Gene Enrichment Analysis (L6_vs_L7)_on_Filtered_meanExp

1. load libraries

2. Perform DE analysis using Malignant_CD4Tcells_vs_Normal_CD4Tcells genes

Malignant_CD4Tcells_vs_Normal_CD4Tcells <- read.csv("comparison_L6_vs_L7_with_mean_expression_filtered.csv", header = T)

3. Create the EnhancedVolcano plot

library(ggplot2)
library(EnhancedVolcano)
library(dplyr)

# Define the output directory
output_dir <- "L6_vs_L7"
dir.create(output_dir, showWarnings = FALSE)

# First Volcano Plot
p1 <- EnhancedVolcano(
  Malignant_CD4Tcells_vs_Normal_CD4Tcells,
  lab = Malignant_CD4Tcells_vs_Normal_CD4Tcells$gene,
  x = "avg_log2FC",
  y = "p_val_adj",
  title = "Malignant_CD4Tcells_vs_Normal_CD4Tcells",
  pCutoff = 1e-4,
  FCcutoff = 1.0
)

Warning: One or more p-values is 0. Converting to 10^-1 * current lowest non-zero p-value...

print(p1)  # Display in notebook

ggsave(filename = file.path(output_dir, "VolcanoPlot1.png"), plot = p1, width = 14, height = 10, dpi = 300)

# Second Volcano Plot with selected genes
p2 <- EnhancedVolcano(
  Malignant_CD4Tcells_vs_Normal_CD4Tcells, 
  lab = Malignant_CD4Tcells_vs_Normal_CD4Tcells$gene,
  x = "avg_log2FC", 
  y = "p_val_adj",
  selectLab = c('EPCAM', 'BCAT1', 'KIR3DL2', 'FOXM1', 'TWIST1', 'TNFSF9', 
                'CD80',  'IL1B', 'RPS4Y1', 
                'IL7R', 'TCF7',  'MKI67', 'CD70', 
                'IL2RA','TRBV6-2', 'TRBV10-3', 'TRBV4-2', 'TRBV9', 'TRBV7-9', 
                'TRAV12-1', 'CD8B', 'FCGR3A', 'GNLY', 'FOXP3', 'SELL', 
                'GIMAP1', 'RIPOR2', 'LEF1', 'HOXC9', 'SP5',
                'CCL17', 'ETV4', 'THY1', 'FOXA2', 'ITGAD', 'S100P', 'TBX4', 
                'ID1', 'XCL1', 'SOX2', 'CD27', 'CD28','PLS3','CD70','RAB25' , 'TRBV27', 'TRBV2'),
  title = "Malignant CD4 T cells(cell lines) vs normal CD4 T cells",
  xlab = bquote(~Log[2]~ 'fold change'),
  pCutoff = 1e-4,
  FCcutoff = 1.5, 
  pointSize = 3.0,
  labSize = 5.0,
  boxedLabels = TRUE,
  colAlpha = 0.5,
  legendPosition = 'right',
  legendLabSize = 10,
  legendIconSize = 4.0,
  drawConnectors = TRUE,
  widthConnectors = 0.5,
  colConnectors = 'grey50',
  arrowheads = FALSE,
  max.overlaps = 30
)

Warning: One or more p-values is 0. Converting to 10^-1 * current lowest non-zero p-value...

print(p2)  # Display in notebook

ggsave(filename = file.path(output_dir, "VolcanoPlot2.png"), plot = p2, width = 14, height = 10, dpi = 300)

# Filtering genes
filtered_genes <- Malignant_CD4Tcells_vs_Normal_CD4Tcells %>%
  arrange(p_val_adj, desc(abs(avg_log2FC)))

# Third Volcano Plot - Filtering by p-value and logFC
p3 <- EnhancedVolcano(
  filtered_genes, 
  lab = ifelse(filtered_genes$p_val_adj <= 1e-4 & abs(filtered_genes$avg_log2FC) >= 1.0, filtered_genes$gene, NA),
  x = "avg_log2FC", 
  y = "p_val_adj",
  title = "Malignant CD4 T cells(cell lines) vs normal CD4 T cells",
  pCutoff = 1e-4,
  FCcutoff = 1.0,
  legendPosition = 'right', 
  labCol = 'black',
  labFace = 'bold',
  boxedLabels = FALSE,  # Remove boxed labels
  pointSize = 3.0,
  labSize = 5.0,
  col = c('grey70', 'black', 'blue', 'red'),  # Customize point colors
  selectLab = filtered_genes$gene[filtered_genes$p_val_adj <= 0.05 & abs(filtered_genes$avg_log2FC) >= 1.0]
)

