This time, the virus is on the patient's side. AI helped design it
AI can write emails, create seasoning blends or put pets in Renaissance outfits. One adventurous baker used ChatGPT to concoct a cake from sauerkraut and seaweed. Now, there's an AI-made virus on the scene.
In October, biotech firm Radical Numerics reported the first use of AI-designed viruses in a patient suffering from an antibiotic-resistant infection. Collaborating with Tabula Bioscience, the team utilized a model known as Omnii to develop these viruses. While antibiotics have traditionally been used to treat illnesses like strep throat and bacterial pneumonia, bacteria have evolved to become resistant to these treatments.
According to the Centers for Disease Control and Prevention, over 9.3 million drug-resistant infections occur in the U.S. each year, posing a significant threat, potentially claiming nearly 40 million lives between 2025 and 2050.
Bacteriophages, or phages for short, offer a promising alternative. These viruses specifically target and kill harmful bacteria. However, the challenge lies in identifying a phage that effectively attacks the particular bacterial strain infecting the patient. To overcome this hurdle, scientists first need to determine the exact strain of bacteria causing the infection.
Each strain has a unique set of molecular equipment, or proteins, encoded in sections of DNA. A phage must have its own corresponding molecular machinery to latch onto the bacterium.
To design a phage that can target a specific bacterial strain, scientists begin with an existing prototype and modify the protein-based "legs" of the virus. By tweaking the genes responsible for these proteins, the phage can gain the ability to attach to a strain of bacteria it couldn't previously infect. Once the DNA of the phage is introduced into the bacterial cell, it can hijack the cell's machinery to produce more copies of the virus.
The process of determining which genetic tweaks will produce the desired phage is complex and where AI can assist. By learning the typical DNA sequence of the bacterium, the model can predict the likely nucleotide building blocks within the DNA of the phage. With this information, scientists can make informed decisions about the modifications needed to create an effective phage. The AI model suggests changes to the DNA coding for the phage's anchoring proteins, essentially serving as a prompt for the scientist.
Radical Numerics is keeping the specifics of the virus's administration to the patient confidential. The treatment, while promising, still requires passage through clinical trials and has not received official approval from the Food and Drug Administration. Nonetheless, the company's report has not been peer-reviewed, and the patient's outcome remains unknown.
This cautious optimism comes with a reminder of the potential risks associated with creating synthetic organisms, as any mutations that arise could lead to unintended consequences.
Written by urgent.news from Medical Xpress's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.