Want to bookmark your favorite articles and stories to read or view later? Start your independent membership today.
Join us today
Already a member? Log in
An artificial intelligence research lab in California said it has administered a personalized AI-designed virus to a human patient for the first time as a potential scalable solution to combating antibiotic-resistant superbugs.
AI lab Radical Numerics announced the treatment Tuesday, but it is awaiting scientific review in the form of a peer-reviewed study.
If verified, the treatment, named Omnii-1, could mark the first time AI-designed bacteriophages have been administered to a human patient.
These phages are viruses that specifically infect bacteria. Antibiotic-resistant superbugs are expected to cause nearly 40 million deaths by 2050.
In current approaches to treating bacterial infections with phages, researchers undertake a tedious search of large environmental collections of phages to find one that matches a patient’s specific infection.
It starts with clinicians extracting a sample of the bacteria causing a patient’s infection to find or engineer phages that kill the infectious virus.
The key to this challenge is understanding the genetic characteristics of a potential phage that can kill particular bacterial strains.
Phages kill bacteria through a multi-step process in which the virus first binds to specific receptor molecules on the surface of the target bacteria.
They then enter the bacterial cell to hijack it for their own replication and break it up.
The initial binding of the virus to bacteria is very specific, because a given phage only targets particular strains or species of bacteria.
This specificity is a crucial advantage of phage therapy, which spares beneficial gut microbes that tend to be affected by broad-spectrum antibiotics.
Radical Numerics claims its AI-based approach can lead to rapid, on-demand generation of phages meeting patient needs, thereby accelerating the turnaround time.
“In the world’s first clinical use of AI-designed phages, Omnii-1-generated models were administered to a patient with an antibiotic-resistant bacterial infection under an authorized, physician-led compassionate use pathway,” Radical Numerics wrote in a blog post.
“This marks a first step toward translating AI-guided genome design into personalized therapies,” he says.
The startup claimed that its AI model is trained on various genomic sequences and phage genomes, as well as data on previously measured phage-host interactions.
By leveraging this information, AI could identify and design candidate phages for specific therapeutic needs.
“We synthesize Omnii-1-designed phage variants and measure their recovery and activity on bacterial strains,” the startup said.
Recovery is a measure of a phage’s viability, which indicates whether an AI-designed viral genome can successfully come to life and replicate in the laboratory.
“These experiments help characterize the activity of our variants against target hosts and inform subsequent rounds of modeling and design,” explained Radical Numerics.
The company said its Omnii-1 designs were synthesized and administered to a human patient with an antibiotic-resistant infection who had very few medical options.
But it did not reveal specific details about the treatment’s clinical outcomes, citing patient confidentiality.
Gn Health
