Latest posts

  • Diverse protein assemblies by (negative) design

    Diverse protein assemblies by (negative) design

    A new approach for creating custom protein complexes yields asymmetric assemblies with interchangeable parts. Today we report in Science the design of new protein assemblies made from modular parts. These complexes — which adopt linear, branching, or closed-loop architectures — contain up to six unique proteins, each of which remains folded…

  • Breakthrough of the Year

    Breakthrough of the Year

    The journal Science has selected artificial intelligence algorithms that predict the three-dimensional shapes of proteins — as well as the blizzard of protein structures they have revealed — as their 2021 Breakthrough of the Year. We are honored to have our work in this field recognized alongside that of the…

  • Deep learning dreams up new protein structures

    Deep learning dreams up new protein structures

    Just as convincing images of cats can be created using artificial intelligence, new proteins can now be made using similar tools. In a new report in Nature, we describe the development of a neural network that “hallucinates” proteins with new, stable structures. “For this project, we made up completely random…

  • UW BIOFAB: a force for reproducible science

    UW BIOFAB: a force for reproducible science

    This article was written by Renske Dyedov (UW) Key to advancing any new scientific discovery is the ability for researchers to independently repeat the experiments that led to it. In science today, particularly biology, the lack of reproducibility between experiments is a major problem that slows scientific progress, wastes resources…

  • Deep learning reveals how proteins interact

    Deep learning reveals how proteins interact

    A team led by scientsts in the Baker lab has combined recent advances in evolutionary analysis and deep learning to build three-dimensional models of how most proteins in eukaryotes interact. This breakthrough has significant implications for understanding the biochemical processes that are common to all animals, plants, and fungi. This…

  • COVID-19 vaccine with IPD nanoparticles meets Phase 1/2 trial goals

    COVID-19 vaccine with IPD nanoparticles meets Phase 1/2 trial goals

    This report was written and translated into English by SK bioscience. (Image: SK bioscience) SK bioscience (CEO Jae-yong Ahn) announced on November 4th that the company has confirmed a positive immune response and safety in the final analysis result of the phase I/II clinical trial of the COVID-19 vaccine candidate,…

  • Baker lab joins USAID’s $125M project to detect emerging viruses

    Baker lab joins USAID’s $125M project to detect emerging viruses

    To better identify and prevent future pandemics, the University of Washington has become a partner in a five-year global, collaborative agreement with the U.S. Agency for International Development. The newly launched Discovery & Exploration of Emerging Pathogens – Viral Zoonoses, or DEEP VZN project, has approximately $125 million in anticipated…

  • Stephanie Berger wins additional WRF translational funding

    Stephanie Berger wins additional WRF translational funding

    Washington Research Foundation (WRF) has awarded a $700,000 phase three technology commercialization grant to Stephanie Berger, Ph.D., to support the development of an oral biologic for inflammatory bowel disease (IBD). Berger, a translational investigator at the Institute for Protein Design, received two previous grants totaling $300,500 from WRF for this…

  • On the passing of Tachi Yamada

    On the passing of Tachi Yamada

    Tadataka “Tachi” Yamada MD, KBE served as the Advisory Board Chair of our Institute since its founding almost ten years ago. His tremendous mentorship helped us in innumerable ways to grow from a single-PI Institute founded by David Baker to a group of five faculty and almost 200 scientists and…

  • RoseTTAFold: Accurate protein structure prediction accessible to all

    RoseTTAFold: Accurate protein structure prediction accessible to all

    Today we report the development and initial applications of RoseTTAFold, a software tool that uses deep learning to quickly and accurately predict protein structures based on limited information. Without the aid of such software, it can take years of laboratory work to determine the structure of just one protein. With RoseTTAFold,…