Novel Artificial Intelligence Method Identifies Disease Structures, Mechanisms
Cedars-Sinai Investigators Can Now Study Different Types of Biological Data—Such as Molecular Information and Tissue Imaging—Through a Tool Called MISO, or MultI-modal Spatial Omics
Investigators at Cedars-Sinai and the University of Pennsylvania created a novel artificial intelligence (AI) method that allows them to study different types of biological data—such as molecular information and tissue imaging—from the same tissue sample. Known as MultI-modal Spatial Omics, or MISO, the tool—described in the peer-reviewed journal Nature Methods—can analyze hundreds of thousands of cells at once, then identify important disease structures and mechanisms.
“Pathologists traditionally identify relevant structures in diseased tissue by visually examining stained tissue images—a method that is costly, time-consuming and typically reliant on a single type of tissue imaging,” said Kyle Coleman, PhD, an investigator in the Department of Computational Biomedicine at Cedars-Sinai, who led the team that developed the MISO tool. “MISO streamlines this process by integrating detailed molecular information with tissue histology, enabling automated and precise identification of disease-relevant structures.”
The MISO tool can, for example, distinguish regions with different levels of cancer severity within a single colon cancer tissue sample. Additionally, by integrating transcriptomics, metabolomics, and histology imaging, MISO accurately maps detailed structures of the mouse hippocampus at a high resolution. Investigators hope that MISO can lead to a deeper understanding of disease processes, potentially advancing the development of new therapies.
The MISO software is currently available on GitHub.
Additional authors include Amelia Schroeder, Melanie Loth, Daiwei Zhang, Jeong Hwan Park, Ji-Youn
Sung, Niklas Blank, Alexis J. Cowan, Xuyu Qian, Jianfeng Chen, Jiahui Jiang, Hanying Yan, Laith Z. Samarah, Jean R. Clemenceau, Inyeop Jang, Minji Kim, Isabel Barnfather, Joshua D. Rabinowitz, Yanxiang Deng, Edward B. Lee, Alexander Lazar, Jianjun Gao, Emma E. Furth, Tae Hyun Hwang, Linghua Wang, Christoph A. Thaiss, Jian Hu and Mingyao Li.
Funding: This research was supported by National Institutes of Health grants R01HG013185 and R01LM014592.
Follow Cedars-Sinai Academic Medicine on LinkedIn for more on the latest basic science and clinical research from Cedars-Sinai.