Cargando…
A sensitive, support-vector-machine method for the detection of horizontal gene transfers in viral, archaeal and bacterial genomes
In earlier work, we introduced and discussed a generalized computational framework for identifying horizontal transfers. This framework relied on a gene's nucleotide composition, obviated the need for knowledge of codon boundaries and database searches, and was shown to perform very well across...
Autores principales: | , |
---|---|
Formato: | Texto |
Lenguaje: | English |
Publicado: |
Oxford University Press
2005
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1174904/ https://www.ncbi.nlm.nih.gov/pubmed/16006619 http://dx.doi.org/10.1093/nar/gki660 |
_version_ | 1782124474790838272 |
---|---|
author | Tsirigos, Aristotelis Rigoutsos, Isidore |
author_facet | Tsirigos, Aristotelis Rigoutsos, Isidore |
author_sort | Tsirigos, Aristotelis |
collection | PubMed |
description | In earlier work, we introduced and discussed a generalized computational framework for identifying horizontal transfers. This framework relied on a gene's nucleotide composition, obviated the need for knowledge of codon boundaries and database searches, and was shown to perform very well across a wide range of archaeal and bacterial genomes when compared with previously published approaches, such as Codon Adaptation Index and C + G content. Nonetheless, two considerations remained outstanding: we wanted to further increase the sensitivity of detecting horizontal transfers and also to be able to apply the method to increasingly smaller genomes. In the discussion that follows, we present such a method, Wn-SVM, and show that it exhibits a very significant improvement in sensitivity compared with earlier approaches. Wn-SVM uses a one-class support-vector machine and can learn using rather small training sets. This property makes Wn-SVM particularly suitable for studying small-size genomes, similar to those of viruses, as well as the typically larger archaeal and bacterial genomes. We show experimentally that the new method results in a superior performance across a wide range of organisms and that it improves even upon our own earlier method by an average of 10% across all examined genomes. As a small-genome case study, we analyze the genome of the human cytomegalovirus and demonstrate that Wn-SVM correctly identifies regions that are known to be conserved and prototypical of all beta-herpesvirinae, regions that are known to have been acquired horizontally from the human host and, finally, regions that had not up to now been suspected to be horizontally transferred. Atypical region predictions for many eukaryotic viruses, including the α-, β- and γ-herpesvirinae, and 123 archaeal and bacterial genomes, have been made available online at . |
format | Text |
id | pubmed-1174904 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2005 |
publisher | Oxford University Press |
record_format | MEDLINE/PubMed |
spelling | pubmed-11749042005-07-12 A sensitive, support-vector-machine method for the detection of horizontal gene transfers in viral, archaeal and bacterial genomes Tsirigos, Aristotelis Rigoutsos, Isidore Nucleic Acids Res Article In earlier work, we introduced and discussed a generalized computational framework for identifying horizontal transfers. This framework relied on a gene's nucleotide composition, obviated the need for knowledge of codon boundaries and database searches, and was shown to perform very well across a wide range of archaeal and bacterial genomes when compared with previously published approaches, such as Codon Adaptation Index and C + G content. Nonetheless, two considerations remained outstanding: we wanted to further increase the sensitivity of detecting horizontal transfers and also to be able to apply the method to increasingly smaller genomes. In the discussion that follows, we present such a method, Wn-SVM, and show that it exhibits a very significant improvement in sensitivity compared with earlier approaches. Wn-SVM uses a one-class support-vector machine and can learn using rather small training sets. This property makes Wn-SVM particularly suitable for studying small-size genomes, similar to those of viruses, as well as the typically larger archaeal and bacterial genomes. We show experimentally that the new method results in a superior performance across a wide range of organisms and that it improves even upon our own earlier method by an average of 10% across all examined genomes. As a small-genome case study, we analyze the genome of the human cytomegalovirus and demonstrate that Wn-SVM correctly identifies regions that are known to be conserved and prototypical of all beta-herpesvirinae, regions that are known to have been acquired horizontally from the human host and, finally, regions that had not up to now been suspected to be horizontally transferred. Atypical region predictions for many eukaryotic viruses, including the α-, β- and γ-herpesvirinae, and 123 archaeal and bacterial genomes, have been made available online at . Oxford University Press 2005 2005-07-08 /pmc/articles/PMC1174904/ /pubmed/16006619 http://dx.doi.org/10.1093/nar/gki660 Text en © The Author 2005. Published by Oxford University Press. All rights reserved |
spellingShingle | Article Tsirigos, Aristotelis Rigoutsos, Isidore A sensitive, support-vector-machine method for the detection of horizontal gene transfers in viral, archaeal and bacterial genomes |
title | A sensitive, support-vector-machine method for the detection of horizontal gene transfers in viral, archaeal and bacterial genomes |
title_full | A sensitive, support-vector-machine method for the detection of horizontal gene transfers in viral, archaeal and bacterial genomes |
title_fullStr | A sensitive, support-vector-machine method for the detection of horizontal gene transfers in viral, archaeal and bacterial genomes |
title_full_unstemmed | A sensitive, support-vector-machine method for the detection of horizontal gene transfers in viral, archaeal and bacterial genomes |
title_short | A sensitive, support-vector-machine method for the detection of horizontal gene transfers in viral, archaeal and bacterial genomes |
title_sort | sensitive, support-vector-machine method for the detection of horizontal gene transfers in viral, archaeal and bacterial genomes |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1174904/ https://www.ncbi.nlm.nih.gov/pubmed/16006619 http://dx.doi.org/10.1093/nar/gki660 |
work_keys_str_mv | AT tsirigosaristotelis asensitivesupportvectormachinemethodforthedetectionofhorizontalgenetransfersinviralarchaealandbacterialgenomes AT rigoutsosisidore asensitivesupportvectormachinemethodforthedetectionofhorizontalgenetransfersinviralarchaealandbacterialgenomes AT tsirigosaristotelis sensitivesupportvectormachinemethodforthedetectionofhorizontalgenetransfersinviralarchaealandbacterialgenomes AT rigoutsosisidore sensitivesupportvectormachinemethodforthedetectionofhorizontalgenetransfersinviralarchaealandbacterialgenomes |