Artificial intelligence could help scientists kill cancer cells through a new technique. A predictive model developed by scientists at the University of California, San Francisco (UCSF) and IBM Research enables researchers to encode instructions for cells to execute.
Scientists have essentially created a virtual library of thousands of “command sentences” for cells using machine learning. Like sentences in any language, these “sentences” are also based on combinations of “words” that direct specially engineered immune cells to detect and eliminate cancer cells.
The research was recently published in the journal Science and marks the first time such techniques have been used to eliminate cancer cells.
Developing the framework
Advanced computation techniques allowed scientists to predict whether natural or synthesised elements should be included in a cell in order to give it the behaviours required to respond to complicated diseases.
The study was led by Wendell Lim, director of UCSF Cell Design Institute who called this development a “vital shift for the field.” “Only by having that power of prediction can we get to a place where we can rapidly design new cellular therapies that carry out the desired activities,” Lim added.
Also read: Scientists Saved Cancer Patient’s Life By Using Modified Virus To Kill Tumour
By putting the right receptor (molecules that instruct cells to respond to certain environmental factors) into a type of immune cell [called a T cell – or chimeric antigen receptors (CARs)] can reprogram it to find and kill cancer cells.
According to Kyle Daniels, lead author of the study, they focused on each part of a receptor that is situated inside a cell – containing strings of amino acids referred to as motifs. Each motif acts as a “word” (a command). How these words are arranged into a “sentence” then decides what function the cell performs.
Enter artificial intelligence
Many CAR-T cells are engineered to kill cancer but to also take a break. This break allows cancer cells to grow. Now, this team has combined the “words” in different ways that would encourage CAR-T cells to finish the job without taking any break.
To this end, they generated a library of nearly 2,400 randomly combined command sentences and then tested hundreds of them in T cells to observe how they performed against leukemia.
Also read: New Robotic Technology Detects, Treats Lung Cancer Before It Becomes Deadly
With help from IBM Almaden Research Center, they applied machine learning to create new receptor sentences that they thought would be more effective.
“We changed some of the words of the sentence and gave it a new meaning,” said Daniels. “We predictively designed T cells that killed cancer without taking a break because the new sentence told them, ‘Knock those rogue tumor cells out, and keep at it.’” And it worked!
Now, they want to use artificial intelligence in a range of therapies. What do you think about using machine learning to fight dangerous diseases? Let us know in the comments below. For more in the world of technology and science, keep reading Indiatimes.com.
Daniels, K. G., Wang, S., Simic, M. S., Bhargava, H. K., Capponi, S., Tonai, Y., Yu, W., Bianco, S., & Lim, W. A. (2022). Decoding 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. (2023, January 20). How Artificial Intelligence Found the Words To Kill Cancer Cells. SciTechDaily. https://scitechdaily.com/how-artificial-intelligence-found-the-words-to-kill-cancer-cells/