Mercurial > repos > iuc > data_manager_dada2

comparison data_manager/data_manager.py @ 0:f57c13f5878b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_dada2 commit f8b6b6e72914ad6bcca8423dfa03f59bde80992e"
author iuc
date Fri, 08 Nov 2019 18:47:32 -0500
parents
children bf7b2c14cabc
comparison
equal deleted inserted replaced
-1:000000000000 0:f57c13f5878b
1 import argparse
2 import json
3 import os
4 try:
5 # For Python 3.0 and later
6 from urllib.request import Request, urlopen
7 except ImportError:
8 # Fall back to Python 2 imports
9 from urllib2 import Request, urlopen
10
11 DEFAULT_TAXLEVELS = "Kingdom,Phylum,Class,Order,Family,Genus,Species"
12
13 FILE2NAME = {
14 "silva_132": "Silva version 132",
15 "silva_128": "Silva version 128",
16 "rdp_16": "RDP trainset 16",
17 "rdp_14": "RDP trainset 14",
18 "greengenes_13.84": "GreenGenes version 13.84",
19 "unite_8.0_fungi": "UNITE: General Fasta release 8.0 for Fungi",
20 "unite_8.0_fungi_singletons": "UNITE: General Fasta release 8.0 for Fungi including global and 97% singletons",
21 "RefSeq_RDP_2018_05": "NCBI RefSeq 16S rRNA database supplemented by RDP (05/2018)",
22 "gtdb_2018_11": "GTDB: Genome Taxonomy Database (Bacteria & Archaea) (11/2018)",
23 "hitdb_1": "HitDB version 1 (Human InTestinal 16S rRNA)",
24 "silva_euk_18S_132": "Silva version 132 Eukaryotic 18S",
25 "PR2_4.11.1": "Protist Ribosomal Reference database (PR2) 4.11.1"
26 }
27
28 FILE2TAXURL = {
29 "silva_132": "https://zenodo.org/record/1172783/files/silva_nr_v132_train_set.fa.gz?download=1",
30 "silva_128": "https://zenodo.org/record/824551/files/silva_nr_v128_train_set.fa.gz?download=1",
31 "rdp_16": "https://zenodo.org/record/801828/files/rdp_train_set_16.fa.gz?download=1",
32 "rdp_14": "https://zenodo.org/record/158955/files/rdp_train_set_14.fa.gz?download=1",
33 "unite_8.0_fungi": "https://files.plutof.ut.ee/public/orig/EB/0C/EB0CCB3A871B77EA75E472D13926271076904A588D2E1C1EA5AFCF7397D48378.zip",
34 "unite_8.0_fungi_singletons": "https://files.plutof.ut.ee/doi/06/A2/06A2C86256EED64085670EB0C54B7115F6DAC8F311C656A9CB33E386CFABA0D0.zip",
35 "greengenes_13.84": "https://zenodo.org/record/158955/files/gg_13_8_train_set_97.fa.gz?download=1",
36 "RefSeq_RDP_2018_05": "https://zenodo.org/record/2541239/files/RefSeq-RDP16S_v2_May2018.fa.gz?download=1",
37 "gtdb_2018_11": "https://zenodo.org/record/2541239/files/GTDB_bac-arc_ssu_r86.fa.gz?download=1",
38 "hitdb_1": "https://zenodo.org/record/159205/files/hitdb_v1.00.fa.gz?download=1",
39 "silva_euk_18S_132": "https://zenodo.org/record/1447330/files/silva_132.18s.99_rep_set.dada2.fa.gz?download=1",
40 "PR2_4.11.1": "https://github.com/pr2database/pr2database/releases/download/4.11.1/pr2_version_4.11.1_dada2.fasta.gz"
41 }
42
43 FILE2SPECIESURL = {
44 "silva_132": "https://zenodo.org/record/1172783/files/silva_species_assignment_v132.fa.gz?download=1",
45 "silva_128": "https://zenodo.org/record/824551/files/silva_species_assignment_v128.fa.gz?download=1",
46 "rdp_16": "https://zenodo.org/record/801828/files/rdp_species_assignment_16.fa.gz?download=1",
47 "rdp_14": "https://zenodo.org/record/158955/files/rdp_species_assignment_14.fa.gz?download=1"
48 }
49
50 FILE2TAXLEVELS = {
51 "PR2_4.11.1": "Kingdom,Supergroup,Division,Class,Order,Family,Genus,Species"
52 }
53
54
55 def url_download(url, fname, workdir):
56 """
57 download url to workdir/fname
58 """
59 file_path = os.path.join(workdir, fname)
60 if not os.path.exists(workdir):
61 os.makedirs(workdir)
62 src = None
63 dst = None
64 try:
65 req = Request(url)
66 src = urlopen(req)
67 with open(file_path, 'wb') as dst:
68 while True:
69 chunk = src.read(2**10)
70 if chunk:
71 dst.write(chunk)
72 else:
73 break
74 finally:
75 if src:
76 src.close()
77
78 # special treatment of UNITE DBs: they are zip files containing two fasta (xyz.fasta and developer/xyz.fasta)
79 if fname.startswith("unite"):
80 import glob
81 import gzip
82 import shutil
83 import zipfile
84 # unzip download
85 zip_ref = zipfile.ZipFile(file_path, 'r')
86 zip_ref.extractall(workdir)
87 zip_ref.close()
88 # gzip top level fasta file
89 fastas = glob.glob("%s/*fasta" % workdir)
90 if len(fastas) != 1:
91 msg = "UNITE download %s contained %d fasta file(s): %s" % (url, len(fastas), " ".join(fastas))
92 raise Exception(msg)
93 with open(fastas[0], 'rb') as f_in:
94 with gzip.open(file_path, 'wb') as f_out:
95 shutil.copyfileobj(f_in, f_out)
96
97
98 def remote_dataset(dataset, outjson):
99
100 with open(outjson) as jf:
101 params = json.loads(jf.read())
102
103 workdir = params['output_data'][0]['extra_files_path']
104 os.mkdir(workdir)
105 url_download( FILE2TAXURL[dataset], dataset + ".taxonomy", workdir)
106
107 data_manager_json = {"data_tables": {}}
108 data_manager_entry = {}
109 data_manager_entry['value'] = dataset
110 data_manager_entry['name'] = FILE2NAME[dataset]
111 data_manager_entry['path'] = dataset + ".taxonomy"
112 data_manager_entry['taxlevels'] = FILE2TAXLEVELS.get(dataset, DEFAULT_TAXLEVELS)
113 data_manager_json["data_tables"]["dada2_taxonomy"] = data_manager_entry
114
115 if FILE2SPECIESURL.get(dataset, False ):
116 url_download( FILE2SPECIESURL[dataset], dataset + ".species", workdir)
117 data_manager_entry = {}
118 data_manager_entry['value'] = dataset
119 data_manager_entry['name'] = FILE2NAME[dataset]
120 data_manager_entry['path'] = dataset + ".species"
121 data_manager_json["data_tables"]["dada2_species"] = data_manager_entry
122
123 with file(outjson, 'w') as jf:
124 jf.write(json.dumps(data_manager_json))
125
126
127 if __name__ == '__main__':
128 parser = argparse.ArgumentParser(description='Create data manager json.')
129 parser.add_argument('--out', action='store', help='JSON filename')
130 parser.add_argument('--dataset', action='store', help='Download data set name')
131 args = parser.parse_args()
132
133 remote_dataset(args.dataset, args.out)