AI-designed viruses given to a patient for the first time

Radical Numerics uses its Omnii-1 model to craft bacteriophages delivered under compassionate-use rules, but publishes no patient results

By LineZotpaper
Published
Read Time2 min
A San Francisco AI lab says it has become the first to give a human patient a cocktail of viruses designed by an AI model, a milestone in moving AI-designed biology from the laboratory to the clinic. Radical Numerics announced this week that its Omnii-1 model designed bacteriophages, viruses that attack bacteria, and that the resulting cocktail was administered to a patient under a compassionate-use arrangement. The company has not disclosed how the patient fared.

Radical Numerics, an AI lab focused on bioscience, said the treatment is believed to be the first time a cocktail containing AI-designed bacteriophages has been given to a human. Phages are viruses that specifically infect bacteria and are increasingly sought as an alternative to antibiotics as drug-resistant infections spread.

The company publicly unveiled its AI model, Omnii-1, this week. Using the model, researchers designed viable phages and tested them against bacteria isolated from the antibiotic-resistant infection afflicting their patient. "The cocktail containing Omnii-1-designed phage variants eliminated the patient's antibiotic-resistant isolate in vitro," the company said in its write-up, adding that the investigational cocktail was subsequently administered under compassionate use.

The write-up stops there. Radical Numerics published no results from the human administration, citing the need to protect the patient's privacy, and warned that observations from a single patient do not establish that the therapy is generally safe or effective. It did not say what infection the patient had, though the research describes testing Omnii-1's ability to predict phages that infect Pseudomonas aeruginosa, a bacterium that can cause resistant infections in burn wounds and persistent lung infections in cystic fibrosis patients. The model "performed competitively" against a specialised model at predicting phage-host interactions, according to the company, though nothing in the write-up indicates the patient was infected with Pseudomonas.

The work builds on earlier research, including a Stanford University and Arc Institute project in which AI-designed phages targeting E. coli outperformed a biological predecessor in laboratory tests. Radical Numerics said its result marks "an important milestone in translating AI-designed biology from computational predictions and laboratory validation to clinical administration." The company hopes the work will lead to a process for designing and building phages targeted to individual bacterial infections. The Register reported that Radical Numerics did not respond to questions for this story.

§

Analysis

Why This Matters

  • First clinical administration of AI-designed phages, if confirmed, moves the field from computational predictions and lab validation into human testing.
  • It offers a potential route to personalised treatments for antibiotic-resistant infections, a growing global health threat.
  • The absence of published patient outcomes means the milestone concerns the attempt itself, not yet any evidence of effectiveness.

Background

Bacteriophages were discovered more than a century ago and have long been used as antibacterial agents in parts of the world, but they fell out of broad use in many countries with the rise of antibiotics. Renewed interest has come as antimicrobial resistance has made some antibiotics less effective. Phages appeal because they can target specific bacterial strains, potentially sparing the beneficial gut bacteria that broad-spectrum antibiotics wipe out. AI is already being used to speed up phage engineering, as demonstrated by last year's Stanford and Arc Institute work. Radical Numerics' administration is the first reported use of AI-designed phages in a human, though the company itself stresses the limits of a single case.

Key Perspectives

Radical Numerics: The company frames the treatment as an important milestone and is cautious about overclaiming, noting that observations from a single patient do not establish safety or effectiveness. It hopes to build a process for designing patient-specific phages. Clinicians and researchers: They will want to see results and formal trials. The company itself acknowledges the evidentiary limits, and the prior academic work shows AI-designed phages can work in the lab, but clinical evidence remains absent. Patients with drug-resistant infections: They could benefit if the approach proves effective, making the lack of published outcome data a source of uncertainty about whether the promise will be realised. Critics and skeptics: The single-patient nature of the case and the absence of reported outcomes make it impossible to assess safety or efficacy. Regulatory and manufacturing hurdles remain before personalised AI phage therapy becomes practical.

What to Watch

  • Whether Radical Numerics or the treating clinicians publish any outcome from the compassionate-use case.
  • Any further compassionate-use administrations of Omnii-1-designed phages.
  • Movement toward formal clinical trials, which would provide the evidence needed to establish the therapy's safety and effectiveness.

Sources

Checked

12 claims in this story checked against 1 source: 10 supported.

Show each claim
  1. Partly supportedAI-designed viruses were given to a patient for the first time.www.theregister.com - Articles: “announced the treatment this week, claiming it marks the first time a cocktail containing AI-designed bacteriophages has been administered to a human patient under a compassionate-use arrangement.”
  2. SupportedRadical Numerics says it was the first to give a human patient a cocktail of AI-designed bacteriophages.www.theregister.com - Articles: “Radical Numerics, a San Francisco-based AI lab developing AI models for bioscience, announced the treatment this week, claiming it marks the first time a cocktail containing AI-designed bacteriophages has been administered to a human patient under a compassionate-use arrangement.”
  3. SupportedOmnii-1 was used to design bacteriophages for the cocktail.www.theregister.com - Articles: “Omnii-1, the AI model publicly unveiled by Radical Numerics this week, was used to design viable bacteriophages”
  4. SupportedResearchers tested the designed phages against bacteria isolated from the patient’s antibiotic-resistant infection.www.theregister.com - Articles: “the company used its own AI model to design bacteriophages, which it then tested against bacteria isolated from the antibiotic-resistant infection its patient was suffering from.”
  5. SupportedThe company said, “The cocktail containing Omnii-1-designed phage variants eliminated the patient's antibiotic-resistant isolate in vitro.”www.theregister.com - Articles: ““The cocktail containing Omnii-1-designed phage variants eliminated the patient's antibiotic-resistant isolate in vitro,” the company explained”
  6. SupportedThe investigational cocktail was administered to the patient under compassionate use.www.theregister.com - Articles: ““The investigational cocktail was subsequently administered to the patient under compassionate use.””
  7. SupportedRadical Numerics has published no results from the human administration, citing patient privacy.www.theregister.com - Articles: “Radical Numerics didn’t publish anything about the results of testing the phage in a human, citing the need to protect their privacy.”
  8. SupportedThe company cautioned that observations from one patient do not establish that the therapy is generally safe or effective.www.theregister.com - Articles: “The company also doesn’t want to give the impression that its AI phage therapy is generally safe or effective, noting that observations from a single patient don’t establish much of anything.”
  9. SupportedThe patient’s infection was not identified.www.theregister.com - Articles: “It’s not even stated what infection the patient was suffering from”
  10. Partly supportedThe research says Pseudomonas can cause resistant infections in burn wounds and persistent lung infections in cystic fibrosis patients.www.theregister.com - Articles: “a bacterium that can develop antibiotic resistance and cause infections in patients with burns and other wounds, as well as persistent lung infections in cystic fibrosis patients.”
  11. SupportedThe company’s write-up says the model “performed competitively” against a specialised model at predicting phage-host interactions.www.theregister.com - Articles: “The AI model “performed competitively” against a specialized model at predicting phage-host interactions, the research write-up notes.”
  12. SupportedRadical Numerics called the work “an important milestone in translating AI-designed biology from computational predictions and laboratory validation to clinical administration.”www.theregister.com - Articles: ““This marks an important milestone in translating AI-designed biology from computational predictions and laboratory validation to clinical administration,” Radical Numerics said of its work.”

Zotpaper

Written by Harper Lane on the Tech & AI desk. Claims checked by Ines Fairley, verification. Edited by Angus Burke, chief sub. Plate by Ollie Flash, picture desk.

1 source10 of 12 claims matched to a sourcefirst published
Meet the newsroomHow we workSubscribe