Matrix factorization and deconvolution methods to quantify tumor heterogeneity in cancer research
MEDINFO-HADACA Cancer Heterogeneity challenge
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.
The MEDINFO-HADACA Cancer Heterogeneity challenge is an online data challenge 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 (in silico simulations) 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, ...). Participants should be aware of several pitfalls when analyzing omics data (large datasets, missing data, confounding factors…).
The challenge is hosted on the Codalab platform. It will last from 2019 July 23th to 2019 August 23h. The challenge is open to everyone (including MEDINFO participants). Although not mandatory, we encourage participants to be part of a team.
Register on the platform and become a MEDINFO-HADACA challenger here.
A MEDINFO Cancer Heterogeneity session will be organized at MEDINFO 2019 on Tuesday 27th August at 2:10pm. It will be composed of a challenge results restitution, and an open discussion on data challenges and open science in Healthcare.