MetWAMer: eukaryotic translation initiation site prediction

BMC Bioinformatics

Table 3 Method performances on non-TIS-containing data

Parametrization	Method	TN	FP	Sn
	1^st-ATG	688	15,433	0.0427
	TISHunter	0	16,121	0.0000
	ATGpr	0	16,121	0.0000
	TIS Miner	3,142	12,979	0.1949
	NetStart	575	15,546	0.0357
homogeneous	LLKR	5,179	10,942	0.3213
	WLLKR	7,260	8,861	0.4503
	MFCWLLKR	1,688	14,433	0.1047
	PFCWLLKR	6,785	9,336	0.4209
	BAYES	6,813	9,308	0.4226
cluster-specific	LLKR	6,385	9,736	0.3961
	WLLKR	8,080	8,041	0.5012
	MFCWLLKR	1,995	14,126	0.1238
	PFCWLLKR	8,685	7,436	0.5387
	BAYES	8,057	8,064	0.4998
random split	LLKR	5,155	10,966	0.3198
	WLLKR	7,176	8,945	0.4451
	MFCWLLKR	1,687	14,434	0.1046
	PFCWLLKR	6,748	9,373	0.4186
	BAYES	6,824	9,297	0.4233

16,121 non-TIS-containing instances were used in three separate five-fold cross-validation experiments. Results are shown from applying a non-stratified parameter set (homogeneous), a priori-known cluster-specific parameter sets for k = 3 (cluster-specific), and group-specific parameter sets for a random three-way split of the data (random split). TN represents the number of instances for which the method (correctly) refused to predict a TIS, and FP denotes the number for which some prediction was made, though always incorrect (see Figure 2). $S n = \frac{T N}{T N + F P}$ .

ISSN: 1471-2105