Artificial intelligence can help scientists kill cancer cells using new techniques. A predictive model developed by scientists at the University of California, San Francisco (UCSF) and IBM Research allows researchers to encode the instructions that cells should carry out.
Scientists have created a virtual library of thousands of “command phrases” for cells using machine learning. Like sentences in any language, these “words” are based on combinations of “words” that direct immune cells specifically designed to find and eliminate cancer cells.
The research was recently published in the journal Science And this is the first time that such techniques have been used to remove cancer cells.
Source: Unsplash
Develop a framework
Advanced computational techniques have allowed scientists to predict whether a cell should incorporate natural or synthetic elements to give it the behavior needed to respond to complex diseases.
Source: Unsplash
The study was led by Wendell Lim, director of UCSF’s Cell Design Institute, who called the development “an important shift for the field.” “Only by having this predictive power can we get to the point where we can rapidly design new cell therapies that achieve the desired activities,” Lim added.
A type of immune cell (called a T cell – or chimeric antigen receptors (CARs)) can reprogram the right receptors (molecules that tell cells to respond to certain environmental factors) to detect and kill cancer cells.
According to the study’s lead author, Kyle Daniels, they focus on each part of the receptor located inside the cell, which consists of chains of amino acids called motifs. Each pattern acts as a “word” (command). The way these words are arranged in a “sentence” determines the function the cell performs.
Enter artificial intelligence
Many CAR-T cells are designed to kill but also prevent cancer. This pause allows cancer cells to grow. Now, the team has combined the “words” in different ways to encourage CAR-T cells to do their job without pausing.
Source: Unsplash
To this end, they created a library of about 2,400 randomly combined command phrases, then tested them in hundreds of T cells to monitor how they performed against leukemia.
With the help of the IBM Almaden Research Center, they applied machine learning to create new catch phrases that they found more effective.
Source: Unsplash
“We changed some words in the sentence and gave it a new meaning,” Daniels said. “We hypothetically engineered T cells that killed the cancer without pausing, because the new phrase told them, ‘Get rid of these rogue tumor cells and move on.’ »» And it worked!
They now want to use artificial intelligence in various therapies. What do you think about using machine learning to fight dangerous diseases? Let us know in the comments below. To know more about the world of technology and science, keep reading Indiatimes.com.
References
Daniels, K.G., Wang, S., Simic, M.S., Bhargava, H.K., Caponi, S., Tonai, Y., Yu, W., Bianco, S., & Lim, W. .a. (2022). Decoding the CAR T cell phenotype using combinatorial signaling motif libraries and machine learning. Science, 378(6625), 1194-1200. https://doi.org/10.1126/science.abq0225
Collins, C. (January 20, 2023). How artificial intelligence discovered words to kill cancer cells. SciTechDaily. https://scitechdaily.com/how-artificial-intelligence-found-the-words-to-kill-cancer-cells/
