Prediction of Protein Structural Classes for Low-Similarity Sequences Based on Consensus Sequence and Segmented PSSM

Table 5

Performance comparison of different methods on three datasets.

Dataset	Method	Prediction accuracy (%)
		All-	All-			OA (%)
1189	PSSM-S [36]	93.3	85.1	77.6	65.6	80.2
	LCC-PSSM [25]	89.2	88.8	85.6	58.5	81.2
	MBMGAC-PSSM [40]	79.8	85.0	84.7	50.6	76.3
	RPSSM [34]	67.7	75.2	74.6	17.4	60.2
	AADP-PSSM [15]	69.1	83.7	85.6	35.7	70.7
	AATP [33]	72.7	85.4	82.9	42.7	72.6
	MEDP [35]	85.2	84.0	84.3	45.2	75.8
	PsePSSM [41]	82.0	82.3	84.1	44.0	74.4
	AAC-PSSM-AC [17]	80.7	86.4	81.4	45.2	74.6
	This paper	84.8	85.4	85.0	55.2	78.5
25PDB	PSSM-S [36]	93.8	92.8	92.6	81.7	90.1
	LCC-PSSM [25]	91.7	80.8	79.8	64.0	79.0
	MBMGAC-PSSM [40]	86.7	81.5	79.5	61.7	77.2
	RPSSM [34]	75.6	70.2	52.0	43.3	60.8
	AADP-PSSM [15]	83.3	78.1	76.3	54.4	72.9
	AATP [33]	81.9	74.7	75.1	55.8	71.7
	MEDP [35]	87.8	78.3	76.0	57.4	74.8
	AAC-PSSM-AC [17]	85.3	81.7	73.7	55.3	74.1
	PsePSSM [41]	86.2	78.8	75.7	57.6	75.5
	Xia et al. [42]	92.6	72.5	71.7	71.0	77.2
	This paper	94.4	91.9	71.1	92.5	88.4
640	LCC-PSSM [25]	92.8	88.3	85.9	66.1	82.7
	MBMGAC-PSSM [40]	86.2	83.1	85.3	63.2	79.1
	MEDP [35]	84.8	75.3	86.4	53.8	74.7
	PsePSSM [41]	73.9	76.6	85.3	51.5	71.7
	This paper	83.3	83.1	83.0	60.2	77.0