In the field of gliomas research, the broad availability of genetic and image information originated by computer technologies and the booming of biomedical publications has led to the advent of the big-data era. Machine learning methods were applied as possible approaches to speed up the data mining processes. In this article, we reviewed the present situation and future orientations of machine learning application in gliomas within the context of workflows to integrate analysis for precision cancer care. Publicly available tools or algorithms for key machine learning technologies in the literature mining for glioma clinical research were reviewed and compared. Further, the existing solutions of machine learning methods and their limitations in glioma prediction and diagnostics, such as overfitting and class imbalanced, were critically analyzed.
In patients with low-grade gliomas (LGG), the prognosis is significantly favorable in those with 1p/19q codeletion than in those with 1p/19q intact. Although 1p/19q codeletion has emerged as an accepted indicator for molecular typing of gliomas, numerous studies point to the need to further investigate the overall transcriptomic molecular changes associated with it. To explore the genome-wide effects of 1p/19q codeletion, we evaluated multiple omics profiles from The Cancer Genome Atlas LGG cohort. After systematic analysis, we identified a modest number of genomic features, including gene expression (n = 14), protein expression (n = 8), DNA methylation (n = 9), somatic mutation (n = 7) and copy number variation (n = 35). These features were highly corelated with 1p/19q codeletion status of patients. These features are then used to construct support vector machine classifiers and identify survival-related markers. It is helpful from this research to generate fresh insights into the alterations occurring behind the 1p/19q codeletion and to elucidate the mechanisms of LGG histological typing.