Communications of the ACM
AI Technique Could Lead to Ways to Predict Cancer Prognosis, Treatment Response
The researchers used their new tool to gather insights on neoantigens cataloged in The Cancer Genome Atlas, a public database that holds information from more than 11,000 primary tumors.
Credit: Getty Images
An artificial intelligence technique developed by researchers at the University of Texas Southwestern Medical Center and MD Anderson Cancer Center can determine which neoantigens (cell surface peptides generated by cancer cells) are recognized by the immune system.
The researchers developed the "pMTnet" deep learning algorithm and trained it using data from known binding or nonbinding combinations of neoantigens, the major histocompatibility complexes (MHCs) that present neoantigens on cancer cell surfaces, and the T cell receptors that recognize the neoantigen-MHC complexes.
Using the algorithm, the researchers determined that neoantigens often produce a stronger immune response than tumor-associated antigens.
MD Anderson's Alexandre Reuben said, "The most significant hurdle currently facing immunotherapy is the ability to determine which antigens are recognized by which T cells in order to leverage these pairings for therapeutic purposes. pMTnet outperforms its current alternatives and brings us significantly closer to this objective."
From News-Medical Life Sciences
View Full Article
Abstracts Copyright © 2021 SmithBucklin, Washington, DC, USA
No entries found