Event Embedding of Protein Networks : Compositional Learning of Biological Function

TL;DR

This paper introduces Event2Vec, a compositional sequence embedding model for protein networks, demonstrating significant improvements in pathway coherence and functional analogy accuracy over baseline methods.

Contribution

The work presents a novel additive sequence embedding model that enforces compositional structure, enhancing relational reasoning in biological network embeddings.

Findings

Pathway coherence improved 30.2× over random

Functional analogy accuracy increased to 0.966

Hierarchical pathway organization was enhanced

Abstract

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.