comparison pre_process_protein_name_set.R @ 21:9e0a894d2676 draft

Uploaded

20:e21be0412789

library(stringr)
library(mygene)
library(VennDiagram)
#####
#data
main <- function(peptides_file) {
	peptides_file = read.delim(peptides_file,header=TRUE,stringsAsFactors=FALSE,fill=TRUE)
  peptides_txt = peptides_file
	intensity_columns = names(peptides_txt[,str_detect(names(peptides_txt),"Intensity\\.*")]) #Pulls out all lines with Intensity in them.
	intensity_columns = intensity_columns[2:length(intensity_columns)] #Removes the first column that does not have a bait. 
	peptides_txt_mapped = as.data.frame(map_peptides_proteins(peptides_txt)) #This function as below sets every line to a 1 to 1 intensity to each possible protein.
	peptides_txt_mapped$Uniprot = str_extract(peptides_txt_mapped$mapped_protein, "[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}") #Pulls out just Uniprot id from the script.
	peptides_txt_mapped = subset(peptides_txt_mapped,!is.na(Uniprot)) #removes reverse sequences and any that didn't match a uniprot accession
	columns_comb = c("Uniprot", intensity_columns) 
	peptides_mapped_intensity = subset(peptides_txt_mapped, select = columns_comb) #Subsets out only the needed cloumns for Tukeys (Uniprot IDS and baited intensities)
	swissprot_fasta = scan("/home/philip/galaxy/tools/Moffitt_Tools/uniprot_names.txt",what="character")
	peptides_txt_mapped_log2 = peptides_mapped_intensity
  # Takes the log2 of the intensities. 
	for (i in intensity_columns) { 
		peptides_txt_mapped_log2[,i] = log2(subset(peptides_txt_mapped_log2, select = i))
	}

  }
  return(Tukeys_df)
}

args <- commandArgs(trailingOnly = TRUE)
main(args[1])

21:9e0a894d2676

library(stringr)
library(mygene)
library(VennDiagram)
#####
#data
main <- function(peptides_file, db_path) {
	peptides_file = read.delim(peptides_file,header=TRUE,stringsAsFactors=FALSE,fill=TRUE)
  peptides_txt = peptides_file
	intensity_columns = names(peptides_txt[,str_detect(names(peptides_txt),"Intensity\\.*")]) #Pulls out all lines with Intensity in them.
	intensity_columns = intensity_columns[2:length(intensity_columns)] #Removes the first column that does not have a bait. 
	peptides_txt_mapped = as.data.frame(map_peptides_proteins(peptides_txt)) #This function as below sets every line to a 1 to 1 intensity to each possible protein.
	peptides_txt_mapped$Uniprot = str_extract(peptides_txt_mapped$mapped_protein, "[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}") #Pulls out just Uniprot id from the script.
	peptides_txt_mapped = subset(peptides_txt_mapped,!is.na(Uniprot)) #removes reverse sequences and any that didn't match a uniprot accession
	columns_comb = c("Uniprot", intensity_columns) 
	peptides_mapped_intensity = subset(peptides_txt_mapped, select = columns_comb) #Subsets out only the needed cloumns for Tukeys (Uniprot IDS and baited intensities)
	swissprot_fasta = scan(db_path, what="character")
	peptides_txt_mapped_log2 = peptides_mapped_intensity
  # Takes the log2 of the intensities. 
	for (i in intensity_columns) { 
		peptides_txt_mapped_log2[,i] = log2(subset(peptides_txt_mapped_log2, select = i))
	}

  }
  return(Tukeys_df)
}

args <- commandArgs(trailingOnly = TRUE)
main(args[1], args[2])