|
0
|
1 #!/usr/bin/env python3
|
|
|
2
|
|
|
3 import os
|
|
|
4 import sys
|
|
|
5 import glob
|
|
|
6 import argparse
|
|
|
7 import re
|
|
|
8
|
|
|
9
|
|
|
10 def parse_args(args=None):
|
|
|
11 Description = "Generate samplesheet from a directory of FastQ files."
|
|
|
12 Epilog = "Example usage: python fastq_dir_to_samplesheet.py <FASTQ_DIR> <SAMPLESHEET_FILE>"
|
|
|
13
|
|
|
14 parser = argparse.ArgumentParser(description=Description, epilog=Epilog)
|
|
|
15 parser.add_argument("FASTQ_DIR", help="Folder containing raw FastQ files.")
|
|
|
16 parser.add_argument("SAMPLESHEET_FILE", help="Output samplesheet file.")
|
|
|
17 parser.add_argument(
|
|
|
18 "-st",
|
|
|
19 "--strandedness",
|
|
|
20 type=str,
|
|
|
21 dest="STRANDEDNESS",
|
|
|
22 default="unstranded",
|
|
|
23 help="Value for 'strandedness' in samplesheet. Must be one of 'unstranded', 'forward', 'reverse'.",
|
|
|
24 )
|
|
|
25 parser.add_argument(
|
|
|
26 "-r1",
|
|
|
27 "--read1_extension",
|
|
|
28 type=str,
|
|
|
29 dest="READ1_EXTENSION",
|
|
|
30 default="_R1_001.fastq.gz",
|
|
|
31 help="File extension for read 1.",
|
|
|
32 )
|
|
|
33 parser.add_argument(
|
|
|
34 "-r2",
|
|
|
35 "--read2_extension",
|
|
|
36 type=str,
|
|
|
37 dest="READ2_EXTENSION",
|
|
|
38 default="_R2_001.fastq.gz",
|
|
|
39 help="File extension for read 2.",
|
|
|
40 )
|
|
|
41 parser.add_argument(
|
|
|
42 "-se",
|
|
|
43 "--single_end",
|
|
|
44 dest="SINGLE_END",
|
|
|
45 action="store_true",
|
|
|
46 help="Single-end information will be auto-detected but this option forces paired-end FastQ files to be treated as single-end so only read 1 information is included in the samplesheet.",
|
|
|
47 )
|
|
|
48 parser.add_argument(
|
|
|
49 "-sn",
|
|
|
50 "--sanitise_name",
|
|
|
51 dest="SANITISE_NAME",
|
|
|
52 action="store_true",
|
|
|
53 help="Whether to further sanitise FastQ file name to get sample id. Used in conjunction with --sanitise_name_delimiter and --sanitise_name_index.",
|
|
|
54 )
|
|
|
55 parser.add_argument(
|
|
|
56 "-sd",
|
|
|
57 "--sanitise_name_delimiter",
|
|
|
58 type=str,
|
|
|
59 dest="SANITISE_NAME_DELIMITER",
|
|
|
60 default="_",
|
|
|
61 help="Delimiter to use to sanitise sample name.",
|
|
|
62 )
|
|
|
63 parser.add_argument(
|
|
|
64 "-si",
|
|
|
65 "--sanitise_name_index",
|
|
|
66 type=int,
|
|
|
67 dest="SANITISE_NAME_INDEX",
|
|
|
68 default=1,
|
|
|
69 help="After splitting FastQ file name by --sanitise_name_delimiter all elements before this index (1-based) will be joined to create final sample name.",
|
|
|
70 )
|
|
|
71 return parser.parse_args(args)
|
|
|
72
|
|
|
73
|
|
|
74 def fastq_dir_to_samplesheet(
|
|
|
75 fastq_dir,
|
|
|
76 samplesheet_file,
|
|
|
77 strandedness="unstranded",
|
|
|
78 read1_extension="_R1_001.fastq.gz",
|
|
|
79 read2_extension="_R2_001.fastq.gz",
|
|
|
80 single_end=False,
|
|
|
81 sanitise_name=False,
|
|
|
82 sanitise_name_delimiter="_",
|
|
|
83 sanitise_name_index=1,
|
|
|
84 ):
|
|
|
85 def sanitize_sample(path, extension):
|
|
|
86 """Retrieve sample id from filename"""
|
|
|
87 sample = os.path.basename(path).replace(extension, "")
|
|
|
88 if sanitise_name:
|
|
|
89 if sanitise_name_index > 0:
|
|
|
90 sample = sanitise_name_delimiter.join(
|
|
|
91 os.path.basename(path).split(sanitise_name_delimiter)[
|
|
|
92 :sanitise_name_index
|
|
|
93 ]
|
|
|
94 )
|
|
|
95 # elif sanitise_name_index == -1:
|
|
|
96 # sample = os.path.basename(path)[ :os.path.basename(path).index('.') ]
|
|
|
97 return sample
|
|
|
98
|
|
|
99 def get_fastqs(extension):
|
|
|
100 """
|
|
|
101 Needs to be sorted to ensure R1 and R2 are in the same order
|
|
|
102 when merging technical replicates. Glob is not guaranteed to produce
|
|
|
103 sorted results.
