PlantMetWiki Learnathon Subset: A. thaliana / G. max enzyme-reaction graph with node embeddings

A small, self-contained slice of the PlantMetWiki plant-metabolism knowledge graph, prepared for a Learnathon on heterogeneous-graph link prediction. Task: predict (Protein, catalyzes, Interaction) edges ("this enzyme catalyses this reaction") in a two-organism graph — Arabidopsis thaliana (train/val/test) and Glycine max / soybean (held out entirely, for cross-species generalisation evaluation). Includes pre-computed node embeddings: MAP4 binary fingerprints for metabolites, ESM-C (esmc_300m) embeddings for proteins, and PlantCaduceus (l32) DNA embeddings for gene products. See README.md inside the archive for the full file list and loading code, and LICENSE.md for provenance of each embedding's source sequences.