Seurat object containing a subset of the mouse liver scRNAseq data (Guilliams et al., Cell 2022)

Data used only for demonstration purpose. Namely, to demonstrate the Differential NicheNet pipeline: https://github.com/saeyslab/nichenetr/blob/master/vignettes/differential_nichenet.md

##### CD40 inhibiton in AMI on d5, seq on d7 and d14

# Load necessary libraries for data manipulation, analysis, and visualization

library(dplyr)

library(Seurat)

library(patchwork)

library(plyr)

# Set the working directory to the folder containing the data

setwd("C:/Users/ALL/sciebo - Lang, Alexander (allan101@uni-duesseldorf.de)@uni-duesseldorf.sciebo.de/ALL_NGS/scRNAseq/scRNAseq/01_TS_d5_paper/03_CD40 inhibition on day 5, seq on day 7 and 14/938-2_cellranger_count/outs")

# Read the M0 dataset from the 10X Genomics format

pbmc.data <- Read10X(data.dir = "filtered_feature_bc_matrix/")

RNA <- pbmc.data$`Gene Expression`

ADT <- pbmc.data$`Antibody Capture`

HST <- pbmc.data$`Multiplexing Capture`

# Load the Matrix package

library(Matrix)

# Hashtag 1, 2 and 3 are marking the mouse replicates per condition

# Subset the rows based on row names

subsetted_rows <- c("TotalSeq-B0301", "TotalSeq-B0302", "TotalSeq-B0303")

animals_data <- HST[subsetted_rows, , drop = FALSE]

# Hashtag 4, 5, 6, 7 are representing DMSO d7, TS d7, DMSO d14 and TS d14

subsetted_rows <- c(""TotalSeq-B0304", "TotalSeq-B0305", "TotalSeq-B0306", "TotalSeq-B0307")

treatment_data <- HST[subsetted_rows, , drop = FALSE]

#Create a Seurat obeject and more assays to combine later

RNA <- CreateSeuratObject(counts = RNA)

ADT <- CreateAssayObject(counts = ADT)

Mice <- CreateAssayObject(counts = animals_data)

Treatment <- CreateAssayObject(counts = treatment_data)

seurat <- RNA

#Add the Assays

seurat[["ADT"]] <- ADT

seurat[["HST_Mice"]] <- Mice

seurat[["HST_Treatment"]] <- Treatment

#Check for AK Names

rownames(seurat[["ADT"]])

#Cluster cells on the basis of their scRNA-seq profiles

# perform visualization and clustering steps

DefaultAssay(seurat) <- "RNA"

seurat <- NormalizeData(seurat)

seurat <- FindVariableFeatures(seurat)

seurat <- ScaleData(seurat)

seurat <- RunPCA(seurat, verbose = FALSE)

seurat <- FindNeighbors(seurat, dims = 1:30)

seurat <- FindClusters(seurat, resolution = 0.8, verbose = FALSE)

seurat <- RunUMAP(seurat, dims = 1:30)

DimPlot(seurat, label = TRUE)

FeaturePlot(seurat, features = "Col1a1", order = T)

# Normalize ADT data,

DefaultAssay(seurat) <- "ADT"

seurat <- NormalizeData(seurat, normalization.method = "CLR", margin = 2)

#Demultiplex cells based on Mouse_Hashtag Enrichment

seurat <- NormalizeData(seurat, assay = "HST_Mice", normalization.method = "CLR")

seurat <- HTODemux(seurat, assay = "HST_Mice", positive.quantile = 0.60)

#Visualize demultiplexing results

# Global classification results

table(seurat$HST_Mice_classification.global)

DimPlot(seurat, group.by = "HST_Mice_classification")

#Demultiplex cells based on Treatment_Hashtag Enrichment

seurat <- NormalizeData(seurat, assay = "HST_Treatment", normalization.method = "CLR")

seurat <- HTODemux(seurat, assay = "HST_Treatment", positive.quantile = 0.60)

#Visualize demultiplexing results

# Global classification results

table(seurat$HST_Treatment_classification.global)

DimPlot(seurat, group.by = "HST_Treatment_classification")

Idents(seurat) <- seurat$HST_Treatment_classification

pbmc.singlet <- subset(seurat, idents = "Negative", invert = T)

Idents(pbmc.singlet) <- pbmc.singlet$HST_Mice_classification

pbmc.singlet <- subset(pbmc.singlet, idents = "Negative", invert = T)

DimPlot(pbmc.singlet, group.by = "HST_Treatment_maxID")

#Redo the clssification to remove the doublettes

pbmc.singlet <- HTODemux(pbmc.singlet, assay = "HST_Treatment", positive.quantile = 0.99)

table(pbmc.singlet$HST_Treatment_classification.global)

DimPlot(pbmc.singlet, group.by = "HST_Treatment_classification")

pbmc.singlet <- subset(pbmc.singlet, idents = "Doublet", invert = T)

pbmc.singlet <- HTODemux(pbmc.singlet, assay = "HST_Mice", positive.quantile = 0.99)

table(pbmc.singlet$HST_Mice_classification.global)

pbmc.singlet <- subset(pbmc.singlet, idents = "Doublet", invert = T)

pbmc.singlet <- HTODemux(pbmc.singlet, assay = "HST_Mice", positive.quantile = 0.60)

pbmc.singlet <- HTODemux(pbmc.singlet, assay = "HST_Treatment", positive.quantile = 0.60)

DimPlot(pbmc.singlet, group.by = "HST_Treatment_maxID")

DimPlot(pbmc.singlet, group.by = "HST_Mice_maxID")

seurat <- pbmc.singlet

seurat$mice <- seurat$HST_Mice_maxID

seurat$treatment <- seurat$HST_Treatment_maxID

library(plyr)

seurat$treatment <- revalue(seurat$treatment, c(

"TotalSeq-B0304" = "DMSO_d7",

"TotalSeq-B0305" = "TS_d7",

"TotalSeq-B0306" = "DMSO_d14",

"TotalSeq-B0307" = "TS_d14"

