GENESPACE优雅的绘制基因组共线性图

R语言数据分析指南

发布于 2023-08-18 13:44:43

5040

发布于 2023-08-18 13:44:43

欢迎关注R语言数据分析指南

❝本节来介绍一个用于多个基因组的共线性和直系同源模式分析及可视化的R包「GENESPACE」，软件运行需要依赖其它软件如「OrthoFinder、MCScanX」等，分析环境配置好可以一站式完成数据的分析及可视化同时具有很高的自定性。小编下面进行部分的结果展示，软件安装等更多的详细内容请参考作者的官方文档。 ❞

官方文档

❝https://github.com/jtlovell/GENESPACE (https://htmlpreview.github.io/?https://github.com/jtlovell/tutorials/blob/main/riparianGuide.html) ❞

软件安装

if (!requireNamespace("devtools", quietly = TRUE))
    install.packages("devtools")
devtools::install_github("jtlovell/GENESPACE")

library(GENESPACE)

定义软件路径

genomeRepo <- "~/path/to/store/rawGenomes"
wd <- "~/path/to/genespace/workingDirectory"
path2mcscanx <- "~/path/to/MCScanX/"

下载基因组数据

urls <- c(
  human ="000/001/405/GCF_000001405.40_GRCh38.p14/GCF_000001405.40_GRCh38.p14_",
  mouse = "000/001/635/GCF_000001635.27_GRCm39/GCF_000001635.27_GRCm39_",
  platypus = "004/115/215/GCF_004115215.2_mOrnAna1.pri.v4/GCF_004115215.2_mOrnAna1.pri.v4_",
  chicken = "016/699/485/GCF_016699485.2_bGalGal1.mat.broiler.GRCg7b/GCF_016699485.2_bGalGal1.mat.broiler.GRCg7b_",
  sandLizard = "009/819/535/GCF_009819535.1_rLacAgi1.pri/GCF_009819535.1_rLacAgi1.pri_")

genomes2run <- names(urls)
urls <- file.path("https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF", urls)
translatedCDS <- sprintf("%stranslated_cds.faa.gz", urls)
geneGff <- sprintf("%sgenomic.gff.gz", urls)

names(translatedCDS) <- genomes2run
names(geneGff) <- genomes2run
writeDirs <- file.path(genomeRepo, genomes2run)
names(writeDirs) <- genomes2run
for(i in genomes2run){
  print(i)
  if(!dir.exists(writeDirs[i]))
    dir.create(writeDirs[i])
  download.file(
    url = geneGff[i], 
    destfile = file.path(writeDirs[i], basename(geneGff[i])))
  download.file(
    url = translatedCDS[i], 
    destfile = file.path(writeDirs[i], basename(translatedCDS[i])))
}

解析基因组注释文件

genomes2run <- c("human", "mouse", "platypus", "chicken", "sandLizard")
parsedPaths <- parse_annotations(
  rawGenomeRepo = genomeRepo,
  genomeDirs = genomes2run,
  genomeIDs = genomes2run,
  presets = "ncbi",
  genespaceWd = wd)

软件运行

gpar <- init_genespace(
  wd = wd,
  ploidy = 1, 
  path2mcscanx = path2mcscanx)
out <- run_genespace(gpar, overwrite = T)

数据可视化

ripDat <- plot_riparian(
  gsParam = out, 
  refGenome = "human", 
  forceRecalcBlocks = FALSE)

ripDat <- plot_riparian(
  out, 
  refGenome = "human",
  useOrder = FALSE, 
  useRegions = FALSE)

更改顺序

ripDat <- plot_riparian(
  gsParam = out, 
  refGenome = "mouse",
  genomeIDs = c("mouse", "human", "platypus", "chicken"), 
  forceRecalcBlocks = FALSE)

调整排序

ripDat <- plot_riparian(
  gsParam = out, 
  #reorderBySynteny = FALSE,
  syntenyWeight = 0,
  refGenome = "human")

自定义标签

ggthemes <- ggplot2::theme(
  panel.background = ggplot2::element_rect(fill = "white"))
customPal <- colorRampPalette(
  c("darkorange", "skyblue", "darkblue", "purple", "darkred", "salmon"))
ripDat <- plot_riparian(
  gsParam = out, 
  palette = customPal,
  braidAlpha = .75,
  chrFill = "lightgrey",
  addThemes = ggthemes,
  refGenome = "human")

部分区域高亮展示

roi <- data.frame(
  genome = c("human", "chicken"), 
  chr = c("X", "Z"), 
  color = c("#FAAA1D", "#17B5C5"))
ripDat <- plot_riparian(
  gsParam = out, 
  highlightBed = roi,
  refGenome = "human", 
  genomeIDs = c("sandLizard", "chicken", "human", "mouse", "platypus"),
  customRefChrOrder = c("X", 1:22))