David Baker's University of Washington lab has shifted protein design from a solitary pursuit into a collaborative ecosystem where over 100 researchers work toward creating custom proteins for medicine, vaccines, and biosensors. One year after winning the Nobel Prize in Chemistry for his foundational work in computational protein design, Baker describes his vision as a "communal brain" that combines deep learning methods with human creativity to achieve atomic-level precision in protein engineering.

What's the Difference Between Predicting Proteins and Designing Them?

When John Jumper and Demis Hassabis won the Nobel Prize alongside Baker for developing AlphaFold, their AI model solved a decades-old problem: predicting how a protein's amino acid sequence folds into a 3D structure. But Baker's work tackles a harder challenge: designing entirely new proteins that don't exist in nature, with sequences custom-built to perform specific tasks.

The scale of this challenge is staggering. A small protein made of just 100 amino acids has roughly 20 to the power of 100 possible sequences, yet only a vanishingly tiny fraction can fold into stable, functional structures. Misplacing a single amino acid by just one angstrom, a unit of measurement used to describe atomic distances, can mean the difference between a drug binding tightly to its target or failing completely.

Last November, Nathaniel Bennett, a former postdoctoral researcher in Baker's lab, published a landmark paper in Nature demonstrating that AI could now design full-length antibodies from scratch that bind to user-specified targets. This breakthrough addressed what Bennett calls the "holy grail" of antibody design: creating custom antibodies without time-consuming experimental screening, with applications across cancer and autoimmune disease.

Why Is Baker's Lab Culture Central to This Scientific Breakthrough?

Baker's approach to leadership directly shapes the lab's scientific output. Rather than operating as a traditional hierarchical research group, the Institute for Protein Design functions as what Baker calls a "communal brain," where researchers across multiple floors collaborate freely and challenge each other's work without fear of rank or status.

Graduate students and postdoctoral researchers describe a culture that prioritizes intellectual honesty over hierarchy. Seth Woodbury, a graduate student designing metallohydrolases for sustainability applications, noted that Baker actively facilitates connections between researchers whose expertise might unlock new directions. Woody Ahern, another graduate student, emphasized that Baker maintains "a very reasonable disdain for hierarchy," allowing anyone to speak up in meetings and question the work.

Baker implements practical rituals to reinforce this collaborative ethos. He hosts weekly chocolate hours and maintains a strict "no travel rule" in the weeks following his Nobel Prize win, choosing to remain fully present with his team despite avalanche of invitations and media attention. International graduate student Ria Sonigra, who reached out to Baker with a cold email before applying, noted that despite overseeing over 100 trainees, Baker knows each person's project and expectations before their next meeting.

How to Build a High-Impact Research Lab

• Prioritize mentorship over individual achievement: Baker emphasized that "the people that you mentor are more important than any science you do," recognizing that his former trainees have gone on to lead major biotech companies and academic departments.
• Create informal connection points: Weekly rituals like chocolate hour and open-door policies reduce barriers to collaboration and help researchers feel comfortable asking colleagues for help or feedback.
• Flatten hierarchical structures: Allowing graduate students and postdocs to question senior researchers' work and speak freely in meetings breeds a culture focused on scientific merit rather than rank.
• Invest in international talent: Baker actively supports international students by connecting them with peers and helping navigate application processes, expanding the lab's diversity and global perspective.

What's the Gap Between Lab Success and Real-World Medicine?

Despite the excitement around AI-designed proteins, Baker is candid about the distance between computational success and clinical reality. When asked to separate hype from reality, he stated clearly: "The reality is that we can now design proteins on a computer. The hype is that for therapeutics, there's a lot more than the basic activity of a protein binding or catalyzing a reaction. Whether de novo proteins will revolutionize medicine will require improving our understanding of the biology".

AI-designed proteins must clear multiple hurdles before becoming medicines. They need to be manufacturable at scale, remain stable in the human body, and avoid triggering unwanted immune responses or side effects. This gap has fueled industry debate over whether generating entirely new therapeutic proteins is even feasible, despite recent breakthroughs in antibody design.

Bennett, who co-founded Xaira Therapeutics in 2024 with over 1 billion dollars in total funding, is now testing whether AI-designed proteins can clear these real-world hurdles. The company's leadership team includes Baker as scientific advisor and Marc Tessier-Lavigne, former president of Stanford and Chief Scientific Officer of Genentech, as CEO. The board includes Nobel laureate Carolyn Bertozzi, former FDA head Scott Gottlieb, and former Johnson & Johnson CEO Alex Gorsky, reflecting the high stakes and resources devoted to translating protein design into medicine.

How Did Protein Design Become a Nobel-Worthy Field?

Baker's Nobel Prize recognition reflects decades of foundational work by the broader structural biology community. The field's early breakthroughs trace back to 1988, when William DeGrado demonstrated that protein sequences not found in nature could achieve stable 3D folds, challenging the long-held belief that only evolution could create functional proteins. A decade later, Steve Mayo led a Science study showing that an in silico predicted protein could be experimentally validated to adopt a target structure.

Baker and then-postdoctoral researcher Brian Kuhlman expanded the scope in 2003 by designing proteins with flexible backbones that represented entirely new folds, making it possible to create new proteins from scratch rather than just modifying natural ones. Top7, the first protein created on a computer with a custom amino acid sequence that folds into a never-before-seen structure, became a symbol of this achievement.

Today, DeGrado, Mayo, and Kuhlman continue advancing structural biology as prominent faculty members at the University of California San Francisco, California Institute of Technology, and University of North Carolina Chapel Hill, respectively. Baker emphasized that "the prize was given because protein design has so much promise now, and that reflects the work of the whole community," acknowledging that his Nobel recognition represents a collective scientific achievement rather than individual brilliance.

Baker

The 2024 Nobel Prize ceremony itself underscored AI's transformative reach across disciplines. Baker shared the Chemistry Prize with Demis Hassabis and John Jumper for AlphaFold, while Geoffrey Hinton and John Hopfield won the Physics Prize for foundational discoveries in machine learning with neural networks. Together, these prizes marked a pivotal moment when AI moved beyond computer science to become a transformative force across biology, chemistry, and physics, earning recognition as a breakthrough deemed to confer the "greatest benefit to humankind".

Baker