|
3
|
1 """
|
|
|
2 Actual function class of open reading frame searching tool
|
|
|
3 Served as a bridge between util class and entry.
|
|
|
4
|
|
|
5 Author Nedias Sept, 2016
|
|
|
6 """
|
|
|
7 from Bio import SeqIO
|
|
|
8 from Bio.SeqRecord import SeqRecord
|
|
|
9 import ORFFinder
|
|
|
10 import os
|
|
|
11 import GTranslator
|
|
|
12
|
|
|
13
|
|
|
14 # Get command and parameter from entry and call corresponding function
|
|
|
15 def exec_tool(options):
|
|
|
16 # If format is fasta
|
|
|
17 if options.format and options.format == "fasta":
|
|
|
18 exec_fasta(options.input, options.outputa, options.outputd, options.length)
|
|
|
19 # TODO: If format is fastq
|
|
|
20 elif options.format and options.format == "fastq":
|
|
|
21 print("Process Fastq File(TODO:Not Implemented)")
|
|
|
22 # TODO: If format is sam
|
|
|
23 elif options.format and options.format == "sam":
|
|
|
24 print("Process Sam File(TODO:Not Implemented)")
|
|
|
25 # TODO: If format is bam
|
|
|
26 elif options.format and options.format == "bam":
|
|
|
27 print("Process Bam File(TODO:Not Implemented)")
|
|
|
28
|
|
|
29
|
|
|
30 # Read the input fasta file find all open reading frames(ORFs)
|
|
|
31 # input: 1.in_file: input file in fasta format
|
|
|
32 # 2.outputa: all ORFs found are saved in this file
|
|
|
33 # 3.outputd: all ORFs longer than designated length are saved in this file
|
|
|
34 # 4.length: filter all ORFs if less than percentage of the length of the longest ORF found
|
|
|
35 # return: execute status code
|
|
|
36 # TODO: Seq and Rev_seq need to be process in the same time
|
|
|
37 def exec_fasta(in_file, output_all, output_dest, length):
|
|
|
38
|
|
|
39 # Open input file(read only)
|
|
|
40 input_file = open(in_file, "rU")
|
|
|
41 # Open all match file(create or override)
|
|
|
42 all_mth_file = open(output_all, "w+")
|
|
|
43 # Open all match file(create or override)
|
|
|
44 desi_file = open(output_dest, "w+")
|
|
|
45
|
|
|
46 # Scan through all Sequenced data in input file
|
|
|
47 for record in SeqIO.parse(input_file, "fasta"):
|
|
|
48
|
|
|
49 # for each sequence, use function in ORFFinder to abstract all ORFs
|
|
|
50 seq = record.seq
|
|
|
51 # Get all start and end positions in +strand
|
|
|
52 result = ORFFinder.get_all_orf(str(seq), False)
|
|
|
53 # Get all start-end pairs in +strand
|
|
|
54 pairs = ORFFinder.find_all_orf(result)
|
|
|
55
|
|
|
56 # Reverse the sequenced data
|
|
|
57 rev_seq = seq[::-1]
|
|
|
58 # Get all start and end positions in -strand
|
|
|
59 rev_result = ORFFinder.get_all_orf(str(rev_seq), True)
|
|
|
60 # Get all start-end pairs in -strand
|
|
|
61 rev_pairs = ORFFinder.find_all_orf(rev_result)
|
|
|
62
|
|
|
63 # Get longest start-end pair of both strands
|
|
|
64 longest_match = ORFFinder.get_longest_pair(pairs, rev_pairs)
|
|
|
65
|
|
|
66 # Calculate the designated length
|
|
|
67 match_length = int(longest_match * int(length) / 100)
|
|
|
68
|
|
|
69 # All ORFs
|
|
|
70 all_frags = []
|
|
|
71 # All designated ORFs
|
|
|
72 desi_frags = []
|
|
|
73
|
|
|
74 # TODO: considering make the result in dictionary and make this four for-loop into 2 or 1 loop
|
|
|
75 # For each pair in the +strand
|
|
|
76 for pair in pairs[:-1]:
|
|
|
77 # Intercept ORF from the original sequence using the start-end pair, and than translate the sequence
|
|
|
78 # into polypeptide sequence
|
|
|
79 frag = SeqRecord(GTranslator.nucleotide_to_polypeptide(record.seq[pair[0]:pair[1]], False), record.id + "|"
|
|
|
80 + str(pair[0]) + "-" + str(pair[1]),
|
|
|
81 '', '')
|
|
|
82 all_frags.append(frag)
|
|
|
83
|
|
|
84 # For each pair in the -strand
|
|
|
85 for pair2 in rev_pairs[:-1]:
|
|
|
86 # Intercept ORF from the original sequence using the start-end pair, and than translate the sequence
|
|
|
87 # into polypeptide sequence
|
|
|
88 frag = SeqRecord(GTranslator.nucleotide_to_polypeptide(rev_seq[pair2[0]:pair2[1]], True),
|
|
|
89 record.id + "|" + str(len(rev_seq) - pair2[0]) + "-" + str(len(rev_seq) - pair2[1]),
|
|
|
90 '', '')
|
|
|
91 all_frags.append(frag)
|
|
|
92
|
|
|
93 desi_pairs = ORFFinder.get_desi_pairs(pairs, match_length)
|
|
|
94 rev_desi_pairs = ORFFinder.get_desi_pairs(rev_pairs, match_length)
|
|
|
95
|
|
|
96 # For each designated pair in the +strand
|
|
|
97 for pair in desi_pairs:
|
|
|
98 # Intercept ORF from the original sequence using the start-end pair, and than translate the sequence
|
|
|
99 # into polypeptide sequence
|
|
|
100 frag = SeqRecord(GTranslator.nucleotide_to_polypeptide(seq[pair[0]:pair[1]], False),
|
|
|
101 record.id + "|" + str(pair[0]) + "-" + str(pair[1]), '', '')
|
|
|
102 desi_frags.append(frag)
|
|
|
103
|
|
|
104 # For each designated pair in the strand
|
|
|
105 for pair in rev_desi_pairs:
|
|
|
106 # Intercept ORF from the original sequence using the start-end pair, and than translate the sequence
|
|
|
107 # into polypeptide sequence
|
|
|
108 frag = SeqRecord(GTranslator.nucleotide_to_polypeptide(rev_seq[pair[0]:pair[1]], True),
|
|
|
109 record.id + "|" + str(len(rev_seq) - pair[0]) + "-" + str(len(rev_seq) - pair[1]),
|
|
|
110 '', '')
|
|
|
111 desi_frags.append(frag)
|
|
|
112
|
|
|
113 # Write the result to output file
|
|
|
114 SeqIO.write(all_frags, all_mth_file, "fasta")
|
|
|
115 SeqIO.write(desi_frags, desi_file, "fasta")
|
|
|
116
|
|
|
117 # Close file entry
|
|
|
118 input_file.close()
|
|
|
119 all_mth_file.close()
|
|
|
120 desi_file.close()
|
|
|
121
|
|
|
122 return 0
|
