Machine Learning Identifies Robust Matrisome Markers and Regulatory Mechanisms in Cancer

Abstract

The expression and regulation of matrisome genes-the ensemble of extracellular matrix, ECM, ECM-associated proteins and regulators as well as cytokines, chemokines and growth factors-is of paramount importance for many biological processes and signals within the tumor microenvironment. The availability of large and diverse multi-omics data enables mapping and understanding of the regulatory circuitry governing the tumor matrisome to an unprecedented level, though such a volume of information requires robust approaches to data analysis and integration. In this study, we show that combining Pan-Cancer expression data from The Cancer Genome Atlas (TCGA) with genomics, epigenomics and microenvironmental features from TCGA and other sources enables the identification of "landmark" matrisome genes and machine learning-based reconstruction of their regulatory networks in 74 clinical and molecular subtypes of human cancers and approx. 6700 patients. These results, enriched for prognostic genes and cross-validated markers at the protein level, unravel the role of genetic and epigenetic programs in governing the tumor matrisome and allow the prioritization of tumor-specific matrisome genes (and their regulators) for the development of novel therapeutic approaches.

Keywords: big data; bioinformatics; cancer; extracellular matrix; matrisome; regulatory networks.

Figure A1

Patterns of staining, intensity, quantity and location, as well as examples, of COL19A1 in Head and Neck Squamous Cell Carcinoma (HNSC) and LGALS4 in STAD. Snapshots from The Human Protein Atlas (THPA, www.proteinatlas.org).

Figure 1

Landmark matrisome gene and regulators. (a) Pipeline for the identification of tumor subtype-specific (“landmark”) matrisome genes and their regulators; (b) % abundance of core and matrisome associated as well as collagens, extracellular matrix moieties (ECM)-affiliated proteins, ECM glycoproteins, ECM regulators, proteoglycans and secreted factors in landmark genes; (c) % abundance of interactions impinging on collagens, ECM-affiliated proteins, ECM glycoproteins, ECM regulators, proteoglycans and secreted factors, by tumor type.

Figure 2

Distribution (%) of different classes of regulators (gene programs, transcription factors, miRNAs and stromal/immune content) for the landmark matrisome genes in the different tumor subtypes.

Figure 3

Prognostic landmark matrisome genes. Only age-independent prognostic genes (p value < 0.05, COX-proportional hazard model adjusted for age) are reported.