We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.


Download Mobile App
Recent News Expo Clinical Chem. Molecular Diagnostics Hematology Immunology Microbiology Pathology Technology Industry Focus


AI Predicts Tumor-Killing Cells with High Accuracy

By LabMedica International staff writers
Posted on 16 May 2024

Cellular immunotherapy involves extracting immune cells from a patient's tumor, potentially enhancing their cancer-fighting capabilities through engineering, and then expanding and reintroducing them into the body. T cells, a primary type of white blood cell or lymphocyte, circulate in the blood and monitor for virally infected or cancerous cells. Among these, T cells that infiltrate solid tumors are known as tumor-infiltrating lymphocytes, or TILs. However, not all TILs effectively recognize and attack tumor cells. To address this, scientists have now employed artificial intelligence (AI) to create a predictive model that can identify the most effective TILs for use in cancer immunotherapy.

The new AI-driven predictive model, called TRTpred developed by scientists at Ludwig Cancer Research (New York, NY, USA) ranks T cell receptors (TCRs) according to their tumor reactivity. To create TRTpred, the researchers utilized 235 TCRs from patients with metastatic melanoma, already categorized as tumor-reactive or non-reactive. They input the global gene-expression profiles of the T cells harboring each TCR into a machine learning model to identify patterns distinguishing tumor-reactive T cells from their inactive counterparts. This model, enhanced with additional algorithms, supports personalized cancer treatments tailored to the unique cellular composition of each patient’s tumors.

Image: The AI predictive model identifies the most potent cancer killing immune cells for use in immunotherapies (Photo courtesy of Shutterstock)
Image: The AI predictive model identifies the most potent cancer killing immune cells for use in immunotherapies (Photo courtesy of Shutterstock)

The TRTpred model was used to analyze TILs from 42 patients with melanoma, gastrointestinal, lung, and breast cancer, pinpointing tumor-reactive TCRs with about 90% accuracy. The selection process was further refined using a secondary algorithmic filter to isolate those T cells with “high avidity”—meaning they bind strongly to tumor antigens. It was observed that T cells identified by TRTpred and this secondary filter as both tumor-reactive and high avidity were predominantly located within the tumors rather than in the surrounding stromal tissue. This aligns with previous studies suggesting that effective T cells often deeply penetrate tumor islets.

A third filter was then introduced to enhance the identification of TCRs recognizing a diverse array of tumor antigens. This filter groups TCRs based on similar physical and chemical characteristics, assuming TCRs in each group recognize the same antigen. This enhanced system, named MixTRTpred, was then tested by growing human tumors in mice, extracting TCRs from their TILs, and employing MixTRTpred to identify T cells that were tumor-reactive, had high avidity, and targeted multiple tumor antigens. The researchers then engineered mouse T cells to express these TCRs and demonstrated that these modified cells could effectively eradicate tumors when reintroduced into the mice.

“The implementation of artificial intelligence in cellular therapy is new and may be a game-changer, offering new clinical options to patients,” said Ludwig Lausanne’s Alexandre Harari, who led the study published on May 7, 2024 in Nature Biotechnology.

Related Links:
Ludwig Cancer Research

Platinum Member
Flu SARS-CoV-2 Combo Test
OSOM® Flu SARS-CoV-2 Combo Test
Magnetic Bead Separation Modules
POCT Fluorescent Immunoassay Analyzer
Gold Member
Hemoglobin Testing System

Latest Immunology News

AI Tool Predicts Cancer Patients’ Response to Immunotherapy

Molecular Profiling Improves Diagnosis for Children with High Risk Cancers

Blood Test Measures Immune Response to Epstein-Barr Virus in MS Patients

LGC Clinical Diagnostics