A machine learning based Glioblastoma Survival Predictor
Glioblastoma (GBM) is a very aggressive malignant brain tumor with the vast majority of patients surviving less than 12 months (Short-term survivors [STS]). Only around 2% of patients survive more than 36 months (Long-term survivors [LTS]). GlioSurvML is a machine learning classifier built to predict the survival group of glioblastoma patients based on transcriptomics. Please refer to the publication for more details here.
The current web tool includes 2 ML classifiers
- based on gene expression profiles
- based on gene expression profiles along with “age at diagnosis (in yrs)” information
- The method needs RMA normalized and log2 transformed gene expression profiles of Affymetrix microarray platform
- Table must contain Samples as columns and gene symbols as rows. The sample input files are given.
- The “age at diagnosis” information is read as years.
At present, the classifier is built for Affymetrix U133 plus 2 array data. The classifier for RNA-seq data will be developed and updated in the future.