Building multiclass classifiers for remote homology detection and fold recognition

BMC Bioinformatics

Table 1 Dataset Statistics.

Statistic	sf95	sf40	fd25	fd40
ASTRAL filtering	95%	40%	25%	40%
Number of Sequences	2115	1119	1294	1651
Number of Folds	25	25	25	27
Number of Superfamilies	47	37	137	158
Avg. Pairwise Similarity	12.8%	11.5%	11.6%	11.4
Avg. Max. Similarity	63.5%	33.9%	32.2%	34.3
Avg. Pairwise Similarity (within folds)	25.6%	17.9%	16.7%	17.4
Avg. Pairwise Similarity (outside folds)	10.4%	11.03%	11.2%	11.0

The percent similarity between two sequences is computed by aligning the pair of sequences using SW-GSM with a gap opening of 5.0 and gap extension of 1.0. "Avg. Pairwise Similarity" is the average of all the pairwise percent identities, "Avg. Max. Similarity" is the average of the maximum pairwise percent identity for each sequence i.e, it measures the similarity to its most similar sequence. The "Avg. Pairwise Similarity (within folds)" and "Avg. Pairwise Similarity (outside folds)" is the average of the average pairwise percent sequence similarity within the same fold and outside the fold for a given sequence.

ISSN: 1471-2105