Expression-based Drug Prioritization |
|
This module incorporates predictive modeling of cancer drugs using expression of genes. Among two kinds of models, the first model (based on whole transcriptome and better performances of models) requires expression of all the genes present in genome , while second model (based on top 50 correlated genes) requires limited number of genes with limited performance of models. The expression-based models based on whole transcriptome performed best among all other features in our study, providing even better prioritization of cancer drugs.
This tool requires mRNA expression data on Affymetrix Human Genome U133 Plus 2.0 arrays with background correction done by RMA (Robust Multichip Average) and quantile normalization (as described in CCLE database). For more information see HELP page. |
| Models-based on whole transcriptome Models-based on top 50 correlated genes | |||||