Integration of Graph Neural Network and Neural-ODEs for Tumor Dynamic Prediction

TL;DR

This paper introduces a novel approach combining graph neural networks and Neural-ODEs to improve personalized tumor dynamic predictions using multimodal genomics and treatment data, demonstrating significant improvements over existing models.

Contribution

The paper presents a new heterogeneous graph encoder with Neural-ODEs for tumor modeling, effectively integrating multimodal data to enhance prediction accuracy.

Findings

Significantly outperforms empirical tumor models.

Effectively utilizes multimodal data for better predictions.

Shows promise for pre-clinical applications.

Abstract

In anti-cancer drug development, a major scientific challenge is disentangling the complex relationships between high-dimensional genomics data from patient tumor samples, the corresponding tumor's organ of origin, the drug targets associated with given treatments and the resulting treatment response. Furthermore, to realize the aspirations of precision medicine in identifying and adjusting treatments for patients depending on the therapeutic response, there is a need for building tumor dynamic models that can integrate both longitudinal tumor size as well as multimodal, high-content data. In this work, we take a step towards enhancing personalized tumor dynamic predictions by proposing a heterogeneous graph encoder that utilizes a bipartite Graph Convolutional Neural network (GCN) combined with Neural Ordinary Differential Equations (Neural-ODEs). We applied the methodology to a large collection of patient-derived xenograft (PDX) data, spanning a wide variety of treatments (as well as their combinations) on tumors that originated from a number of different organs. We first show that the methodology is able to discover a tumor dynamic model that significantly improves upon an empirical model which is in current use. Additionally, we show that the graph encoder is able to effectively utilize multimodal data to enhance tumor predictions. Our findings indicate that the methodology holds significant promise and offers potential applications in pre-clinical settings.