American scientists from Harvard Medical School have developed a program based on artificial intelligence (AI) to design proteins with certain properties. These biological elements are expected to be used as antibodies to fight cancer, in vaccines against viruses, to breed resistant crops, and for other purposes. The research was published in the scientific journal magazine Science.
The new neural network was called EVOLVEpro.
“We can create a better, faster, stronger protein. We can design it to be more effective at binding to a target, increase the effectiveness of treatment, or improve its function. If we can measure it, we can improve it,” said co-author Dr. Omar Abudayyeh.
The team has already used EVOLVEpro to develop six proteins. The researchers found that two AI-designed monoclonal antibodies were 30 times better at adhering to their targets.
The miniature CRISPR nuclease was five times more effective at making genetic changes. The protein used to edit the N gene was twice as efficient at inserting the sequences into different parts of the genome.
A protein called Bxb1 integrase was found to be four times more efficient at inserting DNA into cells for programmed gene integration applications, and T7 RNA polymerase, a protein for making RNA, was found to be 100 times more efficient at making exact copies of RNA; This is important. Scientists stated that it is used to produce mRNA for mRNA therapy or vaccines.
Previous scientists educated AI to detect difficult-to-treat liver disease before the first symptoms appear.
What are you thinking?
Source: Gazeta
Barbara Dickson is a seasoned writer for “Social Bites”. She keeps readers informed on the latest news and trends, providing in-depth coverage and analysis on a variety of topics.