))

library(plyr)

seurat$mice <- revalue(seurat$mice, c(

"TotalSeq-B0301" = "1",

"TotalSeq-B0302" = "2",

"TotalSeq-B0303" = "3"

))

#Cluster cells on the basis of their scRNA-seq profiles without doublettes

# perform visualization and clustering steps

DefaultAssay(seurat) <- "RNA"

seurat <- NormalizeData(seurat)

seurat <- FindVariableFeatures(seurat)

seurat <- ScaleData(seurat)

seurat <- RunPCA(seurat, verbose = FALSE)

seurat <- FindNeighbors(seurat, dims = 1:30)

seurat <- FindClusters(seurat, resolution = 0.8, verbose = FALSE)

seurat <- RunUMAP(seurat, dims = 1:30)

DimPlot(seurat, label = TRUE)

DefaultAssay(seurat) <- "ADT"

seurat <- NormalizeData(seurat, normalization.method = "CLR", margin = 2)

setwd("C:/Users/ALL/sciebo - Lang, Alexander (allan101@uni-duesseldorf.de)@uni-duesseldorf.sciebo.de/ALL_NGS/scRNAseq/scRNAseq/01_TS_d5_paper/03_CD40 inhibition on day 5, seq on day 7 and 14/Analyse")

saveRDS(seurat, file= "TSd5.v0.1.RDS")

Disclaimer: I am not the owner of this data. It is a reparsed extract from the Seurat object subset of mouse liver scRNAseq data (Guilliams et al., Cell 2022) as published by Browaeys Robin (https://zenodo.org/record/5840787#.YrHDETVBw18).

The purpose is to test the SUNNy algorithm currently being developed.

##### CD40 activation and the effect on Neutrophils

# Load necessary libraries for data manipulation, analysis, and visualization

library(dplyr)

library(Seurat)

library(patchwork)

library(plyr)

# Set the working directory to the folder containing the data

setwd("C:/Users/ALL/sciebo - Lang, Alexander (allan101@uni-duesseldorf.de)@uni-duesseldorf.sciebo.de/ALL_NGS/scRNAseq/scRNAseq/05_FGK45 Wirkung auf Neutros - scRNAseq/938-1_cellranger_count/outs")

# Read the M0 dataset from the 10X Genomics format

pbmc.data <- Read10X(data.dir = "filtered_feature_bc_matrix/")

RNA <- pbmc.data$`Gene Expression`

ADT <- pbmc.data$`Antibody Capture`

HST <- pbmc.data$`Multiplexing Capture`

# Load the Matrix package

library(Matrix)

# Hashtag 1, 2 and 3 are marking the organs (heart, blood, spleen)

# Subset the rows based on row names

subsetted_rows <- c("TotalSeq-B0301", "TotalSeq-B0302", "TotalSeq-B0303")

animals_data <- HST[subsetted_rows, , drop = FALSE]

# Hashtag 4, 5, 6, 7 are representing IgG_1, IgG_1, FGK45_1 and FGK45_1

subsetted_rows <- c("TotalSeq-B0304", "TotalSeq-B0305", "TotalSeq-B0306", "TotalSeq-B0307")

treatment_data <- HST[subsetted_rows, , drop = FALSE]

#Create a Seurat obeject and more assays to combine later

RNA <- CreateSeuratObject(counts = RNA)

ADT <- CreateAssayObject(counts = ADT)

Organ <- CreateAssayObject(counts = animals_data)

Treatment <- CreateAssayObject(counts = treatment_data)

seurat <- RNA

#Add the Assays

seurat[["ADT"]] <- ADT

seurat[["HST_Mice"]] <- Organ

seurat[["HST_Treatment"]] <- Treatment

#Check for AK Names

rownames(seurat[["ADT"]])

#Cluster cells on the basis of their scRNA-seq profiles

# perform visualization and clustering steps

DefaultAssay(seurat) <- "RNA"

seurat <- NormalizeData(seurat)

seurat <- FindVariableFeatures(seurat)

seurat <- ScaleData(seurat)

seurat <- RunPCA(seurat, verbose = FALSE)

seurat <- FindNeighbors(seurat, dims = 1:30)

seurat <- FindClusters(seurat, resolution = 0.8, verbose = FALSE)

seurat <- RunUMAP(seurat, dims = 1:30)

DimPlot(seurat, label = TRUE)

FeaturePlot(seurat, features = "S100a9", order = T)

# Normalize ADT data,

DefaultAssay(seurat) <- "ADT"

seurat <- NormalizeData(seurat, normalization.method = "CLR", margin = 2)

#Demultiplex cells based on Mouse_Hashtag Enrichment

seurat <- NormalizeData(seurat, assay = "HST_Mice", normalization.method = "CLR")

seurat <- HTODemux(seurat, assay = "HST_Mice", positive.quantile = 0.99)

#Visualize demultiplexing results

# Global classification results

table(seurat$HST_Mice_classification.global)

DimPlot(seurat, group.by = "HST_Mice_classification")

#Demultiplex cells based on Treatment_Hashtag Enrichment

seurat <- NormalizeData(seurat, assay = "HST_Treatment", normalization.method = "CLR")

seurat <- HTODemux(seurat, assay = "HST_Treatment", positive.quantile = 0.99)

#Visualize demultiplexing results

# Global classification results

table(seurat$HST_Treatment_classification.global)

DimPlot(seurat, group.by = "HST_Treatment_classification")

Idents(seurat) <- seurat$HST_Treatment_classification

pbmc.singlet <- subset(seurat, idents = "Negative", invert = T)

