Comparison of context-free and contextualized representations in differentiating between binding and nonbinding proteins. The scores are computed using cosine similarity on n = 22 unique protein pairs (2 binding and 20 nonbinding); since PINNACLE generates multiple representations per protein based on context, there are n = 7,956 pairwise computations (180 binding and 7,776 nonbinding) for the contextualized representations. The binding proteins evaluated are PD-1/PD-L1 and B7-1/CTLA-4. Pairwise scores also are calculated for each of these four proteins and proteins that they do not bind with (that is, RalB, RalBP1, EPO, EPOR, C3 and CFH). The gap between the average scores of binding and nonbinding proteins is annotated for context-free and contextualized representations. The significance of the score gaps between binding and nonbinding proteins is measured using a one-sided nonparametric permutation test. The data are represented as mean values with error bars indicating a 95% confidence interval.
