PlantMetWiki Full Dataset: 421-species enzyme-reaction graph with node embeddings and link-prediction splits

The complete PlantMetWiki plant-metabolism knowledge graph (421 plant species), prepared for heterogeneous-graph link prediction. Task: predict (Protein, catalyzes, Interaction) edges ("this enzyme catalyses this reaction"), where the destination is always a Conversion-subtype node (the reaction itself). Three complementary train/val/test split strategies are included: a random 80/10/10 split, an organism-held-out split (tests cross-species generalisation), and a pathway-held-out split (tests generalisation to unseen biological contexts). Includes pre-computed node embeddings, already attached to the PyTorch Geometric HeteroData object as node features: 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, coverage numbers, and loading code, and LICENSE.md for provenance of each embedding's source sequences. v2 change: the target edge's destination now always collapses through the reified Catalysis node directly to the Conversion node it controls (Protein -> Catalysis -> Conversion, collapsed to Protein -> Conversion) rather than stopping at the Catalysis instance record -- every Catalysis node has exactly one Protein and one Conversion neighbour, so this loses nothing but a handful of exact-duplicate pairs, and brings reaction chemistry one hop closer to Protein for message-passing models. All three split files were rebuilt against this redefinition; v1's splits targeted the Catalysis instance node instead. This version also bundles training/fulldata_baseline_common.py and training/fulldata_baseline_train.py (the HeteroConv-SAGE baseline that uses this target edge) as standalone reference code under README.md's changelog. See the README's Changelog section for details. This is the full-graph counterpart of the 2-species Learnathon subset (10.5281/zenodo.20736061) — same task and file format, complete species coverage instead of an A. thaliana / G. max slice.