Idents(pbmc.singlet) <- pbmc.singlet$HST_Mice_classification

pbmc.singlet <- subset(pbmc.singlet, idents = "Negative", invert = T)

DimPlot(pbmc.singlet, group.by = "HST_Treatment_maxID")

#Redo the clssification to remove the doublettes

pbmc.singlet <- HTODemux(pbmc.singlet, assay = "HST_Treatment", positive.quantile = 0.99)

table(pbmc.singlet$HST_Treatment_classification.global)

DimPlot(pbmc.singlet, group.by = "HST_Treatment_classification")

pbmc.singlet <- subset(pbmc.singlet, idents = "Doublet", invert = T)

pbmc.singlet <- HTODemux(pbmc.singlet, assay = "HST_Mice", positive.quantile = 0.99)

table(pbmc.singlet$HST_Mice_classification.global)

pbmc.singlet <- subset(pbmc.singlet, idents = "Doublet", invert = T)

pbmc.singlet <- HTODemux(pbmc.singlet, assay = "HST_Mice", positive.quantile = 0.60)

pbmc.singlet <- HTODemux(pbmc.singlet, assay = "HST_Treatment", positive.quantile = 0.60)

DimPlot(pbmc.singlet, group.by = "HST_Treatment_maxID")

DimPlot(pbmc.singlet, group.by = "HST_Mice_maxID")

seurat <- pbmc.singlet

seurat$organ <- seurat$HST_Mice_maxID

seurat$mouse <- seurat$HST_Treatment_maxID

seurat$treatment <- seurat$HST_Treatment_maxID

library(plyr)

seurat$treatment <- revalue(seurat$treatment, c(

"TotalSeq-B0304" = "IgG",

"TotalSeq-B0305" = "IgG",

"TotalSeq-B0306" = "FGK45",

"TotalSeq-B0307" = "FGK45"

))

library(plyr)

seurat$organ <- revalue(seurat$organ, c(

"TotalSeq-B0301" = "heart",

"TotalSeq-B0302" = "blood",

"TotalSeq-B0303" = "spleen"

))

seurat$mouse <- revalue(seurat$mouse, c(

"TotalSeq-B0304" = "1",

"TotalSeq-B0305" = "2",

"TotalSeq-B0306" = "3",

"TotalSeq-B0307" = "4"

))

#Cluster cells on the basis of their scRNA-seq profiles without doublettes

# perform visualization and clustering steps

DefaultAssay(seurat) <- "RNA"

seurat <- NormalizeData(seurat)

seurat <- FindVariableFeatures(seurat)

seurat <- ScaleData(seurat)

seurat <- RunPCA(seurat, verbose = FALSE)

seurat <- FindNeighbors(seurat, dims = 1:30)

seurat <- FindClusters(seurat, resolution = 0.8, verbose = FALSE)

seurat <- RunUMAP(seurat, dims = 1:30)

DimPlot(seurat, label = TRUE)

DefaultAssay(seurat) <- "ADT"

seurat <- NormalizeData(seurat, normalization.method = "CLR", margin = 2)

setwd("C:/Users/ALL/sciebo - Lang, Alexander (allan101@uni-duesseldorf.de)@uni-duesseldorf.sciebo.de/ALL_NGS/scRNAseq/scRNAseq/05_FGK45 Wirkung auf Neutros - scRNAseq/Analyse")

saveRDS(seurat, file = "FGK45_heart_blood_spleen.v0.1.RDS")

This dataset is a Seurat object with 3 patient samples from pre-treatment ('pre') condition subset from the original data set Bassez et al. 2021: "BIOKEY_13_Pre", "BIOKEY_14_Pre", and "BIOKEY_5_Pre", without downsampling or further per sample filtering. No cells were discarded based on quality control metrics and data was normalized using Seurat NormalizeData function. All available metadata was included.

Markers included have a log-fold above 1 and expressed in at least 50% of the cluster cells. In all the rest of the tabs: Markers for each of cell subtype (Myeloid, T/NK cells, vascular/lymphatic endothelial cells, enterocytes, and fibroblasts) clusters (compared internally to the other clusters in the same cell subtype), identified by the FindAllMarkers command in Seurat. Markers included have a log-fold above 0.6 and expressed in at least 25% of the cluster cells. (XLSX)

CD8 T cell exhaustion is a major barrier limiting anti-tumor therapy. Though checkpoint blockade temporarily improves exhausted CD8 T cell (Tex) function, the underlying epigenetic landscape of Tex remains largely unchanged, preventing their durable “reinvigoration.†Whereas the transcription factor (TF) TOX has been identified as a critical initiator of Tex epigenetic programming, it remains unclear whether TOX plays an ongoing role in preserving Tex biology after cells commit to exhaustion. Here, we decoupled the role of TOX in the initiation versus maintenance of CD8 T cell exhaustion by temporally deleting TOX in established Tex. Induced TOX ablation in committed Tex resulted in apoptotic-driven loss of Tex, reduced expression of inhibitory receptors including PD-1, and a pronounced decrease in terminally differentiated subsets of Tex cells. Simultaneous gene expression and epigenetic profiling revealed a critical role for TOX in ensuring ongoing chromatin accessibility and transcri..., Cells from inducible-Cre (Rosa26CreERT2/+Toxfl/fl P14) mice where TOX was temporally deleted from mature populations of LCMV-specific T exhausted cells after establishment of chronic LCMV infection 5 days post infection were subjected to scRNA and scATACseq coassay,naive cells and WT cells were used as controls. Analysis pipeline developed by Josephine Giles and vignettes published by Satija and Stuart labs.Transcript count and peak accessibility matrices deposited in GSE255042,GSE255043. Seurat/Signac was used to process the scRNA and scATACseq coassay data The processed Seurat/Signac object above was subsequently used for downstream RNA and ATAC analyses as described below: DEGs between TOX WT and iKO cells within each subset were identified using FindMarkers (Seurat, Signac), with a log2-fold-change threshold of 0, using the SCT assay. DACRs were identified using FindMarkers using the "LR" test, with a log2-fold-change threshold of 0.1, a min.pct of 0.05, and included the number of c..., , # Continuous expression of TOX safeguards exhausted CD8 T cell epigenetic fate

https://doi.org/10.5061/dryad.8kprr4xx9

Seurat/Signac pipeline for multiomic scRNA-seq and scATAC-seq dataset, generated following inducible TOX deletion in LCMV-Cl13

