Drug Discovery Industry Roundup with Barry Bunin — January 4, 2023

Barry Bunin, PhD Founder & CEO Collaborative Drug Discovery

Barry Bunin, PhD
Founder & CEO
Collaborative Drug Discovery

AI + Machine Learning = Inflection Point for Biopharma. That’s the 2023 forecast from FIERCE Pharma, which points to a flood of AI and machine learning products. The article describes new offerings from a number of companies seeking to “revolutionize” drug discovery with AI and ML algorithms and approaches such as patients-on-a-chip technologies. The article claims: “Forcing the revolution is the exorbitant cost of R&D given the typical time needed to develop a therapy (12 to 18 years) and the failure rate (90%). AI tools can significantly reduce both.” The article quotes Quris CEO Isaac Bentwich as saying: “It’s three revolutions that are culminating now, with Hollywood style timing. It’s a perfect storm—organs on a chip coming of age, AI becoming powerful and focused on this problem and the regulator saying animal studies suck.”  At CDD, we’ve always focused on handling the bioactivity, chemical structure and biological sequence data correctly and gracefully – given models are only as good or bad as the data accessible to multiple brains with the domain expertise to appreciate the scope and limitations of the data interpretation.

  * * *

Do You Happen to Speak Protein? There’s a Chatbot that Might. The Wall Street Journal carries an article headlined “How AI That Powers Chatbots and Search Queries Could Discover New Drugs.” The premise is that natural language processing algorithms like the ones used in Google searches and OpenAI’s ChatGPT promise to slash the time required to bring medications to market. The article reads, in part: “Natural language algorithms, which quickly analyze language and predict the next step in a conversation, can also be applied to this biological data to create protein-language models. The models encode what might be called the grammar of proteins—the rules that govern which amino acid combinations yield specific therapeutic properties—to predict the sequences of letters that could become the basis of new drug molecules. As a result, the time required for the early stages of drug discovery could shrink from years to months.”  As with the previous article, the foundational challenge is optimally managing the data, upon which (m)any models can be built.

  * * *

From “Creature of the Black Lagoon” to Algae Microbots. Thoughts of the 1954 horror film “Creature of the Black Lagoon” somehow came to mind when I read this recent headline in Drug Discovery News “Algae Microrobots Fight Persistent Bacterial Infections.” Bioengineers are finding a heroic role for algae, using it to create robots as delivery trucks for antibiotics to provide more efficient drug delivery. The article quotes Liangfang Zhang, a bioengineer at the University of California, San Diego and coauthor of the study published in Nature Materials. “There was a lot of brainstorming and discussion to come up with the idea of algae robots.” Zhang’s group landed on algae cells for a few reasons. A microrobot delivery system would need to be big enough to carry a dose of medicine, but small enough to penetrate deep into tissues. They chose to work with chlamydomonas reinhardtii, a species of algae that is about 10 micrometers long. The story becomes even more fascinating—and a bit science fiction sounding—with the description of what made the algae robots so efficient at delivering antibiotics to the lungs of a mouse: “Traditional antibiotics passively float around and unevenly diffuse drugs across tissues. The algae zigged and zagged, dodging immune cells that slowly chased after them. This meant that the drug reached all corners of the lung. The persistent swimming paid off; the microrobots required a 3,000-fold lower dose of antibiotics to clear the infection than an intravenous transfusion of the same antibiotics against the same bacteria.” Zig-zagging to dodge slowpoke immune cells…

  * * *

Will Big Pharma End Up Owning Cannabis? That’s the fear expressed in a recent guest essay in The New York Times headlined “It’s Not Just About Pot. Our Entire Drug Policy Needs an Overhaul.” The writer notes that President Biden recently signed a law to ease onerous restrictions on marijuana research,  and is encouraged that the President has ordered the Department of Health and Human Services and the attorney general to review the scheduling status of cannabis.  “This legal process could lead to federal regulation of sales for recreational use or a national law that requires a prescription for marijuana.” The author is all for reducing marijuana from its current status as a dangerous Schedule 1 substance, on par with heroin, but fears that rescheduling under current categories would remain overly restrictive. She writes: “Change, however, is tricky. Rescheduling marijuana could upend state regulations by imposing prescription requirements. This could give cannabis to Big Pharma, which is the only industry with the capacity to make and sell Food and Drug Administration-regulated medicine.”

=

Barry A. Bunin, PhD, is the Founder & CEO of Collaborative Drug Discovery, which provides a modern approach to drug discovery research informatics trusted globally by thousands of leading researchers. The CDD Vault is a hosted biological and chemical database that securely manages your private and external data.