Stratifying cancer patients based on multiple kernel learning and dimensionality reduction
Thanh Trung Giang, Thanh Phương Nguyễn, Dang Hung Tran · 2017
In the cancer research, a number of stratification methods have been successfully applied and have assisted in the treatment process. Currently, various data types related to the cancer patients have been measured and collected. This fact leads to a great need of data integration for obtaining more comprehensive cancer study. Most of the previous work is based on a single data type and employed a tailor-made method for a specific data type. In this paper, we have proposed an efficient approach, using multiple kernel learning methods, to better stratify cancer patients. We integrated the three most related-cancer data, including gene expression, DNA methylation, and miRNA expression. The model has combined multiple kernel learning methods and dimensionality reduction. The achieved results demonstrated that our integrative model was more accurate than the ones based on single data type. Our work holds a great promise to contribute to theoretical cancer research and effectively support the prevention and prognosis.