其他
纯R代码实现ssGSEA算法评估肿瘤免疫浸润程度
前些天在生信技能树公众号群主说从学徒的作业学到了知识，就是我，详情如下：
神技能-自动化批量从PDF里面提取表格
这其实是一个非常棒的作业，不仅仅是PDF提取基因列表这样的奇淫巧技，更多知识点等你来学！
Goals:
文献为《Local mutational diversity drives intratumoral
immune heterogeneity in non-small cell lung cancer》要复现的图片为
Clues:
a.主要是两个操作：ssGSEA和ggplot（点图+cor.test结果呈现）;
b.大家看问题角度不同，其实会比较有趣，比如，用R包提取pdf的做法（`因为我当时比较有时间，所以就不断地折腾，其实时间不够的话，我会复制粘贴到excel中再读进去`）；比如，我的代码被不断说‘太丑’（`还好有把参照的其他代码放进去，那你说丑就丑吧；不过，其实操作能有最简单的函数实现，我就不给自己本来就不大的脑容量找麻烦了`）；
c.对我来说，需要考虑的地方有两点，（1）如果你读了文章的话，会看到，绘制热图有提到`nomalized to 0-1`，后面搜索之后，才有了normalize那个function；（2）`duplicated gene_name的过滤`，要依据一定的规则会比较好，网上没有查到相关的有让我信服的推荐，后来，采用了jimmy的median排序进行操作（`算是没有标准的标准`）；这里需要了解，GSVA函数里的两个输入，data和gene_set，既然，gene_set是gene-name，data指定需要是gene-name为主体；
Steps:
1.从supplementarytable中将数据集读出来，这个在文章中有提到
虽然我不咋想承认，但故事总得圆圆满满，请点击获取这部分漂亮的代码；
rm(list=ls())
library(pdftools)
options(stringsAsFactors = F)
b <- pdf_text('SupplementaryTables.pdf')
geneset_substract<- function(tmp){split_to_line<- gsub('\r','',strsplit(tmp,split = '\n')[[1]])
gene_name<- apply(data.frame(split_to_line),1,function(x){ line<- strsplit(x,split=' ')[[1]]
pos<- grep('[A-Za-z\\d+]|\\d+',line)
res <- line[pos[1]]})
cell_type<- apply(data.frame(split_to_line),1,function(x){ line<- strsplit(x,split=' ')[[1]]
pos<- grep('[A-Za-z\\d+]|\\d+',line)
res <- line[pos]
res <- res[c(-1,-length(res))]
s <- ''
for (i in 1:length(res)){
s<- paste(s,res[i])}
return(s)})
result<- data.frame(gene_name,cell_type)
return(result)
}
gene_set <- data.frame()
for(i in 20:36){
gene_set<- rbind(gene_set,geneset_substract(b[i]))
}
gene_set <- gene_set[c(-1,-2),]
list <- list()
for(i in 1:length(unique(gene_set$cell_type))){
list[[i]] <- gene_set$gene_name[gene_set$cell_type== (unique(gene_set$cell_type)[i])]
}
names(list)<- unique(gene_set$cell_type)
save(list,file='gene_set.Rdata')
2.提取矩阵和表型信息，需要手动从GEO下载，试了就知道为啥（如果试了不知道为啥，就留言）；进行ssGSEA分析，只是用到了处理后的矩阵和基因集两个内容；对score结果归一化后进行热图绘制；
rm(list=ls())
###矩阵信息提取
a <- read.table('GSE112996_merged_fpkm_table.txt.gz',
header = T,
row.names=1)
raw_data<- a[,-1]
###表型信息提取
pheno <- read.csv(file = 'GSE112996_series_matrix.txt')
pheno <- data.frame(num1 = strsplit(as.character(pheno[42,]),split='\t')[[1]][-1],
num2 = gsub('patient: No.','P',strsplit(as.character(pheno[51,]),split='\t')[[1]][-1]))
####数据过滤
data<- a[!apply(raw_data,1,sum)==0,]
####去除重复基因名的行，归一化
data$median=apply(data[,-1],1,median)
data=data[order(data$GeneName,data$median,decreasing = T),]
data=data[!duplicated(data$GeneName),]
rownames(data)=data$GeneName
uni_matrix <- data[,grep('\\d+',colnames(data))]
uni_matrix <- log2(uni_matrix+1)
colnames(uni_matrix)<- gsub('X','',gsub('\\.','\\-',colnames(uni_matrix)))
uni_matrix<- uni_matrix[,order(colnames(uni_matrix))]
library(genefilter)
library(GSVA)
library(Biobase)
load('gene_set.Rdata')
gsva_matrix<- gsva(as.matrix(uni_matrix), list,method='ssgsea',kcdf='Gaussian',abs.ranking=TRUE)
library(pheatmap)
