Comprehensive in situ mapping of human cortical transcriptomic cell types

The ability to spatially resolve the cellular architecture of human cortical cell types over informative areas is essential to understanding brain function. We combined in situ sequencing gene expression data and single-nucleus RNA-sequencing cell type definitions to spatially map cells in sections of the human cortex via probabilistic cell typing. We mapped and classified a total of 59,816 cells into all 75 previously defined subtypes to create a first spatial atlas of human cortical cells in their native position, their abundances and genetic signatures. We also examined the precise within- and across-layer distributions of all the cell types and provide a resource for the cell atlas community. The abundances and locations presented here could serve as a reference for further studies, that include human brain tissues and disease applications at the cell type level.

De novo spatiotemporal modelling of cell-type signatures identifies novel cell populations in the developmental human heart

With the emergence of high throughput single cell techniques, the understanding of cellular diversity in biologically complex processes has rapidly increased. The next step towards comprehension of e.g. key organs in the mammal development is to obtain spatiotemporal atlases of the cellular diversity. However, targeted cell typing approaches relying on existing single cell data achieve incomplete and biased maps that could mask the molecular and cellular heterogeneity present in a tissue slide. Here we applied spage2vec, a de novo approach to spatially resolve and characterize cellular diversity during human heart development. We obtained well defined spatial maps of tissue samples from 4.5 to 9 post conception weeks, not biased by probabilistic cell typing approaches. We found previously unreported molecular diversity within cardiomyocytes and epicardial cells and identified their characteristic expression signatures by matching them with specific subpopulations found in single cell RNA sequencing datasets.

Exploiting marker genes for robust classification and characterization of single-cell chromatin accessibility

Background: Single-cell Assay for Transposase Accessible Chromatin using sequencing (scATAC-seq) measures genome-wide chromatin accessibility for the discovery of cell-type specific regulatory networks. ScATAC-seq combined with single-cell RNA sequencing (scRNA-seq) offers important avenues for ongoing research, such as novel cell-type specific activation of enhancer and transcription factor binding sites as well as chromatin changes specific to cell states. On the other hand, scATAC-seq data is known to be challenging to interpret due to its high number of zeros as well as the heterogeneity derived from different protocols. Because of the stochastic lack of marker gene activities, cell type identification by scATAC-seq remains difficult even at a cluster level. Results: In this study, we exploit reference knowledge obtained from external scATAC-seq or scRNA-seq datasets to define existing cell types and uncover the genomic regions which drive cell-type specific gene regulation. To investigate the robustness of existing cell-typing methods, we collected 7 scATAC-seq datasets targeting mouse brain for a meta-analytic comparison of neuronal cell-type annotation, including a reference atlas generated by the BRAIN Initiative Cell Census Network (BICCN). By comparing the area under the receiver operating characteristics curves (AUROCs) for the three major cell types (inhibitory, excitatory, and non-neuronal cells), cell-typing performance by single markers is found to be highly variable even for known marker genes due to study-specific biases. However, the signal aggregation of a large and redundant marker gene set, optimized via multiple scRNA-seq data, achieves the highest cell-typing performances among 5 existing marker gene sets, from the individual cell to cluster level. That gene set also shows a high consistency with the cluster-specific genes from inhibitory subtypes in two well-annotated datasets, suggesting applicability to rare cell types. Next, we demonstrate a comprehensive assessment of scATAC-seq cell typing using exhaustive combinations of the marker gene sets with supervised learning methods including machine learning classifiers and joint clustering methods. Our results show that the combinations using robust marker gene sets systematically ranked at the top, not only with model based prediction using a large reference data but also with a simple summation of expression strengths across markers. To demonstrate the utility of this robust cell typing approach, we trained a deep neural network to predict chromatin accessibility in each subtype using only DNA sequence. Through model interpretation methods, we identify key motifs enriched about robust gene sets for each neuronal subtype. Conclusions: Through the meta-analytic evaluation of scATAC-seq cell-typing methods, we develop a novel method set to exploit the BICCN reference atlas. Our study strongly supports the value of robust marker gene selection as a feature selection tool and cross-dataset comparison between scATAC-seq datasets to improve alignment of scATAC-seq to known biology. With this novel, high quality epigenetic data, genomic analysis of regulatory regions can reveal sequence motifs that drive cell type-specific regulatory programs.

Comprehensive in situ mapping of human cortical transcriptomic cell types

The ability to spatially resolve the cellular architecture of human cortical cell types over informative areas is essential to understanding brain function. We combined in situ sequencing gene expression data and single-nucleus RNA-sequencing cell type definitions to spatially map cells in sections of the human cortex via probabilistic cell typing. We mapped and classified a total of 59,816 cells into all 75 previously defined subtypes to create a first spatial atlas of human cortical cells in their native position, their abundances and genetic signatures.

sc-REnF:An entropy guided robust feature selection for clustering of single-cell rna-seq data

ABSTRACTMany single-cell typing methods require pure clustering of cells, which is susceptible towards the technical noise, and heavily dependent on high quality informative genes selected in the preliminary steps of downstream analysis. Techniques for gene selection in single-cell RNA sequencing (scRNA-seq) data are seemingly simple which casts problems with respect to the resolution of (sub-)types detection, marker selection and ultimately impacts towards cell annotation. We introduce sc-REnF, a novel and robust entropy based feature (gene) selection method, which leverages the landmark advantage of ‘Renyi’ and ‘Tsallis’ entropy achieved in their original application, in single cell clustering. Thereby, gene selection is robust and less sensitive towards the technical noise present in the data, producing a pure clustering of cells, beyond classifying independent and unknown sample with utmost accuracy. The corresponding software is available at: https://github.com/Snehalikalall/sc-REnF

MarkerCapsule: Explainable Single Cell Typing using Capsule Networks

ABSTRACTMany single cell typing methods require manual annotation which casts problems with respect to resolution of (sub-)types, manpower resources and bias towards existing human knowledge. The integration of heterogeneous data and biologically meaningful interpretation of results are further current key challenges. We introduce MarkerCapsule, which leverages the landmark advantages of capsule networks achieved in their original applications in single cell typing. Thereby, the small amount of labeled data required and the naturally arising, biologically meaningful interpretation of cell types in terms of characteristic gene activity patterns are exemplary strengths, beyond outperforming the state of the art in terms of basic typing accuracy. MarkerCapsule is available at: https://github.com/sumantaray/MarkerCapsule.