Screening non-coding RNAs in transcriptomes from neglected species using PORTRAIT: case study of the pathogenic fungus Paracoccidioides brasiliensis

Table 2 Speed performance (in minutes), standard efficiency measures and cross validation accuracy. Indices were calculated from the mean of predictions of the classifiers regarding dbTS_OP and dbTS_OA sets.

	ACC (%)	SPC (%)	SEN (%)	F-M (%)	PPV (%)	Time (min.)*	CV acc. (%)
PORTRAIT	91.9	95.6	86.5	90.8	92.9	21.6	92.1
nB classifier	73.2	75.1	70.1	72.6	65.3	16.1	72.9
CPC	90.8	90.9	90.7	90.8	87.0	1,789.7	95.8**
Random	49.1	45.6	54.6	49.7	44.0	0.07	-

ACC = accuracy; SPC = specificity; SEN = sensitivity; F-M = F-measure; PPV = positive predictive value; CV acc. = cross-validation accuracy. Prediction threshold in all measures was 0.5 for all classifiers.
*All processes were run on a Intel^® XEON™ 1.80 MHz × 86 with 512 Mb RAM computer. Runtime refers to prediction of 6,022 sequences from dbPB.
**As reported by Kong et al, 2007. Training set used was not dbTS.

ISSN: 1471-2105