Gene Network Cancer Prediction Method Based on Multi-group Algorithm
Multi-group-based identification of cancer markers is of great significance to the study of cancer molecular mechanisms, but most of the current work is based on protein-protein interaction data. Therefore, a novel approach based on multi-gene regulatory network and multi-group data is proposed to analyze the molecular mechanisms of cancer and predict biomarkers. Firstly, this method integrates multi-group data, and takes gastric cancer and esophageal cancer as examples to construct cancer-specific networks of gastric cancer and esophageal cancer respectively. Then, weighted co-expression network analysis is carried out on these two networks, and hierarchical clustering module is used to calculate the relationship between the first principal component of the module and all known cancer markers. Finally, cancer-specific modules are screened out. Then, disease-specific biological pathways were extracted and potential cancer markers were identified by similarity assessment. The experimental results show that the specific modules predicted by this method have functional characteristics, and the result of prediction using the correlation coefficient method in the module is more accurate.
KeywordsCancer Gene Co-expression Network Gene expression regulation Multigroup data
This work was supported by grants from The National Natural Science Foundation of China (No. 61862056), the Guangxi Natural Science Foundation (No. 2017GXNSFAA198148) foundation of Wuzhou University (No. 2017B001), Guangxi Colleges and Universities Key Laboratory of Professional Software Technology, Wuzhou University.
- 2.Engelward, B., Ngo, L.P., Swartz, C., et al.: High throughput microarray technology for genotoxicity and cytotoxicity. Environ. Mol. Mutagen. 60, 37 (2019)Google Scholar