From: A stochastic context free grammar based framework for analysis of protein sequences
 | Number of known instances of the pattern | Number of known sequences containing the pattern | ||
---|---|---|---|---|
 | Total | Training set | Total | Positive test set |
PS00028 | 10129 (88%) | 9 (45%) | 1598 (54%) | 14 (14%) |
PS00518 | 1092 (9%) | 1 (5%) | 1089 (37%) | 32 (31%) |
PS00752 | 7 (<<1%) | 1 (5%) | 7 (<<1%) | 0 (0%) |
PS01030 | 28 (<<1%) | 4 (20%) | 28 (1%) | 3 (3%) |
PS01102 | 20 (<<1%) | 1 (5%) | 20 (1%) | 3 (3%) |
PS01300 | 169 (1%) | 3 (15%) | 169 (6%) | 22 (22%) |
PS01358 | 117 (1%) | 1 (5%) | 73 (2%) | 28 (27%) |
Total | 11562 (100%) | 20 (100%) | 2984* (100%) | 102* (100%) |