AI editor turns microbes into renewable fuels

Oak Ridge National Laboratory researchers used artificial intelligence and other scientific fields to improve their CRISPR Cas9 genome editing tools. As a result, they can genetically alter microbes to produce renewable chemicals and fuels. Also, Interesting Engineering said the study will prevent expensive “typos” in editing an organism’s genetic code. 

You can find many scientists developing new renewable energy sources, and the ones from genetically modified microbes are a welcome addition. Soon, artificial intelligence may unlock a more eco-friendly and sustainable future from microbes. Moreover, the AI editor may facilitate drug development by taking them from specific genomes.

This article will discuss how scientists created their AI editor and used it to produce renewable energy from microbes. Later, I will cover similar AI applications.

How does the AI editor work?

CRISPR, or Clustered Regularly Interspaced Short Palindromic Repeats, is a bioengineering tool that modifies genetic code to improve an organism’s performance and correct mutations. Also, the CRISPR Cas9 tool uses a unique guide RNA that aids the Cas9 enzyme to bind with a genome. 

However, it’s more effective on mammalian cells and fruit flies, not microbes. That is why they needed a better understanding of cell nuclei, which store genetic material. 

Consequently, Oak Ridge National Laboratory scientists built an artificial intelligence model called iterative random forest. The AI trained on a dataset containing 50,000 guide RNAs targeting the E. coli bacteria’s genome.

“The model helped us identify clues about the molecular mechanisms that underpin the efficiency of our guide RNAs,” said Erica Prates, computational systems biologist at ORNL, “giving us a rich library of molecular information that can help us improve CRISPR technology.”

Unlike other AI editors, the scientists designed it as an explainable program. The unique design prevents the black box problem plaguing most AI software.

You may also like: Scientists turn humid air into a renewable energy source

The black box problem refers to the phenomenon where artificial intelligence becomes so complex that even its creators can’t understand how it is transforming. More importantly, refining CRISPR Cas9 models facilitates linking genes to physical traits.

As mentioned, the AI editor can modify microbe genomes to improve bioenergy feedstock plants and bacterial fermentation of biomass. “We’re greatly improving our predictions of guide RNA with this research,” stated Carrie Eckert, Synthetic Biology group leader at ORNL.

“This paper even has implications across the human scale,” she added. “If you’re looking at any sort of drug development, for instance, where you’re using CRISPR to target a specific region of the genome, you must have the most accurate model to predict those guides.”

What are the other similar AI applications?

Several companies have been exploring AI’s medical research applications. For example, Insilico Medicine created the world’s first fully AI-generated drug.

The Hong Kong-based biotechnology firm calls it INS018_055, which would treat idiopathic pulmonary fibrosis. It created this wondrous technology with its Pharma.AI, which has three parts:

• PandaOmics identifies the parts of a virus that a drug must target.
• Chemistry42 designs new potential drug compounds that aim at PandaOmics’ targets.
• InClinico predicts the success rate of clinical trials and identifies trial design issues.

The tech startup used Pharma.AI to design and synthesize roughly 80 molecules. Identifying targets and determining a promising drug candidate took around 18 months. As a result, it achieved “unprecedented success rates for preclinical drug candidates.”

The LabGenius company also used artificial intelligence to facilitate antibody production. Its namesake AI program produces an antibody from millions of possible combinations quickly.

You may also like: DragGAN Click-And-Drag Photo Editor Went Viral

LabGenius makes antibody development easier and faster than humans doing it manually. “The only input you give the system as a human is, here’s an example of a healthy cell, here’s an example of a diseased cell,” the CEO said. “And then you let the system explore the different [antibody] designs that can differentiate between them.”

The AI program chooses more than 700 initial options from 100,000 potential antibodies. Afterward, it designs, builds, and tests them automatically.” Meanwhile, humans oversee the process by moving samples from one machine to another.

It learns from experimental results, increasing the chances of producing better results. As a result, it is significantly more efficient than human protein designers.

Conclusion

Oak Ridge National Laboratory researchers developed an AI editor for microbe genomes. Soon, it could help us produce renewable energy from microorganisms.

It also makes genome editing more effective and efficient than ever. Nevertheless, the scientists plan to improve their tool using data from other lab experiments and microbial species.

Gain more information about this study by checking the ORNL webpage. Moreover, learn more about the latest digital tips and trends at Inquirer Tech.