comparison pre_process_protein_name_set.R @ 28:dbd1af88f060 draft

Uploaded

27:2d78642361c3

  # Get the minimum from each column while ignoring the -Inf; get the min of these mins for the 
  # global min; breaks when there's only one intensity column.
	global_min = min(apply(peptides_txt_mapped_log2[,2:ncol(peptides_txt_mapped_log2)],2,function(x) {
	  min(x[x != -Inf])
	}))
	peptides_txt_mapped_log2[peptides_txt_mapped_log2 == -Inf] <- 0
  #uniprot accessions WITHOUT isoforms; it looks like only contaminants contain isoforms anyways.
	mapped_protein_uniprotonly = str_extract(peptides_txt_mapped_log2$Uniprot,"[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}") 
	mapped_protein_uniprot_accession = str_extract(peptides_txt_mapped_log2$Uniprot,"[OPQ][0-9][A-Z0-9]{3}[0-9](-[0-9]+)?|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}(-[0-9]+)?|[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}")
	peptides_txt_mapped_log2$mapped_protein = mapped_protein_uniprotonly
  # Runs the Tukey function returning completed table.
  peptides_txt_mapped_log2 = subset(peptides_txt_mapped_log2,mapped_protein %in% swissprot_fasta)
	protein_intensities_tukeys = get_protein_values(peptides_txt_mapped_log2,intensity_columns)
  protein_intensities_tukeys[protein_intensities_tukeys == 1] <- 0
  write.table(protein_intensities_tukeys, "./tukeys_output.txt", row.names = FALSE, col.names = TRUE, quote = FALSE, sep = "\t")	

}

    peptides_in = subset(peptides_in,peptides_in$Proteins != "")
    results_list = list()
    k = 1
    for (i in 1:nrow(peptides_in)) {
        protein_names = peptides_in[i,"Proteins"]
        protein_names_split = unlist(strsplit(protein_names,";"))
        for (j in 1:length(protein_names_split)) {
            peptides_mapped_proteins = data.frame(peptides_in[i,],mapped_protein=protein_names_split[j],stringsAsFactors=FALSE)
            results_list[[k]] = peptides_mapped_proteins
            k = k+1
            

    mapped_peptides_unique_subset = subset(mapped_peptides_in, mapped_protein == unique_mapped_proteins_list[i])
    # Calculate Tukey's Biweight from library(affy); returns a single numeric.
    # Results_list[[i]] = data.frame(Protein=unique_mapped_proteins_list[i],Peptides_per_protein=nrow(mapped_peptides_unique_subset)).
    for (j in intensity_columns_list) {
      # Populates with new Tukeys values.
      Tukeys_df[i,j] = 2^(tukey.biweight(mapped_peptides_unique_subset[,j]))
    }
  }
  return(Tukeys_df)
}

28:dbd1af88f060

  # Get the minimum from each column while ignoring the -Inf; get the min of these mins for the 
  # global min; breaks when there's only one intensity column.
	global_min = min(apply(peptides_txt_mapped_log2[,2:ncol(peptides_txt_mapped_log2)],2,function(x) {
	  min(x[x != -Inf])
	}))
	peptides_txt_mapped_log2[peptides_txt_mapped_log2 == -Inf] <- NA
  #uniprot accessions WITHOUT isoforms; it looks like only contaminants contain isoforms anyways.
	mapped_protein_uniprotonly = str_extract(peptides_txt_mapped_log2$Uniprot,"[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}") 
	mapped_protein_uniprot_accession = str_extract(peptides_txt_mapped_log2$Uniprot,"[OPQ][0-9][A-Z0-9]{3}[0-9](-[0-9]+)?|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}(-[0-9]+)?|[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}")
	peptides_txt_mapped_log2$mapped_protein = mapped_protein_uniprotonly
  # Runs the Tukey function returning completed table.
  peptides_txt_mapped_log2 = subset(peptides_txt_mapped_log2,mapped_protein %in% swissprot_fasta)
  if (nrow(peptides_txt_mapped_log2) == 0) {
    print("Uniprot Database does not have any of the proteins in the peptides file")
    quit()
  }
	protein_intensities_tukeys = get_protein_values(peptides_txt_mapped_log2,intensity_columns)
  protein_intensities_tukeys[protein_intensities_tukeys == 1] <- 0
  write.table(protein_intensities_tukeys, "./tukeys_output.txt", row.names = FALSE, col.names = TRUE, quote = FALSE, sep = "\t")	

}

    peptides_in = subset(peptides_in,peptides_in$Proteins != "")
    results_list = list()
    k = 1
    for (i in 1:nrow(peptides_in)) {
        protein_names = peptides_in[i,"Proteins"]
        protein_names_split = unlist(str_split(protein_names,";"))
        for (j in 1:length(protein_names_split)) {
            peptides_mapped_proteins = data.frame(peptides_in[i,],mapped_protein=protein_names_split[j],stringsAsFactors=FALSE)
            results_list[[k]] = peptides_mapped_proteins
            k = k+1
            

    mapped_peptides_unique_subset = subset(mapped_peptides_in, mapped_protein == unique_mapped_proteins_list[i])
    # Calculate Tukey's Biweight from library(affy); returns a single numeric.
    # Results_list[[i]] = data.frame(Protein=unique_mapped_proteins_list[i],Peptides_per_protein=nrow(mapped_peptides_unique_subset)).
    for (j in intensity_columns_list) {
      # Populates with new Tukeys values.
      Tukeys_df[i,j] = 2^(tukey.biweight(na.omit(mapped_peptides_unique_subset[,j])))
    }
  }
  return(Tukeys_df)
}