The sexually transmitted disease has become increasingly resistant to existing antibiotics.

© Science Photo Library/Science Source

A Nobel laureate, he identified an enzyme that cuts DNA, laying the groundwork for milestones in scientific research and medicine, like insulin.

© Marty Katz for The New York Times

AI systems have recently had a lot of success in one key aspect of biology: the relationship between a protein’s structure and its function. These efforts have included the ability to predict the structure of most proteins and to design proteins structured so that they perform useful functions. But all of these efforts are focused on the proteins and amino acids that build them.

But biology doesn’t generate new proteins at that level. Instead, changes have to take place in nucleic acids before eventually making their presence felt via proteins. And information at the DNA level is fairly removed from proteins, with lots of critical non-coding sequences, redundancy, and a fair degree of flexibility. It’s not necessarily obvious that learning the organization of a genome would help an AI system figure out how to make functional proteins.

But it now seems like using bacterial genomes for the training can help develop a system that can predict proteins, some of which don’t look like anything we’ve ever seen before.

Read full article

Comments

© CHRISTOPH BURGSTEDT/SCIENCE PHOTO LIBRARY

ByHeart, the maker of the product, has been linked to an outbreak of illnesses among infants that led to their hospitalizations.

© Cheyanne Mumphrey/Associated Press

A Pennsylvania plant run by the company, ByHeart, was shut down this year after inspectors found mold, a leaking roof and more than 2,500 dead insects in a food production area.

© Eugene Gologursky/Getty Images