An improved alignment-free model for dna sequence similarity metric

BMC Bioinformatics

Table 4 The clustering results of six alignment-free models against sliding window size on the dataset DS2, DS3 and DS4

Dataset	Assessment method	Model	Size of sliding window
Dataset	Assessment method	Model	2	3	4	5	6
DS2	purity	kTuple	0.8842	0.9123	0.8947	0.7789	0.7404
		DMk	0.9474	0.9404	0.9474	0.8667	0.5123
		AMI	0.5895	0.6035	0.6140	0.5614	0.5965
		CV	N/A	0.7158	0.7684	0.8421	0.8421
		TSM	0.8667	0.8702	0.8772	0.8807	0.9018
		CPF	0.9754	0.9439	0.9368	0.9404	0.9123
DS2	F-measure	kTuple	0.8921	0.9184	0.9012	0.6631	0.6381
		DMk	0.9487	0.9419	0.9490	0.7477	0.3854
		AMI	0.4871	0.4924	0.5009	0.4104	0.4370
		CV	N/A	0.6126	0.7708	0.8457	0.8419
		TSM	0.8749	0.8789	0.8845	0.8878	0.9087
		CPF	0.9755	0.9451	0.9379	0.9416	0.9158
DS3	purity	kTuple	0.5935	0.6290	0.6290	0.5452	0.4968
		DMk	0.8968	0.8806	0.8774	0.7484	0.5774
		AMI	0.5387	0.5484	0.5452	0.5516	0.5581
		CV	N/A	0.4484	0.5419	0.5935	0.4452
		TSM	0.6290	0.6032	0.5774	0.5774	0.6452
		CPF	0.9806	0.9419	0.9194	0.9387	0.9226
DS3	F-measure	kTuple	0.4755	0.5158	0.5185	0.3862	0.3952
		DMk	0.8972	0.8836	0.8811	0.6336	0.3083
		AMI	0.4241	0.4699	0.4871	0.4284	0.4936
		CV	N/A	0.3473	0.4272	0.4816	0.2307
		TSM	0.5046	0.4871	0.4208	0.4224	0.5364
		CPF	0.9809	0.9446	0.9222	0.9420	0.9262
DS4	purity	kTuple	0.6215	0.6853	0.7092	0.6853	0.5538
		DMk	0.9641	0.9243	0.8367	0.7490	0.3984
		AMI	0.5100	0.5618	0.5896	0.6096	0.6494
		CV	N/A	0.7092	0.6375	0.6414	0.6175
		TSM	0.6096	0.6972	0.7131	0.7251	0.6653
		CPF	0.9761	0.9801	0.9721	0.9681	0.9641
DS4	F-measure	kTuple	0.5616	0.5146	0.5240	0.5497	0.3469
		DMk	0.9644	0.9242	0.7220	0.5476	0.2395
		AMI	0.3886	0.4330	0.5062	0.4848	0.5714
		CV	N/A	0.6790	0.4237	0.4986	0.4610
		TSM	0.4722	0.4970	0.5068	0.6516	0.4703
		CPF	0.9761	0.9801	0.9721	0.9681	0.9641

ISSN: 1471-2105