On AI Advances in Scientific Research
Last week, researchers from Arc Institute, NVIDIA, Stanford University, UC Berkeley, and UC San Francisco introduced Evo 2, an AI-driven "genomic foundation model" designed to understand and generate biological sequences—specifically DNA, RNA, and proteins—across the tree of life, leveraging a massive dataset and advanced AI architecture.
Brian Hie, Assistant Professor of Chemical Engineering at Stanford University and Arc Institute Innovation Investigator: "With Evo 2, we make the biological design of complex systems more accessible to researchers, enabling the creation of new and beneficial advances in a fraction of the time it would previously have taken.”
Patrick Hsu, Arc Institute Co-Founder and Assistant Professor of Bioengineering at UC Berkeley: “Evo 2 represents a major milestone for generative genomics. By advancing our understanding of these fundamental building blocks of life, we can pursue solutions in healthcare and environmental science that are unimaginable today."
Anthony Costa, director of digital biology at NVIDIA: “Evo 2 has fundamentally advanced our understanding of biological systems ... by overcoming previous limitations in the scale of biological foundation models with a unique architecture and the largest integrated dataset of its kind … the Arc Institute has given scientists around the world a new partner in solving humanity’s most pressing health and disease challenges.”
Separately, Google in collaboration with Imperial College and Stanford University announced an AI co-scientist to help scientists generate novel hypotheses and research proposals, accelerating scientific and biomedical discoveries.
Dr. Tiago Dias da Costa, Imperial College London: “We spend a considerable amount of time identifying the right scientific questions to ask, designing experiments to answer them, and evaluating the results - sometimes only to uncover inconclusive or uninformative findings … this could be game-changing; ruling out ‘dead ends’ and effectively enabling us to progress at an extraordinary pace.”
Vivek Natarajan, Google AI Research: “The AI co-scientist is designed to be a tool that helps scientists by generating hypotheses and research plans, but it’s not meant to replace the scientist.”
OUR TAKE
Both Evo 2 and Google’s AI Co-Scientist underscore AI’s transformative role in scientific research —Evo 2 as a specialized platform for genomic breakthroughs, and the AI Co-Scientist as a tool for hypothesis formation across multiple scientific disciplines.
Beyond their stated research focus, their capabilities could be leveraged in fields like astrobiology and materials design for Evo 2, or urban planning, economic forecasting and climate modeling for the AI Co-Scientist.
These advances in scientific discovery raise technical, ethical, regulatory, and societal challenges that require collaboration among scientists, developers, business leaders, and policymakers to be effectively addressed.