Artificial intelligence is making rapid advances in computational biology. Recently, Stanford researchers and the ARC Institute created the first genome generated by the world. In what can be called great, the new virus created by AI can infect and kill bacteria.
Scientists have already used AI to design individual protein and even small multiple gene systems. However, creating a complete genome is much more complex. In simple words, a genome must have many interactive genes and regulatory switches that allow an organism to grow, copy and survive. For scientists, until now, making all this work together was a great challenge.
“Genome Design requires orchesting multiple interacting genes and regulatory elements WHILE MAINTAING A BALANCE THAT ENABLE REPLICATION, HOST SPECIFICITY, AND EVOLUTIONARY FITNESS. Two-Component System, ”The Team Said In A Post On arcinstitute.org.
How did they do it?
In the test case, the researchers selected a small virus called bacteriophage φx174 (pronounced Phi-X-174). This virus infects E. coli bacteria and has a small but complicated genome: 5,386 DNA letters and 11 genes, most of which overlap each other. This virus was also the first genome to be completely sequenced in 1977 and the first synthesized from scratch in 2003. Now, it is the first to be designed by AI.
When it came to training AI, scientists used a genomic language model called Evo that was adjusted in thousands of genomes of the virus family so that the dialect of φx174 could speak. With the help of indications, the AI generated thousands of candidate genomes.
The team made a series of quality controls and laboratory tests. They built personalized software to ensure that each design consisted of all the essential key and protein genes necessary to infect E.Coli. Later, the team synthesized hundreds of these genomes in the laboratory and tried them by inserting them into bacteria to see if they could reproduce. After this, 16 new functional viruses emerged and each of them brought dozens to hundreds of mutations never seen in nature.
A prominent design even borrowed a protein full of DNA from a distant relative, something that human engineers had tried and failed to do before. CrioElectronics microscopy confirmed the new protein adjustment and worked inside the virus cover.
The story continues under this announcement
The scientists had trained Evo in 2M virus and then asked them to design new. Of 302 attempts, 16 proved to be functional in laboratory tests. IA viruses contained 392 mutations never seen in nature, including the combinations that scientists had previously tried and could not create. When bacteria developed resistance to natural viruses, the versions designed by AI passed through the defenses in the days when traditional viruses failed.
This is a significant achievement, since it marks a new phase in biotechnology. From reading DNA (sequencing) to writing it (synthesis) and now to design it, this is a new milestone. At a time when AI is redefining domains such as education, productivity and several ways of creativity, a development like this shows how far we have come. The greatest conclusion here is the unlimited potential that AI has to accelerate scientific discoveries and advances.
© ie Online Media Services Pvt Ltd
(Tagstotranslate) Virus designed by AI
Source link