task2-基于小鼠的基因集数据库资源

作业链接-基于小鼠的基因集数据库资源

许多不同的物种间都具有同源性。现代分子生物学中的同源性描述的是基因与基因之间相似关系，它表明的是两个相比较的序列之间的匹配程度。一般来说，如果两条基因序列相似性达80% ，就可以把它们称为“同源基因(homologousgene)”。

下载地址

# http://bioinf.wehi.edu.au/software/MSigDB/human_H_v5p2.rdata
# http://bioinf.wehi.edu.au/software/MSigDB/mouse_H_v5p2.rdata

#检查是否安装相应的R包
if (!requireNamespace(c("BiocManager",""), quietly = TRUE)){install.packages("BiocManager")}
if (!requireNamespace("clusterProfiler", quietly = TRUE)){BiocManager::install("clusterProfiler")}
if (!requireNamespace("org.Hs.eg.db", quietly = TRUE)){BiocManager::install("org.Hs.eg.db")}
if (!requireNamespace("org.Mm.eg.db", quietly = TRUE)){BiocManager::install("org.Mm.eg.db")}
if (!requireNamespace("homologene", quietly = TRUE)){install.packages("homologene")}

#加载相应的数据
load("human_H_v5p2.rdata")
load("mouse_H_v5p2.rdata")
#加载R包
library(clusterProfiler)
library(org.Hs.eg.db)
library(org.Mm.eg.db)
library(homologene)

human <- lapply(Hs.H, function(x){bitr(x, fromType = "ENTREZID", toType = "SYMBOL", OrgDb = org.Hs.eg.db)[,2]
})

mouse <- lapply(Mm.H, function(x){bitr(x, fromType = "ENTREZID",toType = "SYMBOL",OrgDb = org.Mm.eg.db)[,2]})

human_2_mouse <- sapply(names(human), function(x){homologene(human[[x]], inTax = 9606, outTax = 10116)[2]})
names(human_2_mouse) = sub("(.*?)\\.\\d+", "\\1", names(human_2_mouse),perl=TRUE)#重命名

human_length = sapply(names(human),function(x){length(human[[x]])})
mouse_length = sapply(names(mouse),function(x){length(mouse[[x]])})
human_only = sapply(names(human), function(x){length(setdiff(human_2_mouse[[x]],mouse[[x]]))})
mouse_only = sapply(names(human), function(x){length(setdiff(mouse[[x]],human_2_mouse[[x]]))})
intersect_human_mouse = sapply(names(human), function(x){length(intersect(human_2_mouse[[x]],mouse[[x]]))})

result = data.frame(human_genes=human_length,mouse_genes=mouse_length,overlap=intersect_human_mouse,human_specific=human_only,mouse_specific=mouse_only)

作业-当然可以自己造轮子

arrange <- function(data, start=1, end=length(data)){
  if(start == end){
    print(data)
  }else{
    i = start
    for (number in start:end) {
      mid=data[number];data[number]=data[i];data[i]=mid #i和number元素的位置互换
      arrange(data, start + 1, end)
      #如果前面n中元素位置发生了互换，那这个可以保证又换回来
      mid=data[number];data[number]=data[i];data[i]=mid       
    }
  }
}
arrange(1:3)
#arrange(1:9)

参考

https://www.sohu.com/a/258367748_777125
https://mp.weixin.qq.com/s/DgF0v1vQj65BPCvAFfZjQw
https://www.cnblogs.com/sunriseblogs/p/9873013.html