Health IT, Pharma

Artificial intelligence, big data and harnessing the “body’s hidden drugs”

As far as medical science has advanced, we’ve still not come close to paralleling the […]

As far as medical science has advanced, we’ve still not come close to paralleling the amazing natural processes that go on, every day, in the human body.

Berg, a Boston-area startup, builds off that concept of studying healthy tissues to understand the body’s molecular and cellular natural defenses – and what leads to a disease’s pathogenesis. It’s using concepts of artificial intelligence and big data to scope out potential drug compounds – ones that could have more broad-ranging benefits, pivoting away from today’s trend toward targeted therapies. The company’s funded solely by Carl Berg, a Silicon Valley real estate kingpin.

Aaron Krol over at Bio-IT World penned a very thoughtful, probing and well-written piece about the company: Berg and the Pursuit of the Body’s Hidden Drugs. He acknowledges the skepticism that comes hand-in-hand with Berg CEO Niven Narain‘s claims: halving the time and cost of bringing a new drug to market, using molecules naturally found in the body to treat intractable diseases like cancer and diabetes.

But if Berg’s approach proves to be feasible, it could have pretty far-reaching implications for drug development, Krol says. Here’s why:

Berg’s first drug candidate also bucks a key trend in cancer care. Most pharma companies today are looking at narrowly-targeted cancer drugs, meant to treat small molecular subtypes of the disease. This has led to some of the biggest recent advances in oncology, with drugs like Herceptin and Gleevec seeing huge survival gains for their targeted patient populations, but it has also limited the impact of any one therapy.

By contrast, BPM 31510 has a broad mechanism of action, and Berg is enrolling patients with any type of solid tumor in its clinical trials. If the therapy does turn out to be among the 10% or so of drugs that make it all the way from Phase I studies to FDA approval, the benefit to patients could be especially large.

Even a skeptic has to hold out a little hope for a result like that.

The company’s AI platform, called Interrogative Biology, identifies potential drug candidates faster than human-led R&D efforts, Krol wrote, adding: “If even a fraction of those treatments make a real difference to patients, it would represent a genuine advance for the industry.”

Of course, this isn’t the only company using artificial intelligence and big data computing to identify plausible new drug compounds – North Carolina-based Cloud Pharmaceuticals, for instance, is raising $20 million to pursue a similar path. But this concept of in-silico testing is still a nascent field with seemingly few competitors, and it begs closer attention.

Berg differs from competitors, Krol says, because all it’s looking for is naturally occurring, potentially therapeutic proteins, enzymes or peptides. He continues:

That approach has some real advantages for drug design. For example, by flagging molecules that are over- or under-abundant in diseased cells, Interrogative Biology can often find promising biomarkers to help with the diagnosis or prognosis of an illness, even when it doesn’t turn up a drug candidate; Berg has a separate diagnostics division working to commercialize some of those markers. The same biomarkers can also help Berg to stratify patients in its clinical trials, providing advance knowledge of which patient subpopulations are most likely to respond to treatment. Narain even suspects that Berg will have an easier time with toxicology than other pharma companies, because its therapeutics are already present in the human body.

Yet there are also challenges to working with endogenous molecules. Intellectual property will be a continual headache, since by definition a naturally occurring molecule can’t be claimed as a new and protected product. “Nobody’s going to get a composition and matter on these, obviously,” says Narain, referring to the preferred choice for pharma patents, covering the chemical structure of the drug itself. “That’s why we stayed under the radar for a good five years [with BPM 31510], developing IP around method and use, predictive modeling, the stratified approach, the key metabolic drivers around the mechanism of action, and the formulation.”

The full article’s worth a read. Here’s the link again.

Shares0
Shares0