Conventional single cell sequencing methods help to gain insight into cellular differences and functions. However, this only happens with static snapshots and not with time-lapse films. This limitation makes it difficult to draw conclusions about the dynamics of cell development and gene activity. The recently introduced ̵
Single cell speed
Researchers at the Institute for Computational Biology at Helmholtz Zentrum München and the Mathematics Department at TUM developed ‘scVelo’ (single cell speed). The method estimates the RNA speed using an AI-based model by solving the full genetic transcription dynamics. This enables them to generalize the concept of RNA speed to a variety of biological systems, including dynamic populations.
“We used scVelo to uncover cell development in the endocrine pancreas, in the hippocampus and to investigate dynamic processes in lung regeneration – and this is just the beginning,” says Volker Bergen, main developer of scVelo and first author of the corresponding study at Natural biotechnology.
With scVelo, researchers can estimate the response rates of RNA transcription, splicing, and degradation without the need for experimental data. These rates can help to better understand cell identity and phenotypic heterogeneity. Their introduction of a latent time reconstructs the unknown development time in order to position the cells along the trajectory of the underlying biological process. This is particularly useful to better understand cell decision making. In addition, scVelo reveals regulatory changes and putative driver genes. This not only helps to understand how, but also why cells develop as they do.
Enable personalized treatments
AI-based tools like scVelo lead to personalized treatments. The transition from static snapshots to full dynamic allows researchers to transition from descriptive to predictive models. In the future, this could help to better understand disease progression, such as tumor formation, or to decode cell signals in response to cancer treatment.
“ScVelo has been downloaded almost 60,000 times since its publication last year. It has become a stepping stone for the kinetic basis of single cell transcriptomics,” added Prof. Fabian Theis, who designed the study and is a director at the Institute for Computational Biology the Helmholtz Centers Munich and the Chair for Mathematical Modeling of Biological Systems at the TUM.
New model of machine learning describes the dynamics of cell development
Volker Bergen et al., Generalization of RNA Velocity to Transient Cell States by Dynamic Modeling, Natural biotechnology (2020). DOI: 10.1038 / s41587-020-0591-3
Provided by the Helmholtz Association of German Research Centers
Quote: AI and single cell genomics: New software predicts the fate of cells (2020, August 3), accessed on August 4, 2020 from https://phys.org/news/2020-08-ai-single-cell-genomics- software cell. html
This document is subject to copyright. Except for fair business for private study or research purposes, no part may be reproduced without written permission. The content is provided for informational purposes only.