Search

Precise prognosis of cancer patients is important because it is associated with suggesting appropriate therapeutic strategies. Several computational and statistical methods have been proposed, but further improvement of these methods in terms of prediction accuracy is required. This paper presents a deep learning-based method for learning networks of prognostic genes, instead of only individual biomarker genes, for more accurate cancer prognosis prediction. This method utilizes generative adversarial networks, where the generator uses a biological network instead of a traditional fully connected network to learn the distributions of gene expression (mRNA), copy number variation, single nucleotide polymorphism, and DNA methylation data from cancer patients. The proposed model was applied to seven cancer types and exhibited higher prediction accuracy as compared to the existing state-of-the-art methods. On average, the area under the curve (AUC) was improved by 4% compared to the best performing existing methods for seven cancer types. In particular, for pancreatic adenocarcinoma, AUC was improved by 27.9%. The identified prognostic genes were reproducible and functionally meaningful. To the best of our knowledge, the proposed method represents the first attempt to learn genetic networks from multi-omics data.

Background and objectives: The present study aimed to evaluate the clinicopathological significance and prognostic implications of REG4 immunohistochemical expression in colorectal cancer (CRC). Materials and Methods: We performed immunohistochemical analysis for REG4 cytoplasmic expression in 266 human CRC tissues. Correlations between REG4 expression, clinicopathological characteristics, and survival were investigated in CRC. Results: REG4 was expressed in 84 of 266 CRC tissues (31.6%). REG4 expression was significantly more frequent in the right colon than that in the left colon and rectum (p = 0.002). However, we observed no significant correlation between REG4 expression and other clinicopathological parameters. REG4 expression was significantly higher in CRCs with low stroma than in those with high stroma (p = 0.006). In addition, REG4 was more frequently expressed in CRCs with the mucinous component than in those without it (p < 0.001). There was no significant correlation between REG4 expression and overall recurrence-free survival (p = 0.132 and p = 0.480, respectively). Patients with REG4 expression showed worse overall and recurrence-free survival in the high-stroma subgroup (p = 0.001 and p = 0.017, respectively), but no such correlation was seen in the low stroma subgroup (p = 0.232 and p = 0.575, respectively). Conclusions: REG4 expression was significantly correlated with tumor location, amount of stroma, and mucinous component in CRCs. In patients with high stroma, REG4 expression was significantly correlated with poor overall and recurrence-free survival.