ZC3H20 null mutant analysis

This is an R Markdown Notebook. When you execute code within the notebook, the results appear beneath the code.

Try executing this chunk by clicking the Run button within the chunk or by placing your cursor inside it and pressing Cmd+Shift+Enter.

Complete analysis of WT T. brucei Chromium scRNA-seq

#install.packages(‘Seurat’) v3.2.2.999 #BiocManager::install(“scran”) v1.14.6 #BiocManager::install(“scater”) v1.14.6 #BiocManager::install(“MAST”) #BiocManager::install(“slingshot”) v1.4.0 #BiocManager::install(“tradeSeq”) 1.3.21 #BiocManager::install(“clusterExperiment”) v2.6.1 #BiocManager::install(“ggpubr”) v0.4.0 #BiocManager::install(“clustree”) v0.4.3 #install.packages(“phateR”) #BiocManager::install(“ComplexHeatmap”) v2.2.0 #remotes::install_github(“carmonalab/STACAS”) v1.0.1 #install.packages(“bigmemory”) v4.5.36

library(slingshot)

Loading required package: princurve

library(slingshot)
library(tradeSeq)
library(clusterExperiment)

Attaching package: ‘clusterExperiment’

The following object is masked from ‘package:scater’:

    plotHeatmap

library(ComplexHeatmap)

Loading required package: grid
========================================
ComplexHeatmap version 2.2.0
Bioconductor page: http://bioconductor.org/packages/ComplexHeatmap/
Github page: https://github.com/jokergoo/ComplexHeatmap
Documentation: http://jokergoo.github.io/ComplexHeatmap-reference

If you use it in published research, please cite:
Gu, Z. Complex heatmaps reveal patterns and correlations in multidimensional 
  genomic data. Bioinformatics 2016.
========================================

library(ComplexHeatmap)
library(ggpubr)
library(dplyr)

Attaching package: ‘dplyr’

The following object is masked from ‘package:MAST’:

    combine

The following object is masked from ‘package:matrixStats’:

    count

The following object is masked from ‘package:Biobase’:

    combine

The following objects are masked from ‘package:GenomicRanges’:

    intersect, setdiff, union

The following object is masked from ‘package:GenomeInfoDb’:

    intersect

The following objects are masked from ‘package:IRanges’:

    collapse, desc, intersect, setdiff, slice, union

The following objects are masked from ‘package:S4Vectors’:

    first, intersect, rename, setdiff, setequal, union

The following objects are masked from ‘package:BiocGenerics’:

    combine, intersect, setdiff, union

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

library(STACAS)
library(STACAS)
library(gridExtra)

Attaching package: ‘gridExtra’

The following object is masked from ‘package:dplyr’:

    combine

The following object is masked from ‘package:MAST’:

    combine

The following object is masked from ‘package:Biobase’:

    combine

The following object is masked from ‘package:BiocGenerics’:

    combine

Load in WT integrated replicates already normalised and var genes found and ZC3H20 KO filtered data

# ZC3H20 KO count data and create seurat object
ZC3H20_KO_counts_data <- read.csv("PATH/ZC3H20_KO_counts_data.csv", row.names=1)

ZC3H20 <- CreateSeuratObject(ZC3H20_KO_counts_data, project = "ZC3H20_KO")

# WT replicate data is provided as an seurat object or can be generated with script "WT_differentiation_scRNA-seq"

load("PATH/WT_integrated_seurat_object")

# Load is VSGs provided
VSG_list <- read.table("PATH/VSG_list", quote="\"", comment.char="")

## Normalise data with SCRAN

# Export to a SingleCellExperiment object 

sce_ZC3H20 <- as.SingleCellExperiment(ZC3H20)

# Pre-cluster cells. Factors are first generated within clusters then rescaled to normalize between clusters
qclust <- scran::quickCluster(sce_ZC3H20, min.size = 30)

# Compute size factors - removes low abundance genes
sce_ZC3H20 <- scran::computeSumFactors(sce_ZC3H20, clusters = qclust)
sce_ZC3H20 <- scater::logNormCounts(sce_ZC3H20)

## Convert back to Seurat object 
ZC3H20 <- as.Seurat(sce_ZC3H20, counts = "counts", data = "logcounts")

## Detect variable genes and remove VSG
VSGs <-as.character(VSG_list$V1)

# find variable genes with scran

dec <- modelGeneVar(sce_ZC3H20)
top.hvgs2 <- getTopHVGs(dec, n=3000)
#write.csv(top.hvgs2, file = "scran_HVGs")

## variable genes with seurat

ZC3H20.features <- FindVariableFeatures(ZC3H20, selection.method = "vst", nfeatures = 3000, assay = "RNA") 

top3000 <- head(VariableFeatures(ZC3H20.features), 3000)
#write.csv(top3000, file = "seurat_HVGs")

## find those in common

common_var_genes <- intersect(top.hvgs2, top3000)

## remove the VSGs
var_genes <- subset(common_var_genes, ! common_var_genes %in% VSGs)

# Add to object 

ZC3H20@assays[["RNA"]]@var.features <- var_genes
#write.csv(var_genes, file = "Common_variable_genes_ZC3H20")
#save(ZC3H20, file = "ZC3H20_seurat_norm")

Integrate the ZC3H20 KO data and WT data with STACAS

ref.integrated <- IntegrateData(anchorset=ref.anchors.filtered, dims=1:8, features.to.integrate=all.genes, sample.tree = mySampleTree)

