Polled Digital Cell Sorter (p-DCS): Automatic identification of hematological cell types from single cell RNA-sequencing clusters

Abstract

Background Single cell RNA sequencing (scRNA-seq) brings unprecedented opportunities for mapping the heterogeneity of complex cellular environments such as bone marrow, and provides insight into many cellular processes. Single cell RNA-seq has a far larger fraction of missing data reported as zeros (dropouts) than traditional bulk RNA-seq, and unsupervised clustering combined with Principal Component Analysis (PCA) can be used to overcome this limitation. After clustering, however, one has to interpret the average expression of markers on each cluster to identify the corresponding cell types, and this is normally done by hand by an expert curator. Results We present a computational tool for processing single cell RNA-seq data that uses a voting algorithm to automatically identify cells based on approval votes received by known molecular markers. Using a stochastic procedure that accounts for imbalances in the number of known molecular signatures for different cell types, the method computes the statistical significance of the final approval score and automatically assigns a cell type to clusters without an expert curator. We demonstrate the utility of the tool in the analysis of eight samples of bone marrow from the Human Cell Atlas. The tool provides a systematic identification of cell types in bone marrow based on a list of markers of immune cell types, and incorporates a suite of visualization tools that can be overlaid on a t-SNE representation. The software is freely available as a Python package at https://github.com/sdomanskyi/DigitalCellSorter . Conclusions This methodology assures that extensive marker to cell type matching information is taken into account in a systematic way when assigning cell clusters to cell types. Moreover, the method allows for a high throughput processing of multiple scRNA-seq datasets, since it does not involve an expert curator, and it can be applied recursively to obtain cell sub-types. The software is designed to allow the user to substitute the marker to cell type matching information and apply the methodology to different cellular environments.

Digital Cell Sorter (DCS): a cell type identification, anomaly detection, and Hopfield landscapes toolkit for single-cell transcriptomics

“…We compared the performance of our previous pDCS method ( Domanskyi et al, 2019b ), with the new Hopfield classifier and the consensus annotation classifier described in Voting algorithm. To evaluate the algorithms’ performance, we randomly generated 100 mixtures of pure cell types, representing a gold standard, and evaluated the algorithms based on their automatic annotation.…”

“…The voting algorithm in DCS is based on an extensive revision of our polled Digital Cell Sorter method ( Domanskyi et al, 2019b ). Prior information on cell markers is encoded in a marker/cell type matrix M km where k is the cell type, and m is the marker gene.…”

“…We remark that, in contrast to the previous version of our algorithm ( Domanskyi et al, 2019b ), we now account for negative markers, that is, markers that should not be significantly expressed, in the cell type assignment. The normalization procedure has been modified accordingly.…”

“…Here, we join the ongoing effort to provide the community with user-friendly tools for the second part of single-cell transcriptomics analysis, starting with pre-processing and quality control and ending with cell type annotation, visualization, and analysis of the annotated clusters. In addition to state-of-the-art methods, our Digital Cell Sorter (DCS) platform introduces three new algorithms: (1) An enhanced version of our recently-developed algorithm for the automatic annotation of cell types, polled DCS (pDCS) ( Domanskyi et al, 2019b ), which uses a predefined set of markers to calculate a voting score and annotate cell clusters with cell type information and its statistical significance. The enhanced version of pDCS uses a marker-cell type matrix normalization method to account for markers that are known to be unexpressed in certain cell types.…”

Naturally occurring combinations of receptors from single cell transcriptomics in endothelial cells

“…We used the DCS pipeline [18,19] to process the single-cell RNA-seq PanglaoDB database [20]. The pipeline was applied to each sample independently to normalize the data and identify endothelial and non-endothelial cells.…”