Evaluating Sequence and Structural Similarity Metrics for Predicting Shared Paralog Functions

Abstract

Gene duplication is the primary source of new genes, resulting in most genes having identifiable paralogs. Over evolutionary time scales, paralog pairs may diverge in some respects but many retain the ability to perform the same functional role. Protein sequence identity is often used as a proxy for functional similarity and can predict shared functions between paralogs as revealed by synthetic lethal experiments. However, the advent of alternative protein representations, including embeddings from protein language models (PLMs) and predicted structures from AlphaFold, raises the possibility that alternative similarity metrics could better capture functional similarity between paralogs. Here, using two species (budding yeast and human) and two different definitions of shared functionality (shared protein-protein interactions, synthetic lethality) we evaluated a variety of alternative similarity metrics. For some tasks, predicted structural similarity or PLM embedding similarity outperform sequence identity, but more importantly these similarity metrics are not redundant with sequence identity, i.e. combining them with sequence identity leads to improved predictions of shared functionality. By adding contextual features, representing similarity to homologous proteins within and across species, we can significantly enhance our predictions of shared paralog functionality. Overall, our results suggest that alternative similarity metrics capture complementary aspects of functional similarity beyond sequence identity alone. GRAPHICAL ABSTRACT O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=156 SRC="FIGDIR/small/617835v1_ufig1.gif" ALT="Figure 1"> View larger version (35K): org.highwire.dtl.DTLVardef@21ed4org.highwire.dtl.DTLVardef@136184eorg.highwire.dtl.DTLVardef@75e0e5org.highwire.dtl.DTLVardef@1001932_HPS_FORMAT_FIGEXP M_FIG C_FIG