Barry Bunin, PhD
Founder & CEO
Collaborative Drug Discovery
“How an ‘Impossible’ Idea Led to a Pancreatic Cancer Breakthrough.” That’s the headline for an article in The New York Times about the drug daraxonrasib from Revolution Medicines, that is nearing regulatory approval and has substantially extended the lives of patients with pancreatic cancer. The article notes: “It works by targeting a cellular protein that fuels not just nearly all pancreatic tumors, but also many lung and colon cancers. Those three are the leading causes of cancer deaths.” The drug targets the KRAS protein, described as a “greasy ball” that was “impossible” to therapeutically attack. The Times reports, “And now that the protein-targeting strategy shows promise, multiple companies have jumped into the fray. Dozens of similar drugs are now being tested for cancers of the pancreas, lung and colon.”
* * *
“Precision Oncology in the Age of AI: Lessons from AI-Driven Drug Discovery and Clinical Translation.” That’s the title of a study published in BJC Report, a Springer Nature journal that points to a reported phase 2a randomized, placebo-controlled clinical trial that “has marked a significant inflection point in the field of translational medicine.” The study involves a TNIK inhibitor generated through de novo generative modeling that was evaluated in patients with idiopathic pulmonary fibrosis (IPF). The authors note TNIK, as a signaling kinase, is also relevant to tumor progression, making the study relevant to oncology drug discovery. They say: “This trial represents an early instance in which a small molecule identified using AI-supported compound generation advanced to clinical evaluation beyond preclinical proof-of-concept.” The paper concludes: “Importantly, the frameworks validated in this early trial may be particularly impactful for oncology. Cancer drug development is uniquely challenged by tumor heterogeneity, clonal evolution, and acquired resistance, creating an urgent need for adaptive and data-driven strategies. As integrative coordination frameworks, AI-enabled platforms can uniquely synthesize multi-omics data and real-time clinical feedback to address these complexities. Such a paradigm will facilitate the delivery of safer, more precise anticancer therapies, ultimately advancing the landscape of translational oncology.”
* * *
“Amazon Launches AI Drug Discovery Platform." Pharmaceutical Technology carries that headline about Amazon Web Services (AWS) launching an AI application to design and test novel drugs more quickly and confidently. The system, called Amazon Bio Discovery, gives researchers direct access to a broad catalogue of specialized AI biological foundation models (bioFMs) that are trained on vast biological datasets. The models are intended to evaluate and accelerate the development of new antibody therapies. “AI agents make powerful scientific capabilities accessible to all drug researchers, not just those with computational expertise,” said Rajiv Chopra, Vice President of AWS Healthcare AI and Life Sciences. “These AI systems can design drug molecules, coordinate testing, learn from results, and get smarter with each experiment.” Of course it is worth mentioning in passing that CDD Vault is available in multiple modalities on multiple continents, to support researchers wherever they are around the world 24/7 .
* * *
OpenAI Introduces GPT-Rosalind for Life Sciences Research. In a Research Release, OpenAI said Rosalind supports evidence synthesis, hypothesis generation, experimental planning, and other multi-step research tasks to accelerate early stages of discovery. OpenAI said, “Over time, these systems could help life sciences organizations discover breakthroughs that wouldn’t otherwise be possible, with a much higher rate of success.” This announcement must be considered in context with similar initiatives into life science from all the major AI companies (Anthropic, xAI/SpaceX, NVIDIA, Amazon, Microsoft, Google).
“Rethinking Nature’s Pharmacy: AI Era and Natural Product Drug Discovery.” That’s the title of a study published on PubMed about how AI can accelerate the discovery of natural products for therapeutics. The paper notes: “Natural products (NPs), also referred to as bioactive small molecules originating from sources such as plants, animals, fungi, and microorganisms, have constituted the cornerstone of medical practice for thousands of years. … Despite the long-standing success of natural products in drug discovery, the pharmaceutical sector experienced a pronounced decline in NP-driven research beginning in the 1990s. This transition was not attributable to a lack of therapeutic promise but rather to a set of inherent technical and logistical challenges that rendered the conventional discovery process inefficient, costly, and often unpredictable.” The authors go on to describe how AI can help: “The convergence of AI with complementary emerging technologies, such as organ-on-chip platforms and quantum computing, further augments this vision. These synergies promise enhanced accuracy in predicting drug behavior and more comprehensive modeling of biological complexity, significantly reducing false positives within the development pipeline. To achieve widespread adoption and regulatory acceptance, however, it is imperative to address issues with the interpretability of current deep learning systems. Developing explainable AI (XAI) frameworks will provide insight into algorithmic decision-making, thereby fostering scientific trust and facilitating integration into stringent regulatory processes.” Of course with future leaning statements, one must always consider both the challenges (and which will remain) vs the opportunities (which things will change and in which order).
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.