Abstract
Single cell RNA sequencing (scRNAseq) can be used to infer a temporal ordering of cellular states. Current methods for the inference of cellular trajectories rely on unbiased dimensionality reduction techniques. However, such biologically agnostic ordering can prove difficult for modeling complex developmental or differentiation processes. The cellular heterogeneity of dynamic biological compartments can result in sparse sampling of key intermediate cell states. To overcome these limitations, we develop a supervised machine learning framework, called Pseudocell Tracer, which infers trajectories in pseudospace rather than in pseudotime. The method uses a supervised encoder, trained with adjacent biological information, to project scRNAseq data into a low-dimensional manifold that maps the transcriptional states a cell can occupy. Then a generative adversarial network (GAN) is used to simulate pesudocells at regular intervals along a virtual cell-state axis. We demonstrate the utility of Pseudocell Tracer by modeling B cells undergoing immunoglobulin class switch recombination (CSR) during a prototypic antigen-induced antibody response. Our results revealed an ordering of key transcription factors regulating CSR to the IgG1 isotype, including the concomitant expression of Nfkb1 and Stat6 prior to the upregulation of Bach2 expression. Furthermore, the expression dynamics of genes encoding cytokine receptors suggest a poised IL-4 signaling state that preceeds CSR to the IgG1 isotype.
Highlights
Single-cell RNA sequencing has emerged as a dominant tool for analyzing the transcriptional states of individual cells in diverse biological contexts [1,2]
In the past decade advances in computing and single cell sequencing technologies have ushered in a new era of discovery in biology and medicine
We reason that use of prior knowledge of the system can aid in the extraction of obscured information from scRNAseq datasets
Summary
Single-cell RNA sequencing (scRNAseq) has emerged as a dominant tool for analyzing the transcriptional states of individual cells in diverse biological contexts [1,2]. Computational analyses of scRNAseq datasets have enabled rigorous delineation of known cellular identities as well as the discovery of novel cell types [3]. Such datasets have been used to infer a temporal ordering of dynamic cellular states or cellular trajectories [4]. Dimensionality reduction techniques [14], such as PCA [15], ICA [16], and UMAP [17], are used to project and visualize single cells based on their gene expression profiles in low dimensional space (Fig 1A, left). Unsupervised low dimensional projections can reveal salient temporal structure in largescale scRNAseq datasets, especially when a dominant transcriptional regulatory program directs the biological process. Gene expression abundances from the original high dimensional profiles can be plotted along a pseudotime coordinate to display their changes along the inferred trajectory (Fig 1A, right)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