Author

Yinghui Jane Huang

Script information

Purpose: Generate and process Seurat/Signac object for downstream analyses Written: Nov 2021 through Oct 2022 Adapted from: Analysis pipeline developed by Josephine Giles and vignettes published by Satija and Stuart labs Input dataset: Transcript count and peak accessibility matrices deposited in GSE255042,GSE255043

Signac Object Generation

1) Create individual signac objects for each sample from the raw 10x cellranger output.

2) Merge individual objects to create one seurat object.

3) Add metadata to merged seurat object.

Following are the steps in the attached html file for analysis of the paired data (ATAC+RNA)

• Load fr...,

Serialized R data files (.rds) associated with the inDrop single-cell RNA-seq analysis in Huang et al., 2019. Each file has a single Seurat object containing a subset of clusters from the full processed dataset, which were separated into different objects due to file size limitations. Raw data (UMIFM counts) are included in the corresponding slot in each Seurat object. Seurat objects can be re-merged into a single object containing the full dataset using the MergeSeurat function.

A. Cell type labels used based on re-analysis of IPF and healthy control data from GSE135893 (Kropski-Vanderbilt Univ single cell cohort) [24]. Clustering was performed using R package Seurat and cell types were identified using known markers. Ciliated_0 and Ciliated_1: Ciliated epithelial cell subpopulations; AT2_2, AT2_13, AT2_29, AT2_30: Alveolar epithelial cell type II subpopulations; SPP1_mac_3: SPP1+ monocytes/macrophages; C1QA_mac_4, C1QA_mac_5, C1QA_mac_9, C1QA_mac_12: C1QA+ macrophage subpopulations; Mono_7, Mono_21: Monocyte subpopulations; Tc_8: cytotoxic T cells; Th_10: helper T cells; AT1_11, MUC5Bpos_AT1_15, Basal_AT1_17: Alveolar epithelial cell type I subpopulations; ACKR1_pos_endo_14: ACKR1+ endothelial cells; ACKR1_neg_endo_16 and ACKR1_neg_endo_20: ACKR1- endothelial cell subpopulations; Diff_cil_18: Differentiating ciliated epithelial cells; Fibroblasts_19 and Fibroblasts_23: Fibroblast subpopulations; Sm_26: smooth muscle; Prolif_mac_22: Proliferating macrophages; Ly_endo_24: Lymphatic endothelium; Bcells_25: B cells; PC_28: Plasma cells; MC_27: mast cells; Mesothelial_31: mesothelial cells. B. Heatmap (left panel) and correlation matrix (right panel) in GSE47460 (Kaminski-LGRC bulk expression cohort) of genes included in the signature derived from the dataset shown in panel A. (ZIP)

Development of the dorsal aorta is a key step in the establishment of the adult blood-forming system since hematopoietic stem and progenitor cells (HSPCs) arise from ventral aortic endothelium in all vertebrate animals studied. Work in zebrafish has demonstrated that arterial and venous endothelial precursors arise from distinct subsets of lateral plate mesoderm. Here, we profile the transcriptome of the earliest detectable endothelial cells (ECs) during zebrafish embryogenesis to demonstrate that tissue-specific EC programs initiate much earlier than previously appreciated, by the end of gastrulation. Classic studies in the chick embryo showed that paraxial mesoderm generates a subset of somite-derived endothelial cells (SDECs) that incorporate into the dorsal aorta to replace HSPCs as they exit the aorta and enter circulation. We describe a conserved program in the zebrafish, where a rare population of endothelial precursors delaminates from the dermomyotome to incorporate exclusively into the developing dorsal aorta. Although SDECs lack hematopoietic potential, they act as a local niche to support the emergence of HSPCs from neighboring hemogenic endothelium. Thus, at least three subsets of ECs contribute to the developing dorsal aorta: vascular ECs, hemogenic ECs, and SDECs. Taken together, our findings indicate that the distinct spatial origins of endothelial precursors dictate different cellular potentials within the developing dorsal aorta. Methods Single-cell RNA sample preparation After FACS, total cell concentration and viability were ascertained using a TC20 Automated Cell Counter (Bio-Rad). Samples were then resuspended in 1XPBS with 10% BSA at a concentration between 800-3000 per ml. Samples were loaded on the 10X Chromium system and processed as per manufacturer’s instructions (10X Genomics). Single cell libraries were prepared as per the manufacturer’s instructions using the Single Cell 3’ Reagent Kit v2 (10X Genomics). Single cell RNA-seq libraries and barcode amplicons were sequenced on an Illumina HiSeq platform. Single-cell RNA sequencing analysis The Chromium 3’ sequencing libraries were generated using Chromium Single Cell 3’ Chip kit v3 and sequenced with (actually, I don’t know:( what instrument was used?). The Ilumina FASTQ files were used to generate filtered matrices using CellRanger (10X Genomics) with default parameters and imported into R for exploration and statistical analysis using a Seurat package (La Manno et al., 2018). Counts were normalized according to total expression, multiplied by a scale factor (10,000), and log-transformed. For cell cluster identification and visualization, gene expression values were also scaled according to highly variable genes after controlling for unwanted variation generated by sample identity. Cell clusters were identified based on UMAP of the first 14 principal components of PCA using Seurat’s method, Find Clusters, with an original Louvain algorithm and resolution parameter value 0.5. To find cluster marker genes, Seurat’s method, FindAllMarkers. Only genes exhibiting significant (adjusted p-value < 0.05) a minimal average absolute log2-fold change of 0.2 between each of the clusters and the rest of the dataset were considered as differentially expressed. To merge individual datasets and to remove batch effects, Seurat v3 Integration and Label Transfer standard workflow (Stuart et al., 2019)

