Big Data • Big Analytics • Big Insight

July 10, 2013

‘Sandbox for Geeks’ Powers Open Medical Research

Alex Woodie

The people behind Sage Bionetworks hope that a new community-driven approach to research that features a big pool of scientific data that is open to all–or a “sandbox for geeks” as its founder put it–will result in progress being made in the battles against diseases such as arthritis, Alzheimer’s, and breast cancer.

In the scientific community, secrecy is often part and parcel of the process, and critical to one’s ability to monetize a breakthrough. While getting rich is definitely a big incentive, there’s a growing stream of thought in the scientific community that a democratic approach that involves sharing data and working together may actually be more effective at advancing the cause of science, finding breakthroughs, and improving the lives of millions of people

Dr. Stephan Friend, who founded the non profit Sage Bionetworks in 2009, is a believer in using this community-based approach to further scientific inquiry and discovery, and replacing getting rich with getting published. Central to this process is Synapse, which he dubs a “sandbox for geeks,” or a platform for crowdsourcing answers to biomedical questions.

Synapse provides data scientists with an open repository of analysis-ready data that scientific teams can work on in an open, online forum. The information can be accessed directly through a Web portal that features social media tools to enhance collaboration.

Dr. Friend was honored at the White House on June 20, when he was named one of the nation’s Open Science Champion of Change. During the event, Dr. Friend spoke about the potential for Synapse to drive innovation. “At the core of Sage Bionetworks is the idea of building a precompetitive commons where citizens and researchers can come, interact, give and take basic research and build on one another’s insights,” Dr. Friend said, according to a story in the Herald Online.

Dr. Friend also unveiled Sage Bionetwork’s next projects, including challenges to crowd-source progress towards battling arthritis and Alzheimer’s.

The goal of the Rheumatoid Arthritis Responder Challenge is to “make complex genetic and genomic patient data available and ask the crowd of challenge participants to generate predictive models that will help doctors know which patients are most likely to respond to treatment,” according to Dr. Robert Plenge, a leading organizer of the challenge and the Director of Genetics & Genomics at Brigham & Women’s Hospital.

Similarly, the Alzheimer’s Disease Big Data Challenge hopes to develop faster and more accurate predictive models for Alzheimer’s risk in pre-clinical populations. “It’s time to disrupt ‘business-as-usual’ with innovative ‘big data’ techniques,” said George Vradenburg, Convener of The Global CEO Initiative on Alzheimer’s Disease, which is helping to lead the challenge.

The two challenges will be run in partnership with the Dream Project, a distributed systems biology group that has run two dozen successful open computational challenges over the last five years. Sage Bionetworks and the Dream Project teamed up last year with the successful Breast Cancer Prognosis Challenge (BCC), which attracted 350 participants from more than 35 countries who submitted a total of 1,700 models.

Related Items:

Using Visualization to Unlock Secrets in Big Data

IDC Talks Convergence in High Performance Data Analysis

Datameer Reports Big Growth with Hadoop Tools