Transcriptome dynamics-based operon prediction in prokaryotes

BMC Bioinformatics

Table 5 The contribution of transcriptomic features in improving the classification accuracy

Dataset	All			Genomic			Transcriptomic			IGR, CuScore			IGR, CuScore
	All			Features			Features			and IGR-Expr			and Diff-Expr
	NN	RF	SVM	NN	RF	SVM	NN	RF	SVM	NN	RF	SVM	NN	RF	SVM
PG1	0.98	0.97	0.97	0.9	0.89	0.9	0.89	0.87	0.88	0.96	0.96	0.96	0.91	0.94	0.87
PG2	0.99	0.99	0.97	0.95	0.95	0.92	0.9	0.9	0.91	0.97	0.97	0.96	0.97	0.96	0.97
PG3	0.98	0.97	0.97	0.95	0.94	0.9	0.92	0.89	0.91	0.96	0.95	0.95	0.96	0.95	0.96
HS2336	0.95	0.97	0.97	0.86	0.86	0.86	0.89	0.88	0.89	0.94	0.96	0.95	0.88	0.89	0.88

Four subsets of features have been tested and compared by the corresponding accuracy values. The first column reports the accuracy results with all the features. The next two columns show the accuracy values achieved, respectively, with genomic and transcriptomic features. Finally, the last two columns display the improvement, in classification accuracy, obtained combining one transcriptomic feature to the two genomic features.

ISSN: 1471-2105