Leaderboard Now Open: CPTAC’s DREAM Proteogenomics Computational Challenge

The National Cancer Institute’s Clinical Proteomic Tumor Analysis Consortium (CPTAC) is pleased to announce the opening of the leaderboard to its Proteogenomics Computational DREAM Challenge. The leadership board remains open for submissions during September 25, 2017 through October 8, 2017, with the Challenge expected to run until November 17, 2017.

DREAMing of Better Solutions
The aim of the CPTAC DREAM Proteogenomics Computational Challenge is to encourage the next generation of computational methods for extracting information from cancer proteomes and linking those data to genomic and transcriptomic information.  This is encouraged by focusing a community of experts on a specific problem for a limited time, work that might take several years in a single lab, and asking whether it could be done by the crowd (crowdsourcing) in several months.

The science goal is to predict proteomic and phosphoproteomic data from multiple other data types.  Method performance will be blindly evaluated using a previously unseen validation dataset generated by CPTAC.  Open competitions allow participants to see which schemes work and which do not.  While researchers won’t know the true impact of DREAM algorithms for a while, these competitions encourage cross-disciplinary researchers from around the world to work together on a common problem.

While the CPTAC DREAM Proteogenomics Computational Challenge already has more than 400 registered participants spanning 20 countries, representative of 6 continents, it is not too late to join!  Nature Methods supports the submission of an overview paper describing the "NCI-CPTAC DREAM Proteogenomics Computational Challenge" and broadly applicable insights that emerge from it, while NVIDIA Foundation is providing a $25,000 contribution for a cash award.

For information on the DREAM Challenge, click here.

For details on how to submit trained models, click here.

For Challenge timelines, click here.