Global Pan-cancer serum miRNA classifier across 13 cancer types: Analysis of 46,349 clinical samples

This repository contains the data and results from the paper,  "Global Pan-cancer serum miRNA classifier across 13 cancer types: Analysis of 46,349 clinical samples".

The fully reproducible analysis code using the data and producing the results included in this repository is provided in miRBiTExplorer.  The overall results and the expression of  miRNAs in each samples and the combination of binary rules for the highly expressed miRNAs can be interactively visualised and explored in the Shiny App miRBitExplorer. 

Content

This repository contains the data stored in the pancancermirnadata.zip file that contains data stored in four folders namely:

1. train - all the files needed to run the script to train pan-cancer serum classifier.

2. test - all the files needed to run the script to test the pan-cancer serum classifier performance.

3. validation - all the files needed to run the script to validate the pan-cancer serum classifier in the non_cancer and other disease samples.

4. neo- all the files needed to run the script to compare the results when the benign samples are categorized under "non_cancer" and when benign samples are categorized under "cancer/benign" group.

All the codes that are associated with reproducing the results with the data is deposited in the Github Link.