For virtually every patient with colorectal cancer (CRC), hematoxylin–eosin (HE)–stained tissue slides are available. These images contain quantitative information, which is not routinely used to objectively extract prognostic biomarkers. In the present study, we investigated whether deep convolutional neural networks (CNNs) can extract prognosticators directly from these widely available images. We hand-delineated single-tissue regions in 86 CRC tissue slides, yielding more than 100,000 HE image patches, and used these to train a CNN by transfer learning, reaching a nine-class accuracy of >94% in an independent data set of 7,180 images from 25 CRC patients. With this tool, we performed automated tissue decomposition of representative multitissue HE images from 862 HE slides in 500 stage I–IV CRC patients in the The Cancer Genome Atlas (TCGA) cohort, a large international multicenter collection of CRC tissue. Based on the output neuron activations in the CNN, we calculated a “deep stroma score,” which was an independent prognostic factor for overall survival (OS) in a multivariable Cox proportional hazard model (hazard ratio [HR] with 95% confidence interval [CI]: 1.99 [1.27–3.12], p = 0.0028), while in the same cohort, manual quantification of stromal areas and a gene expression signature of cancer-associated fibroblasts (CAFs) were only prognostic in specific tumor stages. We validated these findings in an independent cohort of 409 stage I–IV CRC patients from the “Darmkrebs: Chancen der Verhütung durch Screening” (DACHS) study who were recruited between 2003 and 2007 in multiple institutions in Germany. Again, the score was an independent prognostic factor for OS (HR 1.63 [1.14–2.33], p = 0.008), CRC-specific OS (HR 2.29 [1.5–3.48], p = 0.0004), and relapse-free survival (RFS; HR 1.92 [1.34–2.76], p = 0.0004). A prospective validation is required before this biomarker can be implemented in clinical workflows. In our retrospective study, we show that a CNN can assess the human tumor microenvironment and predict prognosis directly from histopathological images.

Multi-omics experiments at bulk or single-cell resolution facilitate the discovery of hypothesis-generating biomarkers for predicting response to therapy, as well as aid in uncovering mechanistic insights into cellular and microenvironmental processes. Many methods for data integration have been developed for the identification of key elements that explain or predict disease risk or other biological outcomes. The heterogeneous graph representation of multi-omics data provides an advantage for discerning patterns suitable for predictive/exploratory analysis, thus permitting the modeling of complex relationships. Graph-based approaches—including graph neural networks—potentially offer a reliable methodological toolset that can provide a tangible alternative to scientists and clinicians that seek ideas and implementation strategies in the integrated analysis of their omics sets for biomedical research. Graph-based workflows continue to push the limits of the technological envelope, and this perspective provides a focused literature review of research articles in which graph machine learning is utilized for integrated multi-omics data analyses, with several examples that demonstrate the effectiveness of graph-based approaches.

Objective: Bone morphogenetic protein (BMP)-9, a member of the transforming growth factor-β family of cytokines, is constitutively produced in the liver. Systemic levels act on many organs and tissues including bone and endothelium, but little is known about its hepatic functions in health and disease. Design: Levels of BMP-9 and its receptors were analysed in primary liver cells. Direct effects of BMP-9 on hepatic stellate cells (HSCs) and hepatocytes were studied in vitro, and the role of BMP-9 was examined in acute and chronic liver injury models in mice. Results: Quiescent and activated HSCs were identified as major BMP-9 producing liver cell type. BMP-9 stimulation of cultured hepatocytes inhibited proliferation, epithelial to mesenchymal transition and preserved expression of important metabolic enzymes such as cytochrome P450. Acute liver injury caused by partial hepatectomy or single injections of carbon tetrachloride (CCl₄) or lipopolysaccharide (LPS) into mice resulted in transient downregulation of hepatic BMP-9 mRNA expression. Correspondingly, LPS stimulation led to downregulation of BMP-9 expression in cultured HSCs. Application of BMP-9 after partial hepatectomy significantly enhanced liver damage and disturbed the proliferative response. Chronic liver damage in BMP-9-deficient mice or in mice adenovirally overexpressing the selective BMP-9 antagonist activin-like kinase 1-Fc resulted in reduced deposition of collagen and subsequent fibrosis. Conclusions: Constitutive expression of low levels of BMP-9 stabilises hepatocyte function in the healthy liver. Upon HSC activation, endogenous BMP-9 levels increase in vitro and in vivo and high levels of BMP-9 cause enhanced damage upon acute or chronic injury.