July 22, 2025
Barry Bunin, PhD
Founder & CEO
Collaborative Drug Discovery
“Sniffing Out Tuberculosis in Human Breath” is the headline for a Drug Discovery News article about how scientists are turning to breath samples as a way to detect tuberculosis economically and conveniently in the remote areas of Yogyakarta, on the island of Java, where tuberculosis (TB) runs rampant. The World Health Organization estimates that about a quarter of the global population has been affected by TB. Five to 10 percent of this population are active TB patients, meaning they acquire symptoms and develop the disease. The rest of the infected population harbors what is considered inactive or latent TB, in which the pathogens live inside their bodies without causing any symptoms. “TB is a curable disease if we can diagnose it quickly,” said Dr. Jane Hill, a chemical and biological engineer at the University of British Columbia. Hill’s work focuses on studying volatile molecules in breath as they relate to various diseases. She leads an ongoing initiative called the Human Breath Atlas that maps molecules in human breath to determine health status. The article describes how Dr. Antonia Saktiawati, a clinical scientist at Gadjah Mada University in Indonesia, developed an electronic nose-sensing (eNose) device that can detect TB from exhaled breath at a much lower cost than traditional testing.
* * *
“NVIDIA-backed AI Startup SandboxAQ Creates New Data to Speed Up Drug Discovery.” That’s the headline Reuters carries about an artificial intelligence startup spun out of Alphabet's Google and backed by NVIDIA, that has publicly released a trove of data it hopes will speed up the discovery of new medical treatments by helping scientists understand how drugs stick to proteins. The goal is to help scientists predict whether a drug will bind to its target in the human body. Reuters says that while the data is backed up by real-world scientific experiments, it did not come from a lab. Instead, SandboxAQ, which has raised nearly $1 billion in venture capital, generated the data using NVIDIA's chips and will feed it back into AI models that it hopes scientists can use to rapidly predict whether a small-molecule pharmaceutical will bind to the protein that researchers are targeting, a key question that must be answered before a drug candidate can move forward. The Times of India notes that “SandboxAQ utilized existing experimental data to calculate approximately 5.2 million new, ‘synthetic’ three-dimensional molecules. These molecules, not yet observed in the real world, were computed using equations validated by real-world data."
* * *
“Can A.I. Find Cures for Untreatable Diseases—Using Drugs We Already Have?” That’s the headline for an article in The New Yorker about the nonprofit called Every Cure, which trained an AI model on what developers described as “the world’s knowledge of every disease, gene, protein, and molecule, as well as the interactions between them.” The algorithm began to propose previously unknown applications for known treatments. The article states “Doctors have long prescribed off-label medications, usually through trial and error or in clinical trials, but now AI appears poised to supercharge the practice.” Every Cure’s AI platform, dubbed the MATRIX, is trained on what are known as “knowledge graphs”—networks of data representing the relationships between genes, proteins, drugs, and diseases. Knowledge graphs pull their information from the scientific literature and from curated medical sources: biobanks with health data from millions of people, for example, or repositories of chemicals and their safety profiles. Every Cure was founded by Dr. David Faigenbaum, who as a 25-year-old medical student nearly died from Castleman disease, and after prescribed regimens failed to help, began experimenting on his own blood and lymph nodes and identified a link between two processes—a signaling cascade known as mTOR—and convinced his doctors to give him a potent suppressor of the pathway called sirolimus. The drug had been on the market for more than a decade; it was often given to transplant patients to stop their immune systems from attacking a new organ. He has since been in remission for more than a decade. The article reads: “He focused on a central irony: the medication that saved his life already existed, and nobody had thought to give it to him. ‘There is a systemic problem,’ he told me. ‘There are all these drugs available, sitting in your local pharmacy, but they aren’t being used to treat all the conditions they could.’”
* * *
“Harnessing AI and Quantum Computing for Accelerated Drug Discovery: Regulatory Frameworks for In Silico to In Vivo Validation.” That’s the headline for an article in The Journal of Pharmaceutical and BioTech Industry about using technology to reduce the cost of drug discovery. The article describes using a detailed structural model of a protein to enable digital drug design to predict potential drug candidates, thereby reducing or eliminating the need for time-consuming laboratory and animal testing. The article reads, in part: “Knowing the molecular structure of a possible candidate drug can provide insights into how drugs interact with targets at an atomic level, at significantly lower expenditures, and with maximum effectiveness. AI and quantum computers can rapidly screen out potential new drug candidates, determine the toxicity level of a known drug, and eliminate drugs with high toxicity at the beginning of the drug development phase, thereby avoiding expensive laboratory and animal testing. The Food and Drug Administration (FDA) and other regulatory bodies are increasingly supporting the use of in silico to in vitro/in vivo validation methods and assessments of drug safety and efficacy.”
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.