Scientists at California-based biotech start-up Profluent have used artificial intelligence (AI) to design new proteins that can kill bacteria. The team used an AI system called ProGen to generate millions of new proteins and then test a sample of them to see if they worked.
Proteins are made up of chains of amino acids, and the sequence of these acids determines the protein’s shape and function. ProGen works in a similar way to AI systems that can generate text, and it learned how to generate new proteins by studying the grammar of how amino acids combine to form 280 million existing proteins.
Instead of the researchers choosing a topic for the AI to write about, they could specify a group of similar proteins for it to focus on. In this case, they chose a group of proteins with antimicrobial activity. The researchers programmed checks into the AI’s process so it wouldn’t produce amino acid “gibberish”, but they also tested a sample of the AI-proposed molecules in real cells.
Of the 100 molecules they physically created, 66 participated in chemical reactions similar to those of natural proteins that destroy bacteria in egg whites and saliva. This suggested that these new proteins could also kill bacteria. The researchers selected the five proteins with the most intense reactions and added them to a sample of Escherichia coli bacteria. Two of the proteins destroyed the bacteria.
The researchers then imaged them with X-rays. Even though their amino acid sequences were up to 30% different from any existing proteins, their shapes almost matched naturally occurring proteins. James Fraser at the University of California, San Francisco, who was part of the team, said it was not clear from the outset that the AI could work out how to change the amino acid sequence so much and still produce the correct shape.
This research demonstrates that AI-designed proteins can be effective in killing bacteria, and it opens up the possibility of using a similar approach to create new test molecules for drug development. However, it is worth noting that these molecules will still have to be tested in labs, which is time-consuming.