A0753
Title: A Bayesian approach to model uncertainty in single-cell genomic data
Authors: Shanshan Ren - University College London (United Kingdom) [presenting]
Tom Bartlett - University College London (United Kingdom)
Lina Gerontogianni - The Francis Crick Institute (United Kingdom)
Swati Chandna - Birkbeck, University of London (United Kingdom)
Abstract: Network models provide a powerful framework for analyzing single-cell count data, facilitating the characterization of cellular identities, disease mechanisms, and developmental trajectories. However, uncertainty modeling in unsupervised learning with genomic data remains insufficiently explored. Conventional clustering methods assign a singular identity to each cell, potentially obscuring transitional states during differentiation or mutation. The purpose is to introduce a variational Bayesian framework for clustering and analyzing single-cell genomic data, employing a Bayesian Gaussian mixture model to estimate the probabilistic association of cells with distinct clusters. This approach captures cellular transitions, yielding biologically coherent insights into neurogenesis and breast cancer progression. The inferred clustering probabilities enable further analyses, including differential expression analysis and pseudotime analysis. Furthermore, it is proposed to utilize the area under the curve (AUC) in clustering scRNA-seq data to quantitatively evaluate overall clustering performance. This methodological advancement enhances the resolution of single-cell data analysis, enabling a more nuanced characterization of dynamic cellular identities in development and disease.
