High-Resolution Profiling of Human Vocal Fold Cellular Landscapes With Single-Nuclei RNA Sequencing.

Introduction: The function of the vocal folds (VFs) is determined by the phenotype, abundance, and distribution of differentiated cells within specific microenvironments. Identifying this histologic framework is crucial in understanding laryngeal disease. A paucity of studies investigating VF cellular heterogeneity has been undertaken.

Interpretable and context-free deconvolution of multi-scale whole transcriptomic data with UniCell deconvolve.

We introduce UniCell: Deconvolve Base (UCDBase), a pre-trained, interpretable, deep learning model to deconvolve cell type fractions and predict cell identity across Spatial, bulk-RNA-Seq, and scRNA-Seq datasets without contextualized reference data. UCD is trained on 10 million pseudo-mixtures from a fully-integrated scRNA-Seq training database comprising over 28 million annotated single cells spanning 840 unique cell types from 898 studies. We show that our UCDBase and transfer-learning models achieve comparable or superior performance on in-silico mixture deconvolution to existing, reference-based, state-of-the-art methods.

Integration of Single-Cell Transcriptomics With a High Throughput Functional Screening Assay to Resolve Cell Type, Growth Kinetics, and Stemness Heterogeneity Within the Comma-1D Cell Line.

Cell lines are one of the most frequently implemented model systems in life sciences research as they provide reproducible high throughput testing. Differentiation of cell cultures varies by line and, in some cases, can result in functional modifications within a population. Although research is increasingly dependent on these model systems, the heterogeneity within cell lines has not been thoroughly investigated.