Executive Overview
For billions of years, life on Earth has evolved through a slow, relentless process of trial and error governed by natural selection. Every protein, enzyme, and biological structure studied by modern science represents a tiny fraction of what is biologically possible—only what evolution happened to forge under specific terrestrial conditions.
Today, a groundbreaking scientific initiative known as AI BioDesign is poised to shatter these natural limitations. By merging the predictive power of artificial intelligence with large-scale laboratory automation, researchers are beginning to design, synthesize, and test entirely new molecules and biological functions that have never existed in nature, yet are entirely compatible with the laws of physics and chemistry.
Spearheaded by a formidable coalition—including the Seattle-based biomedical research nonprofit the Allen Institute, the University of Washington, and the Fred Hutchinson Cancer Center—the initiative represents a philosophical and practical shift in how humanity interacts with biology. Leading the charge is David Baker, Chief Scientific Officer of AI BioDesign and co-recipient of the 2024 Nobel Prize in Chemistry for his pioneering work in computational protein design.
While the potential applications of this technology are staggering—ranging from bespoke cures for currently untreatable cancers and neurodegenerative disorders to ocean-clearing plastic-eating enzymes—they also invite critical scrutiny. Venturing into uncharted biological territory raises pressing questions regarding biosecurity, environmental safety, and the limits of human understanding in the age of machine learning. In an exclusive interview, David Baker sits down with WIRED to discuss the boundless promises, inherent risks, and profound responsibilities of engineering biology from scratch.
Detailed Chronology: The Road to Computational Protein Design
To understand the magnitude of AI BioDesign, it is essential to trace the rapid evolution of computational biology over the past few decades. The discipline has transitioned from basic observation to hyper-advanced generation at an unprecedented pace.
Phase 1: The Era of Observation and Sequencing (Late 20th Century)
For most of the history of molecular biology, scientists were constrained to studying what nature had already provided. Sequencing genomes and mapping natural protein structures consumed years of rigorous laboratory work. Researchers could modify natural proteins through directed evolution, but they were fundamentally bound to modifying pre-existing templates shaped by evolutionary history.
Phase 2: The Computational Turn and AlphaFold (2010s–2020)
The paradigm began to shift as computational power grew and algorithms improved. Scientists began developing physics-based models to predict how amino acid sequences fold into three-dimensional protein structures. This era culminated in breakthroughs like AlphaFold, which revolutionized structural biology by accurately predicting protein structures from sequences. This laid the groundwork for David Baker and his peers to ask a reverse question: Instead of predicting a structure from a sequence, can we design a sequence to form an entirely custom-built structure?
Phase 3: The Generative AI Boom in Biology (2021–2024)
With the advent of deep learning architectures—specifically generative models like diffusion networks (such as RFdiffusion)—the field entered a renaissance. Scientists could suddenly prompt computers to generate novel protein backbones from scratch, tailor-made to perform specific tasks. This monumental leap was validated globally when David Baker was awarded the 2024 Nobel Prize in Chemistry for computational protein design, cementing the transition of biology from an observational science to an engineering discipline.
Phase 4: The Birth of AI BioDesign (Present Day)
The launch of AI BioDesign marks the maturation of these technologies. By combining large-scale automated laboratory experiments with cutting-edge AI, the initiative moves beyond theoretical modeling into high-throughput physical synthesis, bridging the gap between digital generation and tangible, real-world application.
Supporting Context & Metrics: The Scale of the Biological Frontier
To grasp the potential of AI BioDesign, one must understand the sheer mathematical scale of the protein universe.
- The Protein Permutation Problem: Proteins are built from just 20 standard amino acids. However, a typical protein chain consisting of 200 amino acids yields $20^200$ possible combinations—a number that vastly exceeds the total number of atoms in the observable universe.
- Nature’s Tiny Slice: Out of this unfathomable combinatorial space, natural evolution has only sampled a microscopic fraction. AI BioDesign aims to chart the unmapped expanses of this vast chemical ocean.
