October 2, 2014
  • Question. Collaborate. Contribute.

  • GA4GH/DREAM Workflow Execution Challenge

    GA4GH/DREAM Workflow Execution Challenge

    Launches July 5 (Pre-registration is open)

    The goal of this challenge is to evaluate systems and platforms for executing portable analysis workflows in the interest of developing common standards and best practices. Participants will run high quality genomics workflows in their system of choice to assess portability and reproducibility in a concrete way.

  • Parkinson’s Disease Digital Biomarker DREAM Challenge

    Parkinson’s Disease Digital Biomarker DREAM Challenge

    Launching July 6, 2017 (Pre-registration is open)

    Using data collected through two Parkinson’s Disease mobile research studies, the goal of this challenge is to identify the best methods for processing mobile sensor data in order to distinguish gait and motor differences between Parkinson’s Disease patients and controls.

  • NCI-CPTAC DREAM Proteogenomics Challenge

    NCI-CPTAC DREAM Proteogenomics Challenge

    Launches June 26 (Registration is open)

    This challenge will use public and novel proteogenomic data generated by the Clinical Proteomic Tumor Analysis Consortium (CPTAC) to benchmark an understanding of the interfaces between different layers of information in a population of cancer cells.

  • Multiple Myeloma DREAM Challenge

    Multiple Myeloma DREAM Challenge

    June 30 (Pre-registration is open)

    The Multiple Myeloma DREAM Challenge provides an opportunity to combine integration of large scale molecular and clinical data and state of the art analytical approaches to facilitate risk stratification in over 25,000 patients in the US alone. Additionally, it provides the ability to benchmark novel methods with the greatest potential to yield patient care benefits in the future.

  • The Digital Mammography DREAM Challenge.

    The Digital Mammography DREAM Challenge.

    June 29, 2016- May 2017 (competitive phase closed)

    With generous support from the Laura and John Arnold Foundation this $1.2 million Challenge, one of two large prize Coding4Cancer Challenges, seeks to improve the accuracy of breast cancer detection and reduce the current rate of patient callbacks.

DREAM Challenges pose fundamental questions about systems biology and translational medicine. Designed and run by a community of researchers from a variety of organizations, our 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, we 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.
Sage

FEATURED PUBLICATION

Keller A, Gerkin R, et. al.  Predicting human olfactory perception from chemical features of odor molecules; Science; 24 Feb 2017; Vol 355; Issue 6327;  820-826; DOI: 10.1126/science.aai2014  

FEATURED CONTENT

The DREAM Challenge team discuss what DREAM Means to them in this new DREAM Challenges Video produced at the 2016 conference in Phoenix.  
July 24, 2017

DREAM Challenge Community competition launches to learn how to use smartphone and wearable sensors to monitor health

Recent advances in mobile health have demonstrated great potential to leverage sensor-based technologies for remote monitoring of health and disease – particularly for diseases affecting motor function such as Parkinson’s. While there are many projects that have successfully collected sensor data from people in the real-world setting, researchers still have a poor understanding of what the data can tell us about health. (Read more.)

June 2, 2017

IBM and Sage Bionetworks announce winners of first phase of DREAM Digital Mammography Challenge

IBM and Sage Bionetworks announced today the winners of the first phase of its DREAM Digital Mammography (DM) Challenge have developed algorithms that had 5% fewer false-positive errors in breast cancer screenings than recently published state of the art computerized methods1. This 5 percent improvement could potentially lead to less anxiety and unnecessary procedures for an estimated two million women per year in the United States and could help reduce costs associated with follow-up exams and biopsies. (Read more)

June 2, 2017

Can Machine Learning Help Improve Accuracy in Breast Cancer Screening?

Breast Cancer is the most common cancer in women. It is estimated that one out of eight women will be diagnosed with breast cancer in their lifetime. The good news is that 99 percent of women whose breast cancer was detected early (stage 1 or 0) survive beyond five years after diagnosis, leading countries around the world to implement breast cancer screening programs for early detection. (Read more)