Warning: One or more p-values is 0. Converting to 10^-1 * current lowest non-zero p-value...

print(p3)  # Display in notebook

ggsave(filename = file.path(output_dir, "VolcanoPlot3.png"), plot = p3, width = 14, height = 10, dpi = 300)

# Fourth Volcano Plot - More refined filtering
p4 <- EnhancedVolcano(
  filtered_genes, 
  lab = ifelse(filtered_genes$p_val_adj <= 1e-4 & abs(filtered_genes$avg_log2FC) >= 1.0, filtered_genes$gene, NA),
  x = "avg_log2FC", 
  y = "p_val_adj",
  title = "Malignant CD4 T cells (cell lines) vs Normal CD4 T cells",
  subtitle = "Highlighting differentially expressed genes",
  pCutoff = 1e-4,
  FCcutoff = 1.0,
  legendPosition = 'right',
  colAlpha = 0.8,  # Slight transparency for non-significant points
  col = c('grey70', 'black', 'blue', 'red'),  # Custom color scheme
  gridlines.major = TRUE,
  gridlines.minor = FALSE,
  selectLab = filtered_genes$gene[filtered_genes$p_val_adj <= 0.05 & abs(filtered_genes$avg_log2FC) >= 1.0]
)

Warning: One or more p-values is 0. Converting to 10^-1 * current lowest non-zero p-value...

print(p4)  # Display in notebook

ggsave(filename = file.path(output_dir, "VolcanoPlot4.png"), plot = p4, width = 14, height = 10, dpi = 300)

message("All volcano plots have been displayed and saved successfully in the 'L6_vs_L7' folder.")

All volcano plots have been displayed and saved successfully in the 'L6_vs_L7' folder.

4. Enrichment Analysis-1

# Load necessary libraries
library(clusterProfiler)

clusterProfiler v4.14.4 Learn more at https://yulab-smu.top/contribution-knowledge-mining/

Please cite:

S Xu, E Hu, Y Cai, Z Xie, X Luo, L Zhan, W Tang, Q Wang, B Liu, R Wang, W Xie, T Wu, L Xie, G Yu. Using
clusterProfiler to characterize multiomics data. Nature Protocols. 2024, 19(11):3292-3320

Attaching package: 'clusterProfiler'

The following object is masked from 'package:stats':

    filter

library(org.Hs.eg.db)

Loading required package: AnnotationDbi
Loading required package: stats4
Loading required package: BiocGenerics

Attaching package: 'BiocGenerics'

The following object is masked from 'package:gridExtra':

    combine

The following objects are masked from 'package:dplyr':

    combine, intersect, setdiff, union

The following object is masked from 'package:SeuratObject':

    intersect

The following objects are masked from 'package:stats':

    IQR, mad, sd, var, xtabs

The following objects are masked from 'package:base':

    anyDuplicated, aperm, append, as.data.frame, basename, cbind, colnames, dirname, do.call,
    duplicated, eval, evalq, Filter, Find, get, grep, grepl, intersect, is.unsorted, lapply, Map,
    mapply, match, mget, order, paste, pmax, pmax.int, pmin, pmin.int, Position, rank, rbind, Reduce,
    rownames, sapply, saveRDS, setdiff, table, tapply, union, unique, unsplit, which.max, which.min

Loading required package: Biobase
Welcome to Bioconductor

    Vignettes contain introductory material; view with 'browseVignettes()'. To cite Bioconductor, see
    'citation("Biobase")', and for packages 'citation("pkgname")'.

