This repository contains datasets of selected paralog pairs (Ensembl 111), labeled with various "common function" annotations, including PPI, SL, and GO datasets for both human (Homo sapiens) and budding yeast (Saccharomyces cerevisiae). These paralog pairs are characterized using different sequence similarity features, such as AlphaFold-predicted structures, Protein Language Model embeddings, and similarity searches from various databases. These datasets are used in the following manuscript: Evaluating Sequence and Structural Similarity Metrics for Predicting Shared Paralog Functions For the corresponding analysis notebooks, see: github.com/cancergenetics/paralog_seq_similarity/