This dataset contains 4 zip files: -A zip file containing raw and filtered scRNAseq matrices, as well as preprocessed Seurat objects (.Rdata) of both whole dataset and subset of Mesp1-derived cells of the anterior part of 2 E10.5 mouse embryos (embryo 1 and 2). The subset is comprised of the "Anterior somites" and "Cardiopharyngeal mesoderm" clusters. -A zip file containing raw and filtered scRNAseq matrices, as well as preprocessed Seurat objects (.Rdata) of whole dataset of Myf5-derived cells of the anterior part of 2 E11.5 mouse embryos (embryo 1 and 2). -A zip file containing raw and filtered scRNAseq matrices, as well as preprocessed Seurat objects (.Rdata) of whole dataset Myf5-GFP cells of the anterior part of an E12.5 mouse embryo. -A zip file containing raw and filtered scRNAseq matrices, as well as preprocessed Seurat objects (.Rdata) of both whole dataset Myf5-GFP cells of the anterior part of an E14.5 mouse embryo. "cellType" and "myoVSnonmyo" clustering information can be f...

Neuroblastoma, a rare embryonic tumor arising from neural crest development, is responsible for 15% of pediatric cancer-related deaths. Recently, several single-cell transcriptome studies were performed on neuroblastoma patient samples to investigate the cell-of-origin and tumor heterogeneity. However, these individual studies involved a small number of tumors and cells, limiting the conclusions that could be drawn. To overcome this limitation, we integrated seven single-cell or single-nucleus data sets into a harmonized cell atlas covering 362,991 cells across 68 patient samples. We use this atlas to decipher the transcriptional landscape of neuroblastoma at single-cell resolution revealing associations between transcriptomic profiles and clinical outcomes within the tumor compartment. In addition, we characterize the complex immune cell landscape and uncover considerable heterogeneity among tumor-associated macrophages. Finally, we showcase the utility of our atlas as a resource by expanding it with new data and using it as a reference for data-driven cell-type annotation.

seuratObj_NBAtlas_share_v20240130.rds: Seurat Object of the NBAtlas. Be aware, using this object requires roughly 14 GB of memory.
SeuratObj_Share_50kSubset_NBAtlas_v20240130.rds: Light-weight version of the NBAtlas (50 k subset) for portable use.

v2:

seuratObj_NBAtlas_share_v20241203.rds: Cleaned Seurat Object of the NBAtlas (doublets from the zooms filtered out).

v3:

SeuratMeta_TumorZoom_NBAtlas_v20250228.rds: Metadata of tumor zoom, for annotation use "clusters" or "cluster_nr", for umap coordinates use "scviUMAP_1" and "scviUMAP_2". This metadata can be used to subset the entire atlas Seurat object to obtain a tumor zoom Seurat object.

BackgroundDelirium seriously affects the prognosis of patients and greatly reduces the ability to work and live. Peripheral inflammatory events may contribute to the development of delirium, the mechanism of which is still unclear. There is a lack of effective diagnostic and treatments for delirium in clinical practice. The study aims to investigate alterations in peripheral immune cell subsets under inflammatory stress and to explore causal associations with delirium.MethodsSingle-cell transcriptional sequencing data of human peripheral blood mononuclear cells (PBMC) before and after lipopolysaccharide (LPS) intervention were processed by the Seurat package in R software. PBMC subsets and cellular markers were defined after downscaling and clustering by the Harmony algorithm to identify characteristic subsets in the context of inflammatory stress. Subsequently, a two-sample Mendelian randomization (MR) study was used to explore the causal associations of these inflammation-related PBMC subsets and their molecular phenotypes with delirium. Based on publicly available genetic data, the study incorporated 70 PBMC-associated immune traits, including 8 types of circulating immune cells, 33 B cell subsets and molecular phenotypes, 13 T cell subsets, and 16 B cell-associated cytokines. The results were also validated for robustness, heterogeneity, and horizontal pleiotropy.ResultsUnder LPS-induced inflammatory stress, B cells, T cells, monocytes, and dendritic cells in human PBMC showed significant activation and quantitative changes. Of these, only lymphocyte and B cell counts were causally associated with delirium risk. This risk link is also seen in the TNF pathway. Further studies of B cells and their subsets revealed that this association may be related to unswitched memory B cells and CD27 expressed on memory B cells. Annotation of the screened SNPs revealed significant polymorphisms in CD27 and CD40 annotated by rs25680 and rs9883798, respectively. The functions of the key annotated genes may be related to the regulation of immune responses, cell differentiation, proliferation, and intercellular interactions.ConclusionThe present study revealed the potential possibility that B cell, memory B cell subset, and TNF-related molecules may be involved in the development of delirium due to peripheral inflammation, which can provide clues for further investigation of delirium prevention and treatment strategies.

Codes and single cell data for "Insulin is expressed by enteroendocrine cells during human fetal development" paper.

Folder: Cell_Ranger_output
Data produced using 10x sequencing.
This folder contains all the Cell Ranger output raw files from all 6 subjects used for single cell RNA sequencing (2x Neonatal- S1056, S1127, 2x fetal 21 weeks GA- S1100A, S1102, 2x fetal 23weeks GA S1130, S1143).
Each subject has two 10X runs- one done on CD45 negatively selected small intestinal cells and the other on non-selected small intestinal cells.

