r语言去除字符串两端多余空格 r去掉字符串两边的空格trimws ards zhongda xiejianfeng临床数据清洗 类似于 onehot编码格式

trimws(x, which = c("both", "left", "right"), whitespace = "[ \t\r\n]")

自建函数切割sample

自建函数分离样本中某一列 按照某种要求某种标准 某种格式

??read_xls
pheno_data=openxlsx::read.xlsx("G:/raw_material for omics_chaojie/Sepsis/sepsis和ARDS队列-患者信息.xlsx",
                 sheet=7)
head(pheno_data)
#制作wgcna的表型信息
{
  
  library(dplyr)
  
  #自建函数从字符串提取想要的字符,如果存在，就变成1，如果不存在则变成0
  strsplit("abdomen_sepsis/ pneumonia_abdomen_sepsis/ abdomen_sepsis_Sshock",split  = "/")
  #r语言去除字符串两端多余空格
  trimws(c(" abdo " ,' n_sepsi ',"s/ pneumonia"), which = c("both", "left", "right"), whitespace = "[ \t\r\n]")
  
  any(c(1,3,4)==5)
  get_mydesired_string=function(x,strings){
    #strings="abdomen_sepsis/  abdomen/ sepsis/ ab"
    #x="ab"
    
    elements=strsplit(strings,split  = "/")[[1]]
    #r语言去除字符串两端多余空格 两边空格
    elements=trimws(elements, which = c("both", "left", "right"), whitespace = "[ \t\r\n]")
    if(any(which(elements==x))==TRUE)
    { myelements=elements[which(elements==x)]
    myelements=1} else { myelements=0}
    
    return(myelements)
  }
  get_mydesired_string('sepsis',"abdom/en_/sepsis/ asepsis/ sepsis/ abdhock")
  
  
  
  head(pheno_data)
  pheno_data$'abdomen_sepsis'
  str(pheno_data)
  
  lapply(pheno_data$Group, get_mydesired_string,x="abdomen_sepsis")
  sapply(pheno_data$Group, get_mydesired_string,x="abdomen_sepsis")
  
  pheno_data$abdomen_sepsis=sapply(pheno_data$Group, get_mydesired_string,x="abdomen_sepsis")
  pheno_data$pneumonia_abdomen_sepsis=sapply(pheno_data$Group, get_mydesired_string,x="pneumonia_abdomen_sepsis")
  pheno_data$abdomen_sepsis_Sshock=sapply(pheno_data$Group, get_mydesired_string,x="abdomen_sepsis_Sshock")
  pheno_data$abdomen_Sshock=sapply(pheno_data$Group, get_mydesired_string,x="abdomen_Sshock")
  
  pheno_data$pneumonia_abdomen_Sshock=sapply(pheno_data$Group, get_mydesired_string,x="pneumonia_abdomen_Sshock")
  pheno_data$pneumonia_sepsis=sapply(pheno_data$Group, get_mydesired_string,x="pneumonia_sepsis")
  pheno_data$pneumonia_sepsis_Sshock=sapply(pheno_data$Group, get_mydesired_string,x="pneumonia_sepsis_Sshock")
  
  pheno_data$ARDS_moderate=sapply(pheno_data$Group, get_mydesired_string,x="ARDS_moderate")
  pheno_data$ARDS_severe=sapply(pheno_data$Group, get_mydesired_string,x="ARDS_severe")
  
  pheno_data$pneumonia_Sshock=sapply(pheno_data$Group, get_mydesired_string,x="pneumonia_Sshock")
  
  
}

#pheno_data$pneumonia_abdomen_Sshock=lapply(pheno_data$Group, get_mydesired_string,x="pneumonia_abdomen_Sshock")
head(pheno_data)
str(pheno_data)


??read.xlsx
patient_sample_dia=openxlsx::read.xlsx("G:/raw_material for omics_chaojie/Sepsis/sepsis和ARDS队列-患者信息.xlsx",
                                       sheet=2,rows=1:27,)
#制作patient sample信息
if(1==1){
  head(patient_sample_dia)
  dim(patient_sample_dia)
  
  patient_sample_dia=patient_sample_dia[,3:27]
  colnames(patient_sample_dia)[1:2]=c('patient','sample')
  head(patient_sample_dia)
  
  #以逗号为分隔取第几个元素
  #自建函数
  strsplit("15196、15197",split="、")
  
  get_mydesired_element=function(location, strings){
    #location=2
    # strings="15196、15197"
    elements=strsplit(strings,split="、")[[1]][location]
    #去除空格
    elements=elements=trimws(elements, which = c("both", "left", "right"), whitespace = "[ \t\r\n]")
    return(elements)
  }
  
  lapply(patient_sample_dia$sample,
         get_mydesired_element,location=1)
  
  patient_sample_dia$sample_1=unlist(lapply(patient_sample_dia$sample,get_mydesired_element,location=1))
  patient_sample_dia$sample_2=unlist(lapply(patient_sample_dia$sample,get_mydesired_element,location=2))
  patient_sample_dia
  
  patient_sample_dia=patient_sample_dia %>%select(c(patient,sample_1,sample_2),everything())
  
  setdiff(pheno_data$Sample.Name,patient_sample_dia$sample_1) #[1]801 20056 11216
  setdiff(patient_sample_dia$sample_1,pheno_data$Sample.Name) #"2201"
  setdiff(patient_sample_dia$sample_2,pheno_data$Sample.Name)
  str(patient_sample_dia)
  
}


#24个病人为何有26个样本 找到样本与病人的对应关系
head(pheno_data)
View(pheno_data)
setdiff()

#检查mrna和ciclerna测序的样本名 各26个
if(1==1){
  library(readxl)
  mrna_exp=readxl::read_xls("G:/raw_material for omics_chaojie/Sepsis/H1712290A Arraystar_Human_LncRNA_8x60k v4.0 1-color 20180206-zq lnca/Report/GeneralData/mRNA Expression Profiling/mRNA Expression Profiling Data.xls",
                            range =  cell_rows(c(9:11)))
  head(mrna_exp)
  grep(mrna_exp[1,],pattern = '1121',value = T)#是否有2201样本
  
  ciclerna_exp=readxl::read_xls("G:/raw_material for omics_chaojie/Sepsis/H1712290B AS-CR-005 Human Circular RNA Microarray v2 20180201 zq cias/File 2. Data/CircRNA Expression Profiling Data.xls",
                                range =  cell_rows(c(21:23)))
  head(mrna_exp)
  grep(mrna_exp[1,],pattern = '200',value = T)#是否有2201样本
  
  length(patient_sample_dia$sample_1)
}

getwd()
save(pheno_data,patient_sample_dia,
     file ="G:/papers_for_ARDS/r_scripts_for_ARDS_From_zhongda/lncRNA_mRNA_cicleRNA/meta_infor_raw.RData" )

load("G:/papers_for_ARDS/r_scripts_for_ARDS_From_zhongda/lncRNA_mRNA_cicleRNA/meta_infor_raw.RData")

head(patient_sample_dia)