Improving Disease Comorbidity Prediction Based on Human Interactome with Biologically Supervised Graph Embedding

TL;DR

This paper introduces Biologically Supervised Graph Embedding (BSE), a novel method that significantly improves disease comorbidity prediction accuracy by selecting biologically relevant features from the human interactome, outperforming existing techniques.

Contribution

The study presents BSE, a new biologically supervised graph embedding approach that enhances feature selection and prediction accuracy for disease comorbidity using the human interactome.

Findings

BSE improves prediction accuracy up to 50% in ROC metrics.

BSE enhances the biological relevance of selected features.

Statistically significant improvements across multiple metrics.

Abstract

Comorbidity carries significant implications for disease understanding and management. The genetic causes for comorbidity often trace back to mutations occurred either in the same gene associated with two diseases or in different genes associated with different diseases respectively but coming into connection via protein-protein interactions. Therefore, human interactome has been used in more sophisticated study of disease comorbidity. Human interactome, as a large incomplete graph, presents its own challenges to extracting useful features for comorbidity prediction. In this work, we introduce a novel approach named Biologically Supervised Graph Embedding (BSE) to allow for selecting most relevant features to enhance the prediction accuracy of comorbid disease pairs. Our investigation into BSE's impact on both centered and uncentered embedding methods showcases its consistent superiority over the state-of-the-art techniques and its adeptness in selecting dimensions enriched with vital biological insights, thereby improving prediction performance significantly, up to 50% when measured by ROC for some variations. Further analysis indicates that BSE consistently and substantially improves the ratio of disease associations to gene connectivity, affirming its potential in uncovering latent biological factors affecting comorbidity. The statistically significant enhancements across diverse metrics underscore BSE's potential to introduce novel avenues for precise disease comorbidity predictions and other potential applications. The GitHub repository containing the source code can be accessed at the following link: https://github.com/xihan-qin/Biologically-Supervised-Graph-Embedding.