Category: Publications
-
Introducing All-Atom versions of RoseTTAFold and RFdiffusion
In a recent preprint, we describe deep-learning breakthroughs that significantly expand the types of proteins and protein assemblies that can be modeled and designed using computers. This work updates two of our most powerful software tools, RoseTTAFold and RFdiffusion, by training them to operate on additional types of molecules beyond just proteins. Through these efforts, we aim to both…
-
Designing protein crystals with sub-nanometer accuracy
Today we report in Nature Materials a general strategy for creating proteins that form into precise and pre-specified crystalline structures. The ability to design such biomaterials with high accuracy sets the stage for the development of advanced optical tools, new technologies for chemical separation, and a range of other applications in biotechnology and medicine. This…
-
Beau Lonnquist and Nathan Greenwood win undergraduate research awards
Congratulations to two of our outstanding undergraduate researchers, Nathan Greenwood and Beau Lonnquist, on receiving prestigious awards from the UW Office of Undergraduate Research! Nathan Greenwood, Washington Research Foundation Fellowship Nathan Greenwood is a fourth-year student at the University of Washington studying Molecular, Cellular, and Developmental Biology. He is interested in the interface of biochemistry…
-
Silk, Wool, and Beyond: AI-Driven Design of Custom Protein Fibers
Today we report in Nature Chemistry a novel approach to designing protein fibers that takes inspiration from silk, wool, and spider webs. This research opens up new avenues in textiles, bioengineering, and beyond. “Silk, wool, and spider webs are all examples of natural protein fibers, and each has a unique blend of flexibility, strength, and…
-
Switch-like proteins inspired by transistors
Today we report in Science the design of custom proteins that can switch between two fully structured conformations. By coupling this molecular motion with a binding event, these proteins serve as biological counterparts to electronic transistors, opening the door to new applications in smart therapeutics, environmental sensing, and more. A team led by postdoctoral scholars…
-
RFdiffusion: A generative model for protein design
A team led by scientists in our lab has created a powerful new way to design proteins by combining structure prediction networks and generative diffusion models. The team demonstrated extremely high computational success and experimentally tested hundreds of A.I.-generated proteins, finding that many may be useful as medications, vaccines, or even new nanomaterials. Originally appearing…
-
Design of heme-binding enzymes
Today we report in JACS [Open Access] the design of enzymes that contain heme, an important iron-containing molecule involved in many biological processes. The design was inspired by the structure and function of natural heme-binding enzymes, including cytochrome P450, which are involved in a wide range of chemical reactions both inside the body and beyond.…
-
Lab Retreat at Pack Forest
In the beautiful backdrop of the University of Washington’s Pack Forest conference center, our team recently gathered for an immersive lab retreat focused on science and community. As a larger-than-average research group, we believe such gatherings are key to maintaining our culture of collective contribution. They also allow for cross-pollination of ideas among people who…