Event Embedding of Protein Networks : Compositional Learning of Biological Function
This work addresses the challenge of improving relational and compositional reasoning tasks in biological networks, representing an incremental advancement over existing methods.
The study tackled the problem of whether enforcing compositional structure in sequence embeddings improves geometric organization for protein-protein interaction networks, finding that compositional embeddings substantially improved pathway coherence (30.2× vs 2.9× above random) and functional analogy accuracy (mean similarity 0.966 vs 0.650).
In this work, we study whether enforcing strict compositional structure in sequence embeddings yields meaningful geometric organization when applied to protein-protein interaction networks. Using Event2Vec, an additive sequence embedding model, we train 64-dimensional representations on random walks from the human STRING interactome, and compare against a DeepWalk baseline based on Word2Vec, trained on the same walks. We find that compositional structure substantially improves pathway coherence (30.2$\times$ vs 2.9$\times$ above random), functional analogy accuracy (mean similarity 0.966 vs 0.650), and hierarchical pathway organization, while geometric properties such as norm--degree anticorrelation are shared with or exceeded by the non-compositional baseline. These results indicate that enforced compositionality specifically benefits relational and compositional reasoning tasks in biological networks.