Loading required package: IRanges
Loading required package: S4Vectors

Attaching package: 'S4Vectors'

The following object is masked from 'package:clusterProfiler':

    rename

The following objects are masked from 'package:dplyr':

    first, rename

The following object is masked from 'package:utils':

    findMatches

The following objects are masked from 'package:base':

    expand.grid, I, unname


Attaching package: 'IRanges'

The following object is masked from 'package:clusterProfiler':

    slice

The following objects are masked from 'package:dplyr':

    collapse, desc, slice

The following object is masked from 'package:sp':

    %over%


Attaching package: 'AnnotationDbi'

The following object is masked from 'package:clusterProfiler':

    select

The following object is masked from 'package:dplyr':

    select

library(enrichplot)

enrichplot v1.26.6 Learn more at https://yulab-smu.top/contribution-knowledge-mining/

Please cite:

T Wu, E Hu, S Xu, M Chen, P Guo, Z Dai, T Feng, L Zhou, W Tang, L Zhan, X Fu, S Liu, X Bo, and G Yu.
clusterProfiler 4.0: A universal enrichment tool for interpreting omics data. The Innovation. 2021,
2(3):100141

library(ReactomePA)

ReactomePA v1.50.0 Learn more at https://yulab-smu.top/contribution-knowledge-mining/

Please cite:

Guangchuang Yu, Qing-Yu He. ReactomePA: an R/Bioconductor package for reactome pathway analysis and
visualization. Molecular BioSystems. 2016, 12(2):477-479

library(DOSE) # For GSEA analysis

DOSE v4.0.0 Learn more at https://yulab-smu.top/contribution-knowledge-mining/

Please cite:

Guangchuang Yu, Li-Gen Wang, Guang-Rong Yan, Qing-Yu He. DOSE: an R/Bioconductor package for Disease
Ontology Semantic and Enrichment analysis. Bioinformatics. 2015, 31(4):608-609

library(ggplot2) # Ensure ggplot2 is available for plotting

# Define threshold for differential expression selection (modified thresholds)
logFC_up_threshold <- 1          # Upregulated logFC threshold
logFC_down_threshold <- -1      # Downregulated logFC threshold
pval_threshold <- 1e-4  # p-value threshold as specified

# Load your differential expression results (modify based on actual data structure)
# Malignant_CD4Tcells_vs_Normal_CD4Tcells <- read.csv("Your_DE_Results_File.csv")

# Select upregulated and downregulated genes
upregulated_genes <- Malignant_CD4Tcells_vs_Normal_CD4Tcells[
  Malignant_CD4Tcells_vs_Normal_CD4Tcells$avg_log2FC > logFC_up_threshold & 
  Malignant_CD4Tcells_vs_Normal_CD4Tcells$p_val_adj < pval_threshold, ]

downregulated_genes <- Malignant_CD4Tcells_vs_Normal_CD4Tcells[
  Malignant_CD4Tcells_vs_Normal_CD4Tcells$avg_log2FC < logFC_down_threshold & 
  Malignant_CD4Tcells_vs_Normal_CD4Tcells$p_val_adj < pval_threshold, ]

# Check for missing genes (NAs) in the gene column and remove them
upregulated_genes <- na.omit(upregulated_genes)
downregulated_genes <- na.omit(downregulated_genes)

# Save upregulated and downregulated gene results to CSV
write.csv(upregulated_genes, "L6_vs_L7/upregulated_genes.csv", row.names = FALSE)
write.csv(downregulated_genes, "L6_vs_L7/downregulated_genes.csv", row.names = FALSE)

# Convert gene symbols to Entrez IDs for enrichment analysis, with checks for missing values
upregulated_entrez <- bitr(upregulated_genes$gene, fromType = "SYMBOL", toType = "ENTREZID", OrgDb = org.Hs.eg.db)

'select()' returned 1:1 mapping between keys and columns
Warning: 6.51% of input gene IDs are fail to map...

downregulated_entrez <- bitr(downregulated_genes$gene, fromType = "SYMBOL", toType = "ENTREZID", OrgDb = org.Hs.eg.db)

'select()' returned 1:1 mapping between keys and columns
Warning: 2.21% of input gene IDs are fail to map...

