonso; Rizzo, Riccardo.

In: BMC Bioinformatics, Vol. 19, 2018, pag. 61-76.

Risultato della ricerca: Article

Lo Bosco, G, Gaglio, S, La Paglia, L, La Rosa, M, Fiannaca, A, Urso, A, Gaglio, S, Rizzo, R, Urso, A & Rizzo, R 2018, 'Deep learning models for bacteria taxonomic classification of metagenomic data', BMC Bioinformatics, vol. 19, pagg. 61-76.
Lo Bosco, Giosue' ; Gaglio, Salvatore ; La Paglia, Laura ; La Rosa, Massimo ; Fiannaca, Antonino ; Urso, Alfonso ; Gaglio, Salvatore ; Rizzo, Riccardo ; Urso, Alfonso ; Rizzo, Riccardo. / Deep learning models for bacteria taxonomic classification of metagenomic data. In: BMC Bioinformatics. 2018 ; Vol. 19. pagg. 61-76.
@article{03249d73e3334fafa8270d783acb7014,
title = "Deep learning models for bacteria taxonomic classification of metagenomic data",
abstract = "Background: An open challenge in translational bioinformatics is the analysis of sequenced metagenomes from various environmental samples. Of course, several studies demonstrated the 16S ribosomal RNA could be considered as a barcode for bacteria classification at the genus level, but till now it is hard to identify the correct composition of metagenomic data from RNA-seq short-read data. 16S short-read data are generated using two next generation sequencing technologies, i.e. whole genome shotgun (WGS) and amplicon (AMP); typically, the former is filtered to obtain short-reads belonging to a 16S shotgun (SG), whereas the latter take into account only some specific 16S hypervariable regions. The above mentioned two sequencing technologies, SG and AMP, are used alternatively, for this reason in this work we propose a deep learning approach for taxonomic classification of metagenomic data, that can be employed for both of them.Results: To test the proposed pipeline, we simulated both SG and AMP short-reads, from 1000 16S full-length sequences. Then, we adopted a k-mer representation to map sequences as vectors into a numerical space. Finally, we trained two different deep learning architecture, i.e., convolutional neural network (CNN) and deep belief network (DBN), obtaining a trained model for each taxon. We tested our proposed methodology to find the best parameters configuration, and we compared our results against the classification performances provided by a reference classifier for bacteria identification, known as RDP classifier. We outperformed the RDP classifier at each taxonomic level with both architectures. For instance, at the genus level, both CNN and DBN reached 91.3{\%} of accuracy with AMP short-reads, whereas RDP classifier obtained 83.8{\%} with the same data.Conclusions: In this work, we proposed a 16S short-read sequences classification technique based on k-mer representation and deep learning architecture, in which each taxon (from phylum to genus) generates a classification model. Experimental results confirm the proposed pipeline as a valid approach for classifying bacteria sequences; for this reason, our approach could be integrated into the most common tools for metagenomic analysis. According to obtained results, it can be successfully used for classifying both SG and AMP data.",
author = "{Lo Bosco}, Giosue' and Salvatore Gaglio and {La Paglia}, Laura and {La Rosa}, Massimo and Antonino Fiannaca and Alfonso Urso and Salvatore Gaglio and Riccardo Rizzo and Alfonso Urso and Riccardo Rizzo",
year = "2018",
language = "English",
volume = "19",
pages = "61--76",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",

}

TY - JOUR

T1 - Deep learning models for bacteria taxonomic classification of metagenomic data

AU - Lo Bosco, Giosue'

