Study shows AI predicts tumor-killing cells with high accuracy

Researchers develop artificial intelligence that predicts tumor-killing cells with high accuracy

TRTpred, a sensitive in silico predictor of tumor-reactive clonotypes. Credit: Biotechnology of nature (2024). DOI: 10.1038/s41587-024-02232-0

Using artificial intelligence, Ludwig Cancer Research scientists have developed a powerful predictive model to identify the most powerful cancer-killing immune cells for use in cancer immunotherapies.

Combined with additional algorithms, the predictive model, described in the current issue of the journal Biotechnology of natureit can be applied to personalized cancer treatments that tailor therapy to the unique cellular makeup of each patient’s tumors.

“The implementation of artificial intelligence in cell therapy is new and can be a game changer, offering new clinical options to patients,” said Alexandre Harari of Ludwig Lausanne, who led the study with the postgraduate student Rémy Pétremand.

Cellular immunotherapy involves extracting immune cells from a patient’s tumor, optionally engineering them to enhance their natural cancer-fighting abilities, and reintroducing them into the body after they have been expanded in culture. T cells are one of two main types of white blood cells, or lymphocytes, that circulate in the blood and patrol for virus-infected or cancerous cells.

T cells that infiltrate solid tumors are known as tumor-infiltrating lymphocytes, or TILs. However, not all TILs are effective in recognizing and attacking tumor cells.

“Only a fraction is actually reactive to the tumor — the majority are bystanders,” Harari explained. “The challenge we faced was to identify the few TILs that are equipped with T-cell receptors capable of recognizing tumor antigens.”

To do this, Harari and his team developed a new AI-based predictive model, called TRTpred, which can classify T-cell receptors (TCRs) based on their tumor reactivity. To develop TRTpred, they used 235 TCRs collected from patients with metastatic melanoma, already classified as tumor-reactive or non-reactive.

The team loaded the global gene expression (or transcriptomic) profiles of T cells bearing each TCR into a machine learning model to identify patterns that differentiate tumor-reactive T cells from inactive counterparts .

“TRTpred can learn from a population of T cells and create a rule that can then be applied to a new population,” Harari explained. “Therefore, when confronted with a new TCR, the model can read its transcriptomic profile and predict whether it is reactive to the tumor or not.”

The TRTpred model analyzed TILs from 42 melanoma and gastrointestinal, lung, and breast cancer patients and identified tumor-reactive TCRs with approximately 90 percent accuracy. The researchers further refined their TIL selection process by applying a secondary algorithmic filter to detect only those tumor-reactive T cells with “high avidity,” meaning those that bind strongly to tumor antigens.

“TRTpred is uniquely a predictor of whether a TCR is reactive in the tumor or not,” Harari explained. “But some tumor-reactive TCRs bind very strongly to tumor cells and are therefore very effective, while others only do so lazily. Distinguishing strong binders from weak ones translates into efficacy.” .

The researchers showed that T cells marked by TRTpred and the secondary algorithm as tumor-reactive and with high avidity were more often found embedded within tumors rather than in the adjacent supporting tissue, known as stroma. This finding aligns with other research showing that effective T cells typically penetrate deep into tumor islets.

The team then introduced a third filter to maximize recognition of various tumor antigens. “What we want to do is maximize the chances of TILs targeting as many different antigens as possible,” Harari said.

This final filter organizes TCRs into groups based on similar physical and chemical characteristics. The researchers hypothesized that the TCRs in each cluster recognize the same antigen. “So we choose within each cluster one TCR to amplify, so we maximize the chances of different antigen targets,” said Vincent Zoete, a computational scientist at Ludwig Lausanne who developed the TCR avidity and clustering algorithms. TCR

The researchers call the combination of TRTpred and algorithmic filters MixTRTpred.

To validate their approach, Harari’s team grew human tumors in mice, extracted TCRs from their TILs, and used the MixTRTpred system to identify T cells that were reactive to the tumor, had high avidity, and directed multiple tumor antigens. They then engineered T cells from mice to express these TCRs and showed that these cells could eliminate tumors when transferred to mice.

“This method promises to overcome some of the shortcomings of current TIL-based therapy, especially for patients suffering from tumors that do not respond to these therapies today,” said Ludwig Lausanne director George Coukos, co-author of the study that plans to launch a Phase I clinical trial that will test the technology in patients.

“Our joint efforts will yield an entirely new type of T-cell therapy.”

More information:
Rmy Ptremand et al, Identification of clinically relevant T-cell receptors for personalized T-cell therapy using combinatorial algorithms, Biotechnology of nature (2024). DOI: 10.1038/s41587-024-02232-0

Provided by Ludwig Cancer Research

Summons: AI predicts tumor-killing cells with high accuracy, study shows (2024, May 7) Retrieved May 7, 2024, from tumor-cells-high-accuracy.html

This document is subject to copyright. Other than any fair dealing for private study or research purposes, no part may be reproduced without written permission. Content is provided for informational purposes only.

#Study #shows #predicts #tumorkilling #cells #high #accuracy
Image Source :

Leave a Comment

Your email address will not be published. Required fields are marked *

Scroll to Top