Verseon acquires Edammo to further its approach to drug discovery
Adityo Prakash, Co-Founder and CEO of Verseon and Ed Ratner, CEO of Edammo, discussed the acquisition with BioSpace.
“We develop completely new drugs on the computer, atom by atom, and then manufacture them in the lab,” Prakash said. “We are changing the way small molecule drugs are designed and developed with a level of efficacy that was not possible before.”
He added that Verseon “also offers entirely new types of drug molecules that you can find with existing high-throughput screening methods or existing libraries.”
Verseon’s process involves design based on molecular physics as well as AI to develop new classes of innovative drugs, “not just for novelty,” Prakash said, “but because they actually deliver better outcomes. “.
Edammo was not specifically focused on biopharma. Ratner described the company’s platform as “widely applicable AI technology.” As such, he has worked in a range of industries including aviation, healthcare, human resources, insurance, manufacturing, pharmaceuticals, retail and more.
Small and large data
Edammo approached AI in a very different way, Ratner said, noting, “Everybody talks about ‘big data,’ because the perspective is that whatever field you’re in, the amount of data is going to grow exponentially – the amount of data you’re working with is huge and you’re building your AI with that assumption.
However, the founding team of Edammo, which includes Ratner, knew that “this was not the case in all areas”. So they approached the “AI problem” by assuming that the amount of data available would be essentially limited.
“We thought that in many areas the amount of data would be limited and roughly comparable to the number of properties describing each example,” he said.
This has become known within the AI industry as Small and Wide Data.
Big data analysis is useful for what some in the industry call “bigger picture ideas” or to help determine if you are looking at “a tree or a building”. Small and large data are best used to “select specific insights and specific insights from individual data components,” Ratner said.
“Basically, it’s a very basic approach,” he continued. “And if the problem has the characterization ‘small and large,’ which means that the number of examples is limited and the number of properties describing the problem is large, we could solve these problems better than anyone.”
This type of approach seems particularly effective for biopharmaceuticals. Prakash noted that biopharma was more often the realm of small data than big data.
“People don’t recognize this or understand it, especially people from a pure biopharmaceutical background, because AI looks like a magic box that solves all the problems, but it’s not,” did he declare.
If researchers try to track every impact a drug would have on the body, across every data point and every type of drug, there’s so much data that Prakash says it’s practically impossible. .
Small molecule design turns out to be something with few evolutionary rules that can help drug design. But small changes in a small molecule can have dramatic changes in its impact in the body. “It makes the problem incredibly complicated,” Prakash noted.
Often when developing new drugs, the available data set is small and sparse. This is more difficult for AI systems dependent on Big Data.
It turns out that Edammo’s Extreme AutoML technology works very well in areas of the life sciences that depend on small datasets and has demonstrated a lower error rate than some external industry benchmarks such than Google AutoML.
Verseon has built many drugs using its own design methodology, which starts with molecular physics but then uses its own AI system to help refine the molecules.
make it exclusive
The company officially unveiled seven programs for a range of indications, including heart disease, diabetes and cancer. He often looked elsewhere to AI companies to see if anyone had better results.
That’s how Verseon found Edammo, “which had significantly better results than the rest of the industry. We thought it could be an incredibly good tool for the field of biopharmaceutical drug development,” Prakash said.
Verseon tried Edammo’s technology, established a relationship, and decided they wanted exclusive use. Edammo, which primarily focused its technology on drug development, was interested in the acquisition. Under the partnership, Edammo’s technology “will be used exclusively for drug development,” Prakash noted.
He added that as Verseon moves into the clinic, analyzing patient data where data may be limited, Edammo’s tools “will be a great addition to our platform.”
No financial details were released regarding the acquisition, but Prakash noted that it was a “sound stock transaction”.
Ratner said “Edammo investors who learned of the details of the acquisition were very excited.”