|
0
|
1 #!/usr/bin/env python
|
|
|
2
|
|
|
3 import argparse
|
|
|
4 import os
|
|
|
5 import re
|
|
|
6 import shutil
|
|
2
|
7
|
|
|
8 import pandas
|
|
|
9 import pysam
|
|
0
|
10 from Bio import SeqIO
|
|
|
11
|
|
|
12
|
|
2
|
13 def get_sample_name(file_path):
|
|
0
|
14 base_file_name = os.path.basename(file_path)
|
|
|
15 if base_file_name.find(".") > 0:
|
|
|
16 # Eliminate the extension.
|
|
|
17 return os.path.splitext(base_file_name)[0]
|
|
2
|
18 return base_file_name
|
|
|
19
|
|
|
20
|
|
|
21 def get_coverage_df(bam_file):
|
|
|
22 # Create a coverage dictionary.
|
|
|
23 coverage_dict = {}
|
|
|
24 coverage_list = pysam.depth(bam_file, split_lines=True)
|
|
|
25 for line in coverage_list:
|
|
|
26 chrom, position, depth = line.split('\t')
|
|
|
27 coverage_dict["%s-%s" % (chrom, position)] = depth
|
|
|
28 # Convert it to a data frame.
|
|
|
29 coverage_df = pandas.DataFrame.from_dict(coverage_dict, orient='index', columns=["depth"])
|
|
|
30 return coverage_df
|
|
|
31
|
|
|
32
|
|
|
33 def get_zero_df(reference):
|
|
|
34 # Create a zero coverage dictionary.
|
|
|
35 zero_dict = {}
|
|
|
36 for record in SeqIO.parse(reference, "fasta"):
|
|
|
37 chrom = record.id
|
|
|
38 total_len = len(record.seq)
|
|
|
39 for pos in list(range(1, total_len + 1)):
|
|
|
40 zero_dict["%s-%s" % (str(chrom), str(pos))] = 0
|
|
|
41 # Convert it to a data frame with depth_x
|
|
|
42 # and depth_y columns - index is NaN.
|
|
|
43 zero_df = pandas.DataFrame.from_dict(zero_dict, orient='index', columns=["depth"])
|
|
|
44 return zero_df
|
|
0
|
45
|
|
|
46
|
|
2
|
47 def output_zc_vcf_file(base_file_name, vcf_file, zero_df, total_zero_coverage, output_vcf):
|
|
|
48 column_names = ["CHROM", "POS", "ID", "REF", "ALT", "QUAL", "FILTER", "INFO", "FORMAT", "Sample"]
|
|
|
49 vcf_df = pandas.read_csv(vcf_file, sep='\t', header=None, names=column_names, comment='#')
|
|
|
50 good_snp_count = len(vcf_df[(vcf_df['ALT'].str.len() == 1) & (vcf_df['REF'].str.len() == 1) & (vcf_df['QUAL'] > 150)])
|
|
|
51 if total_zero_coverage > 0:
|
|
|
52 header_file = "%s_header.csv" % base_file_name
|
|
|
53 with open(header_file, 'w') as outfile:
|
|
|
54 with open(vcf_file) as infile:
|
|
|
55 for line in infile:
|
|
|
56 if re.search('^#', line):
|
|
|
57 outfile.write("%s" % line)
|
|
|
58 vcf_df_snp = vcf_df[vcf_df['REF'].str.len() == 1]
|
|
|
59 vcf_df_snp = vcf_df_snp[vcf_df_snp['ALT'].str.len() == 1]
|
|
|
60 vcf_df_snp['ABS_VALUE'] = vcf_df_snp['CHROM'].map(str) + "-" + vcf_df_snp['POS'].map(str)
|
|
|
61 vcf_df_snp = vcf_df_snp.set_index('ABS_VALUE')
|
|
|
62 cat_df = pandas.concat([vcf_df_snp, zero_df], axis=1, sort=False)
|
|
|
63 cat_df = cat_df.drop(columns=['CHROM', 'POS', 'depth'])
|
|
|
64 cat_df[['ID', 'ALT', 'QUAL', 'FILTER', 'INFO']] = cat_df[['ID', 'ALT', 'QUAL', 'FILTER', 'INFO']].fillna('.')
|
|
|
65 cat_df['REF'] = cat_df['REF'].fillna('N')
|
|
|
66 cat_df['FORMAT'] = cat_df['FORMAT'].fillna('GT')
|
|
|
67 cat_df['Sample'] = cat_df['Sample'].fillna('./.')