Folder: Matlab_codes_and_struct
Done on Matlab R2019b
This folder contains two scripts and their input files.
1. Global_transcriptome_similarity_Matlab.m - Matlab script to create the distance from adult beta cells from Extended Data Fig 2
2. sturcture_for_global_similarity.mat - input file for "Global_transcriptome_similarity_Matlab.m" script
3. SCENIC_analysis_matlab.m - Matlab script to create clustergram of transcription factors with the most differential activities in the different cell types from Extended Data Fig 3
4. EECs_mat_file.mat - input file for "SCENIC_analysis_matlab.m" script

Folder: Seurat_pipline_and_background_subtraction
Done with Seurat package version 3.2.2
This folder contains R scripts for Seurat analysis and script for background (BG) subtraction of the data.
1. BG_subtraction_before_seurat.R - Script that creates a BG subtracted matrix for each Cell Ranger output before Seurat analysis.
2. seurat_pipline_all_cells.R - Script for Seurat analysis for the full atlas and the Enteroendocrine subset.

Folder: Count_tables
This folder contains three BG subtracted UMI tables and their additional metadata.
1. BG_subtracted_count_table_all_cells_before_filt.txt - BG subtracted UMI table of all cells before Seurat filtration and analysis (input file for "seurat_pipline_all_cells.R" script).
2. Metadata_all_cells_before_filteration.xlsx - Metadata for "BG_subtracted_count_table_all_cells_before_filt.txt " (input file for "seurat_pipline_all_cells.R" script).
3. BG_subtracted_count_table_all_cells_after_filt.txt - BG subtracted UMI table of all cells after Seurat filtration and analysis.
4. Metadata_all_cells_after_filteration.xlsx - Metadata for "BG_subtracted_count_table_all_cells_after_filt.txt".
5. BG_sub_count_table_enteroendocrine_cells.txt - BG subtracted UMI table of enteroendocrine cells subset after Seurat filtration and analysis.
6. Metadata_enteroendocrine_cells.xlsx - Metadata for "BG_sub_count_table_enteroendocrine_cells.txt".

By leveraging single-cell transcriptome and T cell receptor (TCR) sequencing, we aimed to track the transcriptional signatures of CAR T cell clonotypes throughout the course of treatment and furthermore identify molecular patterns leading to potent CAR T cell cytotoxicity. The data presented in this study encompass blood and bone marrow samples from patients ≤ 21 years of age with relapsed or refractory B-cell acute lymphoblastic leukemia (B-ALL) participating in the SJCAR19 phase I/II clinical trial (NCT03573700). In brief, patients enrolled in the clinical trial received either 1 x 10^6 (dose level 1) or 3 x 10^6 (dose level 2) per kilogram of body weight following successful generation of autologous CAR T cell products and lymphodepleting chemotherapy. Peripheral blood was drawn from each participant every week until week 4 post-infusion, at week 6 or 8, and month 3 or 6 if feasible. At week 4 post-infusion, blood marrow was also collected from participants. Total T cells (CD3+) were sorted from each post-infusion sample, as well as the pre-infusion CAR T cell products, and processed through 10x Genomics’ single-cell gene expression and V(D)J sequencing platform using the standard protocol. We identified a unique and unexpected transcriptional signature in a subset of pre-infusion CAR T cells that shared TCRs with post-infusion cytotoxic effector CAR T cells. Functional validation of cells with even a subset of these pre-effector markers demonstrated their immediate cytotoxic potential and resistance to exhaustion. Methods Cells were processed using the Chromium Single Cell V(D)J 5' reagents (10X Genomics). T cell receptor V(D)J cDNA was enriched using the Chromium Single Cell V(D)J Enrichment kit for Human T cells. Corresponding libraries were sequenced on the Illumina NovaSeq platform. Sequencing data were processed using CelLRanger v3.1.0 (10X Genomics) with the GRCh38 reference (v3.0.0) modified to include the first 825 nucleotide bases of the CD19-CAR transcript. The resulting gene expression matrices were aggregated, with read depth normalization based on the number of mapped reads. TCR sequences were processed with version 3.1.0 of the GRCh38 V(D)J reference. Aggregated gene expression matrices were analyzed using Seurat (Hao et al, Cell 2021). Cells with fewer than 300 detected genes, more than 4,999 detected genes, with at least 10% of their expression owed to mitochondrial genes, or with no detected CD19-CAR UMIs (unique molecular identifiers) were excluded from downstream analyses. TCR lineages were integrated with gene expression data using shared cellular barcodes. Additional analyses are described in the corresponding manuscript.

