Winners Announced for Crowdsourcing and Data Sharing Competition to Drive Innovation in Prostate Cancer Research

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 three specific questions posed were to:

• Predict overall survival for prostate cancer patients using clinical data
• Predict the exact time to event 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.

Best performers include Team FIMM-UTU from the University of Turku, Finland, and the University of Helsinki, Finland, for the first question regarding prediction of overall survival; and Yuanfang Guan from the University of Michigan for the second question regarding prediction of treatment discontinuation.

“The DREAM Challenge was rewarding in that it enabled us to participate in a collaborative project in which researchers from multiple institutes worked together and compared findings with other teams,” said Tero Aittokallio, member of Team FIMM-UTU. “The most rewarding part however will be to see how our findings will eventually help patients with metastatic castrate resistant prostate cancer.”

Challenge winners and 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. A formal announcement of the winners will be made at the Prostate Cancer Foundation’s 22nd Annual Scientific Retreat in Washington, D.C., in October. 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 to F1000Research, an open science publishing platform, where the models can be reviewed.

"More than 550 researchers from around the world accessed the data over the course of the Challenge,” said Dr. James Costello, University of Colorado Anschutz Medical Campus. “Without the efforts from Project Data Sphere, LLC, Sage Bionetworks with the support and experience of the DREAM Challenges Initiative, and our clinical trial collaborators, these data would have been difficult to access and even harder to use. Project Data Sphere, LLC performed a great deal of data curation to make the clinical variates readily accessible."

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 Sphere platform (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.¹ For 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.

About the Project Data Sphere Initiative

Project Data Sphere, LLC, an independent, not-for-profit initiative of the CEO Roundtable on Cancer's Life Sciences Consortium (LSC), operates the Project Data Sphere® platform (www.ProjectDataSphere.org). Launched in April 2014, the Project Data Sphere platform provides one place where the cancer community can broadly share, integrate, analyze and discuss historical patient-level comparator arm data sets (historical patient-level cancer phase III) from multiple providers, with the goal of advancing research. With its broad-access approach, the initiative brings diverse minds and technology together to help unleash the full potential of existing clinical trial data and speed innovation by generating collective insights that may lead to improved trial design, disease modeling and beyond. The platform currently contains 27,600 patient lives of data; 9,400 of those are across a wide spectrum of prostate cancer populations. In order to ensure that researchers can realize the full potential of this data, PDS teamed with CEO Roundtable on Cancer Member, SAS Institute Inc. SAS, a leader in data and health analytics, developed and hosts the site and provides free state-of-the-art analytic tools to authorized users within the Project Data Sphere environment.

About Sage Bionetworks

Sage Bionetworks is a nonprofit biomedical research organization, founded in 2009, with a vision to promote innovations in personalized medicine by enabling a community-based approach to scientific inquiries and discoveries. Sage Bionetworks strives to activate patients and to incentivize scientists, funders and researchers to work in fundamentally new ways in order to shape research, accelerate access to knowledge and transform human health. It is located on the campus of the Fred Hutchinson Cancer Research Center in Seattle, Washington and is supported through a portfolio of philanthropic donations, competitive research grants, and commercial partnerships. More information is available at www.sagebase.org.

About the DREAM Challenges Initiative

Founded in 2006 by A. Califano (Columbia University) and Gustavo Stolovitzky (IBM Research) the Dialogue on Reverse Engineering Assessment and Methods (DREAM) Challenges Initiative poses fundamental questions about systems biology and translational medicine. Designed and run by a community of researchers from a variety of organizations, the DREAM challenges invite participants to propose solutions — fostering collaboration and building communities in the process. Expertise and institutional support are provided by Sage Bionetworks, along with the infrastructure to host challenges via their Synapse platform. Together, the leaders of the DREAM Challenges Initiative share a vision allowing individuals and groups to collaborate openly so that the “wisdom of the crowd” provides the greatest impact on science and human health. More information is available at: http://dreamchallenges.org/.

¹ American Cancer Society. What are the key statistics about prostate cancer?

² Crawford ED. Hormonal therapy in prostate cancer: Historical approaches. Rev Urol 2004; 6(Suppl 7):S3- S11.