Accurate calculation

AI predicts which Drug combinations kill cancer cells

Tatiana Matveeva, "Scientific Russia"

Researchers from Aalto University, the University of Helsinki and the University of Turku (Finland) have developed a machine learning model that accurately predicts how combinations of different anti-cancer drugs kill different types of cancer cells. The new AI model was trained using a large set of data obtained during previous studies that examined the relationship between drugs and cancer cells, the press service of Aalto University reports. The results of the study were published in the journal Nature Communications (Julkunen et al., Leveraging multi-way interactions for systematic prediction of pre-clinical drug combination effects).

An artificial intelligence model has found associations between drugs and cancer cells that have not been observed before. "The model gives very accurate results. For example, the values of the so–called correlation coefficient in our experiments were more than 0.9, which indicates excellent reliability," says Professor Juho Rousu from Aalto University. In experimental measurements, the correlation coefficient 0.8-0.9 is considered reliable.

The model accurately predicts how a combination of drugs selectively suppresses certain cancer cells if the effect of a combination of drugs on this type of cancer has not been previously tested. This will help cancer researchers prioritize which drug combinations to choose from thousands of options for further research.

The same machine learning approach can be used not only for cancer. In this case, the model will have to be re-trained using data related to this disease. For example, the model can be used to study how different combinations of antibiotics affect bacterial infections or how effectively different combinations of drugs kill cells infected with the SARS-Cov-2 coronavirus.

Portal "Eternal youth" http://vechnayamolodost.ru