SingleCellExperiment objects with BRCs or immune cells from murine secondary lymphoid organs or human lymph nodes and palatne tonsils. In detail: Cells isolated from murine lymph nodes, splenic white pulp or Peyer’s patches were sorted for TdTomato+EYFP+ reticular cells or hematopoeitic immune cell populations using a BD FACSMelody cell sorter (BD Biosciences). Isolated cells from human lymph nodes or tonsilar tissue were sorted for hematopoeitic as well as non-hematopoeitic, non-endothelial cells. Sorted single cell suspensions were emulsified for library generation using the droplet-based 10x Chromium (10x Genomics) system56. The cDNA libraries were generated according to the established commercial protocol for Chromium Single Cell 3’ Reagent Kit (v3 Chemistry) and sequenced by NovaSeq 6000 Illumina sequencing at the Functional Genomic Center Zurich. In order to get sufficient numbers of cells across organs and conditions, for murine BRCs a total of 19 samples (LN: 7 samples; SP: 7 samples; PP: 5 samples) were processed in 8 batches with batches spanning multiple organs. For murine immune cells 6 samples from immunized mice were processed (LN: 2 samples; SP: 2 samples; PP: 2 samples) in one batch. Gene expression estimation from sequencing files was done using CellRanger (v3.0.2) count with Ensembl GRCm38.9 release as reference to build the index for murine samples and GRCh38.9 used as reference for human samples. Next, quality control was performed in R v.4.0.0 using the R/Bioconductor package scater (v.1.16.0) and included removal of damaged and contaminating cells based on (1) very high or low UMI counts (>2.5 median absolute deviation from the median across all cells), (2) very high or low total number of detected genes (>2.5 median absolute deviation from the median across all cells) and (3) high mitochondrial gene content (> 2.5 median absolute deviations above the median across all cells). In addition, in murine BRC samples only Cxcl13-expressing cells were kept for downstream analysis, while cells expressing one of the markers Ptprc, Cd79a, Cd3e, Pecam1, Lyve1 or Cldn5 were removed as contaminants. Similarly, in human BRC samples only cells expressing CXCL13, but not CD3E, MKI67, PTPRC, CD79A, LYVE1, PECAM1 or MYH11 were kept for downstream analysis. For downstream analysis, murine BRCs were first analysed for each organ individually, before they were merged and compared across organs. Downstream analysis was performed using the Seurat R package (v.4.0.1) and included normalization, scaling, dimensionality reduction with PCA and UMAP, graph-based clustering and calculation of unbiased cluster markers. Clusters were characterized based on the expression of calculated cluster markers and canonical marker genes. Following cluster characterization for each organ individually, BRC samples from all organs were merged and integrated across organs to compare subset identities independent of their organ identity and to confirm the presence of shared BRC subsets. Integration was performed using the IntegrateData function from the Seurat package. For immune cell samples only cell types known to interact with BRCs were kept for further analysis.

