Gaussian mixture models and machine learning predict megakaryocytic growth and differentiation potential ex vivo
May 6-11, 2018
The ability to analyze single cells via flow cytometry has resulted in a wide range of biological and medical applications. Currently, there is no established framework to compare and interpret time-series flow cytometry data for cell engineering applications. Manual analysis of temporal trends is time-consuming and subjective for large-scale datasets. We resolved this bottleneck by developing TEmporal Gaussian Mixture models (TEGM), an unbiased computational strategy to quantify and predict temporal trends of developing cell subpopulations indicative of cellular phenotype.
TEGM applies Gaussian mixture models and gradient boosted trees for cell engineering applications. TEGM enables the extraction of subtle features, such as the dispersion and rate of change of surface marker expression for each subpopulation over time. These critical, yet hard-to-discern, features are fed into machine-learning algorithms that predict underlying cell classes. Our framework can be flexibly applied to conventional flow cytometry sampling schemes, and allows for faster and more consistent processing of time-series flow cytometry data.
Please click Additional Files below to see the full abstract.
William M. Miller, Neda Bagheri, Jia J. Wu, Darryl A. Abbott, Nadim Mahmud, Dolores Mahmud, and Meryem K. Terzioglu, "Gaussian mixture models and machine learning predict megakaryocytic growth and differentiation potential ex vivo" in "Cell Culture Engineering XVI", A. Robinson, PhD, Tulane University R. Venkat, PhD, MedImmune E. Schaefer, ScD, J&J Janssen Eds, ECI Symposium Series, (2018). http://dc.engconfintl.org/ccexvi/212