GISMO--gene identification using a support vector machine for ORF classification

L. Krause, A. C. McHardy, T. W. Nattkemper, A. Puhler, J. Stoye, F. Meyer
2006 Nucleic Acids Research  
We present the novel prokaryotic gene finder GISMO, which combines searches for protein family domains with composition-based classification based on a support vector machine. GISMO is highly accurate; exhibiting high sensitivity and specificity in gene identification. We found that it performs well for complete prokaryotic chromosomes, irrespective of their GC content, and also for plasmids as short as 10 kb, short genes and for genes with atypical sequence composition. Using GISMO, we found
more » ... veral thousand new predictions for the published genomes that are supported by extrinsic evidence, which strongly suggest that these are very likely biologically active genes. The source code for GISMO is freely available under the GPL license.
doi:10.1093/nar/gkl1083 pmid:17175534 pmcid:PMC1802617 fatcat:j33nuxiigngjbfmzw25gcwqo6i