Studies from Xinjiang University Yield New Information about Cancer (An Integrated Method Based On Wasserstein Distance and Graph for Cancer Subtype Discovery).

A new report from Xinjiang University in Urumqi, People's Republic of China, discusses a comprehensive method for accurately identifying and distinguishing cancer subtypes for treatment. The method, called WVGMO, combines variational autoencoder measured by Wasserstein distance and graph autoencoder with second-order proximity. The researchers conducted extensive experiments on seven different cancers using four omics data from TCGA and found that WVGMO provided equivalent or better results than other advanced synthesis methods. This research has been peer-reviewed and published in IEEE/ACM Transactions on Computational Biology and Bioinformatics. [Extracted from the article]