Picture yourself accurately predicting the final order of the Kentucky Derby based on a single photo captured just 10 seconds into the race.
A groundbreaking study published in the Proceedings of the National Academy of Sciences introduces TopicVelo, a cutting-edge method developed by researchers at the UChicago Pritzker School of Molecular Engineering and the Chemistry Department. This innovative approach leverages static snapshots from scRNA-seq to analyze the dynamic changes in cells and genes over time.
By merging principles from classical machine learning, computational biology, and chemistry, the team adopted an interdisciplinary and collaborative strategy.
“Our approach combines a simple yet well-established concept in unsupervised machine learning with a traditional transcriptional model. The synergy between these elements yields a more powerful outcome than anticipated,” explained PME Assistant Professor of Molecular Engineering and Medicine Samantha Riesenfeld. She collaborated on the paper with Chemistry Department Prof. Suriyanarayanan Vaikuntanathan and UChicago Chemistry Ph.D. candidate Cheng Frank Gao.
While scRNA-seq provides detailed and robust measurements, the data obtained is inherently static.
2024-04-28 21:51:02
Link from phys.org