|
|
|
104 See also https://stackoverflow.com/questions/6773584/how-is-pythons-glob-glob-ordered
|
|
|
105 """
|
|
|
106 abs_fq_files = glob.glob(os.path.join(fastq_dir, f"**", f"*{extension}"), recursive=True)
|
|
|
107 return sorted(
|
|
|
108 [
|
|
|
109 fq for _, fq in enumerate(abs_fq_files) if re.match('^((?!undetermined|unclassified|downloads).)*$', fq, flags=re.IGNORECASE)
|
|
|
110 ]
|
|
|
111 )
|
|
|
112
|
|
|
113 read_dict = {}
|
|
|
114
|
|
|
115 ## Get read 1 files
|
|
|
116 for read1_file in get_fastqs(read1_extension):
|
|
|
117 sample = sanitize_sample(read1_file, read1_extension)
|
|
|
118 if sample not in read_dict:
|
|
|
119 read_dict[sample] = {"R1": [], "R2": []}
|
|
|
120 read_dict[sample]["R1"].append(read1_file)
|
|
|
121
|
|
|
122 ## Get read 2 files
|
|
|
123 if not single_end:
|
|
|
124 for read2_file in get_fastqs(read2_extension):
|
|
|
125 sample = sanitize_sample(read2_file, read2_extension)
|
|
|
126 read_dict[sample]["R2"].append(read2_file)
|
|
|
127
|
|
|
128 ## Write to file
|
|
|
129 if len(read_dict) > 0:
|
|
|
130 out_dir = os.path.dirname(samplesheet_file)
|
|
|
131 if out_dir and not os.path.exists(out_dir):
|
|
|
132 os.makedirs(out_dir)
|
|
|
133
|
|
|
134 with open(samplesheet_file, "w") as fout:
|
|
|
135 header = ["sample", "fq1", "fq2", "strandedness"]
|
|
|
136 fout.write(",".join(header) + "\n")
|
|
|
137 for sample, reads in sorted(read_dict.items()):
|
|
|
138 for idx, read_1 in enumerate(reads["R1"]):
|
|
|
139 read_2 = ""
|
|
|
140 if idx < len(reads["R2"]):
|
|
|
141 read_2 = reads["R2"][idx]
|
|
|
142 sample_info = ",".join([sample, read_1, read_2, strandedness])
|
|
|
143 fout.write(f"{sample_info}\n")
|
|
|
144 else:
|
|
|
145 error_str = (
|
|
|
146 "\nWARNING: No FastQ files found so samplesheet has not been created!\n\n"
|
|
|
147 )
|
|
|
148 error_str += "Please check the values provided for the:\n"
|
|
|
149 error_str += " - Path to the directory containing the FastQ files\n"
|
|
|
150 error_str += " - '--read1_extension' parameter\n"
|
|
|
151 error_str += " - '--read2_extension' parameter\n"
|
|
|
152 print(error_str)
|
|
|
153 sys.exit(1)
|
|
|
154
|
|
|
155
|
|
|
156 def main(args=None):
|
|
|
157 args = parse_args(args)
|
|
|
158
|
|
|
159 strandedness = "unstranded"
|
|
|
160 if args.STRANDEDNESS in ["unstranded", "forward", "reverse"]:
|
|
|
161 strandedness = args.STRANDEDNESS
|
|
|
162
|
|
|
163 fastq_dir_to_samplesheet(
|
|
|
164 fastq_dir=args.FASTQ_DIR,
|
|
|
165 samplesheet_file=args.SAMPLESHEET_FILE,
|
|
|
166 strandedness=strandedness,
|
|
|
167 read1_extension=args.READ1_EXTENSION,
|
|
|
168 read2_extension=args.READ2_EXTENSION,
|
|
|
169 single_end=args.SINGLE_END,
|
|
|
170 sanitise_name=args.SANITISE_NAME,
|
|
|
171 sanitise_name_delimiter=args.SANITISE_NAME_DELIMITER,
|
|
|
172 sanitise_name_index=args.SANITISE_NAME_INDEX,
|
|
|
173 )
|
|
|
174
|
|
|
175
|
|
|
176 if __name__ == "__main__":
|
|
|
177 sys.exit(main())
|
