Pattern Detection on Glioblastoma’s Waddington Landscape via Generative Adversarial Networks

Abstract

Glioblastoma (GBM) is a highly morbid and lethal disease with poor prognosis. Their emergent properties such as cellular heterogeneity, therapy resistance, and self-renewal are largely attributed to the interactions between a subset of their population known as glioblastoma-derived stem cells (GSCs) and their microenvironment. Identifying causal patterns in the developmental trajectories between GSCs and the mature, well-differentiated GBM phenotypes remains a challenging problem in oncology. The paper presents a blueprint of complex systems approaches to infer attractor dynamics from the single-cell gene expression datasets of pediatric GBM and adult GSCs. These algorithms include Waddington landscape reconstruction, GANs (Generative Adversarial Networks), and fractal dimension analysis. Here I show, a Rssler-like strange attractor with a fractal dimension of roughly 1.7 emerged in all n = 12 patients’ GAN-reconstructed patterns. The findings suggest a strange attractor may be driving the complex dynamics and adaptive behaviors of GBM in signaling state-space.