记录R的一些黑魔法

通路富集结果可视化

1 2 3 4 5 6 7 8

pathway<-read.table("PTC+_transcript_pep_supp_KEGG.txt",header=T,sep="t",stringsAsFactors=FALSE) pp <- ggplot(pathway,aes(richFactor,Pathway)) pp + geom_point() pp + geom_point(aes(size=R0vsR3)) pbubble = pp + geom_point(aes(size=R0vsR3+.5,color=-1*log10(Qvalue))) pbubble + scale_colour_gradient(low="green",high="red") pr = pbubble + scale_colour_gradient(low="green",high="red") + labs(color=expression(-log[10](Qvalue)),size="Gene number",x="Enrich factor",y="KEGG Pathway",title="Top10 of KEGG Pathway") pr + theme(axis.text.y = element_text(size = 16))

数据分段

1	v %>% rank() %>% cut(breaks = 10)

一页多图

1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35

multiplot <- function(..., plotlist=NULL, file, cols=1, layout=NULL) { library(grid) plots <- c(list(...), plotlist) numPlots = length(plots) # If layout is NULL, then use 'cols' to determine layout if (is.null(layout)) { # Make the panel # ncol: Number of columns of plots # nrow: Number of rows needed, calculated from # of cols layout <- matrix(seq(1, cols * ceiling(numPlots/cols)), ncol = cols, nrow = ceiling(numPlots/cols)) } if (numPlots==1) { print(plots[[1]]) } else { # Set up the page grid.newpage() pushViewport(viewport(layout = grid.layout(nrow(layout), ncol(layout)))) # Make each plot, in the correct location for (i in 1:numPlots) { # Get the i,j matrix positions of the regions that contain this subplot matchidx <- as.data.frame(which(layout == i, arr.ind = TRUE)) print(plots[[i]], vp = viewport(layout.pos.row = matchidx$row, layout.pos.col = matchidx$col)) } } }

dplyr mutate以行计算需要Group input by rows，否则上下列会串（血的教训T_T）

1

rowwise()

18.4.26

终于找到ggplot2热图空行的解决方案了！！！facet里加参数scale = “free”

1 2 3 4

ggplot() + geom_tile() + scale_color_gradient2() + facet_wrap(~group, scales = "free")

18.4.28

origin

大专栏  记录R的一些黑魔法td class="code">

## m=matrix(data=sample(rnorm(100,mean=0,sd=2)), ncol=10)
## this function makes a graphically appealing heatmap (no dendrogram) using ggplot
## whilst it contains fewer options than gplots::heatmap.2 I prefer its style and flexibility

ggheat=function(m, rescaling='none', clustering='none', labCol=T, labRow=T, border=FALSE, 
heatscale= c(low='blue',high='red'))
{
  ## the function can be be viewed as a two step process
  ## 1. using the rehape package and other funcs the data is clustered, scaled, and reshaped
  ## using simple options or by a user supplied function
  ## 2. with the now resahped data the plot, the chosen labels and plot style are built

  require(reshape2)
  require(ggplot2)

  ## you can either scale by row or column not both! 
  ## if you wish to scale by both or use a differen scale method then simply supply a scale
  ## function instead NB scale is a base funct

  if(is.function(rescaling))
  { 
    m=rescaling(m)
  } 
  else 
  {
    if(rescaling=='column') 
      m=scale(m, center=T)
    if(rescaling=='row') 
      m=t(scale(t(m),center=T))
  }

  ## I have supplied the default cluster and euclidean distance- and chose to cluster after scaling
  ## if you want a different distance/cluster method-- or to cluster and then scale
  ## then you can supply a custom function 

  if(is.function(clustering)) 
  {
    m=clustering(m)
  }else
  {
  if(clustering=='row')
    m=m[hclust(dist(m))$order, ]
  if(clustering=='column')  
    m=m[,hclust(dist(t(m)))$order]
  if(clustering=='both')
    m=m[hclust(dist(m))$order ,hclust(dist(t(m)))$order]
  }
	## this is just reshaping into a ggplot format matrix and making a ggplot layer

  rows=dim(m)[1]
  cols=dim(m)[2]
  melt.m=cbind(rowInd=rep(1:rows, times=cols), colInd=rep(1:cols, each=rows) ,melt(m))
	g=ggplot(data=melt.m)

  ## add the heat tiles with or without a white border for clarity

  if(border==TRUE)
    g2=g+geom_rect(aes(xmin=colInd-1,xmax=colInd,ymin=rowInd-1,ymax=rowInd, fill=value),colour='white')
  if(border==FALSE)
    g2=g+geom_rect(aes(xmin=colInd-1,xmax=colInd,ymin=rowInd-1,ymax=rowInd, fill=value))

  ## add axis labels either supplied or from the colnames rownames of the matrix

  if(labCol==T) 
    g2=g2+scale_x_continuous(breaks=(1:cols)-0.5, labels=colnames(m))
  if(labCol==F) 
    g2=g2+scale_x_continuous(breaks=(1:cols)-0.5, labels=rep('',cols))

  if(labRow==T) 
    g2=g2+scale_y_continuous(breaks=(1:rows)-0.5, labels=rownames(m))	
	if(labRow==F) 
    g2=g2+scale_y_continuous(breaks=(1:rows)-0.5, labels=rep('',rows))	

  ## get rid of grey panel background and gridlines

  # g2=g2+opts(panel.grid.minor=theme_line(colour=NA), panel.grid.major=theme_line(colour=NA),
  # panel.background=theme_rect(fill=NA, colour=NA))

  ## finally add the fill colour ramp of your choice (default is blue to red)-- and return
  return(g2+scale_fill_continuous("", heatscale[1], heatscale[2]))

}

  ## NB because ggheat returns an ordinary ggplot you can add ggplot tweaks post-production e.g. 
  ## data(mtcars)
  ## x= as.matrix(mtcars)
  ## ggheat(x, clustCol=T)+ opts(panel.background=theme_rect(fill='pink'))

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87

黑白屏恢复：win+ctrl+C

18.5.3 pheatmap怎么拼图

y叔：听说你还不会画heatmap

1 2	x = pheatmap::pheatmap(d) cowplot::plot_grid(x$gtable, ...)

18.5.24 GTF读取

1	rtracklayer::import() %>% as.data.frame()

18.8.3 读取dataframe指定某一列数据类型

1 2	read.table("xx", colClasses = c("id"="character")) fread("xx", ..., colClasses = c("id"="character"))

18.12.4 object名与字符串互换

1 2	get("object") deparse(substitute(object))