Genotype-Phenotype Integration through Machine Learning and Personalized Gene Regulatory Networks for Cancer Metastasis Prediction

TL;DR

This study develops an integrated machine learning framework combining classical models and graph neural networks to improve personalized prediction of cancer metastasis by leveraging gene expression and regulatory network data.

Contribution

It introduces a novel approach that combines traditional ML with graph neural networks and patient-specific regulatory networks for metastasis prediction.

Findings

XGBoost achieved AUROC of 0.7051

GNN captured non-linear regulatory dependencies

Framework enables scalable, interpretable metastasis risk prediction

Abstract

Metastasis is the leading cause of cancer-related mortality, yet most predictive models rely on shallow architectures and neglect patient-specific regulatory mechanisms. Here, we integrate classical machine learning and deep learning to predict metastatic potential across multiple cancer types. Gene expression profiles from the Cancer Cell Line Encyclopedia were combined with a transcription factor-target prior from DoRothEA, focusing on nine metastasis-associated regulators. After selecting differential genes using the Kruskal-Wallis test, ElasticNet, Random Forest, and XGBoost models were trained for benchmarking. Personalized gene regulatory networks were then constructed using PANDA and LIONESS and analyzed through a graph attention neural network (GATv2) to learn topological and expression-based representations. While XGBoost achieved the highest AUROC (0.7051), the GNN captured non-linear regulatory dependencies at the patient level. These results demonstrate that combining traditional machine learning with graph-based deep learning enables a scalable and interpretable framework for metastasis risk prediction in precision oncology.