ShixiangWang

"title"	"gpl"	"bioc_package"	"manufacturer"	"organism"	"data_row_count"
"Illumina Sentrix Array Matrix (SAM) - GoldenGate Methylation Cancer Panel I"	"GPL15380"	"GGHumanMethCancerPanelv1"	"Illumina"	"Homo sapiens"	1536
"Illumina HumanMethylation27 BeadChip (HumanMethylation27_270596_v.1.2)"	"GPL8490"	"IlluminaHumanMethylation27k"	"Illumina, Inc."	"Homo sapiens"	27578
"Illumina HumanMethylation450 BeadChip (HumanMethylation450_15017482)"	"GPL13534"	"IlluminaHumanMethylation450k"	"Illumina, Inc."	"Homo sapiens"	485577
"GE Healthcare/Amersham Biosciences CodeLink™   ADME Rat 16-Assay Bioarray"	"GPL2898"	"adme16cod"	"GE Healthcare"	"Rattus norvegicus"	1280
"[AG] Affymetrix Arabidopsis Genome Array"	"GPL71"	"ag"	"Affymetrix"	"Arabidopsis thaliana"	8297
"[ATH1-121501] Affymetrix Arabidopsis ATH1 Genome Array"	"GPL198"	"ath1121501"	"Affymetrix"	"Arabidopsis thaliana"	22810
"[Bovine] Affymetrix Bovine Genome Array"	"GPL2112"	"bovine"	"Affymetrix"	"Bos taurus"	24128
"[Canine] Affymetrix Canine Genome 1.0 Array"	"GPL39

ShixiangWang

#' @function Summary functions for error bar plot.
#' @references http://www.jianshu.com/p/003138ac593b

## Gives count, mean, standard deviation, standard error of the mean, and confidence interval (default 95%).
##   data: a data frame.
##   measurevar: the name of a column that contains the variable to be summariezed
##   groupvars: a vector containing names of columns that contain grouping variables
##   na.rm: a boolean that indicates whether to ignore NA's
##   conf.interval: the percent range of the confidence interval (default is 95%)
summarySE <- function(data=NULL, measurevar, groupvars=NULL, na.rm=FALSE,

ShixiangWang

getID = function(exp_value, method){
  # compute threshold according to method parameter
  if(method=="quartile"){
    symbol_stat <- summary(exp_value)
    ths1 <- as.numeric(symbol_stat[2])
    ths2 <- as.numeric(symbol_stat[5])
    down_id <- names(exp_value[exp_value<=ths1])
    up_id <- names(exp_value[exp_value>=ths2])
  }else if(method=="mean"){
    ths <- mean(exp_value)

ShixiangWang

pltDiff = function(data=NULL, sample=NULL, target=NULL,
                   group1, group2, group1.name="group1",
                   group2.name="group2", title="data", x_lab="", y_lab="",
                   notch=TRUE){
  require(ggpubr, quietly = TRUE)
  
  if(!is.data.frame(data)) stop("Wrong input! Please check your dataset. The input data type must be data.frame.")
  a = data.frame(value=data[, target], group=ifelse(!(data[,sample]%in%c(group1,group2)),
                                                 NA, ifelse(data[,sample]%in%group1, group1.name, group2.name)))
  a = a[a$group%in%c(group1.name, group2.name), ]

ShixiangWang

T_test = function(data, group1, group2, adj.method="fdr"){
  # the first column of data is identifier
  # the others columns cotain gene expression, samples' name should be colnames
  # group1, group2 are used to compare two groups of data
  # adj.method defines which method used to adjust p values
  
  colnames(data)[1] = "geneSymbol"
  # only get samples we wanna to compare, be sure 
  # all names in group1 and group2 can match colnames of data 

ShixiangWang

#' @function survival analysis according to gene expression for primary tumor
#' @param geneSymbol identify gene symbol 
#' @param exp TCGA format gene expression dataset
#' @param  cli Clinical information dataset
#' @param method method use to dive samples into groups. Options are "quantile", "median", "mean". the "quartile" use first and third quartile as threshold
#' @param trans transform the clinical IDs from '-' separate to '.' separate
#' @return include the plot and p value
#' @author Shixiang Wang

# input test data