Re-training

The Re-training algorithm can predict the risk of relapse (survival) for a breast cancer patient. It derives and employs an optimized personalized classifier for each case by using only the molecularly most similar subset of training samples for predictor building. It also computes ER and HER2 status.

Input

A pre-selected .CEL file with clinical data will be loaded for the analysis. You do not need to set any of the above parameters.

sth

Note: you must have a PDF reader installed to view the generated report.

Quick user guide

Click the PDF to open a short explanation of the report generated by the Re-training algorithm (PDF file):

How to cite the dynamic re-training algorithm

Dynamic classification using case-specific training cohorts outperforms static gene expression signatures in breast cancer, Int J Cancer (2015). Read it here.

Latest news

2022. June 16.: The server computer was replaced by a new and faster machine.

2020. Jan. 2.: Precomputed table for the Metabric study has been added to the download page.

2018.Sept.19.: Precomputed tables for GSE datasets with RS scores are now available to download.