BIOLOGICAL AND HEALTH SCIENCES

New software to measure the immune response against any type of cancer

CONICET scientists developed a new bioinformatic tool based on artificial intelligence that determines the amount and type of tumor-infiltrating white blood cells.


The authors: Romina Girotti, Elmer Fernández, Gabriel Rabinovich, Hugo Lujan, Yamil Mahmoud, Joaquín Merlo, Florencia Veigas, Mónica Balzarini, Matías Miranda and Darío Rocha.

MIXTURE is the name of the new bioinformatic tool made by CONICET researchers. It can precisely quantify the number and type of white blood cells that infiltrate into tumors. Besides, this new software will help to explain why in some cases the immunotherapies against cancer fail in some cases . The results were published in Briefings in Bioinformatics.

“Understanding the relationship between the composition of immune cells that infiltrate into tumors and the mechanisms of resistance to existing therapies would allow scientists to search for therapeutic alternatives for these patients,” says Romina Girotti, CONICET researcher at the Instituto de Biología y Medicina Experimental (CONICET, IBYME) and leader of the study.

The software is equipped with an algorithm based on machine learning, a branch of artificial intelligence that includes data science concepts to optimize the analysis of biological data at a molecular level.

The researchers analysed data from tumor biopsies of breast cancer (703 in total), lung (526), head and neck (494), melanoma (401), and colorectal (452) obtained from the The Cancer Genome Atlas (TCGA).

“The results revealed associations between the proportion of different immune cell types infiltrating into the tumor and different clinical and genetic variables,” Elmer Fernández explains. He is the first author of the study and a CONICET researcher at the Centro de Investigación y Desarrollo en Inmunología y Enfermedades Infecciosas (CIDIE, CONICET-UCCOR).

For instance, in the case of breast cancer, the researchers found associations between the survival of patients and the infiltration of different cell types of the immune system (M1 and M2 macrophages, and CD4 memory T cells) in the tumors.

The scientists analysed four groups of melanoma patients (188 in total) treated with two different types of immunotherapies, anti-CTLA-4 and anti-PD-1 / PD-L1. They found that those who did not respond to these treatments had a greater infiltration of immune response known as M2 macrophages.

“However, we observed that the patients who responded well to these therapies have a greater infiltration of T-CD8 immune cells, which are in charge of eliminating tumor cells,” explains Girotti. He is the head of the Laboratorio de Inmuno-Oncología Traslacional del IBYME.

Girotti added that the study of the immune cell composition of the tumor microenvironment of patients would establish new biomarkers to better predict which patients would respond to immunotherapy.

For all types of cancer, the researchers linked the genetic factors (which vary between people) and the type and number of immune cells infiltrated into tumors. Besides, the scientists determined in what way the association between these to variables affected -for or against- the response of patients to immunotherapies. “This characterization sheds light on potential therapies or strategies for monitoring the patient,” Giordi affirmed.

MIXTURE is free of access to the scientific community and can be applied to any type of tumor, Fernández concluded.

Source: FIL

References

Elmer A Fernández, Yamil D Mahmoud, Florencia Veigas, Darío Rocha, Matías Miranda, Joaquín Merlo, Mónica Balzarini, Hugo D Lujan, Gabriel A Rabinovich, María Romina Girotti, Unveiling the immune infiltrate modulation in cancer and response to immunotherapy by MIXTURE—an enhanced deconvolution method, Briefings in Bioinformatics, , bbaa317, https://ri.conicet.gov.ar/handle/11336/121874

 

About the study:

Elmer Fernández. Independent researcher. CIDIE.

Yamil D. Mahmoud. PhD fellow. IBYME:

Florencia Veigas. PhD fellow. IBYME.

Darío Rocha. Universidad Nacional de Córdoba.

Matías Miranda. UCCOR.

Joaquín Merlo. PhD fellow. IBYME

Mónica Balzarini. Principal researcher. UFYMA (CONICET-INTA).

Hugo D. Lujan. Senior researcher. CIDIE.

Gabriel Rabinovich. Senior researcher. IBYME,

Romina Girotti. Associate researcher. IBYME.