DREAM Project and Sage Bionetworks Join Forces

By Allison Proffitt

February 19, 2013 | Sage Bionetworks and the DREAM Project— Dialogue on Reverse Engineering Assessment and Methods—are merging efforts to run open science computational challenges which foster the broader collaboration of the research community and provide a meaningful impact to both discovery and clinical research.

The two organizations partnered last year on the 2012 Sage Bionetworks-DREAM Breast Cancer Prognosis Challenge. The project was so successful that the two groups are joining efforts permanently.

“Last year when we wanted to run a challenge on breast cancer we turned to [the DREAM Project] to get the experience that we lacked,” Stephen Friend, president and founder of Sage Bionetworks, tells Bio-IT World. “What Sage had was a way of hosting the data and the model in a compute space in way that people could see what each other was doing and get credit… [The partnership] gave us the ability to work on just a beautiful project.”

Participating teams in the breast cancer challenge were asked to submit their computational model to Synapse—Sage Bionetworks’ open computer platform—as open source code made viewable to all participants. Entrants’ models were assessed against a hidden dataset and scores were reported on a real-time leader board. The combination of immediate feedback and code sharing allowed participants to improve their leader board ranking by adjusting their own models or by borrowing the code of others to forge new models.

“The breast cancer project was a very positive experience,” Stolovitzky said. “We worked together and we have similar goals and similar missions and we enjoy each other’s company. It was pretty much a no brainer that we should work together,” Gustavo Stolovitzky, founder of the DREAM Project, says.

Both Sage Bionetworks and DREAM are convinced that open computational challenges represent an innovative new method to rapidly share and evolve predictive disease models that would otherwise take years to produce using the usual siloed research paradigms. Their merger provides a collaborative framework that will bring the ideals of open science one step closer to reality.

“Rather than fragmenting efforts like ours, the best thing we can do is join forces rather than trying to do the same thing from separate platforms,” Stolovitzky says. “Also there’s something Sage has that compliments something DREAM has. We have a lot of experience curating challenges in systems biology, but we never had a real home.”
Sage Bionetworks’ Synapse platform allows data to be shared and worked on collaboratively by teams of teams. Synapse is built to meet the needs of the data scientists that participate in DREAM’s challenges. It provides an open repository of analysis-ready data that scientific teams can work on in an open, online form accessible by all through a collaborative web portal.

The merger will join the Synapse platform with the experience that the DREAM Project brings from running 24 successful computational challenges since its founding in 2006, and will allow Sage Bionetworks and DREAM to run several challenges similar to the Breast Cancer Prognosis Challenge every year.

“The ability to get a million eyeballs on a problem where you don’t necessarily pay the people to do the insights but you allow teams to work together is fundamentally needed,” Friend says, “to—in an affordable, sustainable way—allow all this ‘omics data to be meshed in disease biology.”

The DREAM Project will keeps its community roots and continue to collaborate widely, Stolovitzky says, but the partnership will enable DREAM to grow.
“We really want to scale up and take the next step forward,” he continues. “For me, the next step would be to get all these researchers that are working hard in a very smart way, I would love for all these researchers to work together—not necessarily to win a competition, but to solve in a collaborative way important problems in iterative stages. That’s the vision for the future.”

Says Friend: “People who are dreaming about the world of precision medicine are being beaten back by the extreme costs and difficulty… [Sage-DREAM will be a] joint effort to begin tackling a number of different diseases from cancer to schizophrenia to diabetes to melanoma, where there’s sufficient data to begin to make insights into what drugs are likely to work in which patients.”