Skip to main content

Table 3 Peptide sequence distributions. Peptides are divided into the two classes of binding orientation (I and II). The peptide proportion is reported in the second column. The third and fourth columns contain the number of binders and non-binders, respectively. The fifth column describes class I and class II SH3 domains, with the corresponding proportions of binders and non-binders listed in the last two columns, respectively. The latter information characterizes the domain-specific datasets used to train and test the corresponding domain-specific neural networks. The percentage of binders (3rd and 6th columns) highlights the critical unbalancing and attains acceptable levels only in the two class-specific datasets and in three class II domains in the domain-specific datasets.

From: A neural strategy for the inference of SH3 domain-peptide interaction specificity

Class Number of Peptides Number of Binders Number of Non-binders SH3 Domain Number of Binders (%) Number of Non-binders (%)
I 672 88 (13.1%) 584 (86.9%) Rvs167 19 (2.8%) 653 (97.2%)
     Yfr024c 25 (3.7%) 647 (96.3%)
     Ysc84 12 (1.8%) 660 (98.2%)
     Boi1 15 (2.2%) 657 (97.8%)
     Sho1 37 (5.5%) 635 (94.5%)
     Myo5 35 (5.2%) 637 (94.8%)
II 707 131 (18.5%) 576 (81.5%) Rvs167 44 (6.2%) 663 (93.8%)
     Yfr024c 123 (17.4%) 584 (82.6%)
     Ysc84 67 (9.5%) 640 (90.5%)
     Boi1 16 (2.4%) 691 (97.6%)
     Boi2 6 (0.8%) 701 (99.2%)