ASCO: AI-powered MOSAIC will create 3D atlas for cancer

As part of the major results of clinical trials at ASCO, a new research project made its official debut with the ambitious goal of mapping the interactions of cancer cells with their environment at “near single-cell resolution”.

Dubbed MOSAIC (Multi Omic Spatial Atlas in Cancer), the project brings together a number of academic cancer research organizations as well as artificial intelligence company Owkin, which specializes in machine learning models that generate new biomarkers and therapeutic targets from patient samples and spatial data can be found biology company NanoString.

Launched with $50 million in funding from Owkin, MOSAIC will use a technique known as “spatial omics,” which combines gene sequencing with imaging technologies to analyze RNA and proteins for more than just their presence or quantity , but also where they are physically located within cells and the microenvironment in which they live.

According to the consortium, which includes the University of Pittsburgh, Gustave Roussy, the University Hospital Lausanne, the University Hospital Erlangen/Friedrich-Alexander-Universität Erlangen-Nürnberg and the Charité-Universitätsmedizin Berlin, the research project is 100 times larger than any existing spatial omics Record. More organizations are expected to join the initiative in the coming months.

According to the partners, data from around 7,000 patients of different types of cancer will be generated and could help researchers to better understand cancer at the molecular level, characterize different types of cancer more precisely and identify new targets that could eventually lead to new, improved therapies. Current projects typically involve fewer than 50 patients.

Thomas Clozel

“I believe that spatial omics combined with AI is the catalyst that will drive the next revolution in cancer research,” said Thomas Clozel, CEO of Owkin, in a LinkedIn post. “By combining genes with tissues and tumors with the microenvironment, discoveries can be made from patient data that would not be possible when examining cell lines.”

A key goal of the consortium will initially be to develop standards governing how spatial omics data should be analyzed and compared, hoping to provide common guidance for research groups working in the field. The hope is that over time, the standardized data and methods for data generation and analysis will be made available to the global biomedical community to accelerate research in this area.

MOSAIC will initially focus on cancers with unmet medical needs, including non-small cell lung cancer, triple negative breast cancer, diffuse large B-cell lymphoma, ovarian cancer, glioblastoma, mesothelioma and bladder cancer, the partners said.