EnsembleFam: towards more accurate protein family prediction in the twilight zone

BMC Bioinformatics

Table 4 Number of prediction made by pHMM and EnsembleFam for twilight zone proteins where \(30 < \text {identity} \le 40\)

Method	seq1	seq2	seq3	seq4	seq5	seq6	seq7	seq8	seq9	seq10	seq11	seq12	seq13	seq14
pHMM	57	54	58	17	13	7	7	56	50	50	38	1	1	54
EnsembleFam	1	0	0	2	0	0	3	1	1	1	1	2	2	1

For each test sequence, the maximum number of predictions can be 86, i.e, the sequence belongs to all sub-subfamilies. And the minimum number of predictions can be 0, i.e., the sequence does not belong to any of the sub-subfamily. DeepFam was not included in this comparison, as DeepFam always predict a single label irrespective of the number of families

ISSN: 1471-2105