Virulence factor prediction in Streptococcus pyogenes using classification and clustering based on microarray data
| Autor: | Liliana López-Kleine, Francisco Torres-Avilés, Luz A. Gordillo, Fabio Hernán Tejedor |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
Streptococcus pyogenes
Virulence Factors Microarray analysis techniques Computational Biology Virulence General Medicine Computational biology Biology Microarray Analysis Bioinformatics medicine.disease_cause Applied Microbiology and Biotechnology Virulence factor Support vector machine Bacterial Proteins medicine Cluster Analysis Classification methods DNA microarray Transcriptome Cluster analysis Biotechnology |
| Zdroj: | Applied Microbiology and Biotechnology. 93:2091-2098 |
| ISSN: | 1432-0614 0175-7598 |
| DOI: | 10.1007/s00253-012-3917-3 |
| Popis: | Interesting biological information as, for example, gene expression data (microarrays), can be extracted from publicly available genomic data. As a starting point in order to narrow down the great possibilities of wet lab experiments, global high throughput data and available knowledge should be used to infer biological knowledge and emit biological hypothesis. Here, based on microarray data, we propose the use of cluster and classification methods that have become very popular and are implemented in freely available software in order to predict the participation in virulence mechanisms of different proteins coded by genes of the pathogen Streptococcus pyogenes. Confidence of predictions is based on classification errors of known genes and repetitive prediction by more than three methods. A special emphasis is done on the nonlinear kernel classification methods used. We propose a list of interesting candidates that could be virulence factors or that participate in the virulence process of S. pyogenes. Biological validations should start using this list of candidates as they show similar behavior to known virulence factors. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|