CARY, N.C.–(BUSINESS WIRE)–Winners of the Prostate Cancer DREAM Challenge were formally recognized at the Prostate Cancer Foundation’s 22nd Annual Scientific Retreat, October 8-10, in Washington, D.C. The Prostate Cancer DREAM Challenge is the first research challenge in prostate cancer to marry crowdsourcing with data sharing, paving a new way to tackle key research questions about metastatic castration-resistant prostate cancer (mCRPC), an advanced form of the disease with poor outcomes.
“Prostate Cancer DREAM Challenge participants produced first-class work in an incredibly competitive landscape,” said Dr. Howard Soule, Chief Science Officer, Prostate Cancer Foundation. “The findings of the best performers could impact trial design by addressing the historical challenge of clinical trials to define their inclusion/exclusion criteria.”
The Challenge called upon the cancer research and computational biology community to find solutions to key open clinical research questions about mCRPC and explore innovative research and modeling approaches. The two specific questions posed were to:
- Predict overall survival for prostate cancer patients using clinical data
- Predict treatment discontinuation for prostate cancer patients treated with docetaxel
This challenge produced unprecedented levels of participation, with more than 550 registrants, comprising more than 60 teams. Three rounds of leaderboard scoring allowed teams to submit up to five predictions per round; in total, nearly 1,200 model predictions and almost 160 final submissions were received across two sub-challenges.
A total of 11 teams were selected as winners between the two sub-challenges. Team FIMM-UTU from the University of Turku, Finland, and the University of Helsinki, Finland, was the best performing team for the first sub-challenge regarding prediction of overall survival; the best performing teams for the second sub-challenge regarding prediction of treatment discontinuation came from a variety of departments at universities across Japan, Canada, the United States and Europe.
“The Prostate Cancer DREAM Challenge attracted a substantial number of participants to address specialized questions in prostate cancer research,” said Dr. Oliver Sartor, Laborde Professor of Cancer Research, Medicine and Urology Departments, Tulane University School of Medicine. “The best performing teams developed very credible methodologies that could have implications for moving beyond overall survival as an endpoint for prostate cancer studies.”
Complete results can be found on the Prostate Cancer DREAM Challenge homepage. The winners will be invited to co-author a Challenge overview paper that will be submitted for peer review to Nature Biotechnology. Winners will also each receive a share of an educational award from Project Data Sphere, LLC, sponsored by AstraZeneca. Also, top performers will be invited to present their team’s winning method at the RECOMB/ISCB Regulatory and Systems Genomics/DREAM Conference in Philadelphia, Pa., in November. Finally, solvers will be able to submit write-ups on their models toF1000Research, an open science publishing platform, where the models can be reviewed.
Data for the Challenge was standardized and integrated from four different, de-identified clinical trials with more than 2,000 mCRPC patients treated with first-line docetaxel. The data sets were provided to Project Data Sphere, LLC by AstraZeneca, Celgene, Memorial Sloan Kettering Cancer Center and Sanofi US.
Project Data Sphere, LLC, and Sage Bionetworks with the support and experience of the DREAM Challenges Initiative, came together to make the Challenge possible. Utilizing multiple clinical trial data sets from the Project Data Sphereplatform (www.ProjectDataSphere.org), the Challenge was hosted on Synapse (https://www.synapse.org), Sage Bionetworks’ open compute platform that allowed data to be worked on interactively by Challenge participants, as individuals or as teams.
Prostate cancer is the most common cancer among men, with approximately 233,000 new diagnoses in 2014 in the U.S.1For patients whose disease has spread (metastasized), survival rates are often poor due to the loss of efficacy of hormonal therapy, which has been the standard of care treatment of prostate cancer for more than 70 years2.