Skeletal muscle regeneration relies on the orchestrated interaction of myogenic and non-myogenic cells with spatial and temporal coordination. The regenerative capacity of skeletal muscle declines with aging due to alterations in myogenic stem/progenitor cell states and functions, non-myogenic cell contributions, and systemic changes, all of which accrue with age. A holistic network-level view of the cell-intrinsic and -extrinsic changes influencing muscle stem/progenitor cell contributions to muscle regeneration across the lifespan remains poorly resolved. To provide a comprehensive atlas of regenerative muscle cell states across mouse lifespan, we collected a compendium of 273,923 single-cell transcriptomes from hindlimb muscles of young, old, and geriatric (4-7, 20, and 26 months old, respectively) mice at six closely sampled time-points following myotoxin injury. We identified 29 muscle-resident cell types, eight of which exhibited accelerated or delayed dynamics in their abundances between age groups, including T and NK cells and multiple macrophage subtypes, suggesting that the age-related decline in muscle repair may arise from temporal miscoordination of the inflammatory response. We performed a pseudotime analysis of myogenic cells across the regeneration timespan and found age-specific myogenic stem/progenitor cell trajectories in old and geriatric muscles. Given the critical role that cellular senescence plays in limiting cell contributions in aged tissues, we built a series of tools to bioinformatically identify senescence in these single-cell data and assess their ability to identify senescence within key myogenic stages. By comparing single-cell senescence scores to co-expression of hallmark senescence genes Cdkn2a and Cdkn1a, we found that an experimentally derived gene list derived from a muscle foreign body response (FBR) fibrosis model accurately (receiver-operator curve AUC = 0.82-0.86) identified senescent-like myogenic cells across mouse ages, injury time-points, and cell-cycle states, in a manner comparable to curated gene-lists. Further, this scoring approach in both single-cell and spatial transcriptomic datasets pinpointed transitory senescent-like subsets within the myogenic stem/progenitor cell trajectory that are associated with stalled MuSC self-renewal states across all ages of mice. This new resource on mouse skeletal muscle aging provides a comprehensive portrait of the changing cellular states and interactions underlying skeletal muscle regeneration across the mouse lifespan. Methods Mouse muscle injury and single-cell isolation. The Cornell University Institutional Animal Care and Use Committee (IACUC) approved all animal protocols (approval # 2014-0085), and experiments were performed in compliance with its institutional guidelines. Mice were maintained at 70-73°F on a 14/10-h light/dark with humidity mainly at 40%. Muscle injury was induced in young (4-7 months-old [mo]), old (20 mo), and geriatric (26 mo) C57BL/6J mice (Jackson Laboratory # 000664; NIA Aged Rodent Colonies) by injecting both tibialis anterior (TA) muscles with 10 µl of notexin (10 µg/ml; Latoxan, France). The mice were sacrificed, and TA muscles were collected at 0, 1, 2, 3.5, 5, and 7 days post-injury (dpi) with n = 3-4 biological replicates per sample. Each TA was processed independently to generate single-cell suspensions. At each time point, the young and old samples are biological replicates of TA muscles from distinct mice, and the geriatric samples are biological replicates of two TA muscles from each of the two mice. A mixture of male and female mice was used. See Supplemental Table 1 for additional details. Muscles were digested with 8 mg/ml Collagenase D (Roche, Basel, Switzerland) and 10 U/ml Dispase II (Roche, Basel, Switzerland) and then manually dissociated to generate cell suspensions. Myofiber debris was removed by filtering the cell suspensions through a 100 µm and then a 40 µm filter (Corning Cellgro # 431752 and # 431750). After filtration, erythrocytes were removed by incubating the cell suspension inan erythrocyte lysis buffer (IBI Scientific # 89135-030). Single-cell RNA-sequencing library preparation. After digestion, the single-cell suspensions were washed and resuspended in 0.04% BSA in PBS at a concentration of 106 cells/ml. A hemocytometer was used to manually count the cells to determine the concentration of the suspension. Single-cell RNA-sequencing libraries were prepared using the Chromium Single Cell 3’ reagent kit v3 (10x Genomics, Pleasanton, CA) following the manufacturer’s protocol (10x Genomics: Resolving Biology to Advance Human Health, 2020). Cells were diluted into the Chromium Single Cell A Chip to yield a recovery of 6,000 single-cell transcriptomes with <5% doublet rate. Libraries were sequenced on the NextSeq 500 (Illumina, San Diego, CA) (Illumina | Sequencing and array-based solutions for genetic research, 2020). The sequencing data was aligned to the mouse reference genome (mm10) using CellRanger v5.0.0 (10x Genomics) (10x Genomics: Resolving Biology to Advance Human Health, 2020). Preprocessing single-cell RNA-sequencing data. From the gene expression matrix, the downstream analysis was carried out in R (v3.6.1). First, the ambient RNA signal was removed using the default SoupX (v1.4.5) workflow (autoEstCounts and adjustCounts; github.com/constantAmateur/SoupX) (Young and Behjati, 2020). Samples were then preprocessed using the standard Seurat (v3.2.3) workflow (NormalizeData, ScaleData, FindVariableFeatures, RunPCA, FindNeighbors, FindClusters, and RunUMAP; github.com/satijalab/seurat) (Stuart et al., 2019). Cells with fewer than 200 genes, with fewer than 750 UMIs, and more than 25% of unique transcripts derived from mitochondrial genes were removed. After preprocessing, DoubletFinder (v2.0.3) was used to identify putative doublets in each dataset (McGinnis, Murrow, and Gartner, 2019). The estimated doublet rate was 5% according to the 10x Chromium handbook. The putative doublets were removed from each dataset. Next, the datasets were merged and then batch-corrected with Harmony (github.com/immunogenomics/harmony) (v1.0) (Korsunsky et al., 2019). Seurat was then used to process the integrated data. Dimensions accounting for 95% of the total variance were used to generate SNN graphs (FindNeighbors) and SNN clustering was performed (FindClusters). A clustering resolution of 0.8 was used resulting in 24 initial clusters. Cell type annotation in single-cell RNA-sequencing data. Cell types were determined by expression of canonical genes. Each of the 24 initial clusters received a unique cell type annotation. The nine myeloid clusters were challenging to differentiate between, so these clusters were subset out (Subset) and re-clustered using a resolution of 0.5 (FindNeighbors, FindClusters) resulting in 15 initial clusters. More specific myeloid cell type annotations were assigned based on the expression of canonical myeloid genes. This did not help to clarify the monocyte and macrophage annotations, but it did help to identify more specific dendritic cell and T cell subtypes. These more specific annotations were transferred from the myeloid subset back to the complete integrated object based on the cell barcode. Analysis of cell type dynamics. We generated a table with the number of cells from each sample (n = 65) in each cell type annotation (n = 29). We removed the erythrocytes from this analysis because they are not a native cell type in skeletal muscle. Next, for each sample, we calculated the percent of cells in each cell type annotation. The mean and standard deviation were calculated from each age and time point for every cell type. The solid line is the mean percentage of the given cell type, the ribbon is the standard deviation around the mean, and the points are the values from individual replicates. We evaluated whether there was a significant difference in the cell type dynamics over all six-time points using non-linear modeling. The dynamics for each cell type were fit to some non-linear equation (e.g., quadratic, cubic, quartic) independent and dependent on age. The type of equation used for each cell type was selected based on the confidence interval and significance (p < 0.05) of the leading coefficient. If the leading coefficient was significantly different from zero, it was concluded that the leading coefficient was needed. If the leading coefficient was not significantly different than zero, it was concluded that the leading coefficient was not needed, and the degree of the equation went down one. No modeling equation went below the second degree. The null hypothesis predicted that the coefficients of the non-linear equation were the same across the age groups while the alternative hypothesis predicted that the coefficients of the non-linear equation were different across the age groups. We conducted a One-Way ANOVA to see if the alternative hypothesis fits the data significantly better than the null hypothesis and we used FDR as the multiple comparison test correction (using the ANOVA and p.adjust (method = fdr) functions in R, respectively). T cell exhaustion scoring. We grouped the three T cell populations (this includes Cd3e+ cycling and non-cycling T cells and Cd4+ T cells) and z-scored all genes. The T cell exhaustion score was calculated using a transfer-learning method developed by Cherry et al 2023 and a T cell exhaustion gene list from Bengsch et al 2018 (Bengsch et al., 2018; Cherry et al., 2023). The Mann-Whitney U-test was performed on the T cell exhaustion score between ages. Senescence scoring. We tested two senescence-scoring methods along with fourteen senescence gene lists (Supplemental Table 2) to identify senescent-like cells within the scRNA-seq dataset. The Two-way Senescence Score (Sen Score) was calculated using a transfer-learning method developed by Cherry et al 2023 (Cherry et al., 2023). With this

Following files submitted:
1. adult_raw.RDS : Raw seurat object of the processed adult (n=24) snRNA-seq samples.
2. adult_filtered.RDS : Filtered (after QC) seurat object of the processed adult (n=24) snRNA-seq samples.
3. adultgc_filtered.RDS : Seurat object of adult granule cell subset after additional filtering (See Fig3A).
4. fetal_raw.RDS : Raw seurat object of the processed fetal (n=3) snRNA-seq samples.
5. fetal_filtered.RDS : Filtered (after QC) seurat object of the processed fetal (n=3) snRNA-seq samples.
6. neurolin.RDS : Seurat object of fetal neurogenic lineage subset (See Fig2D).

scRICA_qc_integration_rmCN13_rmCN1IL3376_anno_v3.rds contains the Seurat object of all cell types.

scRICA_qc_integration_rmCN13_rmCN1IL3376_anno_v3_CAFs.rds contains the Seurat object of the cancer-associated fibroblast subset of scRICA_qc_integration_rmCN13_rmCN1IL3376_anno_v3.rds.

scRICA_qc_integration_rmCN13_rmCN1IL3376_anno_v3_CAFs_subtypes.rds contains the Seurat object of cancer-associated fibroblast subtypes.