
Proteins designed with an ultra-rapid software tool called ProteinMPNN were much more likely to fold up as intended. Credit: Ian Haydon, UW Medicine Institute for Protein Design
Key Points:
- Across multiple papers, researchers used machine learning to create protein molecules more accurately and quickly than previously possible.
- Among the new proteins made were nanoscale rings the researchers believe could become parts for custom nanomachines.
- The findings could lead to new advancements in pharmaceutical research, such as drug development and disease treatment, as well as environmental research, including carbon capture and sustainable materials.
In the new papers, biologists at the University of Washington School of Medicine show that machine learning can be used to create protein molecules much more accurately and quickly than previously possible.
To go beyond the proteins found in nature, the research team broke down the challenge of protein design into three parts and used new software solutions for each.
First, a new protein shape must be generated. In a paper published July 21 in Science, the team showed that artificial intelligence can generate new protein shapes in two ways.
Second, to speed up the process, the team devised a new algorithm for generating amino acid sequences. Described in the Sept. 15 issue of Science, this software tool, called ProteinMPNN, runs in about 1 second. That’s more than 200 times faster than the previous best software. Its results are superior to prior tools, and the software requires no expert customization to run.
Third, the team used AlphaFold, a tool developed by Alphabet’s DeepMind, to independently assess whether the amino acid sequences they came up with were likely to fold into the intended shapes.
In another paper appearing in Science Sept. 15, a team from the same lab confirmed that the combination of new machine learning tools could reliably generate new proteins that functioned in the laboratory.
“We found that proteins made using ProteinMPNN were much more likely to fold up as intended, and we could create very complex protein assemblies using these methods,” said project scientist Basile Wicky, a postdoctoral fellow at the Institute for Protein Design and part of the Baker Lab at University of Washington.
Among the new proteins made were nanoscale rings the researchers believe could become parts for custom nanomachines.
Overall, the scientists say they hope this advance will lead to many new vaccines, treatments, tools for carbon capture, and sustainable biomaterials.
“This is the very beginning of machine learning in protein design. In the coming months, we will be working to improve these tools to create even more dynamic and functional proteins,” said David Baker, director of the Institute for Protein Design.
Information courtesy of University of Washington.