Merging dataset 2 into 1
Extracting anchors for merged samples
Finding integration vectors
Finding integration vector weights
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
Integrating data
Adding a command log without an assay associated with it

rr ref.integrated <- FindClusters(ref.integrated, resolution = 0.4)

Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck

Number of nodes: 10894
Number of edges: 547702

Running Louvain algorithm...
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
Maximum modularity in 10 random starts: 0.8576
Number of communities: 6
Elapsed time: 2 seconds

rr ref.integrated <- FindClusters(ref.integrated, resolution = 0.4)

Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck

Number of nodes: 10894
Number of edges: 547702

Running Louvain algorithm...
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
Maximum modularity in 10 random starts: 0.8576
Number of communities: 6
Elapsed time: 2 seconds

rr # Run UMAP with same number of dims as for FindNeighbors ref.integrated <- RunUMAP(ref.integrated, reduction = , dims = 1:7, min.dist = 0.01)

14:48:17 UMAP embedding parameters a = 1.896 b = 0.8006
14:48:17 Read 10894 rows and found 7 numeric columns
14:48:17 Using Annoy for neighbor search, n_neighbors = 30
14:48:17 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
14:48:18 Writing NN index file to temp file /var/folders/rd/tjq29jm572b7j_j3fg5k_s340000gn/T//RtmpyjyWIo/file14b54b378a0b
14:48:18 Searching Annoy index using 1 thread, search_k = 3000
14:48:22 Annoy recall = 100%
14:48:23 Commencing smooth kNN distance calibration using 1 thread
14:48:26 Initializing from normalized Laplacian + noise
14:48:26 Commencing optimization for 200 epochs, with 423126 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
14:48:32 Optimization finished

rr # Run UMAP with same number of dims as for FindNeighbors ref.integrated <- RunUMAP(ref.integrated, reduction = , dims = 1:7, min.dist = 0.01)

14:48:32 UMAP embedding parameters a = 1.896 b = 0.8006
14:48:32 Read 10894 rows and found 7 numeric columns
14:48:32 Using Annoy for neighbor search, n_neighbors = 30
14:48:32 Building Annoy index with metric = cosine, n_trees = 50
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
14:48:34 Writing NN index file to temp file /var/folders/rd/tjq29jm572b7j_j3fg5k_s340000gn/T//RtmpyjyWIo/file14b52b47fec1
14:48:34 Searching Annoy index using 1 thread, search_k = 3000
14:48:37 Annoy recall = 100%
14:48:38 Commencing smooth kNN distance calibration using 1 thread
14:48:40 Initializing from normalized Laplacian + noise
14:48:40 Commencing optimization for 200 epochs, with 423126 positive edges
0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|
14:48:47 Optimization finished

rr p <- DimPlot(ref.integrated, label = FALSE) p[[1]]\(layers[[1]]\)aes_params\(alpha = 0.3 p[[1]]\)layers[[1]]\(aes_params\)shape = 16 #pdf(file = _WT_KO_intergation_cluster.pdf, width = 3, height = 3) p + NoLegend() + UMAP_theme

rr

save(ref.integrated, file = _WT_integrated_seurat_scaleall)

rr

Markers between clusters

DefaultAssay(ref.integrated) <-
WT_ZC3H20.markers <- FindAllMarkers(ref.integrated, only.pos = TRUE, min.pct = 0.25, logfc.threshold = 0.25, test.use = ) #write.csv(WT_ZC3H20.markers, file = _ZC3H20_integrated_markers.csv)

rr # Get the lineage, selecting the same starting cluster if any lin <- getLineages(SlingshotDataSet(sce), clusterLabels = clusters, start.clus = A.1)

Using full covariance matrix

rr #pdf(file = 3_mutant_smooth.pdf, width = 1.5, height = 1.5) plotSmoothers(sce_GAM_line, counts, gene = —Tb927.7.970, lwd = 0.3, size = 1/10, pointCol = , plotLineages = FALSE) + labs(title = 3) + scale_color_manual(values =c(#f8766d, #f8766d, #00bfc4)) + NoLegend() + geom_line(data = smooth_data_WT, aes(x = smooth_data_WT\(time, y = smooth_data_WT\)Tbrucei---Tb927.7.970)) + geom_line(data = smooth_data_ZC3H20, aes(x = smooth_data_ZC3H20\(time, y = smooth_data_ZC3H20\)Tbrucei---Tb927.7.970), color=#00bfc4) + theme(plot.title = element_text(size = 9, face = ), axis.text.x = element_text(size = 8), axis.title.x = element_text(size = 8), axis.title.y = element_text(size = 8), axis.text.y = element_text(size = 8))

Scale for 'colour' is already present. Adding another scale for 'colour',
which will replace the existing scale.

PrctCellExpringGene <- function(object, genes, group.by = "all"){
  if(group.by == "all"){
    prct = unlist(lapply(genes,calc_helper, object=object))
    result = data.frame(Markers = genes, Cell_proportion = prct)
    return(result)
  }
  
  else{        
    list = SplitObject(object, group.by)
    factors = names(list)
    
    results = lapply(list, PrctCellExpringGene, genes=genes)
    for(i in 1:length(factors)){
      results[[i]]$Feature = factors[i]
    }
    combined = do.call("rbind", results)
    return(combined)
  }
}

calc_helper <- function(object,genes){
  counts = object[['RNA']]@counts
  ncells = ncol(counts)
  if(genes %in% row.names(counts)){
    sum(counts[genes,]>0)/ncells
  }else{return(NA)}
}

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Cmd+Option+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Cmd+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.