|
|
|
68 cat_df['temp'] = cat_df.index.str.rsplit('-', n=1)
|
|
|
69 cat_df[['CHROM', 'POS']] = pandas.DataFrame(cat_df.temp.values.tolist(), index=cat_df.index)
|
|
|
70 cat_df = cat_df[['CHROM', 'POS', 'ID', 'REF', 'ALT', 'QUAL', 'FILTER', 'INFO', 'FORMAT', 'Sample']]
|
|
|
71 cat_df['POS'] = cat_df['POS'].astype(int)
|
|
|
72 cat_df = cat_df.sort_values(['CHROM', 'POS'])
|
|
|
73 body_file = "%s_body.csv" % base_file_name
|
|
|
74 cat_df.to_csv(body_file, sep='\t', header=False, index=False)
|
|
|
75 with open(output_vcf, "w") as outfile:
|
|
|
76 for cf in [header_file, body_file]:
|
|
|
77 with open(cf, "r") as infile:
|
|
0
|
78 for line in infile:
|
|
2
|
79 outfile.write("%s" % line)
|
|
|
80 else:
|
|
|
81 shutil.move(vcf_file, output_vcf)
|
|
|
82 return good_snp_count
|
|
0
|
83
|
|
|
84
|
|
2
|
85 def output_metrics_file(base_file_name, average_coverage, genome_coverage, good_snp_count, output_metrics):
|
|
|
86 bam_metrics = [base_file_name, "", "%4f" % average_coverage, genome_coverage]
|
|
|
87 vcf_metrics = [base_file_name, str(good_snp_count), "", ""]
|
|
|
88 metrics_columns = ["File", "Number of Good SNPs", "Average Coverage", "Genome Coverage"]
|
|
|
89 with open(output_metrics, "w") as fh:
|
|
|
90 fh.write("# %s\n" % "\t".join(metrics_columns))
|
|
|
91 fh.write("%s\n" % "\t".join(bam_metrics))
|
|
|
92 fh.write("%s\n" % "\t".join(vcf_metrics))
|
|
|
93
|
|
|
94
|
|
|
95 def output_files(vcf_file, total_zero_coverage, zero_df, output_vcf, average_coverage, genome_coverage, output_metrics):
|
|
|
96 base_file_name = get_sample_name(vcf_file)
|
|
|
97 good_snp_count = output_zc_vcf_file(base_file_name, vcf_file, zero_df, total_zero_coverage, output_vcf)
|
|
|
98 output_metrics_file(base_file_name, average_coverage, genome_coverage, good_snp_count, output_metrics)
|
|
|
99
|
|
|
100
|
|
|
101 def get_coverage_and_snp_count(bam_file, vcf_file, reference, output_metrics, output_vcf):
|
|
|
102 coverage_df = get_coverage_df(bam_file)
|
|
|
103 zero_df = get_zero_df(reference)
|
|
|
104 coverage_df = zero_df.merge(coverage_df, left_index=True, right_index=True, how='outer')
|
|
|
105 # depth_x "0" column no longer needed.
|
|
|
106 coverage_df = coverage_df.drop(columns=['depth_x'])
|
|
|
107 coverage_df = coverage_df.rename(columns={'depth_y': 'depth'})
|
|
|
108 # Covert the NaN to 0 coverage and get some metrics.
|
|
|
109 coverage_df = coverage_df.fillna(0)
|
|
|
110 coverage_df['depth'] = coverage_df['depth'].apply(int)
|
|
|
111 total_length = len(coverage_df)
|
|
|
112 average_coverage = coverage_df['depth'].mean()
|
|
|
113 zero_df = coverage_df[coverage_df['depth'] == 0]
|
|
|
114 total_zero_coverage = len(zero_df)
|
|
|
115 total_coverage = total_length - total_zero_coverage
|
|
|
116 genome_coverage = "{:.2%}".format(total_coverage / total_length)
|
|
|
117 # Output a zero-coverage vcf fil and the metrics file.
|
|
|
118 output_files(vcf_file, total_zero_coverage, zero_df, output_vcf, average_coverage, genome_coverage, output_metrics)
|
|
0
|
119
|
|
|
120
|
|
|
121 if __name__ == '__main__':
|
|
|
122 parser = argparse.ArgumentParser()
|
|
|
123
|
|
2
|
124 parser.add_argument('--bam_input', action='store', dest='bam_input', help='bam input file')
|
|
0
|
125 parser.add_argument('--output_metrics', action='store', dest='output_metrics', required=False, default=None, help='Output metrics text file')
|
|
|
126 parser.add_argument('--output_vcf', action='store', dest='output_vcf', required=False, default=None, help='Output VCF file')
|
|
|
127 parser.add_argument('--reference', action='store', dest='reference', help='Reference dataset')
|
|
2
|
128 parser.add_argument('--vcf_input', action='store', dest='vcf_input', help='vcf input file')
|
|
0
|
129
|
|
|
130 args = parser.parse_args()
|
|
|
131
|
|
2
|
132 get_coverage_and_snp_count(args.bam_input, args.vcf_input, args.reference, args.output_metrics, args.output_vcf)
|
