Nobel laureate David Baker’s AI BioDesign initiative aims to create molecules not found in nature

David Baker, who shared the 2024 Nobel Prize in Chemistry for computational protein design, is leading AI BioDesign, a project that uses artificial intelligence and large-scale laboratory experiments to design molecules and biological functions not found in nature but physically and chemically possible. The initiative is a collaboration between the Allen Institute, the University of Washington, and the Fred Hutchinson Cancer Center.

The project aims to create databases, models, and tools that could serve as foundational resources for developing future medicines and technologies. Potential applications include new drugs for cancer and neurodegenerative diseases, enzymes capable of breaking down ocean plastics, and even biological computers. Baker describes the potential of these methods as comparable to historic technological transformations such as industrialization, electrification, and the digital revolution.

Baker highlights that computational design allows researchers to evaluate risks before synthesizing molecules, including unintended interactions with living systems, environmental effects, or misuse. He notes that designs can be screened computationally, tested in contained lab settings, and validated experimentally before real-world deployment. The project also advocates for governance structures, such as monitoring and logging synthetic DNA sequences and their creators, to address safety and security concerns.

The initiative explores the idea that nature has only sampled a fraction of what is physically and chemically possible in biological systems. By leveraging AI, researchers seek to engineer proteins—molecular machines central to all organic matter on Earth—with novel structures and functions. Baker’s team sets ambitious goals, including creating cures for new diseases within weeks, developing crops resilient to harsh conditions, and designing molecular machines to extract critical minerals from waste or repair infrastructure.

Baker acknowledges that AI models may design functional molecules whose mechanisms are not fully understood, a common pattern in scientific progress where observation of efficacy precedes mechanistic insight. While strong experimental evidence can justify advancing projects, deeper understanding remains a key objective for both research and broader scientific inquiry.

The project also addresses ethical questions about which molecules or biological functions should not be designed, even if technically possible. Baker argues that decisions should balance potential benefits against risks to public safety, security, or the environment. He advocates for evolving governance frameworks alongside advances in AI and biotechnology to ensure responsible development.