Barry Bunin, PhD
Founder & CEO
Collaborative Drug Discovery
"How AI is Taking Over Every Step of Drug Discovery” Whether it is hype and overstatement or true…that’s the headline for an article in Chemical & Engineering News about using AI and machine learning to speed discovery efforts. The article quotes Avner Schlessinger, who heads the AI Small Molecule Drug Discovery Center at Icahn School of Medicine at Mount Sinai, as saying: “These tools have expedited the process of drug discovery operations significantly. They allow us to explore
chemical spaces that we could not explore earlier.” Nodding to the Nobel Prize–winning algorithms AlphaFold and Rosetta—the article quotes Gaurav Chopra, the James Tarpo Jr. and Margaret Tarpo Professor of Chemistry and a professor of computer science at Purdue University as saying: “AlphaFold has been great. It provided researchers with a tool to decipher the structure of a protein based on its sequence and how a drug would bind to it with a fair amount of accuracy. And Rosetta allowed them to design novel proteins that are not seen in nature.” Schlessinger adds that human effort remains essential, as AI and machine learning still need interventions from chemists and data from wet labs. Of course AlphaFold2, ESMFold, Boltz-2, and CDD’s proprietary generative bioisosteres and ultrafast deep learning private similarity search to SureChEMBL, ChEMBL and Enamine compounds are part of the AI module directly within CDD Vault:
https://www.collaborativedrug.com/ai-drug-discovery
Because CDD Vault AI suggestions are reasonable to expert synthetic medicinal chemists, the new suggestions avoid Michael Acceptors, PAINS, and violations of Baldwin’s Rules. Unlikely previous generative chemistry capabilities, the CDD Vault AI algorithms suggest novel compounds generally reasonable to highly critical synthetic chemists. Deep learning similarity and bioisosteres are automatically generated in the background for every compound in CDD Vault…or any compound imagined and drawn on the fly, including substructures and reagents.
* * *
“Lilly Deploys World’s Largest, Most Powerful AI Factory for Drug Discovery Using NVIDIA Blackwell-Based DGX SuperPOD” That’s the headline for a recent NVIDIA release about the AI factory using the NVIDIA BioNeMo platform, and built with over 1,000 NVIDIA Blackwell Ultra GPUs, to accelerate drug discovery and development. The AI factory will be used to train large scale biomedical foundation and frontier models for drug discovery and development. Select models will be made available on Lilly TuneLab — an AI and machine learning platform that provides biotech companies with access to drug discovery models built on $1 billion worth of Lilly’s proprietary data. “Our foundation models are spawning new possibilities for our chemists, helping them uncover new motifs and configurations of atoms that were out of reach with traditional methods,” said Thomas Fuchs, Chief AI Officer at Lilly. “AI gives us the means to accelerate progress toward both developing and delivering better, more personalized and targeted medicines.” Diogo Rau, Executive Vice President and Chief Information and Digital Officer at Lilly, said: “AI agents can work 24/7 and explore ideas that humans might not have the time or capacity to experiment with. At the end of the day, it’s all about human learning — not machine learning. Machines are helping make humans smarter by stimulating new ideas for new molecules.”
To dig deeper into TuneLabs, the Global Head of Lilly TuneLab is Aliza Apple:
https://www.linkedin.com/in/aliza-apple/
* * *
“Is GLP-1 the New AI? Drugmaker Eli Lilly Joins the $1 Trillion Market-Cap Club.”That’s the headline for a MarketWatch article comparing the wealth generated by GLP-1 to that of AI, reporting that Eli Lilly & Co. is the first pharmaceutical stock to hit a $1 trillion valuation, with its stock’s rise driven by a methodical approach to capturing an obesity-drug market that didn’t exist five years ago. The article notes that of the 10 U.S. companies to reach the trillion dollar category, Eli Lilly is the only one, aside from Warren Buffett’s Berkshire Hathaway, that isn’t a tech stock, but notes: “One could argue, however, that two of the tech companies in the club — NVIDIA Corp. and Amazon.com Inc. — are increasingly being recognized for their work in drug development and medical services, respectively.”
* * *
“Why is Tuberculosis Still a Global Challenge?.” That’s the headline posed by Drug Discovery News in a review of the deadly disease, which also points to the encouraging work being done on TB by the Gates Foundation. While relatively rare in the U.S. and Europe, the article reads: “However, TB is still a major threat in large parts of the world. Someone living in Lesotho, the Central African Republic, or Gabon is at least 3,000 times more likely to die from TB than someone in the US or Denmark. In 2023, 1.25 million people died from the disease, which meant that TB reclaimed its place as the world’s deadliest infectious disease after three years of COVID-19.” Turning to the positive, the article reads: “One of the most promising candidates is M72/AS01E, now in a landmark Phase 3 clinical trial sponsored by the Gates Medical Research Institute and funded by the Gates Foundation and the Wellcome Trust. The trial includes sites across four African countries and Indonesia. Originally developed by GSK in collaboration with Aeras Technologies and the International AIDS Vaccine Initiative, M72 could become the first new TB vaccine in more than a century, and the first ever to protect adults and adolescents.” The article concludes: “If M72 performs similarly in its Phase 3 trial and wins regulatory approval, it could transform global TB control. WHO estimates suggest that widespread vaccination could prevent 76 million new TB cases over the next 25 years, potentially ending TB’s reign as the world’s deadliest infectious disease.”
CDD is proud to support the Gates Foundation’s work on TB drug discovery since 2008, including the current public private partnership with multiple multinational pharmaceutical companies in the TB Drug Accelerators (TBDA).
“How AI Can Create a Virtual Programmable Human and Revolutionize Drug Discovery.” Medical Xpress carries that headline about Northeastern University researchers Lei Xie and You Wu and their recently published study in Drug Discovery Today titled “AI-Powered Programmable Virtual Humans Toward Human Physiologically-based Drug Discovery.” Xie, a professor of pharmaceutical sciences at Northeastern, said his team wants to create a digital representation of the human body to show not just how a compound might work, but how it would affect other systems within the body. “What we propose is a different way for drug discovery, by not just using AI to speed up discovery, but redefining what discovery means,” Xie said. “True innovation will come when AI helps us understand how the entire human system responds to treatment. We're building a framework that learns and reasons across all levels of biology."
CDD has proudly supported Neglected Tropical Disease Collaborations with Northeastern University for decades with Professors Michael Pollastri and Lori Ferrins:
https://www.collaborativedrug.com/neasternu-lab-nest-case-studyy.”
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.