February 6, 2026
Barry Bunin, PhD
Founder & CEO
Collaborative Drug Discovery
Lilly and NVIDIA Announce Lilly TuneLab “First of It’s Kind AI Co-Innovation Lab” The companies announced they were jointly investing up to $1 billion over five years in talent, infrastructure, and compute. The collaboration will initially focus on creating a continuous learning system that tightly connects Lilly’s agentic wet labs with computational dry labs, enabling 24/7 AI-assisted experimentation to support biologists and chemists. This scientist-in-the-loop framework aims to enable experiments, data generation and AI model development to continuously inform and improve one another. “For nearly 150 years, we’ve been working to bring life-changing medicines to patients,” said David A. Ricks, chair and CEO of Lilly. “Combining our volumes of data and scientific knowledge with NVIDIA’s computational power and model-building expertise could reinvent drug discovery as we know it. By bringing together world-class talent in a startup environment, we’re creating the conditions for breakthroughs that neither company could achieve alone.” It is worth mentioning in passing that Lilly has a strong history of innovation including projects like Innocentive, Chorus and CDD.
* * *
"Llamas Are Big Pharma’s Secret Weapon to Find New Drugs." Readers of this recent headline in Bloomberg, might have thought: Llamas? Don’t you mean LLMs? But it turns out that the shaggy members of the camel family naturally produce very small single-domain antibodies, dubbed “nanobodies,” which show promise as building blocks in creating new drugs. “They have this Lego-like nature that you can just snap them together any way you want to, which is really unique,” says Mark Lappe, Chief Executive of Inhibrx Biosciences Inc. “If you try to do that with regular antibodies, it’s wildly complex.” The nanobodies created by llamas can squeeze into tighter spots and better penetrate tissue than human antibodies, because they’re smaller and simpler. Some have been reported to cross the blood-brain barrier, eliciting hope for neurological diseases. Michael Quigley, Chief Scientific Officer at Sanofi, says “I do think nanobodies will be a mainstay of many portfolios going forward.” Life is reportedly good for the llamas. They roam around the farms where they are kept, occasionally putting up with an inoculation to trigger growth of new types of nanobodies. And when they get to retirement age there’s a long line of volunteers to give them new homes.
* * *
"What Happens When You Stop Taking GLP-1s? “The Hunger and Food Noise Symptoms Come Back with a Vengeance.” That’s from a recent Wall Street Journal article about results from a recent analysis published in the British Medical Journal finding that people who take GLP-1s and then stop, regain weight four times faster than those who lose weight through lifestyle interventions. The analysis also found that improvements in health markers, such as blood pressure, cholesterol and blood-glucose levels, were lost after stopping use of GLP-1s, with levels returning to baseline within 1.4 years. Katherine H. Saunders, a Clinical Assistant Professor of Medicine at Weill Cornell Medicine and co-founder of FlyteHealth, a medical obesity-treatment company, says when individuals go off a GLP-1, “The hunger and food noise symptoms come back with a vengeance.” Not surprisingly, weight loss experts say the best success comes when use of GLP-1s includes diet and lifestyle changes. But Dr. Robert Kushner, an obesity-medicine specialist and professor emeritus at Northwestern University says he’s only had a handful of patients who were able to keep their weight off long-term after stopping a GLP-1 medication.
* * *
“A New AI Tool Could Dramatically Speed Up the Discovery of Life-Saving Medicines.” Science X carries that headline for story about a new AI framework from China, called DrugCLIP that can scan millions of potential drug compounds against thousands of protein targets in just a few hours—ten million times faster than current virtual screening methods. DrugCLIP learns a shared chemogenomic representation of protein targets and small molecules, enabling large-scale, docking-free virtual screening. By embedding billions of compounds and thousands of protein pockets into a unified space, DrugCLIP rapidly identifies active ligands, supports multi-target and genome-wide screening, and delivers consistent enrichment across diverse targets. The creators of DrugCLIP published their work in Science. The AI only needs to measure the distance between the vectors to find a match. By turning the physical shape of a potential drug into numbers, the system can search through trillions of possibilities instantly. To make this work for thousands of targets at once, the team used AlphaFold 2, to predict the 3D structures of about 10,000 human proteins. The scientists, in their paper, wrote: “Its speed enables trillion-scale screening covering the human druggable proteome, providing an open- access resource that forms a foundation for next-generation drug discovery, particularly for less understood targets"
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.