Barry Bunin, PhD
Founder & CEO
Collaborative Drug Discovery
“How A.I. Is Revolutionizing Drug Development.” That’s the headline for a recent article in The New York Times about how scientists are generating data to train A.I. algorithms to design better medicine, faster. With the article noting “But the
transformation is just getting underway.” The article quotes consulting firm McKinsey & Company (with their own agenda of course) as saying: AI is a “once-in-a-century opportunity” for the pharmaceutical business. The article includes a look at the
laboratory at Terray Therapeutics, with a funny take on the typical microtiter plate: “Proteins in solution combine with chemical molecules held in minuscule wells in custom silicon chips that are like microscopic muffin tins. Every interaction is recorded, millions and millions each day, generating 50 terabytes of raw data daily — the equivalent of more than 12,000 movies.” Humans are still very much in the loop. The article quotes David Baker, a biochemist and director of the Institute for Protein Design at the University of Washington, with a dose of realism: “Generative A.I. is transforming the field, but the drug-development process is messy and very human.”
* * *
“The New Holy Grail for Weight-Loss Drugs Is Sleep Apnea.” The Wall Street Journal carries that headline for an article about clinical trials showing that hefty weight loss from drugs like Zepbound, Ozempic, and other GLP-1 receptor agonists could help open the airways of obese individuals, reducing the frequent stops and starts to breathing while they sleep. Sleep apnea (and obesity) are two of the more common ailments that effect people I talk with regularly. The article notes: “Ozempic, Zepbound and their GLP-1 cousins have become wildly popular, ringing up more than a million prescriptions a week. But many people can’t get the medicines because their health plans don’t cover them and the drugs would cost upward of $1,300 a month out of pocket. … The business thesis: Proving health benefits of drugs such as Zepbound beyond weight loss could persuade more health insurers to finally reimburse the expensive drugs, opening the door to billions of dollars in more sales.”
* * *
"Study Shows Generative AI Can Speed Up Clinical Trial Enrollment for Pennies per Patient.” That’s the headline from a recent article in FIERCE Biotech about researchers at Mass General Brigham finding that artificial intelligence software like ChatGPT could help speed up the screening process to find patients eligible for clinical trials—though they cautioned that
additional safeguards would be necessary. Using a version of OpenAI’s GPT-4 program through Microsoft’s Azure cloud service, the researchers found that a tailored generative AI application was able to quickly comb through patient notes within electronic medical records and accurately identify those with heart failure who met the criteria for a study. The article says, “The researchers pegged the price of the AI’s review at an average of 11 cents per patient—compared to orders of magnitude higher with traditional manual screening methods, where annual costs can reach into the tens of thousands and vary significantly by study type and phase.”
* * *
“Scientists Make DNA Discovery that Could Help Find Pancreatic Cancer Cure." That’s the headline for an article in The Guardian about a team of researchers from the UK and US finding that pancreatic cancer is able to shut down molecules in one of the body’s most important genes, helping the disease to grow and spread rapidly. For the study, published in the journal Gastro Hep Advances, the researchers analyzed healthy as well as pancreatic cancer tissue samples. They found pancreatic cancers triggered DNA methylation, causing molecules in the normally beneficial HNF4A gene to switch off, allowing tumors to grow extremely quickly. The article notes that the HNF4A gene is crucial to human health because it helps many of the body’s organs to function properly. But the researchers discovered pancreatic cancer can disable the gene’s benefits. The article quotes Dr. Maria Hatziapostolou, of Nottingham Trent University’s John van Geest Cancer Research Centre, as saying: “This work, which has provided new understanding and knowledge of how the cancer behaves, will hopefully help pave the way for potential new treatments in the future. … Loss of HNF4A drives pancreatic cancer development and aggressiveness and we now know (that) correlates with poor patient survival.”
* * *
Progress in Creating RNA Vaccines Against Cancer. Derek Lowe in his blog for Science, writes of a recent review from a team at Sloan-Kettering on the push to use the RNA vaccine technology as a platform for oncology. Lowe writes: “One of the points you come away with is that the CAR-T story may actually get you thinking about the field in the wrong way. Those are
given to patients with various blood cancers/leukemias who have basically burned through all existing chemotherapies. They have advanced disease and have generally had it for a long time, and this is likely to be their last shot. But cancer vaccines, as the authors note here, are most likely to be efficacious in treating very early disease stages or as outright preventatives.” Figuring out the science and policies for if, when, and for whom to give cancer vaccines before they have cancer, is an interesting challenge.
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.
Other posts you might be interested in
View All Posts
News
2 min
August 28, 2024
Nanome and Collaborative Drug Discovery (CDD) Announce Partnership That Streamlines Cheminformatic Workflows for Drug Discovery
Read More
News
2 min
August 22, 2024
Collaborative Drug Discovery Introduces CDD AI Support ChatBot
Read More
News
3 min
August 16, 2024
CDD Vault Integrates Enamine Compound Collection into AI-Powered Structural Similarity Searches
Read More