Human Cell Atlas is the world’s largest growing single cell reference atlas. It contains references to millions of cells across tissues, organs, and developmental stages. These references will help physicians understand the effects of aging, the environment, and disease on cells, and ultimately help patients better diagnose and treat them. Still, there are challenges with the Reference Atlas. Single-cell datasets may contain measurement errors (batch effects), global availability of compute resources is limited, and raw data sharing may be legally restricted. Often.
Researchers at Helmholtz Zentrum München and Technische Universität München (TUM) have developed a new algorithm called “scArches,” which stands for single-cell structure surgery. The biggest advantage: “Instead of sharing raw data between clinics and research centers, the algorithm uses transfer learning to compare new datasets from single selgenomics with existing references to maintain privacy and anonymity. This makes it much easier to anonymize and interpret new datasets and dramatically democratize the use of single-cell reference atlases, “said Mohammad Lotfollahi, a leading algorithm scientist. Says.
Researchers applied scArches to their research COVID-19 (New Coronavirus Infection) With some lung bronchial samples. They compared cells from COVID-19 patients with healthy references using single-cell transcriptomics. The algorithm was able to isolate the affected cells from the reference, allowing users to identify cells in need of treatment in both mild and severe COVID-19 cases. Biological variation between patients did not affect the quality of the mapping process.
Fabian Theis: “Our vision is to use cell references as easily in the future as current genomic references. In other words, if you want to bake a cake, you usually have your own. You wouldn’t want to come up with a recipe-instead you just look it up in a cookbook. Use scArches to formalize and simplify this lookup process. “
Details of scArches: https://github.com/theislab/scarches
References: Mohammad Lotfollahi, Mohsen Naghipourfar, Malte D. Luecken, Matin Khajavi, Maren Büttner, Marco Wagenstetter, Žiga Avsec, Adam Gayoso, Nir Yosef, Marta Interlandi, Sergei Rybakov, “Mapping Single Cell Data to Reference Atlas”, Alex Misharin and Fabian J. Theis, August 30, 2021 Nature biotechnology..
DOI: 10.1038 / s41587-021-01001-7
Computational biologist Mohammad Lotfollahi is a team leader in the Fabian Theis laboratory at Helmholtz Zentrum München and a PhD student at the TUM School of Life Sciences at the Technische Universität München. He works closely with Fabian Tyce, director of the Institute for Computational Biology in Helmholtz-Sentrum Munich and coordinator of the Helmholtz Artificial Intelligence Cooperation Unit (Helmholtz AI). Theis chairs the mathematical modeling of biological systems at TUM.
AI helps find single diseased cells
https://scitechdaily.com/the-human-cell-atlas-ai-helps-to-spot-single-diseased-cells/ AI helps find single diseased cells