Barry Bunin, PhD
Founder & CEO
Collaborative Drug Discovery
“Dual CRISPR Therapy Plus Long-Acting ART Eliminates HIV in Mice” That headline from FIERCE Biotech marks another milestone in the long fight against HIV. The article describes work by a research team led by scientists from the Lewis Katz School of Medicine at Temple University and the University of Nebraska Medical Center that used CRISPR to inactivate or snip out two different genes in HIV-infected humanized mice. By combining this approach with a long-acting form of antiretroviral therapy, the researchers were able to eliminate the virus in around 60% of the models—a big boost from the 29% they reported in 2019. Kamel Khalili, Ph.D., a member of the Temple University team, said: “The importance of this strategy is twofold: First, CRISPR remains the method of choice for permanent elimination of the virus, and second, this combination for targeting the virus along with some other method to prevent spread, such as inactivation of CCR5 by CRISPR, can be improved for permanent elimination of the virus.”
* * *
EHR + AI = Predictive Cancer Diagnosis. That’s the short take from a recent article in Nature headlined “A Deep Learning Algorithm to Predict Risk of Pancreatic Cancer from Disease Trajectories.” The abstract reads in part: “We trained machine learning models on the sequence of disease codes in clinical histories and tested prediction of cancer occurrence within incremental time windows.” Using two different data sets totaling 9 million patient records from Denmark and the U.S., the researchers asked the AI model to look for telltale signs based on the data contained in the records. The ability to predict the disease within 36 months was sufficiently accurate that the researchers wrote: “These results improve the ability to design realistic surveillance programs for patients at elevated risk, potentially benefiting lifespan and quality of life by early detection of this aggressive cancer.” Co-senior investigator Søren Brunak, Professor of Disease Systems Biology and Director of Research at the Novo Nordisk Foundation Center for Protein Research at the University of Copenhagen, was quoted in Harvard Medical News, saying “AI-based screening is an opportunity to alter the trajectory of pancreatic cancer, an aggressive disease that is notoriously hard to diagnose early and treat promptly when the chances for success are highest.”
* * *
“Ozempic and Wegovy Have Taken Over Obesity Treatment. Can They Help With Cancer, Too?” That’s the headline from a FIERCE Biotech article reporting “Novo Nordisk’s Ozempic and Wegovy may have benefits beyond helping patients shed pounds. They appear to reverse the impairments in cancer-fighting natural killer cells seen in people with obesity, independent of weight loss.” Researchers from Maynooth University in Ireland reported that a long-acting glucagon-like peptide-1 (GLP-1) analogue restored natural killer cell function in 20 people with obesity. The article notes Novo Nordisk was not involved in the study.
* * *
“Computing Our Way to Antibodies” is the headline of a recent blog in Science by Derek Lowe, in which he notes that traditional research methods of using animal models to search for interesting antibodies could use a boost from AI and machine learning. He writes that the human body can (in theory) make a quintillion (ten to the eighteenth) different types of antibodies. “Combine that with the way that these protein can join together in all sorts of complex oligomeric structures, and you get a variety of binding patterns that is literally impossible to form any useful mental picture of,” he writes. Lowe points to a paper on using language models for protein structure and design work, and another new paper in which the authors are trying for de novo antibody generation computationally. He writes: “The eventual goal is for ‘zero-shot’ examples, that is, providing an antibody for a specific antigen where there are no prior antibodies known to build off of.” And ends with: “Antibodies for everything?”
* * *
“World’s Pharma Giants Bet on AI to Develop Drugs Faster.” Bloomberg carries that headline for an article saying, “Morgan Stanley estimates that over the next decade, the use of AI in early-stage drug development could translate into an additional 50 novel therapies worth more than $50 billion in sales.” The article says there’s been a surge in venture capitalists requesting evaluations of potential AI drug discovery companies over the past five years. It quotes Stanford University professor Russ Altman, who’s conducted due diligence of biotech startups for VCs for decades, as saying the interest has gone “from zero to a hundred.”
=
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.