gsva_matrix1<- t(scale(t(gsva_matrix)))
gsva_matrix1[gsva_matrix1< -2] <- -2
gsva_matrix1[gsva_matrix1>2] <- 2
anti_tumor <- c('Activated CD4 T cell', 'Activated CD8 T cell', 'Central memory CD4 T cell', 'Central memory CD8 T cell', 'Effector memeory CD4 T cell', 'Effector memeory CD8 T cell', 'Type 1 T helper cell', 'Type 17 T helper cell', 'Activated dendritic cell', 'CD56bright natural killer cell', 'Natural killer cell', 'Natural killer T cell')
pro_tumor <- c('Regulatory T cell', 'Type 2 T helper cell', 'CD56dim natural killer cell', 'Immature dendritic cell', 'Macrophage', 'MDSC', 'Neutrophil', 'Plasmacytoid dendritic cell')
anti<- gsub('^ ','',rownames(gsva_matrix1))%in%anti_tumor
pro<- gsub('^ ','',rownames(gsva_matrix1))%in%pro_tumor
non <- !(anti|pro)
gsva_matrix1<- rbind(gsva_matrix1[anti,],gsva_matrix1[pro,],gsva_matrix1[non,])
normalization<-function(x){
return((x-min(x))/(max(x)-min(x)))}
nor_gsva_matrix1 <- normalization(gsva_matrix1)
annotation_col = data.frame(patient=pheno$num2)
rownames(annotation_col)<-colnames(uni_matrix)
bk = unique(c(seq(0,1, length=100)))
pheatmap(nor_gsva_matrix1,show_colnames = F,cluster_rows = F,cluster_cols = F,annotation_col = annotation_col,breaks=bk,cellwidth=5,cellheight=5,fontsize=5,gaps_row = c(12,20),filename = 'ssgsea.png')
save(gsva_matrix,gsva_matrix1,pheno,file = 'score.Rdata')
3.计算score加和后，ggplot2进行绘图；
rm(list=ls())
anti_tumor <- c('Activated CD4 T cell', 'Activated CD8 T cell', 'Central memory CD4 T cell', 'Central memory CD8 T cell', 'Effector memeory CD4 T cell', 'Effector memeory CD8 T cell', 'Type 1 T helper cell', 'Type 17 T helper cell', 'Activated dendritic cell', 'CD56bright natural killer cell', 'Natural killer cell', 'Natural killer T cell')
pro_tumor <- c('Regulatory T cell', 'Type 2 T helper cell', 'CD56dim natural killer cell', 'Immature dendritic cell', 'Macrophage', 'MDSC', 'Neutrophil', 'Plasmacytoid dendritic cell')
load('score.Rdata')
anti<- as.data.frame(gsva_matrix1[gsub('^ ','',rownames(gsva_matrix1))%in%anti_tumor,])
pro<- as.data.frame(gsva_matrix1[gsub('^ ','',rownames(gsva_matrix1))%in%pro_tumor,])
anti_n<- apply(anti,2,sum)
pro_n<- apply(pro,2,sum)
patient <- pheno$num2[match(colnames(gsva_matrix1),pheno$num1)]
library(ggplot2)
data <- data.frame(anti=anti_n,pro=pro_n,patient=patient)
anti_pro<- cor.test(anti_n,pro_n,method='pearson')
gg<- ggplot(data,aes(x = anti, y = pro),color=patient) +
xlim(-20,15)+ylim(-15,10)+
labs(x="Anti-tumor immunity", y="Pro-tumor suppression") +
geom_point(aes(color=patient),size=3)+geom_smooth(method='lm')+
annotate("text", x = -5, y =7.5,label=paste0('R=',round(anti_pro$estimate,4),'\n','p<0.001'))
ggsave(gg,filename = 'cor.png')
参考内容：
1.GSVA: The Gene Set Variation Analysis package for microarray and RNA-seq data
■ ■ ■
全国巡讲约你
第一站-重庆 （已结束）
粤港澳大湾区专场 （已结束）
第二站-济南 （已结束）
千呼万唤进北京（已结束）
七月份我们不外出，只专注单细胞！
系统学习单细胞分析，报名生信技能树的线下培训，手慢无