A supercomputer in the Lawrence Livermore National Laboratory, which will be used in a new public-private project to speed discovery of new drug therapies. Photo: Lawrence Livermore National Laboratory via UCSF

A public-private partnership involving big-data supercomputing, artificial intelligence, and data sharing aims to push cancer drugs out to consumers faster than ever before.

The Accelerating Therapeutics for Opportunities in Medicine, or ATOM, has a stated target of decreasing the timeframe from drug target to clinical candidate from six years to just 12 months, they said. Such an acceleration would be an integral part of realizing the so-called “cancer moonshot” over the next decade.

Lawrence Livermore National Laboratory, the Frederick National Laboratory for Cancer Research, the University of California – San Francisco, and Glaxo Smith Kline (GSK) announced the formation of ATOM last Friday, saying their goals were “tightly aligned with those of the 21st Century Cures Act,” and the “cancer moonshot” legislation passed into law last December.

The collaboration proposes to leverage supercomputing simulations, and known biological trials, into targeted treatments of tumors, they announced.

“ATOM is a novel public-private partnership that draws on the Lab’s unique capabilities to create a paradigm change in drug development,” said Bill Goldstein, the director of Lawrence Livermore. “It will help to strengthen U.S. leadership in high-performance computing and, by speeding the discovery of therapeutics, contribute to biosecurity.”

The kickoff will be GSK’s contributions of data on 2 million failed compounds, plus 500 more molecules that the company found did not pass the development process, but could still be viable, they announced.

“GSK is working to set a precedent with pharmaceutical companies by sharing data on failed compounds,” said John Baldoni, a GSK senior vice president of R&D. “As we have learned more about what modern supercomputers can do, we’ve gained confidence that this approach can make a big difference in creating medicines.”

Lawrence Livermore will contribute its best supercomputers, including a next-generation system called Sierra. Jeremy Thomas, a spokesman for the Lawrence Livermore National Laboratory, told Laboratory Equipment that Sierra is expected to be up and running next year - and would be between four and six times faster than the current fastest system, known as Sequoia.

The computing power will “generate new dynamic models that can better predict how molecules will behave in the body compared to the current iterative and time-consuming practices,” the group says.

Precision oncology and drug expertise will come from the Frederick Laboratory, as well as UC, San Francisco.

The data will be from GSK and publicly available sources – and “future consortium members,” according to the release. Thomas, the Lawrence Livermore spokesman, said ATOM was "actively looking for additional partners" beyond the four currently taking part.