Extended Data Fig. 6: Comparison of PLM embedding similarity and sequence identity for PHROG VPFs.
From: Large language models improve annotation of prokaryotic viral proteins
(a) The intra-family pairwise sequence embedding similarity, measured using cosine similarity, and sequence identity, measured using global alignment identity, were calculated for all annotated PHROG VPFs. Families are colored by functional category annotation. Solid line represents a linear regression for each function with shading representing a 95% bootstrapped confidence interval for the regression estimation. (b) Linear regression results for each category. R-value is measured using Pearson correlation coefficient. P-value is calculated using the Wald Test.
