Last year, when Italy was under siege from COVID-19, scientists at Exscalate4Cov, a public-private consortium of 18 institutions across Europe led by Italian pharmaceutical company Dompé farmaceutici, had just begun the hunt to find a therapeutic for COVID-19. Eight scientists, all located throughout Europe, met in a virtual room to discuss potential molecules. Each scientist held up a 3-D rendering of a molecule they simulated and walked the others through it. Inside this space, scientists could together scour these molecules, pulling them apart, enlarging them, and binding them to possible compounds. They asked each other questions and on a virtual whiteboard, sketched out possibilities for success and failure in each compound. This virtual setting also allowed them to compare molecules side by side.
Armed with $3 million in funding from the European Union, the group crowdsourced suggestions for treatments and analyzed those suggestions using supercomputers. By October they had submitted their first candidate for a Phase III clinical trial in Europe: a generic osteoporosis medication called Raloxifene.
The trial is now completed. “We’re waiting for the final results, but we are very confident on the possible success of the clinical trial,” says Andrea Beccari, lead scientist at Exscalate and head of research and develop platforms at Dompé farmaceutici. The outcome will not only determine whether Raloxifene will work against COVID-19—but it could also inform new drug design.
To create a new drug, scientists first look at how a disease enters human cells and then engineer a mechanism for interfering with that infection. Traditionally, they’ve done this on paper, sketching out proteins and simulating how a molecule or compound might bind to it. Current software often doesn’t provide enough visual landscape for scientists to understand the full scope of how molecules, especially those with multiple binding sides, relate to one another. That’s why Exscalate worked with a company called Nanome, which hopes to accelerate drug development by giving scientists a way to visualize molecules in three-dimensional space on an Oculus headset.
Beccari said that using supercomputers, the group took a list of 400,000 potential molecules and simulated their ability to latch onto proteins in the COVID-19 virus. In addition to analyzing them through computers, they also used virtual reality to better understand how these compounds might bind to COVID-19’s viral proteins and how they would work in humans. What was important to predict was whether a drug would be capable of reaching the lungs.
“For example, Remdesivir, which is a very good antiviral molecule, has very little effect on humans just because it does not arrive in the lungs in a sufficient concentration,” says Beccari. But in their machine-learning supported analysis, they found a family of molecules that are able to inhibit the virus and reach the lungs, he says. The first of these molecules is Raloxifene.
“Computers always generate solutions,” says Beccari. “But not all of these simulations are good just because the computer says.”
Beccari says that the platform gives scientists a lot more information than they can easily glean from a two-dimensional format. That ultimately speeds up their ability to sift through the molecules that their supercomputers suggest as plausible candidates. In the future, he’d like to see 3-D platforms like Nanome integrate with other platforms and tools. For instance, his organization created an ultrafast algorithm for understanding molecule docking. It would be great, he says, to do both their computational work and their collaborative work inside of one space.
Moving forward, the group will be working on designing drugs similar to Raloxifene that improve on its current abilities against COVID-19. In that context, Becarri says, collaboration among scientists will be especially key. “In the artificial intelligence era we think people still rule,” he says.