Atlas of Breast Cancer Ecosystem Made by AI Machine Learning
Swiss researchers apply AI to create a resource for future precision medicine.
Posted May 31, 2019
Breast cancer is one of the most common cancers, and one of the leading causes of death in women globally. Breast cancer is a disease where cells located in the breast grow out of control. Although a majority of breast cancers are discovered in women at the age of 50 years or older, the disease can affect anyone, including men and younger women, according to the Centers for Disease Control and Prevention (CDC). Last year there were 9.6 million deaths and 18.1 million new cases of breast cancer diagnosed globally according to the latest report from the International Agency for Research on Cancer (IARC) released in September 2018. In 2019 alone, the U.S. National Cancer Institute estimates that there will be 268,600 new female breast cancer cases and 41,760 fatalities. Earlier this month, researchers based in Switzerland published in Cell their study in using applied artificial intelligence (AI) machine learning to create a comprehensive tumor and immune atlas of breast cancer ecosystems that lays the foundation for innovative precision medicine and immunotherapy.
The study was led by professor Bernd Bodenmiller, Ph.D. at the Institute of Molecular Life Sciences at the University of Zurich in Switzerland. Bodenmiller is a recipient of the 2019 Friedrich Miescher Award, Switzerland’s highest distinction for outstanding achievements in biochemistry. His team worked in collaboration with the Systems Biology Group at IBM Research in Zurich led by María Rodríguez Martínez, Ph.D. with the shared goal to produce a foundation for more targeted breast cancer treatment through precision medicine.
Cancer is complex. Breast cancer is heterogeneous—disease progression and responses to treatment are impacted by the ecosystem of tumor cells and healthy cells.
“New treatment approaches are needed to increase the success of breast cancer precision medicine,” wrote the research scientists. “A first step is to comprehensively describe the complex cellular and phenotypic diversity of tumor ecosystems and the relationships among its components for a large number of patients.”
“We knew that breast cancer ecosystems are comprised of tumor cells that communicate and interact with surrounding non-cancer cell types, including immune cells, stromal cells, and cells of the vasculature,” wrote researcher Marianna Rapsomaniki at IBM Research in Zurich in her May 16, 2019 report. “Cancer cells and tumor-associated cells are phenotypically and functionally heterogeneous with characteristics determined by both genetic make-up and environmental influences.”
“Given the heterogeneity of cell phenotypes and cellular relationships in breast cancer, patient classification and treatment should ideally consider the entire tumor ecosystem,” wrote the research team in Cell.
The research team used mass cytometry to analyze 144 breast tumor and 50 non-tumor human tissue samples. Mass cytometry, a platform for high-dimensional single-cell analysis, is used as a tool for understanding complex biological systems by combining the technology of flow cytometry with elemental mass spectrometry.
Using mass cytometry, the researchers generated massive amounts of data with the simultaneous quantification of over 70 proteins in more than 26 million cancer and immune cells.
Pattern-recognition capabilities of AI machine learning is well suited for tasks involving massive amounts of complex data. The team applied AI machine learning to create a detailed atlas of breast cancer ecosystems by identifying and distinguishing between the many diverse cells interwoven within the tumors.
“This large-scale, single-cell atlas deepens our understanding of breast tumor ecosystems and suggests that ecosystem-based patient classification will facilitate identification of individuals for precision medicine approaches targeting the tumor and its immunoenvironment,” reported the researchers.
Now with this new breast cancer ecosystem atlas, scientists around the world have a valuable resource to accelerate discoveries of more targeted treatment for breast cancer at the molecular level—opening the door for precision medicine and immunotherapy breakthroughs in the future.
Copyright © 2019 Cami Rosso All rights reserved.
Wagner, Johanna, Rapsomaniki, Maria Anna, Chevrier, Stéphane, Anzeneder, Tobias, Langwieder, Claus, Dykgers, August, Rees, Martin, Ramaswamy, Annette, Muenst, Simone, Soysal, Savas Deniz, Jacobs, Andrea, Windhager, Jonas, Silina, Karina, van den Broek, Maries, Johannes Dedes, Konstantin, Martínez, Maria Rodríguez, Weber, Walter Paul, Bodenmiller, Bernd. “A Single-Cell Atlas of the Tumor and Immune Ecosystem of Human Breast Cancer.” Cell. April 11, 2019.
Rapsomaniki, Marianna. “Deciphering Breast Cancer Heterogeneity Using Machine Learning.” IBM Research. May 16, 2019. Retrieved from https://www.ibm.com/blogs/research/2019/05/breast-cancer-machine-learning/
Nyfeler, Melanie (2019, Jan 15). UZH Researcher Wins Prestigious Biochemistry Award [Press Release]. Universität Zürich. Retrieved from https://idw-online.de/en/news708909
Spitzer, Matthew H., Nolan, Garry P. “Mass Cytometry: Single Cells, Many Features.” Cell. May 5, 2017.