A machine learning one-class logistic regression model to predict stemness for single cell transcriptomics and spatial omics.

Cell annotation is a crucial methodological component to interpreting single cell and spatial omics data. These approaches were developed for single cell analysis but are often biased, manually curated and yet unproven in spatial omics. Here we apply a stemness model for assessing oncogenic states to single cell and spatial omic cancer datasets. This one-class logistic regression machine learning algorithm is used to extract transcriptomic features from non-transformed stem cells to identify dedifferentiated cell states in tumors. We found this method identifies single cell states in metastatic tumor cell populations without the requirement of cell annotation. This machine learning model identified stem-like cell populations not identified in single cell or spatial transcriptomic analysis using existing methods. For the first time, we demonstrate the application of a ML tool across five emerging spatial transcriptomic and proteomic technologies to identify oncogenic stem-like cell types in the tumor microenvironment.

A spatially resolved single-cell genomic atlas of the adult human breast.

The adult human breast is comprised of an intricate network of epithelial ducts and lobules that are embedded in connective and adipose tissue1-3. Although most previous studies have focused on the breast epithelial system4-6, many of the non-epithelial cell types remain understudied. Here we constructed the comprehensive Human Breast Cell Atlas (HBCA) at single-cell and spatial resolution. Our single-cell transcriptomics study profiled 714,331 cells from 126 women, and 117,346 nuclei from 20 women, identifying 12 major cell types and 58 biological cell states. These data reveal abundant perivascular, endothelial and immune cell populations, and highly diverse luminal epithelial cell states. Spatial mapping using four different technologies revealed an unexpectedly rich ecosystem of tissue-resident immune cells, as well as distinct molecular differences between ductal and lobular regions. Collectively, these data provide a reference of the adult normal breast tissue for studying mammary biology and diseases such as breast cancer.

A spatially resolved single cell genomic atlas of the adult human breast.

The adult human breast comprises an intricate network of epithelial ducts and lobules that are embedded in connective and adipose tissue. While previous studies have mainly focused on the breast epithelial system, many of the non-epithelial cell types remain understudied. Here, we constructed a comprehensive Human Breast Cell Atlas (HBCA) at single-cell and spatial resolution. Our single-cell transcriptomics data profiled 535,941 cells from 62 women, and 120,024 nuclei from 20 women, identifying 11 major cell types and 53 cell states. These data revealed abundant pericyte, endothelial and immune cell populations, and highly diverse luminal epithelial cell states. Our spatial mapping using three technologies revealed an unexpectedly rich ecosystem of tissue-resident immune cells in the ducts and lobules, as well as distinct molecular differences between ductal and lobular regions. Collectively, these data provide an unprecedented reference of adult normal breast tissue for studying mammary biology and disease states such as breast cancer.

Multiplex imaging of human induced pluripotent stem cell-derived neurons with CO-Detection by indEXing (CODEX) technology.

BACKGROUND: Human induced pluripotent stem cell (iPSC) models have been hailed as a breakthrough for understanding disease and developing new therapeutics. The major advantage of iPSC-derived neurons is that they carry the genetic background of the donor, and as such could be more predictive for clinical translation. However, the development of these cell models is time-consuming and expensive and it is thus critical to maximize readout of markers for immunocytochemistry. One option is to use a highly multiplexed fluorescence imaging assay, like CO-Detection by indEXing (CODEX), which allows detection of 50 + targets in situ. NEW METHOD: This paper describes the development of CODEX in neuronal cell cultures derived from human iPSCs. RESULTS: We differentiated human iPSCs into mixed neuronal and glial cultures on glass coverslips. We then developed and optimized a panel of 21 antibodies to phenotype iPSC-derived neuronal subtypes of cortical, dopaminergic, and striatal neurons, as well as astrocytes, and pre-and postsynaptic proteins. COMPARISON WITH EXISTING METHODS: Compared to standard immunocytochemistry, CODEX oligo-conjugated fluorophores circumvent antibody host interactions and allow for highly customized multiplexing. CONCLUSION: We show that CODEX can be applied to iPSC neuronal cultures and developed fixation and staining protocols for the neurons to sustain the multiple wash-stain cycles of the technology. Furthermore, we demonstrate both cellular and subcellular resolution imaging of multiplexed markers in the same sample.