AU - Gaglio, Salvatore

AU - La Paglia, Laura

AU - La Rosa, Massimo

AU - Fiannaca, Antonino

AU - Urso, Alfonso

AU - Gaglio, Salvatore

AU - Rizzo, Riccardo

AU - Urso, Alfonso

AU - Rizzo, Riccardo

PY - 2018

Y1 - 2018

N2 - Background: An open challenge in translational bioinformatics is the analysis of sequenced metagenomes from various environmental samples. Of course, several studies demonstrated the 16S ribosomal RNA could be considered as a barcode for bacteria classification at the genus level, but till now it is hard to identify the correct composition of metagenomic data from RNA-seq short-read data. 16S short-read data are generated using two next generation sequencing technologies, i.e. whole genome shotgun (WGS) and amplicon (AMP); typically, the former is filtered to obtain short-reads belonging to a 16S shotgun (SG), whereas the latter take into account only some specific 16S hypervariable regions. The above mentioned two sequencing technologies, SG and AMP, are used alternatively, for this reason in this work we propose a deep learning approach for taxonomic classification of metagenomic data, that can be employed for both of them.Results: To test the proposed pipeline, we simulated both SG and AMP short-reads, from 1000 16S full-length sequences. Then, we adopted a k-mer representation to map sequences as vectors into a numerical space. Finally, we trained two different deep learning architecture, i.e., convolutional neural network (CNN) and deep belief network (DBN), obtaining a trained model for each taxon. We tested our proposed methodology to find the best parameters configuration, and we compared our results against the classification performances provided by a reference classifier for bacteria identification, known as RDP classifier. We outperformed the RDP classifier at each taxonomic level with both architectures. For instance, at the genus level, both CNN and DBN reached 91.3% of accuracy with AMP short-reads, whereas RDP classifier obtained 83.8% with the same data.Conclusions: In this work, we proposed a 16S short-read sequences classification technique based on k-mer representation and deep learning architecture, in which each taxon (from phylum to genus) generates a classification model. Experimental results confirm the proposed pipeline as a valid approach for classifying bacteria sequences; for this reason, our approach could be integrated into the most common tools for metagenomic analysis. According to obtained results, it can be successfully used for classifying both SG and AMP data.

AB - Background: An open challenge in translational bioinformatics is the analysis of sequenced metagenomes from various environmental samples. Of course, several studies demonstrated the 16S ribosomal RNA could be considered as a barcode for bacteria classification at the genus level, but till now it is hard to identify the correct composition of metagenomic data from RNA-seq short-read data. 16S short-read data are generated using two next generation sequencing technologies, i.e. whole genome shotgun (WGS) and amplicon (AMP); typically, the former is filtered to obtain short-reads belonging to a 16S shotgun (SG), whereas the latter take into account only some specific 16S hypervariable regions. The above mentioned two sequencing technologies, SG and AMP, are used alternatively, for this reason in this work we propose a deep learning approach for taxonomic classification of metagenomic data, that can be employed for both of them.Results: To test the proposed pipeline, we simulated both SG and AMP short-reads, from 1000 16S full-length sequences. Then, we adopted a k-mer representation to map sequences as vectors into a numerical space. Finally, we trained two different deep learning architecture, i.e., convolutional neural network (CNN) and deep belief network (DBN), obtaining a trained model for each taxon. We tested our proposed methodology to find the best parameters configuration, and we compared our results against the classification performances provided by a reference classifier for bacteria identification, known as RDP classifier. We outperformed the RDP classifier at each taxonomic level with both architectures. For instance, at the genus level, both CNN and DBN reached 91.3% of accuracy with AMP short-reads, whereas RDP classifier obtained 83.8% with the same data.Conclusions: In this work, we proposed a 16S short-read sequences classification technique based on k-mer representation and deep learning architecture, in which each taxon (from phylum to genus) generates a classification model. Experimental results confirm the proposed pipeline as a valid approach for classifying bacteria sequences; for this reason, our approach could be integrated into the most common tools for metagenomic analysis. According to obtained results, it can be successfully used for classifying both SG and AMP data.

UR - http://hdl.handle.net/10447/292404

UR - https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-018-2182-6

M3 - Article

VL - 19

SP - 61

EP - 76

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

ER -