Good news! Welcome to novel antibiotics! This is only the beginning and this could be a breakthrough!
When will we be able to remove the sneezing gene from the human genome? 😊
"In brief
- Bacteriophages kill bacteria, and scientists hope engineered phages could work as new antibiotics.
- Stanford researchers applied a generative AI model, called Evo 2, to this challenge. Given a starting place – in this case bacteriophage ΦX174 – Evo 2 suggested new DNA sequences.
- Based on genomes written by Evo 2, the researchers synthesized and tested nearly 300 phages for effectiveness against E. coli.
They ended up with 16 that proved exceptional. - Given its potential, the researchers have made Evo 2 openly and freely available. Acknowledging safety concerns, they point to the importance of having tools like Evo 2 to address existing natural pathogens and the ability to build safety checks into AI tools – something that doesn’t happen when pathogens evolve naturally.
..."
From the editor's summary and abstract:
"Editor’s summary
The ability to design complex biological systems with artificial intelligence (AI) has the potential to transform biotechnology, but progress has largely been limited to the scale of individual genes and proteins, with whole-genome design remaining out of reach.
King et al. used generative AI models trained on millions of natural genomes to design entire bacteriophages ...
Experimental tests yielded 16 functional genomes with diverse sequences, structures, and fitness profiles.
A cocktail of the generated bacteriophages rapidly overcame bacteria that had evolved resistance to a natural bacteriophage. This work lays a foundation for AI-guided design of biological function at the whole-genome scale. ...
Structured Abstract
INTRODUCTION
Evolution continuously forges new biological innovations written in genomes. Navigating this vast design space could access functions that would transform biotechnology, but even the simplest genomes are highly complex and can be rendered nonviable by a single mutation. Accordingly, most progress in biological design has been made at the scale of individual genes and gene circuits, whereas design at the scale of whole genomes has remained largely beyond reach.
RATIONALE
Genome language models are artificial intelligence (AI) algorithms that have shown promise in designing biological systems. Much like how other language models are trained on large corpora of text, genome language models are trained on large corpora of DNA comprising millions of genomes from all domains of life. This enables these models to learn the evolutionary constraints that shape DNA sequences in nature.
However, the ability of genome language models to generate entire functional genomes has not been tested.
Bacteriophages, viruses that infect bacteria, are specifically well suited for this task, as they are relatively small, experimentally tractable, and have broad applications in molecular biology, microbial engineering, and therapeutics.
RESULTS
In this work, we leveraged genome language models, Evo 1 and Evo 2, to generate complete phage genomes with realistic genetic architectures and specificity for a bacterial host, Escherichia coli C.
Using the natural phage ΦX174 as a design template, we established a framework for generating and evaluating thousands of AI-generated genomes, nearly 300 of which we chemically synthesized and tested in laboratory conditions, yielding 16 viable phages.
The viable generated phages showed strong host specificity and diverse fitness profiles, including competitive infection kinetics. The generated phages were different from any known natural phages, exhibiting de novo mutations, divergent genes and regulatory elements, and variable genome lengths.
One of the phages utilized a DNA packaging protein from an evolutionarily distant phage in its capsid structure.
We also tested whether the generated phages could overcome bacterial resistance, a central challenge in developing phage-based antimicrobial therapies, and found that a mixture of designed phages rapidly overcame ΦX174-resistant E. coli strains, whereas a comparable mixture of naturally sourced ΦX174-like phages could not.
CONCLUSION
Our results demonstrate that generative models capture evolutionary constraints in DNA sequences with enough fidelity to produce complete bacteriophage genomes divergent from those observed in nature and with prespecified traits.
Our approach expands what synthetic genomics can achieve alongside methods such as directed evolution and rational engineering, lays out a path for generating adaptive and resilient phage therapies against rapidly evolving pathogens, and establishes a foundation for the generative design of larger, more complex genomes.
Genome design can augment the broader toolkit of genome sequencing, synthesis, and editing, enabling the composition of biological systems at the genome scale."
AI designs a novel E. coli killer | Stanford Report "Using an AI model of their own creation that writes whole genomes, a team of Stanford scientists has engineered a novel bacteria-fighting phage. A new age of antibiotics could be on the horizon."
