예제 #1
0
    proteins_df["Heavy/Medium"] = np.divide(proteins_df["Heavy/Light"],
                                            proteins_df["Medium/Light"])

    peptides_df = pd.ExcelFile(peptides).parse("Sheet1")
    peptides_df = peptides_df[columns]
    peptides_df["Heavy/Medium"] = np.divide(peptides_df["Heavy/Light"],
                                            peptides_df["Medium/Light"])
    peptides_df["isPhospho"] = pd.notnull(peptides_df["phosphoRS Isoform Probability"])

    phospho_peptides = peptides_df[peptides_df["isPhospho"]==True].copy()
    regular_peptides = peptides_df[peptides_df["isPhospho"]==False].copy()

    # annotate sequence_window
    cutils.add_seq_window(phospho_peptides, FASTA_dic)
    #transform the ratios to log10
    cutils.computelog(phospho_peptides)
    cutils.computelog(regular_peptides)
    cutils.computelog(proteins_df)

    #add phosphosite plus site information
    cutils.add_known_pssite(phospho_peptides, phosphositeDB, FASTA_dic)

    #delete non-existing columns
    del_columns = ['Medium/Light', 'Heavy/Medium', u'log10ML', u'log10HM']
    for del_i, df_i in zip(del_columns, [peptides_df, phospho_peptides, regular_peptides]):
        try:
            del df_i[del_i]
        except:
            pass

    #==========================================================================
예제 #2
0

    peptides_df["isPhospho"] = pd.notnull(peptides_df["phosphoRS Isoform Probability"])

    phospho_peptides = peptides_df[peptides_df["isPhospho"]==True].copy()
    regular_peptides = peptides_df[peptides_df["isPhospho"]==False].copy()

    if invert:
        print "inverting ratios...."
        phospho_peptides["Heavy/Light"] = 1 / phospho_peptides["Heavy/Light"]
        regular_peptides["Heavy/Light"] = 1 / regular_peptides["Heavy/Light"]

    # annotate sequence_window
    cutils.add_seq_window(phospho_peptides, FASTA_dic)
    #transform the ratios to log10
    cutils.computelog(phospho_peptides, ratio_columns=["Heavy/Light"])
    cutils.computelog(regular_peptides, ratio_columns=["Heavy/Light"])
    cutils.computelog(proteins_df, ratio_columns=["Heavy/Light"])

    #add phosphosite plus site information
    cutils.add_known_pssite(phospho_peptides, phosphositeDB, FASTA_dic)

    #delete non-existing columns
    del_columns = ['Medium/Light', 'Heavy/Medium', u'log10ML', u'log10HM']
    for del_i, df_i in zip(del_columns, [peptides_df, phospho_peptides, regular_peptides]):
        try:
            del df_i[del_i]
        except:
            pass

    #==========================================================================