All news

AI and single-cell technology help better understand childhood cancer


AI and single-cell technology help better understand childhood cancer

By combining artificial intelligence with cell-by-cell analysis of tumors, researchers from Institut Curie have succeeded in better identifying the mechanisms related to Ewing sarcoma relapses.

Ewing sarcoma tumors are rare pediatric tumors, located in the bone, with around 70 cases a year in France. The major challenge of their study is to better understand their cellular origins and their heterogeneity.

By following the new “single-cell” approach the researchers can study the intratumoral heterogeneity and identify cellular sub-populations liable to be resistant to treatment. “Identifying these populations can help us better understand the causes of relapses,” explains Andrei Zinovyev, who co-leads the ‘Biology of cancer systems team’, Unit U900, jointly with Emmanuel Barillot, both holding interdisciplinary PRAIRIE chairs. To better characterize intratumoral heterogeneity at the level of individual cells, the researchers studied the properties of multi-dimensional data point clouds representing tumors, using a combination of matrix factorization and penalized regression machine learning approaches.

Their work has been published in the international journal Cell Reports: