Ejemplo n.º 1
0
        #Open the files you just created with the gapless sequences and read in the sequences. 
        fp_natural = open(natural_pdb_file_title) 
        natural_data_arr = fp_natural.readlines()
        fp_natural.close()

        fp_designed = open(duncan_designed_sequence_path + designed_pdb_file_title) 
        designed_data_arr = fp_designed.readlines()
        fp_designed.close()

        #filepointer for the partial result
        fpW_natural = open("results_array_natural_" + pdb_id + "_" + chain_id + ".csv","w")
        fpW_designed = open("results_array_" + pdb_id + "_" + chain_id + "_" + method + ".csv","w")

        #write the RSA values:
        fpW_natural.write(af.dump_csv_line(RSA))
        fpW_designed.write(af.dump_csv_line(RSA))

        if(len(RSA) != len(natural_data_arr[0].strip())):
            print "Error !!!!!!!!!"
            #print data_arr[0].strip()
            bad_list.append(natural_pdb_file_title)

        if(len(RSA) != len(natural_data_arr[0].strip())):
            print "Error !!!!!!!!!"
            print "Length of rsa values {:0}".format(len(RSA))
            print "Length of sequence {:0}".format(len(natural_data_arr[0].strip()))

        #Re-format sequences
        for line in natural_data_arr:
            fpW_natural.write(af.dump_csv_line(line.strip()))      
    #Get all the RSA values using DSSP
    seq_data = af.get_noah_RSA_values(pdb_id, chain_id)	
    RSA = seq_data[1] #Get the RSA values
    RSA_dict = seq_data[2] #Get the dict mapping positions to RSA
    new_RSA = af.get_cut_RSA_values(pdb_id, RSA, RSA_dict)

    index = 0
    #Arrays full of the designed and natural sequences
    natural_data_arr = cut_natural_sequences
    designed_data_arr = af.get_cut_designed_sequences(designed_file)
 
    fpW_natural = open("results_array_natural_" + pdb_id + "_" + chain_id + ".csv","w")
    fpW_designed = open("results_array_" + pdb_id + "_" + chain_id + "_" + "soft" + ".csv","w")

    #write the RSA values:
    fpW_natural.write(af.dump_csv_line(new_RSA))
    fpW_designed.write(af.dump_csv_line(new_RSA))

    if(len(new_RSA) != len(natural_data_arr[0].strip())):
        print "Error !!!!!!!!!"
        #print data_arr[0].strip()
        bad_list.append(natural_pdb_file_title)

    if(len(new_RSA) != len(natural_data_arr[0].strip())):
        print "Error !!!!!!!!!"
        print "Length of rsa values {:0}".format(len(RSA))
        print "Length of sequence {:0}".format(len(natural_data_arr[0].strip()))
        print "Length of designed sequence {:0}".format(len(designed_data_arr[0].strip()))

    #Re-format sequences
    for line in natural_data_arr:
Ejemplo n.º 3
0
    RSAValues = []
    RSA = seq_data[1]
    print len(RSA)
    index = 0

    #Open the files you just created with the gapless sequences
    fp_natural = open(natural_pdb_file_title)
    natural_data_arr = fp_natural.readlines()
    fp_natural.close()

    #filepointer for the partial result
    fpW_natural = open(
        "results_array_natural_" + pdb_id + "_" + chain_id + ".csv", "w")

    #write the RSA values:
    fpW_natural.write(af.dump_csv_line(RSA))

    [natural_sample1, natural_sample2] = af.split_natural_sequences(
        natural_data_arr)  #Splits the sequences into two samples
    #filepointer for the partial result
    fpW_natural_sample1 = open(
        "results_array_natural_sample1_" + pdb_id + "_" + chain_id + ".csv",
        "w")
    fpW_natural_sample2 = open(
        "results_array_natural_sample2_" + pdb_id + "_" + chain_id + ".csv",
        "w")

    #write the RSA values:
    fpW_natural_sample1.write(af.dump_csv_line(RSA))
    fpW_natural_sample2.write(af.dump_csv_line(RSA))
    seq_data = af.get_values(pdb_id, chain_id)
    RSAValues = []	
    RSA = seq_data[1]
    print "RSA Length from dssp script: " + str(len(RSA))
    index = 0

    #Open the files you just created with the gapless sequences
    fp_natural = open(natural_pdb_file_title) 
    natural_data_arr = fp_natural.readlines()
    fp_natural.close()

    #filepointer for the partial result
    fpW_natural = open("results_array_natural_" + pdb_id + "_" + chain_id + ".csv","w")

    #write the RSA values:
    fpW_natural.write(af.dump_csv_line(RSA))
    [natural_sample1, natural_sample2] = af.split_natural_sequences(natural_data_arr) #Samples  

    #filepointer for the partial result
    fpW_natural_sample1 = open("results_array_natural_sample1_" + pdb_id + "_" + chain_id + ".csv","w")
    fpW_natural_sample2 = open("results_array_natural_sample2_" + pdb_id + "_" + chain_id + ".csv","w")

    #write the RSA values:
    fpW_natural_sample1.write(af.dump_csv_line(RSA))
    fpW_natural_sample2.write(af.dump_csv_line(RSA))

    if(len(RSA) != len(natural_data_arr[0].strip())):
        print "Error !!!!!!!!!"
        #print data_arr[0].strip()
        bad_list.append(natural_pdb_file_title)