Biological Pathway Informed Models with Graph Attention Networks (GATs)
By: Gavin Wong , Ping Shu Ho , Ivan Au Yeung and more
Potential Business Impact:
Finds hidden gene connections to predict how cells change.
Biological pathways map gene-gene interactions that govern all human processes. Despite their importance, most ML models treat genes as unstructured tokens, discarding known pathway structure. The latest pathway-informed models capture pathway-pathway interactions, but still treat each pathway as a "bag of genes" via MLPs, discarding its topology and gene-gene interactions. We propose a Graph Attention Network (GAT) framework that models pathways at the gene level. We show that GATs generalize much better than MLPs, achieving an 81% reduction in MSE when predicting pathway dynamics under unseen treatment conditions. We further validate the correctness of our biological prior by encoding drug mechanisms via edge interventions, boosting model robustness. Finally, we show that our GAT model is able to correctly rediscover all five gene-gene interactions in the canonical TP53-MDM2-MDM4 feedback loop from raw time-series mRNA data, demonstrating potential to generate novel biological hypotheses directly from experimental data.
Similar Papers
Beyond Attention: Learning Spatio-Temporal Dynamics with Emergent Interpretable Topologies
Machine Learning (CS)
Predicts future events better and faster.
GSAT: Graph Structure Attention Networks
Machine Learning (CS)
Helps computers understand complex data patterns better.
LightTopoGAT: Enhancing Graph Attention Networks with Topological Features for Efficient Graph Classification
Machine Learning (CS)
Makes computer "brains" understand pictures better.