# Check for missing Entrez IDs
missing_upregulated <- upregulated_genes$gene[is.na(upregulated_entrez$ENTREZID)]
missing_downregulated <- downregulated_genes$gene[is.na(downregulated_entrez$ENTREZID)]

# Print out the missing gene symbols for debugging
cat("Missing upregulated genes:\n", missing_upregulated, "\n")

Missing upregulated genes:
  

cat("Missing downregulated genes:\n", missing_downregulated, "\n")

Missing downregulated genes:
  

# Remove genes that couldn't be mapped to Entrez IDs
upregulated_entrez <- upregulated_entrez$ENTREZID[!is.na(upregulated_entrez$ENTREZID)]
downregulated_entrez <- downregulated_entrez$ENTREZID[!is.na(downregulated_entrez$ENTREZID)]

# Define a function to safely run enrichment, plot results, and save them
safe_enrichGO <- function(gene_list, title, filename) {
  if (length(gene_list) > 0) {
    result <- enrichGO(gene = gene_list, OrgDb = org.Hs.eg.db, keyType = "SYMBOL",
                       ont = "BP", pAdjustMethod = "BH", pvalueCutoff = 0.05)
    if (!is.null(result) && nrow(as.data.frame(result)) > 0) {
      p <- dotplot(result, showCategory = 10, title = title)
      print(p)  
      ggsave(paste0("L6_vs_L7/", gsub(".csv", "_dotplot.png", filename)), plot = p, width = 8, height = 6)
      write.csv(as.data.frame(result), file = paste0("L6_vs_L7/", filename), row.names = FALSE)
    } else {
      message(paste("No significant enrichment found for:", title))
    }
  } else {
    message(paste("No genes found for:", title))
  }
}

safe_enrichKEGG <- function(entrez_list, title, filename) {
  if (length(entrez_list) > 0) {
    result <- enrichKEGG(gene = entrez_list, organism = "hsa", pvalueCutoff = 0.05)
    if (!is.null(result) && nrow(as.data.frame(result)) > 0) {
      p <- dotplot(result, showCategory = 10, title = title)
      print(p)
      ggsave(paste0("L6_vs_L7/", gsub(".csv", "_dotplot.png", filename)), plot = p, width = 8, height = 6)
      write.csv(as.data.frame(result), file = paste0("L6_vs_L7/", filename), row.names = FALSE)
    } else {
      message(paste("No significant KEGG pathways found for:", title))
    }
  } else {
    message(paste("No genes found for:", title))
  }
}

safe_enrichReactome <- function(entrez_list, title, filename) {
  if (length(entrez_list) > 0) {
    result <- enrichPathway(gene = entrez_list, organism = "human", pvalueCutoff = 0.05)
    if (!is.null(result) && nrow(as.data.frame(result)) > 0) {
      p <- dotplot(result, showCategory = 10, title = title)
      print(p)
      ggsave(paste0("L6_vs_L7/", gsub(".csv", "_dotplot.png", filename)), plot = p, width = 8, height = 6)
      write.csv(as.data.frame(result), file = paste0("L6_vs_L7/", filename), row.names = FALSE)
    } else {
      message(paste("No significant Reactome pathways found for:", title))
    }
  } else {
    message(paste("No genes found for:", title))
  }
}

# Perform enrichment analyses, generate plots, and save results
safe_enrichGO(upregulated_genes$gene, "GO Enrichment for Upregulated Genes", "upregulated_GO_results.csv")

safe_enrichGO(downregulated_genes$gene, "GO Enrichment for Downregulated Genes", "downregulated_GO_results.csv")

safe_enrichKEGG(upregulated_entrez, "KEGG Pathway Enrichment for Upregulated Genes", "upregulated_KEGG_results.csv")

Reading KEGG annotation online: "https://rest.kegg.jp/link/hsa/pathway"...
Reading KEGG annotation online: "https://rest.kegg.jp/list/pathway/hsa"...

safe_enrichKEGG(downregulated_entrez, "KEGG Pathway Enrichment for Downregulated Genes", "downregulated_KEGG_results.csv")

safe_enrichReactome(upregulated_entrez, "Reactome Pathway Enrichment for Upregulated Genes", "upregulated_Reactome_results.csv")

safe_enrichReactome(downregulated_entrez, "Reactome Pathway Enrichment for Downregulated Genes", "downregulated_Reactome_results.csv")

