# R 樣板紀錄

一些用 R script 呈現 素材版圖。

### 火山圖


#nba <- read.csv("http://datasets.flowingdata.com/ppg2008.csv", sep=",")
#nba <- nba[order(nba$PTS),]
#row.names(nba) <- nba$Name
#nba <- nba[,2:20]
#nba_matrix <- data.matrix(nba)
#nba_heatmap <- heatmap(nba_matrix, Rowv=NA, Colv=NA, col = cm.colors(256), scale="column", margins=c(5,10))


DE <- read.table("diffExpr.P0.001_C1.matrix.log2_1.dat.txt",header=T, sep="\t")
DE <- DE[order(DE$gene),]
row.names(DE) <- DE$gene
DE_V <- DE[,1:9]
DE_matrix <- data.matrix(DE_V)
DE_heatmap <- heatmap(DE_matrix, Rowv=NA, Colv=NA, col = cm.colors(256), scale="column", margins=c(5,10))

### Veen diagram
數量差異比較。
不過要先用 perl 計算好值與排列好資料格式


 fonts()  ##  查詢字體
  grid.newpage();
  venn.plot <- draw.pairwise.venn(
      area1 = 1476+2090,
      area2 = 794+2090, 
      cross.area = 2090,
      fill = c("blue", "green"),
      alpha = rep(0.3, 2),
      category= c("Brain vs. Liver", "Gill vs. Liver"),
      cat.pos = c(-20, 20),
      cat.dist = 0.05,
      euler.d = TRUE,
      cex=3,
      cat.cex= 2,
      fontfamily="Arial Black",
      cat.fontfamily="Arial Black"
  );


	 ## REFERENCE  * for use
draw.pairwise.venn(
*	area1, 
*	area2, 
*	cross.area, 
	category = rep("", 2),
	euler.d = TRUE, 
	scaled = TRUE, 
	inverted = FALSE,
    ext.text = TRUE, 
	ext.percent = rep(0.05, 3), 
	lwd =rep(2, 2), 
	lty = rep("solid", 2), 
	col = rep("black",2), 
*	fill = NULL, 
*	alpha = rep(0.5, 2), 
	label.col = rep("black", 3), 
	cex = rep(1, 3), 
	fontface =rep("plain", 3), 
	fontfamily = rep("serif", 3), 
*	cat.pos= c(-50, 50), 
*	cat.dist = rep(0.025, 2), 
	cat.cex =rep(1, 2), 
	cat.col = rep("black", 2), 
	cat.fontface = rep("plain", 2), 
	cat.fontfamily = rep("serif", 2),
    cat.just = rep(list(c(0.5, 0.5)), 2), 
	cat.default.pos = "outer", 
	cat.prompts = FALSE, 
	ext.pos = rep(0, 2),
    ext.dist = rep(0, 2), 
	ext.line.lty = "solid",
    ext.length = rep(0.95, 2), 
	ext.line.lwd = 1,
    rotation.degree = 0, 
	rotation.centre = c(0.5, 0.5),
	ind = TRUE, 
	sep.dist = 0.05, 
	offset = 0, 
	cex.prop =
    NULL, 
	print.mode = "raw", 
	sigdigs = 3)

### Heatmap

hhh_1 <- read.table(file="molecular_function_count_1",sep="\t",header= T)
hhh <- read.table(file="molecular_function_count",sep="\t",header= T)
len <- as.vector(hhh$term)
qvalue<-as.numeric(hhh_1$p.value)

### heatmap 變形圖
用顏色梯度與形狀大小來丞相三個維度的資料。

p <- ggplot(hhh_1, aes(x=type ,y=term, 
fill=p.value))+labs(fill='p.value\n')+labs(x = "",y = "") 
p +geom_point()+geom_tile( colour="black") + theme_bw(16)+scale_y_discrete(limits=len)+scale_fill_gradientn(colours=heat.colors(50), breaks=c(0,0.05,1) ,labels=c("",0.05,1),limits=c(0,1), space = "Lab",na.value = "white", guide = "colourbar")+theme(axis.text.x = element_text(angle=30, hjust=.9, vjust=.9,size=14),axis.text=element_text(size=14))
ggsave("label.pdf", width=5.5, height=4)

# 長度分布


setwd("E:/____do_test/R_studio/transcriptome_distribution")
 list500 <- read.table(file="500_5k_re.txt", header =TRUE, sep="\t")
 list500_1 <- read.table(file="500_5k_re_1.txt", header =TRUE, sep="\t")

 len500 <- as.vector(list500$lenght.kb.)
 library("ggplot2", lib.loc="~/R/win-library/3.3")
 plot500 <- ggplot(list500_1,aes(x=lenght.kb., y=count, fill=type)) + geom_bar(stat="identity", position="dodge") + scale_fill_brewer(palette="Pastel1") + theme(axis.text.x = element_text(angle=70, hjust=1, vjust=.5))+xlab("length range (nt)") + ylab("counts")+scale_x_discrete(limits=len500)+ ggtitle("Transcript Length Distribution")+labs(fill='transcriptome\n')+ theme(legend.justification=c(0.95,0.95), legend.position=c(0.95,0.95), legend.title = element_text(colour="black", size=16, face="bold"),legend.text = element_text( size = 14),axis.text=element_text(size=12),axis.title=element_text(size=14,face="bold"))
 plot500
ggsave("myplot500_5k_2_3-1.pdf", width=8, height=5)


 plot500 <- ggplot(list500_1,aes(x=lenght.kb., y=count, fill=type)) + geom_bar(stat="identity", position="dodge") + scale_fill_brewer(palette="Pastel1") + theme(axis.text.x = element_text(angle=60, hjust=1, vjust=.5))+xlab("\n\nlength range (nt)") + ylab("counts\n") +scale_x_discrete(limits=len500)+ ggtitle("Transcript Length Distribution")+labs(fill='transcriptome\n')+ theme(legend.justification=c(0.95,0.95), legend.position=c(0.95,0.95), legend.title = element_text(colour="black", size=16, face="bold"),legend.text = element_text(size = 14),axis.text=element_text(size=12),axis.title=element_text(size=14,face="bold"))
 plot500
ggsave("myplot500_5k_3.pdf", width=8, height=5)


 plot500+geom_text(aes(label=count), vjust=-0.5, colour="black",position=position_dodge(.9), size=2, angle=50)
 ggsave("myplot500_5k_1.pdf", width=9, height=5)