annotate vsnp_statistics.py @ 7:de2af65c4633 draft

Uploaded
author greg
date Thu, 22 Jul 2021 18:05:22 +0000
parents d0fbdeaaa488
children 1becb6606626
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
1 #!/usr/bin/env python
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
2
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
3 import argparse
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
4 import csv
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
5 import gzip
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
6 import os
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
7 from functools import partial
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
8
4
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
9 import numpy
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
10 import pandas
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
11 from Bio import SeqIO
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
12
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
13
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
14 def nice_size(size):
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
15 # Returns a readably formatted string with the size
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
16 words = ['bytes', 'KB', 'MB', 'GB', 'TB', 'PB', 'EB']
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
17 prefix = ''
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
18 try:
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
19 size = float(size)
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
20 if size < 0:
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
21 size = abs(size)
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
22 prefix = '-'
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
23 except Exception:
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
24 return '??? bytes'
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
25 for ind, word in enumerate(words):
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
26 step = 1024 ** (ind + 1)
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
27 if step > size:
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
28 size = size / float(1024 ** ind)
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
29 if word == 'bytes': # No decimals for bytes
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
30 return "%s%d bytes" % (prefix, size)
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
31 return "%s%.1f %s" % (prefix, size, word)
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
32 return '??? bytes'
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
33
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
34
4
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
35 def output_statistics(fastq_files, idxstats_files, metrics_files, output_file, gzipped, dbkey):
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
36 # Produce an Excel spreadsheet that
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
37 # contains a row for each sample.
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
38 columns = ['Reference', 'File Size', 'Mean Read Length', 'Mean Read Quality', 'Reads Passing Q30',
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
39 'Total Reads', 'All Mapped Reads', 'Unmapped Reads', 'Unmapped Reads Percentage of Total',
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
40 'Reference with Coverage', 'Average Depth of Coverage', 'Good SNP Count']
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
41 data_frames = []
4
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
42 for i, fastq_file in enumerate(fastq_files):
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
43 idxstats_file = idxstats_files[i]
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
44 metrics_file = metrics_files[i]
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
45 file_name_base = os.path.basename(fastq_file)
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
46 # Read fastq_file into a data frame.
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
47 _open = partial(gzip.open, mode='rt') if gzipped else open
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
48 with _open(fastq_file) as fh:
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
49 identifiers = []
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
50 seqs = []
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
51 letter_annotations = []
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
52 for seq_record in SeqIO.parse(fh, "fastq"):
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
53 identifiers.append(seq_record.id)
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
54 seqs.append(seq_record.seq)
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
55 letter_annotations.append(seq_record.letter_annotations["phred_quality"])
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
56 # Convert lists to Pandas series.
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
57 s1 = pandas.Series(identifiers, name='id')
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
58 s2 = pandas.Series(seqs, name='seq')
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
59 # Gather Series into a data frame.
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
60 fastq_df = pandas.DataFrame(dict(id=s1, seq=s2)).set_index(['id'])
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
61 total_reads = int(len(fastq_df.index) / 4)
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
62 current_sample_df = pandas.DataFrame(index=[file_name_base], columns=columns)
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
63 # Reference
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
64 current_sample_df.at[file_name_base, 'Reference'] = dbkey
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
65 # File Size
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
66 current_sample_df.at[file_name_base, 'File Size'] = nice_size(os.path.getsize(fastq_file))
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
67 # Mean Read Length
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
68 sampling_size = 10000
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
69 if sampling_size > total_reads:
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
70 sampling_size = total_reads
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
71 fastq_df = fastq_df.iloc[3::4].sample(sampling_size)
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
72 dict_mean = {}
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
73 list_length = []
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
74 i = 0
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
75 for id, seq, in fastq_df.iterrows():
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
76 dict_mean[id] = numpy.mean(letter_annotations[i])
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
77 list_length.append(len(seq.array[0]))
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
78 i += 1
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
79 current_sample_df.at[file_name_base, 'Mean Read Length'] = '%.1f' % numpy.mean(list_length)
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
80 # Mean Read Quality
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
81 df_mean = pandas.DataFrame.from_dict(dict_mean, orient='index', columns=['ave'])
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
82 current_sample_df.at[file_name_base, 'Mean Read Quality'] = '%.1f' % df_mean['ave'].mean()
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
83 # Reads Passing Q30
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
84 reads_gt_q30 = len(df_mean[df_mean['ave'] >= 30])
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
85 reads_passing_q30 = '{:10.2f}'.format(reads_gt_q30 / sampling_size)
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
86 current_sample_df.at[file_name_base, 'Reads Passing Q30'] = reads_passing_q30
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
87 # Total Reads
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
88 current_sample_df.at[file_name_base, 'Total Reads'] = total_reads
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
89 # All Mapped Reads
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
90 all_mapped_reads, unmapped_reads = process_idxstats_file(idxstats_file)
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
91 current_sample_df.at[file_name_base, 'All Mapped Reads'] = all_mapped_reads
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
92 # Unmapped Reads
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
93 current_sample_df.at[file_name_base, 'Unmapped Reads'] = unmapped_reads
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
94 # Unmapped Reads Percentage of Total
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
95 if unmapped_reads > 0:
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
96 unmapped_reads_percentage = '{:10.2f}'.format(unmapped_reads / total_reads)
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
97 else:
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
98 unmapped_reads_percentage = 0
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
99 current_sample_df.at[file_name_base, 'Unmapped Reads Percentage of Total'] = unmapped_reads_percentage
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
100 # Reference with Coverage
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
101 ref_with_coverage, avg_depth_of_coverage, good_snp_count = process_metrics_file(metrics_file)
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
102 current_sample_df.at[file_name_base, 'Reference with Coverage'] = ref_with_coverage
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
103 # Average Depth of Coverage
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
104 current_sample_df.at[file_name_base, 'Average Depth of Coverage'] = avg_depth_of_coverage
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
105 # Good SNP Count
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
106 current_sample_df.at[file_name_base, 'Good SNP Count'] = good_snp_count
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
107 data_frames.append(current_sample_df)
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
108 output_df = pandas.concat(data_frames)
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
109 output_df.to_csv(output_file, sep='\t', quoting=csv.QUOTE_NONE, escapechar='\\')
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
110
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
111
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
112 def process_idxstats_file(idxstats_file):
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
113 all_mapped_reads = 0
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
114 unmapped_reads = 0
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
115 with open(idxstats_file, "r") as fh:
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
116 for i, line in enumerate(fh):
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
117 line = line.rstrip('\r\n')
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
118 items = line.split("\t")
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
119 if i == 0:
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
120 # NC_002945.4 4349904 213570 4047
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
121 all_mapped_reads = int(items[2])
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
122 elif i == 1:
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
123 # * 0 0 82774
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
124 unmapped_reads = int(items[3])
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
125 return all_mapped_reads, unmapped_reads
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
126
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
127
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
128 def process_metrics_file(metrics_file):
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
129 ref_with_coverage = '0%'
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
130 avg_depth_of_coverage = 0
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
131 good_snp_count = 0
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
132 with open(metrics_file, "r") as ifh:
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
133 for i, line in enumerate(ifh):
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
134 if i == 0:
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
135 # Skip comments.