No significant Reactome pathways found for: Reactome Pathway Enrichment for Downregulated Genes

4.2. Enrichment Analysis-2-Hallmark

# Load necessary libraries
library(clusterProfiler)
library(org.Hs.eg.db)
library(msigdbr)
library(enrichplot)

# Load Hallmark gene sets from msigdbr
hallmark_sets <- msigdbr(species = "Homo sapiens", category = "H")  # "H" is for Hallmark gene sets

# Convert gene symbols to uppercase for consistency
upregulated_genes$gene <- toupper(upregulated_genes$gene)
downregulated_genes$gene <- toupper(downregulated_genes$gene)

# Check for overlap between your upregulated/downregulated genes and Hallmark gene sets
upregulated_in_hallmark <- intersect(upregulated_genes$gene, hallmark_sets$gene_symbol)
downregulated_in_hallmark <- intersect(downregulated_genes$gene, hallmark_sets$gene_symbol)

# Print the number of overlapping genes for both upregulated and downregulated genes
cat("Number of upregulated genes in Hallmark gene sets:", length(upregulated_in_hallmark), "\n")

Number of upregulated genes in Hallmark gene sets: 75 

cat("Number of downregulated genes in Hallmark gene sets:", length(downregulated_in_hallmark), "\n")

Number of downregulated genes in Hallmark gene sets: 70 

# Define the output folder where the results will be saved
output_folder <- "L6_vs_L7/"

# If there are genes to analyze, proceed with enrichment analysis
if (length(upregulated_in_hallmark) > 0) {
  # Perform enrichment analysis for upregulated genes using Hallmark gene sets
  hallmark_up <- enricher(gene = upregulated_in_hallmark, 
                          TERM2GENE = hallmark_sets[, c("gs_name", "gene_symbol")],  # Ensure TERM2GENE uses correct columns
                          pvalueCutoff = 0.05)
  # Check if results exist
  if (!is.null(hallmark_up) && nrow(hallmark_up) > 0) {
    # Visualize results if available
    up_dotplot <- dotplot(hallmark_up, showCategory = 20, title = "Hallmark Pathway Enrichment for Upregulated Genes")
    
    # Display the plot in the notebook
    print(up_dotplot)
    
    # Save the dotplot to a PNG file
    ggsave(paste0(output_folder, "hallmark_upregulated_dotplot.png"), plot = up_dotplot, width = 10, height = 8)
    
    # Optionally, save the results as CSV
    write.csv(as.data.frame(hallmark_up), file = paste0(output_folder, "hallmark_upregulated_enrichment.csv"), row.names = FALSE)
  } else {
    cat("No significant enrichment found for upregulated genes.\n")
  }
} else {
  cat("No upregulated genes overlap with Hallmark gene sets.\n")
}

if (length(downregulated_in_hallmark) > 0) {
  # Perform enrichment analysis for downregulated genes using Hallmark gene sets
  hallmark_down <- enricher(gene = downregulated_in_hallmark, 
                            TERM2GENE = hallmark_sets[, c("gs_name", "gene_symbol")],  # Ensure TERM2GENE uses correct columns
                            pvalueCutoff = 0.05)
  # Check if results exist
  if (!is.null(hallmark_down) && nrow(hallmark_down) > 0) {
    # Visualize results if available
    down_dotplot <- dotplot(hallmark_down, showCategory = 20, title = "Hallmark Pathway Enrichment for Downregulated Genes")
    
    # Display the plot in the notebook
    print(down_dotplot)
    
    # Save the dotplot to a PNG file
    ggsave(paste0(output_folder, "hallmark_downregulated_dotplot.png"), plot = down_dotplot, width = 10, height = 8)
    
    # Optionally, save the results as CSV
    write.csv(as.data.frame(hallmark_down), file = paste0(output_folder, "hallmark_downregulated_enrichment.csv"), row.names = FALSE)
  } else {
    cat("No significant enrichment found for downregulated genes.\n")
  }
} else {
  cat("No downregulated genes overlap with Hallmark gene sets.\n")
}

NA
NA