LABEL: fast and accurate lineage assignment with assessment of H5N1 and H9N2 influenza A hemagglutinins.

ABSTRACT: The evolutionary classification of influenza genes into lineages is a first step in understanding their molecular epidemiology and can inform the subsequent implementation of control measures. We introduce a novel approach called Lineage Assignment By Extended Learning (LABEL) to rapidly determine cladistic information for any number of genes without the need for time-consuming sequence alignment, phylogenetic tree construction, or manual annotation. Instead, LABEL relies on hidden Markov model profiles and support vector machine training to hierarchically classify gene sequences by their similarity to pre-defined lineages. We assessed LABEL by analyzing the annotated hemagglutinin genes of highly pathogenic (H5N1) and low pathogenicity (H9N2) avian influenza A viruses. Using the WHO/FAO/O

SUBMITTER: Shepard SS 

PROVIDER: S-EPMC3900692 | biostudies-literature | 2014

REPOSITORIES: biostudies-literature