EPFL’s Artificial Intelligence in Molecular Medicine group in Switzerland, led by Charlotte Bunne, has launched spora, a spatial proteomics reference atlas. According to EPFL, it is the world’s largest freely available collection of tissue images with this kind of data, which shows where proteins sit within tissues.
The atlas contains 13,546 images from 5,477 patients, covering 14 tissue types and five imaging technologies, with linked clinical data. It took two years of work with EMBL-EBI, University Hospital Zurich, the University of Zurich and Geneva University Hospitals, and includes tools to build and evaluate artificial intelligence models.
The team now wants to extend the atlas to more tissues, diseases and technologies and to work with clinicians on predicting disease progression and treatment benefit. The work is described in a preprint and was funded by the National AI Initiative for Precision Oncology.
