input_files <- list.files("./", pattern = "*.bed.csv", full.names = TRUE)
n<-length(input_files)
for (i in 1:n){a<-read.csv(input_files[i]);input_data<-a[,c(1:17)];b<-read.table("sp.txt",header = T);y<-left_join(b,input_data,by="geneId");output_file <- file.path(paste0(basename(input_files[i]), ".sp-TE.txt"));write.csv(y, file=output_file, sep='\t',row.names=FALSE)}
#SP中存在TE的个数
data<-read.table("TE-sp-insertion.txt",header = T,sep='\t')
p1 <- ggplot(data, aes(y=TE.count, x=generation, fill = group),axis(size=10)) +geom_boxplot()+scale_fill_manual(values = c("#0072B2", "#D55E00","#E44B4D", "#70AD47"))+theme_bw()+theme(panel.grid.major = element_blank(),panel.grid.minor = element_blank())+theme(plot.title = element_text(hjust = 0.5))+xlab("")
##显著性分析
data<-read.table("95-sp-TE.txt",header = T,sep = '\t')
p1 <- ggplot(data, aes(y=count, x=name, fill = group),axis(size=10)) +geom_boxplot(colour = "black",notch = FALSE,outlier.size = 1.2)+scale_fill_manual(values = c("#0072B2", "#D55E00"))+geom_signif(comparisons = list(c("A","B"),c("C","D"),c("E","F")),map_signif_level = TRUE,step_increase=0.15)+theme_bw()+theme(panel.grid.major = element_blank(),panel.grid.minor = element_blank())+theme(plot.title = element_text(hjust = 0.5))+xlab("")+ theme(axis.text.x = element_text(hjust = 0.5, vjust = 0.5)) + ylab("denovo insertion")
data<-read.table("TW-sp-TE.txt",header = T,sep = '\t')
p1 <- ggplot(data, aes(y=count, x=name, fill = group),axis(size=10)) +geom_boxplot(colour = "black",notch = FALSE,outlier.size = 1.2)+scale_fill_manual(values = c("#E44B4D", "#70AD47"))+geom_signif(comparisons = list(c("A","B"),c("C","D"),c("E","F")),map_signif_level = TRUE,step_increase=0.15)+theme_bw()+theme(panel.grid.major = element_blank(),panel.grid.minor = element_blank())+theme(plot.title = element_text(hjust = 0.5))+xlab("")+ theme(axis.text.x = element_text(hjust = 0.5, vjust = 0.5)) + ylab("denovo insertion")
#SP中TE位置
data<-read.csv("95-CO-sp-teinsertion-location.txt",sep = '\t',header = T)
data<-read.csv("95-TP-sp-teinsertion-location.txt",sep = '\t',header = T)
data<-read.csv("TW-CO-sp-teinsertion-location.txt",sep = '\t',header = T)
data<-read.csv("TW-TP-sp-teinsertion-location.txt",sep = '\t',header = T)
ggplot(data, aes(x=location, y=count,color=generation) )+geom_boxplot()+geom_jitter(alpha=0.2,position = position_jitterdodge(jitter.width = 0.3,jitter.height = 0,dodge.width = 0.8))+ scale_color_manual(values = cols)+theme_classic()+theme(axis.text.x = element_text(angle = 45, hjust = 0.5, vjust = 0.5))
#加截断
ggplot(data, aes(x=location, y=count,color=generation) )+geom_boxplot()+geom_jitter(alpha=0.2,position = position_jitterdodge(jitter.width = 0.3,jitter.height = 0,dodge.width = 0.8))+ scale_color_manual(values = cols)+scale_y_break(breaks = c(1,57))+theme_classic()+theme(axis.text.x = element_text(angle = 45, hjust = 0.5, vjust = 0.5))
#统计有多少SP存在TE
#
data<-read.table("TE-sp-insertion.txt",header = T,sep='\t')
p1 <- ggplot(data, aes(y=gene.count, x=generation, fill = group),axis(size=10)) +geom_boxplot()+scale_fill_manual(values = c("#0072B2", "#D55E00","#E44B4D", "#70AD47"))+theme_bw()+theme(panel.grid.major = element_blank(),panel.grid.minor = element_blank())+theme(plot.title = element_text(hjust = 0.5))+xlab("")
#TE家族
data<-read.table("95-CO-spTE-family-annotate.txt",header = T)
ggplot(data, aes(x=family, y=generation,size=count,color=generation) )+geom_point()+ scale_color_manual(values = cols)+theme_bw()+theme(axis.text.x = element_text(angle = 45, hjust = 0.5, vjust = 0.5))+facet_wrap(~location)
网友评论