Machine learning approaches for predicting craniofacial anomalies with graph neural networks

Abstract

This study explores the use of machine learning algorithms, including traditional approaches and graph neural networks (GNNs), to predict certain diseases by analyzing protein–protein interactions. Protein–protein interactions (PPIs) are complex, multifaceted, and sometimes ever-changing. Therefore, analyzing PPIs and making predictions based on them present significant challenges to traditional computational techniques. However, machine learning, particularly GNNs, with their powerful ability to identify complex patterns within large, convoluted datasets, emerge as compelling and revolutionary tools for unraveling these intricate biological networks. We apply machine learning, aided by SHAP explainability and GNNs, on three networks of distinct sizes, ranging from small to large. While the ML results highlight the higher importance of network features in prediction, GNNs exhibit superior accuracy.