- A New Industrial Revolution: Leaders in the field frequently compare the advent of computational synthetic biology to historic civilizational milestones. Much like industrialization automated physical labor, electrification powered cities, and the digital revolution connected the globe, programmable biology possesses the capacity to rewrite manufacturing, medicine, and environmental remediation.
Official Statements: An Exclusive Interview with David Baker
The following interview has been edited for length and clarity.
JORGE GARAY (WIRED): AI BioDesign seeks to explore possible molecules and biological functions that have never existed in nature. Are there any particular risks involved in venturing into this uncharted territory? How can scientists anticipate those risks and what steps can they take to minimize them before a designed molecule leaves the lab?
DAVID BAKER: What’s exciting about biology is that nature has explored only a fraction of what is physically and chemically possible, which opens a world of possibilities for what we could design. When we explore those possibilities, the primary risks are not much different than those associated with any new biological technology—unintended interactions with living systems, unexpected environmental effects, or misuse.
The advantage we have today is that computational design allows us to evaluate many of these risks before a molecule is ever synthesized. We can screen designs computationally, test them extensively in contained laboratory settings, and subject them to increasingly realistic experimental validation before considering any real-world application.
WIRED: The project mentions possibilities ranging from new drugs to plastic-degrading enzymes and even biological computers. If we have greater predictive power when designing new molecules and biological functions, how far do you think this capability could take us?
DAVID BAKER: My team and I have lofty goals for protein design: We’re working to build a world where a cure for a new disease is created in weeks, not decades. Where our air, water, and soil are clean because we removed pollutants and reimagined the processes that contaminated them. Where crops thrive in conditions that once killed them. Where molecular machines pull critical minerals from waste and repair the infrastructure we depend on.
Proteins are the molecular machines life has developed to create all organic matter we know of here on Earth. Unlocking their full potential requires that we derive engineering principles that make it possible for innovative new ideas, including ones we can’t yet imagine, to be achievable.
WIRED: As these models become more capable, could AI eventually design functional molecules that scientists themselves do not fully understand? If so, would it be enough to experimentally demonstrate that they work and are safe, or do you think we also need to understand the mechanisms?
DAVID BAKER: Science has often progressed in stages, and we see that mirrored in how machine learning has advanced protein design. The first step is usually observing that something works, and we often only later understand why. Machine learning is really good at that first stage—it has vastly improved our capability to observe patterns that can be leveraged for biological design. Strong experimental evidence can justify moving forward with projects, but deeper understanding remains an important objective both for our research and scientific inquiry overall. Much of what we cannot achieve today is due to a lack of understanding or data that defines the parameters for how specific systems work or do not. This is the crux of the AI BioDesign program.
WIRED: Are there molecules or biological functions that, in your opinion, should not be designed, even if it were technically possible to do so? What criteria should determine where that line is drawn?
DAVID BAKER: Decisions should be guided by a balance of potential benefits and potential harms. Applications that address major challenges in health, sustainability, or human well-being have a strong case for development. Conversely, designs that create significant risks to public safety, security, or the environment deserve heightened scrutiny and, in some cases, clear restrictions.
Just as we have developed frameworks for other powerful technologies, we need governance structures that evolve alongside advances in AI and biotechnology. I’ve advocated that those restrictions should include monitoring and logging all synthetic DNA that is manufactured to record the sequence and its creator. This creates a practical barrier to misuse and a record of any ill-intentioned attempts.
Future Outlook: Navigating the Promise and Peril of Programmable Life
As AI BioDesign continues to push the boundaries of what is chemically and biologically possible, humanity stands at a profound crossroads. The ability to engineer custom proteins opens up unprecedented horizons for healing disease, reversing environmental degradation, and manufacturing sustainable materials.
Yet, this power demands rigorous ethical oversight. The scientific community, policymakers, and technologists must work in tandem to establish robust guardrails—such as mandatory DNA synthesis screening, rigorous computational containment, and international regulatory frameworks—to ensure that synthetic biology is harnessed exclusively for the betterment of humanity.
By treating the unmapped vastness of biological possibility with both bold ambition and cautious stewardship, initiatives like AI BioDesign are not merely predicting the future of science—they are actively writing it from the molecule up.
