معلومات عن هذه الحلقة
A drug can look promising in the laboratory and still fail when it reaches human testing. One of the biggest challenges in drug development is predicting what a compound will actually do inside the human body - including whether it will cause dangerous side effects. Could AI help us make those predictions more accurately, before patients are ever exposed?
Dr. Natalie Ma, Ph.D. is Chief Business Officer and a founding team member of Deep Origin ( https://deeporigin.com/ ), a company developing computational tools to help scientists understand biology and accelerate drug discovery.
Dr. Ma holds a PhD in Molecular Biology from Yale University, where her doctoral research focused on engineering biological systems with improved safeguards against genetic transfer and unintended escape. She began her career at the intersection of biotechnology research, biosecurity, and entrepreneurship, and subsequently helped build companies developing novel approaches to infectious disease and drug discovery, including Felix Biotechnology and BiosimAI, which was acquired by Deep Origin.
At Deep Origin, Dr. Ma works to bridge the gap between scientific innovation and practical applications in drug development. She is now helping advance an ambitious effort to transform how we predict the safety of potential medicines.
Through the ARPA-H-funded PREDICTS CATALYST program ( https://arpa-h.gov/explore-funding/programs/catalyst ), Deep Origin and its collaborators are developing computational models to predict how drug candidates interact with the human body, including potential toxicity and other safety risks. The effort includes new in-silico models and interconnected virtual organ systems designed to simulate aspects of human physiology.
With regulators increasingly exploring alternatives to traditional animal testing, this work raises important questions about the future of pharmaceutical research: How accurately can we predict human responses before clinical trials? What evidence will regulators need to trust these new methods? And could better predictions ultimately help us develop safer medicines, reduce failures, and bring effective treatments to patients faster?
#DeepOrigin #NatalieMa #ArtificialIntelligence #DrugDiscovery #DrugDevelopment #ADMET #Toxicology #VirtualHuman #ComputationalBiology #Biotechnology #PrecisionMedicine #PharmaceuticalResearch #ARPAH #AnimalTesting #FutureOfMedicine
