Summary

The data preparation pipeline contains tasks for two distinct scenarios: leukaemia that contains microarray data for 119 patients and ovarian cancer that contains next generation sequencing data for 380 patients.

The disease outcome prediction pipeline offers two strategies for this task:

Graph kernel method: It starts generating personalized networks for ...

Summary

This pipeline contains the following functions: (1) Data processing to handle the tansformations needed to obtain the original pathway scores of the samples according to single sample analysis GSEA (2) Model training based on the disease and healthy sample pathway scores, to classify them (3) Scoring matrix weights optimization according to a gold standard list of drugs (those that went on clinical trials or are approved for the disease).It tests the weights in a range of 0 to 30 (you ...