AI can design new proteins unlock new cures materials 

The new tool, ProteinMPNN, is described by a group of researchers from the University of Washington in two papers published in Science Today (available over here And the over here), a powerful supplement to that technology.

The papers are the latest example of how deep learning is revolutionizing protein design by providing scientists with new research tools. Traditionally researchers design proteins by modifying those that occur in nature, but the MPNN protein will open up a whole new world of potential proteins for researchers to design from scratch.

“In nature, proteins solve essentially all of life’s problems, from accumulating energy from sunlight to making molecules. Everything in biology happens from proteins,” says David Baker, one of the scientists behind the research and director of the Institute for Protein Design at the University of Washington.

“It has evolved over the course of evolution to solve problems that organisms have encountered during evolution. But we are facing new problems today, like Covid. If we could design proteins that were as good at solving new problems as those that evolved during evolution at solving old problems, they would be really powerful.” “.

Proteins are made of hundreds of thousands of amino acids that are linked into long chains, which are then folded into three-dimensional shapes. AlphaFold helps researchers predict the resulting structure, and provides insight into how they might behave.

The MPNN protein will help researchers solve the inverse problem. If they already have a precise protein structure in mind, this will help them find the amino acid sequence that folds into this shape. The system uses a neural network trained on a very large number of examples of amino acid sequences, which fold into 3D structures.

But researchers also need to solve another problem. To design proteins that tackle real-world problems, such as a new enzyme that digests plastic, they must first figure out which protein backbone will have this function.

To do this, researchers in Becker’s lab use two machine learning methods, detailed in Article – Commodity In Science last July, the team calls them “restrictive hallucinations” and “in painting.”

Leave a Comment