Machine learning identifies activation of RUNX/AP-1 as drivers of mesenchymal and fibrotic regulatory programs in gastric cancer.

Gastric cancer (GC) is the fifth most common cancer worldwide and is a heterogeneous disease. Among GC subtypes, the mesenchymal phenotype (Mes-like) is more invasive than the epithelial phenotype (Epi-like). While gene expression of the epithelial-to-mesenchymal transition (EMT) has been studied, the regulatory landscape shaping this process is not fully understood. Here we use ATAC-seq and RNA-seq from a compendium of gastric cancer cell lines and primary tumors to detect drivers of regulatory state changes and their transcriptional responses. Using the ATAC-seq, we developed a machine learning approach to determine the transcription factors (TFs) regulating the subtypes of GC. We identified TFs driving the mesenchymal (RUNX2, ZEB1, SNAI2, AP-1 dimer) as well as the epithelial states (GATA4, GATA6, KLF5, HNF4A, FOXA2, GRHL2) in gastric cancer. We identified DNA copy number alterations associated with dysregulation of these TFs, specifically deletion of GATA4 and amplification of MAPK9 Comparisons with bulk and single-cell RNA-seq datasets identified activation toward fibroblast-like epigenomic and expression signatures in Mes-like GC. The activation of this mesenchymal fibrotic program is associated with differentially accessible DNA cis -regulatory elements flanking up-regulated mesenchymal genes. These findings establish a map of TF activity in GC and highlight the role of copy number driven alterations in shaping epigenomic regulatory programs as potential drivers of gastric cancer heterogeneity and progression.