Compare Fibroblast Datasets

Author

Huiyi Hu

Published

March 12, 2024

Compare Fibroblast peak datasets (paper vs. own study)


Summary

  • Number of overlap peaks: 129347

  • Number of peaks specific to the paper data: 42665

  • Number of peaks specific to own study: 18880

Obtain GRanges object from paper

library(readr)
library(Seurat)
library(Signac)
library(rtracklayer)

setwd("/project2/xinhe/huiyihu/fib_peaks_data_compare")
data <- readRDS("./Fibroblast_snRNA_snATAC.Rds")

# set the active assay from RNA to peaks
DefaultAssay(data) <- "peaks"

# Obtain Granges Object
fib_peaks_paper <- granges(data)

# Export the GRanges object to a BED file and Rds
export(fib_peaks_paper, "fibpeaks_paper.bed", format = "bed")
saveRDS(fib_peaks_paper, "fib_peaks_paper.rds")

Find overlaps (paper vs. own study) and Venn diagram

library(GenomicRanges)
library(rtracklayer)
library(VennDiagram)

setwd("/project2/xinhe/huiyihu/fib_peaks_data_compare")

# Load GRanges Objects
own <- readRDS("./fib_peaks_own_study/Fibroblast-reproduciblePeaks.gr.rds")
paper <- readRDS("./fib_peaks_paper/fib_peaks_paper.rds")

# Find overlaps
overlaps <- findOverlaps(own, paper)

# Identify unique and overlapping regions
own_unique <- setdiff(own, paper)
paper_unique <- setdiff(paper, own)

# Count the unique and overlapping peaks
count_overlaps <- length(subjectHits(overlaps))
count_own_unique <- length(own_unique)
count_paper_unique <- length(paper_unique)

# Create the Venn diagram
venn.plot <- draw.pairwise.venn(area1 = count_own_unique, 
                                area2 = count_paper_unique, 
                                cross.area = count_overlaps, 
                                category = c("own study", "paper"), 
                                fill = c("skyblue", "pink"),
                                lty = "solid",
                                lwd = 1,
                                cex = 1.5,
                                cat.cex = 1.1)

# Display the Venn diagram
grid.draw(venn.plot)