Successful treatment of cancer is still a challenge and this is partly due to a wide heterogeneity of cancer composition across patient population. Unfortunately, accounting for such heterogeneity is very difficult. Clinical evaluation of tumor heterogeneity often requires the expertise of anatomical pathologists and radiologists.
This challenge is dedicated to the quantification of intra-tumor heterogeneity using appropriate statistical methods on cancer omics data.
In particular, it focuses on estimating cell types and proportion in biological samples based on averaged DNA methylation and full patient history. The goal is to explore various statistical methods for source separation/deconvolution analysis (Non-negative Matrix Factorization, Surrogate Variable Analysis, Principal component Analysis, Latent Factor Models, …).
[1] Go on the challenge page, in the Learn the details
tab, in the get_starting_kit
item and download the starting kit by clicking the Starting Kit
button.
[2] On your local machine, unzip the just downloaded zip file stating_kit.zip
and open R in the unziped strating_kit
directory, (e.g. open strating_kit.Rmd
with RStudio).
The unziped strating-kit directory contains:
data.rds
file containing the data.starting_kit.Rmd
corresponding to the vignette of the Challenge (all useful information can be found here).submission_script.Rmd
to modify and to use to submit your predictions.[3] In the R console launch the following command:
rmarkdown::render("starting_kit.Rmd")
Now, let’s submit your prediction (zip file) in the Participate
tab of the codalab challenge.
The discriminating metric will be computed on the A matrix: mean absolute error between the estimate and the groundtruth.
Download | Size (mb) | Phase |
---|---|---|
Starting Kit | 44.163 | #1 Exploration |
Start: July 22, 2019, midnight
Aug. 23, 2019, 2 p.m.
You must be logged in to participate in competitions.
Sign In