AI, Data Science & Cloud Certificates from Google, IBM & Meta — 40% Off
One plan covers every Professional Certificate on Coursera. 40% off Coursera Plus Annual.
Unlock All Certificates
In this 1-hour 8-minute talk from Valence Labs, Dominik Klein presents the innovative "moscot" framework for mapping cells through time and space. Explore how this multi-omics single-cell optimal transport framework addresses limitations in single-cell genomic technologies by enabling comprehensive measurement of cells under native temporal dynamics and in their spatial tissue niche. Learn how moscot incorporates multimodal information and scales to single-cell atlases, demonstrating its capability to efficiently reconstruct developmental trajectories of 1.7 million cells from mouse embryos across 20 time points. Discover applications in enriching spatial transcriptomic datasets, aligning multiple coronal sections of the mouse brain, and uncovering spatiotemporal dynamics of mouse embryogenesis. The presentation covers how moscot resolved endocrine-lineage relationships of delta and epsilon cells in mouse pancreas development, with findings confirmed through experimental validation of NEUROD2 as a regulator of epsilon progenitor cells. This talk is part of the AI for drug discovery community at Portal by Valence Labs and discusses the paper published in Nature.
