K-mer based classifiers extract functionally relevant features to support accurate Peroxiredoxin subgroup distinction

Abstract

BackgroundThe Peroxiredoxins (Prx) are a family of proteins that play a major role in antioxidant defense and peroxide-regulated signaling. Six distinct Prx subgroups have been defined based on analysis of structure and sequence regions in proximity to the Prx active site. Analysis of other sequence regions of these annotated proteins may improve the ability to distinguish subgroups and uncover additional representative sequence regions beyond the active site.\n\nResultsThe space of Prx subgroup classifiers is surveyed to highlight similarities and differences in the available approaches. Exploiting the recent growth in annotated Prx proteins, a whole sequence-based classifier is presented that employs support vector machines and a k-mer (k=3) sequence representation.\n\nDistinguishing k-mers are extracted and located relative to published active site regions.\n\nConclusionsThis work demonstrates that the 3-mer based classifier can attain high accuracy in subgroup annotation, at rates similar to the current state-of-the-art. Analysis of the classifiers automatically derived models show that the classification decision is based on a combination of conserved features, including a significant number of residue regions that have not been previously suggested as informative by other classifiers but for which there is evidence of functional relevance.