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 n...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2018-07-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-018-2182-6 |
| _version_ | 1828803346228576256 |
|---|---|
| author | Antonino Fiannaca Laura La Paglia Massimo La Rosa Giosue’ Lo Bosco Giovanni Renda Riccardo Rizzo Salvatore Gaglio Alfonso Urso |
| author_facet | Antonino Fiannaca Laura La Paglia Massimo La Rosa Giosue’ Lo Bosco Giovanni Renda Riccardo Rizzo Salvatore Gaglio Alfonso Urso |
| author_sort | Antonino Fiannaca |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-12T07:21:38Z |
| format | Article |
| id | doaj.art-c3e67c7435164eda91db30a62fc485f1 |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-12T07:21:38Z |
| publishDate | 2018-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-c3e67c7435164eda91db30a62fc485f12022-12-22T00:33:20ZengBMCBMC Bioinformatics1471-21052018-07-0119S7617610.1186/s12859-018-2182-6Deep learning models for bacteria taxonomic classification of metagenomic dataAntonino Fiannaca0Laura La Paglia1Massimo La Rosa2Giosue’ Lo Bosco3Giovanni Renda4Riccardo Rizzo5Salvatore Gaglio6Alfonso Urso7CNR-ICAR, National Research Council of ItalyCNR-ICAR, National Research Council of ItalyCNR-ICAR, National Research Council of ItalyDipartimento di Matematica e Informatica, Università degli studi di PalermoDipartimento dell’Innovazione Industriale e Digitale, Università degli studi di PalermoCNR-ICAR, National Research Council of ItalyCNR-ICAR, National Research Council of ItalyCNR-ICAR, National Research Council of ItalyAbstract 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.http://link.springer.com/article/10.1186/s12859-018-2182-6MetagenomicClassificationCNNDBNk-mer representationAmplicon |
| spellingShingle | Antonino Fiannaca Laura La Paglia Massimo La Rosa Giosue’ Lo Bosco Giovanni Renda Riccardo Rizzo Salvatore Gaglio Alfonso Urso Deep learning models for bacteria taxonomic classification of metagenomic data BMC Bioinformatics Metagenomic Classification CNN DBN k-mer representation Amplicon |
| title | Deep learning models for bacteria taxonomic classification of metagenomic data |
| title_full | Deep learning models for bacteria taxonomic classification of metagenomic data |
| title_fullStr | Deep learning models for bacteria taxonomic classification of metagenomic data |
| title_full_unstemmed | Deep learning models for bacteria taxonomic classification of metagenomic data |
| title_short | Deep learning models for bacteria taxonomic classification of metagenomic data |
| title_sort | deep learning models for bacteria taxonomic classification of metagenomic data |
| topic | Metagenomic Classification CNN DBN k-mer representation Amplicon |
| url | http://link.springer.com/article/10.1186/s12859-018-2182-6 |
| work_keys_str_mv | AT antoninofiannaca deeplearningmodelsforbacteriataxonomicclassificationofmetagenomicdata AT lauralapaglia deeplearningmodelsforbacteriataxonomicclassificationofmetagenomicdata AT massimolarosa deeplearningmodelsforbacteriataxonomicclassificationofmetagenomicdata AT giosuelobosco deeplearningmodelsforbacteriataxonomicclassificationofmetagenomicdata AT giovannirenda deeplearningmodelsforbacteriataxonomicclassificationofmetagenomicdata AT riccardorizzo deeplearningmodelsforbacteriataxonomicclassificationofmetagenomicdata AT salvatoregaglio deeplearningmodelsforbacteriataxonomicclassificationofmetagenomicdata AT alfonsourso deeplearningmodelsforbacteriataxonomicclassificationofmetagenomicdata |