{"id":61860,"date":"2025-09-12T22:06:50","date_gmt":"2025-09-12T20:06:50","guid":{"rendered":"https:\/\/pharma-trend.com\/en\/medra-launches-continuous-science-platform-to-power-the-scientific-frontier\/"},"modified":"2025-09-12T22:06:50","modified_gmt":"2025-09-12T20:06:50","slug":"medra-launches-continuous-science-platform-to-power-the-scientific-frontier","status":"publish","type":"post","link":"https:\/\/pharma-trend.com\/en\/medra-launches-continuous-science-platform-to-power-the-scientific-frontier\/","title":{"rendered":"Medra Launches Continuous Science Platform to Power the Scientific Frontier"},"content":{"rendered":"
\n

SAN FRANCISCO–(BUSINESS WIRE)–Medra, a startup building \u201cPhysical AI for experimentation,\u201d today announced the launch of its Continuous Science Platform<\/b>, a first-of-its-kind system that integrates robotics and AI to accelerate scientific data generation and discovery.<\/p>\n

<\/a>
<\/a><\/p>\n

\nMedra\u2019s vision is grounded in a simple belief: if AI will one day help eradicate disease, science must first overcome the problem of data scarcity. Unlike large multimodal foundation models trained on massive datasets, scientific AI models remain constrained by decades-long bottlenecks in data creation. AlphaFold2, the protein-folding model that earned Google DeepMind the Nobel Prize in Chemistry, was trained on protein structures collected over nearly 50 years, representing just 0.3% of the data used to train today\u2019s largest AI models.<\/p>\n

\n\u201cScientific frontier models need 1,000X more training data to match the intelligence of current multimodal reasoning models,\u201d said Michelle Lee, PhD, CEO of Medra<\/b>. \u201cThe only way forward is to rethink how we generate scientific data, compressing decades of discovery into months.\u201d<\/p>\n

\nContinuous Science: Physical AI + Scientific AI<\/b><\/p>\n

\nMedra has built new technology that combines the intelligence of general purpose robots with the scientific reasoning of large language models to run lab experiments at scale. It\u2019s a self-improving, closed loop system made up of two parts: Physical AI and Scientific AI.<\/p>\n