#Using sctransform in Seurat

##Tutorial

##packages
library(Seurat)
library(ggplot2)
library(sctransform)

#Load Data and Create Seurat Object

pbmc.data <- Read10X(data.dir = "C:/Users/evrajadh/Documents/RBook/filtered_gene_bc_matrices/hg19/")

#"C:\Users\evrajadh\Documents\RBook\filtered_gene_bc_matrices\hg19"

pbmc <- CreateSeuratObject(counts = pbmc.data)

Warning: Feature names cannot have underscores ('_'), replacing with dashes ('-')

head(pbmc)

View(pbmc)

#Store mitochondria percentage in object meta data
pbmc <- PercentageFeatureSet(pbmc, pattern = "^MT-", col.name = "percent.mt")

#THIS STORES A NEW COLUMN IN METADATA (with nCount_RNA and nFeature_RNA)

#run sctransform
#This covers NORMALIZE, SCALE, and FindVariableFeatures

pbmc <- SCTransform(pbmc, vars.to.regress = "percent.mt", verbose=F)

head(VariableFeatures(pbmc))

[1] "S100A9" "GNLY"   "LYZ"    "S100A8" "NKG7"   "FTL"   

VariableFeatures(pbmc)[1:10]

 [1] "S100A9" "GNLY"   "LYZ"    "S100A8" "NKG7"   "FTL"    "GZMB"   "IGLL5"  "FTH1"   "CCL5"  

interesting_gene_names <- VariableFeatures(pbmc)[1:100]

head(interesting_gene_names)

[1] "S100A9" "GNLY"   "LYZ"    "S100A8" "NKG7"   "FTL"   

#Perform dimensionality reduction by PCA and UMAP embedding (workflow for visualization and clustering

pbmc <- RunPCA(pbmc, verbose=F)

ElbowPlot(pbmc)

pbmc <- RunUMAP(pbmc, dims = 1:30, verbose=F)

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

Computing nearest neighbor graph
Computing SNN

pbmc <- FindClusters(pbmc)

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

Number of nodes: 2700
Number of edges: 111035

Running Louvain algorithm...

0%   10   20   30   40   50   60   70   80   90   100%
[----|----|----|----|----|----|----|----|----|----|
**************************************************|

Maximum modularity in 10 random starts: 0.8342
Number of communities: 12
Elapsed time: 0 seconds

DimPlot(pbmc, label=T)

DimPlot(pbmc, dims = c(2,1), label=T)