3 Integrated scRNA-seq pipeline

• Load the R packages.

# sc libraries
library(Seurat)
library(phateR)
library(DoubletFinder)
library(monocle)
library(slingshot)
library(GSVA)
library(limma)
library(plyr)
library(dplyr)
library(org.Mm.eg.db)
library(org.Hs.eg.db)
library(CellChat)
library(velocyto.R)
library(SeuratWrappers)
library(stringr)
library(scran)
library(ggpubr)
library(viridis)
library(pheatmap)
library(parallel)
library(reticulate)
library(SCENIC)
library(feather)
library(AUCell)
library(RcisTarget)
library(Matrix)
library(foreach)
library(doParallel)
library(clusterProfiler)
library(GPTCelltype)
library(openai)
library(HematoMap)
# st libraries
library(RColorBrewer)
library(Rfast2)
library(SeuratDisk)
library(abcCellmap)
library(biomaRt)
library(copykat)
library(gelnet)
library(ggplot2)
library(parallelDist)
library(patchwork)
library(markdown)
# getpot
library(getopt)
library(tools)
# HemaScopeR
library(HemaScopeR)

• Run the integrated scRNA-seq pipeline.

scRNASeq_10x_pipeline(
                     # input and output
                     input.data.dirs = c('/home/wangzy/HemaScopeR/Demo/SRR7881399.Rds',
                                         '/home/wangzy/HemaScopeR/Demo/SRR7881400.Rds',
                                         '/home/wangzy/HemaScopeR/Demo/SRR7881401.Rds',
                                         '/home/wangzy/HemaScopeR/Demo/SRR7881402.Rds',
                                         '/home/wangzy/HemaScopeR/Demo/SRR7881403.Rds'),
                     project.names = c(  'SRR7881399',
                                         'SRR7881400',
                                         'SRR7881401',
                                         'SRR7881402',
                                         'SRR7881403'), 
                     output.dir = '/home/wangzy/HemaScopeR/Demo/output/',
                     pythonPath = python.path.sc(),
                     databasePath = '/home/wangzy/HemaScopeR/Demo/database/',
                     # quality control and preprocessing
                     gene.column = 2,
                     min.cells = 10,
                     min.feature = 200,
                     mt.pattern = '^mt-',
                     nFeature_RNA.limit = 200,
                     percent.mt.limit = 20,
                     scale.factor = 10000,
                     nfeatures = 3000,
                     ndims = 10,
                     PCs = 1:10,
                     resolution = 0.4,
                     n.neighbors = 10,
                     # remove doublets
                     doublet.percentage = 0.04,
                     doublerFinderwraper.PCs = 1:10,
                     doublerFinderwraper.pN = 0.25,
                     doublerFinderwraper.pK = 0.1,
                     # phateR
                     phate.knn = 10,
                     phate.npca = 10,
                     phate.t = 10,
                     phate.ndim = 2,
                     min.pct = 0.25,
                     logfc.threshold = 0.25,
                     Org = 'hsa',
                     tissuename = 'bone marrow',
                     loom.files.path = c( '/home/wangzy/HemaScopeR/Demo/SRR7881399.loom',
                                          '/home/wangzy/HemaScopeR/Demo/SRR7881400.loom',
                                          '/home/wangzy/HemaScopeR/Demo/SRR7881401.loom',
                                          '/home/wangzy/HemaScopeR/Demo/SRR7881402.loom',
                                          '/home/wangzy/HemaScopeR/Demo/SRR7881403.loom'
                                          ),
                     # cell chat
                     sorting = FALSE,
                     ncores = 10,
                     # activeEachStep
                     Whether_load_previous_results = FALSE,
                     Step1_Input_Data = TRUE,
                     Step1_Input_Data.type = 'Seurat',
                     Step2_Quality_Control = TRUE,
                     Step2_Quality_Control.RemoveBatches = FALSE,
                     Step2_Quality_Control.RemoveDoublets = TRUE,
                     Step3_Clustering = TRUE,
                     Step4_Identify_Cell_Types = TRUE,
                     Step4_Use_Which_Labels = 'clustering',
                     Step4_run_sc_CNV = TRUE,
                     Step5_Visualization = TRUE,
                     Step6_Find_DEGs = TRUE,
                     Step7_Assign_Cell_Cycle = TRUE,
                     Step8_Calculate_Heterogeneity = TRUE,
                     Step9_Violin_Plot_for_Marker_Genes = TRUE,
                     Step10_Calculate_Lineage_Scores = TRUE,
                     Step11_GSVA = TRUE,
                     Step11_GSVA.identify.cellType.features=FALSE,
                     Step11_GSVA.identify.diff.features=FALSE,
                     Step11_GSVA.comparison.design=NULL,
                     Step12_Construct_Trajectories = TRUE,
                     Step12_Construct_Trajectories.monocle = TRUE,
                     Step12_Construct_Trajectories.slingshot = TRUE,
                     Step12_Construct_Trajectories.scVelo = TRUE,
                     Step13_TF_Analysis = TRUE,
                     Step14_Cell_Cell_Interaction = TRUE,
                     Step15_Generate_the_Report = TRUE)