April 20, 2017
By Mark Terry, BioSpace.com Breaking News Staff
“This will revolutionize drug development!” or something along those lines is common enough that a high level of skepticism is expected. San Francisco-based Atomwise Inc. isn’t saying that upfront, but if what they are offering lives up to its potential, it could revolutionize drug development.
This startup uses its Artificial Intelligence Molecular Screen (AIMS) program to sift through millions of compounds, looking to match requested protein and disease targets with potential drugs. And at the moment, Atomwise is offering this service to university scientists, who will then receive 72 potential compounds identified by the AIMS program.
“It’s this easy,” says Han Lim, Atomwise’s Academic Partnerships executive, in a statement. “Researchers tell us the disease and protein to target, we screen millions of molecules for them, and then they receive 72 custom-chosen compounds ready for testing. As a former UC Berkeley principal investigator, I helped design the kind of program I wish existed for my own work.”
The request for proposals was issued yesterday with a deadline of 11:59 PM PDT, June 12, 2017. Recipients will be announced in September. The company states that “The application must be supported by a principal investigator, and the research must be performed within the United States or Canada at a non-profit university or research institute.”
Atomwise has already launched 27 drug discovery projects with a number of organizations, including Merck and Harvard University, working on diseases such as Ebola, multiple sclerosis, and leukemia.
According to Xconomy, there are two motives behind the programs. Bernadette Tansey, writing for Xconomy, says, “The first goal is to help scientists leap over a gap in government funding, which covers basic research on the molecular mechanisms behind illnesses, as well as clinical trials on experimental drugs, but doesn’t support the hunt for drugs to test, says former UC Berkeley research Han Lim, who manages academic partnerships for Atomwise.”
The second is to continue to field-test its drug screening system on a broader group of research projects and diseases.
“That could produce case studies that allow us to demonstrate what we can do,” Alexander Levy, Atomwise’s co-founder and chief operating officer, told Xconomy.
The company was founded in 2012 with Levy’s fellow researchers at the University of Toronto. In 2015, Atomwise participated in Y Combinator’s accelerator program, raising $6 million in seed funding. It then collaborated with 27 institutions and companies, including Stanford University and IBM. Approximately 14 of those projects are continuing and the company, as a result, is bringing in revenue.
High-throughput screening is not new, but advanced use of artificial intelligence (AI) is, if not unique, the sign of things to come. Tansey writes, “Researchers looking for the causes behind a disease often have strong suspects in mind. The culprits are usually biologically active proteins in the body that are knocking essential functions out of whack. While discovering a disease’s molecular cause does reveal it as a possible target for therapeutic drugs, that’s only part of the path toward a medical treatment.”
They then must identify, and in many cases modify, molecules that counteract the problematic protein’s effects.
Atomwise is not the only company to focus on this approach—Numerate is another, as is IBM and Google . Atomwise is utilizing chemical descriptions of the potential compounds, X-ray crystallography images of the target proteins, and known data of known interactions.
Atomwise will evaluate the feasibility of any applications and notify the “winners” in September.
