22import csv
33import pandas as pd
44import sys
5+ from Bio .SeqUtils .ProtParam import ProteinAnalysis
6+ import re
57
68'''
79Write a script to create the files for the Case Final Reports
@@ -36,6 +38,29 @@ def parse_arguments():
3638
3739 return (parser .parse_args ())
3840
41+ # Fucnction to break the pepetides ID on the . to extract gene and AA information
42+ def extract_info (value ):
43+ parts = value .split ('.' )
44+ result = '.' .join ([parts [2 ], parts [3 ], parts [4 ]])
45+ return result
46+
47+ # Function to rearrange string so that G518D looks like 518G/D
48+ def rearrange_string (s ):
49+ match = re .match (r'([A-Za-z]+)([\d-]+)([A-Za-z]*)' , s )
50+ if match :
51+ letters_before = match .group (1 )
52+ numbers = match .group (2 )
53+ letters_after = match .group (3 )
54+
55+ return f"{ numbers } { letters_before } { letters_after }
56+ else :
57+ return s
58+
59+ # Function to calculate molecular weight
60+ def calculate_molecular_weight (peptide ):
61+ analyzed_seq = ProteinAnalysis (peptide )
62+ return analyzed_seq .molecular_weight ()
63+
3964def main ():
4065
4166 # 1. ITB reivew
@@ -54,20 +79,41 @@ def main():
5479 reviewed_canidates = reviewed_canidates [reviewed_canidates .Evaluation != "Pending" ]
5580 reviewed_canidates = reviewed_canidates [reviewed_canidates .Evaluation != "Reject" ]
5681
82+ reviewed_canidates = reviewed_canidates .rename (columns = {'Comments' :'pVAC Review Comments' })
83+ reviewed_canidates ["Variant Called by CLE Pipeline" ] = " "
84+ reviewed_canidates ["IGV Review Comments" ] = " "
85+
86+
87+ # create sorting ID that is gene and transcript to sort in the same order as peptide
88+ reviewed_canidates ['sorting id' ] = reviewed_canidates ['Gene' ] + '.' + reviewed_canidates ['Best Transcript' ]
89+
90+
5791 peptides = pd .read_csv (args .c , sep = "\t " )
5892 peptides = peptides .drop (['cterm_7mer_gravy_score' , 'cysteine_count' , 'n_terminal_asparagine' , 'asparagine_proline_bond_count' ,
5993 'difficult_n_terminal_residue' , 'c_terminal_cysteine' , 'c_terminal_proline' , 'max_7mer_gravy_score' ], axis = 1 )
60- peptides = peptides .rename (columns = {"id" :"ID" , "peptide_sequence" :"CANDIDATE NEOANTIGEN AMINO ACID SEQUENCE WITH FLANKING RESIDUES" })
6194 peptides ["RESTRICTING HLA ALLELE" ] = " "
62- peptides ["CANDIDATE NEOANTIGEN AMINO ACID SEQUENCE MW (CLIENT)" ] = " "
95+
96+ peptides ["CANDIDATE NEOANTIGEN AMINO ACID SEQUENCE MW (CLIENT)" ] = peptides ["peptide_sequence" ].apply (calculate_molecular_weight )
97+
98+ peptides = peptides .rename (columns = {"id" :"ID" , "peptide_sequence" :"CANDIDATE NEOANTIGEN AMINO ACID SEQUENCE WITH FLANKING RESIDUES" })
6399 peptides ["Comments" ] = " "
64100 peptides ["CANDIDATE NEOANTIGEN" ] = peptides ["ID" ].apply (lambda x : '.' .join (x .split ('.' )[:3 ]))
65101 peptides ["CANDIDATE NEOANTIGEN" ] = args .samp + "." + peptides ["CANDIDATE NEOANTIGEN" ]
66102
67-
68-
69103 peptides = peptides [["ID" , "CANDIDATE NEOANTIGEN" , "CANDIDATE NEOANTIGEN AMINO ACID SEQUENCE WITH FLANKING RESIDUES" ,
70104 "RESTRICTING HLA ALLELE" , "CANDIDATE NEOANTIGEN AMINO ACID SEQUENCE MW (CLIENT)" , "Comments" ]]
105+
106+
107+ # creating a ID to sort reviewed canidates by the order of the 51mer
108+ peptides ['sorting id' ] = peptides ['ID' ].apply (extract_info )
109+
110+ reviewed_canidates = reviewed_canidates .set_index ('sorting id' )
111+ reviewed_canidates = reviewed_canidates .reindex (index = peptides ['sorting id' ])
112+ reviewed_canidates = reviewed_canidates .reset_index ()
113+
114+ reviewed_canidates = reviewed_canidates .drop (columns = ['sorting id' ])
115+ peptides = peptides .drop (columns = ['sorting id' ])
116+
71117
72118 if args .WB :
73119 Peptide_file_name = args .WB + '/../manual_review/' + args .samp + "_Peptides_51-mer.xlsx"
0 commit comments