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
136 continue
5
d0fbdeaaa488 "planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/sequence_analysis/vsnp/vsnp_statistics commit 770e89322a15829580ed9577a853660f63233f32"
greg
parents: 4
diff changeset
137 line = line.rstrip('\r\n')
1
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
138 items = line.split("\t")
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
139 if i == 1:
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
140 # MarkDuplicates 10.338671 98.74%
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
141 ref_with_coverage = items[3]
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
142 avg_depth_of_coverage = items[2]
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
143 elif i == 2:
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
144 # VCFfilter 611
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
145 good_snp_count = items[1]
14e29f7d59ca Uploaded
greg
parents: 0
diff changeset
146 return ref_with_coverage, avg_depth_of_coverage, good_snp_count
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
147
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
148
4
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
149 parser = argparse.ArgumentParser()
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
150
4
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
151 parser.add_argument('--dbkey', action='store', dest='dbkey', help='Reference dbkey')
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
152 parser.add_argument('--gzipped', action='store_true', dest='gzipped', required=False, default=False, help='Input files are gzipped')
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
153 parser.add_argument('--input_idxstats_dir', action='store', dest='input_idxstats_dir', required=False, default=None, help='Samtools idxstats input directory')
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
154 parser.add_argument('--input_metrics_dir', action='store', dest='input_metrics_dir', required=False, default=None, help='vSNP add zero coverage metrics input directory')
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
155 parser.add_argument('--input_reads_dir', action='store', dest='input_reads_dir', required=False, default=None, help='Samples input directory')
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
156 parser.add_argument('--list_paired', action='store_true', dest='list_paired', required=False, default=False, help='Input samples is a list of paired reads')
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
157 parser.add_argument('--output', action='store', dest='output', help='Output Excel statistics file')
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
158 parser.add_argument('--read1', action='store', dest='read1', help='Required: single read')
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
159 parser.add_argument('--read2', action='store', dest='read2', required=False, default=None, help='Optional: paired read')
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
160 parser.add_argument('--samtools_idxstats', action='store', dest='samtools_idxstats', help='Output of samtools_idxstats')
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
161 parser.add_argument('--vsnp_azc', action='store', dest='vsnp_azc', help='Output of vsnp_add_zero_coverage')
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
162
4
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
163 args = parser.parse_args()
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
164
4
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
165 fastq_files = []
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
166 idxstats_files = []
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
167 metrics_files = []
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
168 # Accumulate inputs.
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
169 if args.read1 is not None:
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
170 # The inputs are not dataset collections, so
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
171 # read1, read2 (possibly) and vsnp_azc will also
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
172 # not be None.
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
173 fastq_files.append(args.read1)
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
174 idxstats_files.append(args.samtools_idxstats)
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
175 metrics_files.append(args.vsnp_azc)
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
176 if args.read2 is not None:
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
177 fastq_files.append(args.read2)
0
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
178 idxstats_files.append(args.samtools_idxstats)
c21d338dbdc4 Uploaded
greg
parents:
diff changeset
179 metrics_files.append(args.vsnp_azc)
4
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
180 else:
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
181 for file_name in sorted(os.listdir(args.input_reads_dir)):
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
182 fastq_files.append(os.path.join(args.input_reads_dir, file_name))
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
183 for file_name in sorted(os.listdir(args.input_idxstats_dir)):
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
184 idxstats_files.append(os.path.join(args.input_idxstats_dir, file_name))
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
185 if args.list_paired:
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
186 # Add the idxstats file for reverse.
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
187 idxstats_files.append(os.path.join(args.input_idxstats_dir, file_name))
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
188 for file_name in sorted(os.listdir(args.input_metrics_dir)):
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
189 metrics_files.append(os.path.join(args.input_metrics_dir, file_name))
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
190 if args.list_paired:
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
191 # Add the metrics file for reverse.
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
192 metrics_files.append(os.path.join(args.input_metrics_dir, file_name))
2d6c6b01319e Uploaded
greg
parents: 3
diff changeset
193 output_statistics(fastq_files, idxstats_files, metrics_files, args.output, args.gzipped, args.dbkey)