VoPo leverages cellular heterogeneity for predictive modeling of single-cell data.

Stanley, Natalie; Stelzer, Ina A.; Tsai, Amy S.; Fallahzadeh, Ramin; Ganio, Edward; Becker, Martin; Phongpreecha, Thanaphong; Nassar, Huda; Ghaemi, Sajjad; Maric, Ivana; Culos, Anthony; Chang, Alan L.; Xenochristou, Maria; Han, Xiaoyuan; Espinosa, Camilo; Rumer, Kristen; Peterson, Laura; Verdonk, Franck; Gaudilliere, Dyani; Tsai, Eileen

High-throughput single-cell analysis technologies produce an abundance of data that is critical for profiling the heterogeneity of cellular systems. We introduce VoPo (https://github.com/stanleyn/VoPo), a machine learning algorithm for predictive modeling and comprehensive visualization of the heterogeneity captured in large single-cell datasets. In three mass cytometry datasets, with the largest measuring hundreds of millions of cells over hundreds of samples, VoPo defines phenotypically and functionally homogeneous cell populations. VoPo further outperforms state-of-the-art machine learning algorithms in classification tasks, and identified immune-correlates of clinically-relevant parameters. Single-cell technologies are increasingly prominent in clinical applications, but predictive modelling with such data in large cohorts has remained computationally challenging. We developed a new algorithm, 'VoPo', for predictive modelling and visualization of single cell data for translational applications.

PREDICTION models; DATA modeling; ALGORITHMS; MACHINE learning; HETEROGENEITY

Nature Communications, 2020, Vol 11, Issue 1, p1

2041-1723

Academic Journal

10.1038/s41467-020-17569-8