upstream-dependencies/galaxy-sequence-utils/galaxy_utils/sequence/scripts/fastq_groomer.py
1# Dan Blankenberg
2
3import argparse
4
5from galaxy_utils.sequence.fastq import (
6 fastqAggregator,
7 fastqReader,
8 fastqVerboseErrorReader,
9 fastqWriter,
10)
11
12
13class Groomer:
14
15 def __init__(self, file_handle=None):
16 self.file_handle = file_handle
17 args = self._get_args()
18 self.input_filename = args.input_filename
19 self.input_type = args.input_type
20 self.output_filename = args.output_filename
21 self.output_type = args.output_type
22 self.force_quality_encoding = args.force_quality_encoding
23 self.summarize_input = args.summarize_input == 'summarize_input'
24 self.fix_id = args.fix_id
25
26 if self.force_quality_encoding == 'None':
27 self.force_quality_encoding = None
28
29 def run(self):
30 aggregator = fastqAggregator()
31 reader_class = fastqReader
32 if self.summarize_input:
33 reader_class = fastqVerboseErrorReader
34 read_count = None
35
36 writer = fastqWriter(
37 path=self.output_filename,
38 format=self.output_type,
39 force_quality_encoding=self.force_quality_encoding)
40 reader = reader_class(
41 fh=self.file_handle,
42 path=self.input_filename,
43 format=self.input_type,
44 apply_galaxy_conventions=True,
45 fix_id=self.fix_id)
46 with writer, reader:
47 for read_count, fastq_read in enumerate(reader):
48 if self.summarize_input:
49 aggregator.consume_read(fastq_read)
50 writer.write(fastq_read)
51
52 self._print_output(read_count, aggregator)
53
54 def _print_output(self, read_count, aggregator):
55 if read_count is not None:
56 print(f"Groomed {read_count + 1:d} {self.input_type} reads into {self.output_type} reads.")
57 if self.input_type != self.output_type and 'solexa' in [self.input_type, self.output_type]:
58 print("Converted between Solexa and PHRED scores.")
59 if self.summarize_input:
60 print(
61 "Based upon quality and sequence, the input data is valid for:",
62 ", ".join(aggregator.get_valid_formats()) or "None"
63 )
64 ascii_range = aggregator.get_ascii_range()
65 decimal_range = aggregator.get_decimal_range()
66 # print using repr, since \x00 (null) causes info truncation in galaxy when printed
67 print(
68 f"Input ASCII range: {repr(ascii_range[0])}({ord(ascii_range[0]):d}) - {repr(ascii_range[1])}({ord(ascii_range[1]):d})"
69 )
70 print(f"Input decimal range: {decimal_range[0]:d} - {decimal_range[1]:d}")
71 else:
72 print("No valid FASTQ reads were provided.")
73
74 def _get_args(self):
75 types = ['solexa', 'illumina', 'sanger', 'cssanger']
76 type_choices = [t + ext for t in types for ext in ['', '.gz', '.bz2']]
77 fqe_choices = ['None', 'ascii', 'decimal']
78 si_choices = ['summarize_input', 'dont_summarize_input'] # Should be yes/no (leave as is for now)
79
80 p = argparse.ArgumentParser()
81 p.add_argument('input_filename', help='file to groom')
82 p.add_argument('input_type', choices=type_choices, help='input FASTQ quality scores type')
83 p.add_argument('output_filename', help='groomed output file')
84 p.add_argument('output_type', choices=type_choices, help='input FASTQ quality scores type')
85 p.add_argument('force_quality_encoding', choices=fqe_choices, help='force quality score encoding')
86 p.add_argument('summarize_input', choices=si_choices, help='summarize input data')
87
88 fi_group = p.add_mutually_exclusive_group()
89 fi_group.add_argument(
90 '--fix-id', dest='fix_id', action='store_true', help='fix inconsistent identifiers')
91 fi_group.add_argument(
92 '--no-fix-id', dest='fix_id', action='store_false', help='do not fix inconsistent identifiers')
93 p.set_defaults(fix_id=True)
94
95 return p.parse_args()
96
97
98def main():
99 Groomer().run()
100
101
102if __name__ == "__main__":
103 main()