No abstract

and PCT/EP2016/057355 applied for by Spatial Transcriptomics AB (10x Genomics) covering the described technology. M.R. is employed by Illumina Inc. A.R. is a founder and equity holder of Celsius Therapeutics and an SAB member of Syros Pharmaceuticals and Thermo Fisher Scientific.Reporting summary: Further information on research design is available in the Life Sciences Reporting Summary linked to this article. Data availability:The raw mouse data have been deposited to NCBI's GEO archive GSE130682. Raw files for the breast cancer sample are available through an MTA with Åke Borg

Highlights d RAISIN RNA-seq of 1.6 million cells and 6,513 enteric neurons from adult mice and humans d Dozens of neuron subsets that vary by location, circadian phase, age, and species d Putative interactions between neurons and epithelial, stromal, and immune cells d Enteric neurons express risk genes for extraintestinal diseases with gut dysmotility

Single-cell RNA sequencing (scRNA-seq) has enabled researchers to study gene expression at a cellular resolution. However, noise due to amplification and dropout may obstruct analyses, so scalable denoising methods for increasingly large but sparse scRNAseq data are needed. We propose a deep count autoencoder network (DCA) to denoise scRNA-seq datasets. DCA takes the count distribution, overdispersion and sparsity of the data into account using a zero-inflated negative binomial noise model, and nonlinear gene-gene or gene-dispersion interactions are captured. Our method scales linearly with the number of cells and can therefore be applied to datasets of millions of cells. We demonstrate that DCA denoising improves a diverse set of typical scRNA-seq data analyses using simulated and real datasets. DCA outperforms existing methods for data imputation in quality and speed, enhancing biological discovery.