[ad_1]
An artificial intelligence platform known as BacterAI, created by a research team led by a University of Michigan professor, has demonstrated its ability to conduct a staggering number of autonomous scientific experiments – up to 10,000 per day. Breakthrough applications of artificial intelligence could pave the way for rapid advances in a variety of fields, including medicine, agriculture, and environmental science.
The results of the study were published in St Nature Microbiology.
Deciphering microbial metabolism with BacterAI
BacterAI was designed to simulate the metabolism of oral microbes associated with oral health without any input. The complex metabolic processes of bacteria involve the consumption of specific combinations of the 20 amino acids necessary for life. The aim of the study was to determine the exact amino acids beneficial for oral microbes to promote their growth.
“We know next to nothing about most of the bacteria that affect our health. Understanding how bacteria grow is the first step toward reengineering our microbiome,” said Paul Jensen, a UM assistant professor of biomedical engineering who was at the University of Illinois when the project began.
A complex task made easier by artificial intelligence
Deciphering the preferred combination of amino acids for bacteria is a difficult task due to the more than a million possible combinations. However, BacterAI was able to successfully determine the amino acid requirements for the growth of both Streptococcus gordonii and Streptococcus sanguinis.
BacterAI’s approach involved testing hundreds of amino acid combinations a day, refining its focus and changing combinations each day based on the results of the previous day’s experiments. Within nine days, he achieved 90% accuracy in his predictions.
Learning artificial intelligence through trial and error
Unlike traditional methods that use labeled datasets to train machine learning models, BacterAI generates its own datasets through an iterative process of conducting experiments, analyzing the results, and predicting future outcomes. This method allowed him to decipher the feeding rules of bacteria in less than 4000 experiments.
“We wanted our AI agent to take steps and fall, come up with its own ideas and make mistakes. Every day, it gets a little better, a little smarter,” Jensen said, noting the parallels between BacterAI and the learning process between a child.
The future of AI in research
Considering that almost 90% of bacteria have not been researched, conventional methods represent a significant barrier in terms of time and resources required. BacterAI’s ability to run automated experiments can dramatically accelerate discoveries. In one day, the team managed to conduct up to 10,000 experiments.
However, the potential applications of BacterAI extend beyond microbiology. Researchers in any field can pose questions as puzzles for artificial intelligence to solve through this kind of trial and error process.
“With the recent explosion of mainstream artificial intelligence over the past few months, many people are unsure of what it will bring in the future, both positive and negative,” said Adam Damm, a former engineer at Jensen’s lab and lead author of the study. . “But it’s very clear to me that focused AI applications like our project will accelerate everyday research.”
[ad_2]
Source link
