Mercurial > repos > matthias > data_manager_dada2

comparison data_manager/data_manager.py @ 8:da93e6a3fe23 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bernt-matthias/mb-galaxy-tools/tree/master/data_managers/data_manager_dada2 commit 5d8314337211e041568578b0e85001af05b73c2a
author matthias
date Wed, 19 Jun 2019 08:15:26 -0400
parents
children facf9e6c872c
comparison
equal deleted inserted replaced
7:42bbbc4b4739 8:da93e6a3fe23
1 import argparse
2 import json
3 import os
4 import shutil
5 import sys
6 import zipfile
7 try:
8 # For Python 3.0 and later
9 from urllib.request import Request, urlopen
10 except ImportError:
11 # Fall back to Python 2 imports
12 from urllib2 import Request, urlopen
13
14 DEFAULT_TAXLEVELS="Kingdom,Phylum,Class,Order,Family,Genus,Species"
15
16 FILE2NAME = {
17 "silva_132":"Silva version 132",
18 "silva_128":"Silva version 128",
19 "rdp_16":"RDP trainset 16",
20 "rdp_14":"RDP trainset 14",
21 "greengenes_13.84":"GreenGenes version 13.84",
22 "unite_8.0_fungi": "UNITE: General Fasta release 8.0 for Fungi",
23 "unite_8.0_fungi_singletons": "UNITE: General Fasta release 8.0 for Fungi including global and 97% singletons",
24 "RefSeq_RDP_2018_05": "NCBI RefSeq 16S rRNA database supplemented by RDP (05/2018)",
25 "gtdb_2018_11": "GTDB: Genome Taxonomy Database (Bacteria & Archaea) (11/2018)",
26 "hitdb_1": "HitDB version 1 (Human InTestinal 16S rRNA)",
27 "silva_euk_18S_132": "Silva version 132 Eukaryotic 18S",
28 "PR2_4.11.1": "Protist Ribosomal Reference database (PR2) 4.11.1"
29 }
30
31 FILE2TAXURL = {
32 "silva_132":"https://zenodo.org/record/1172783/files/silva_nr_v132_train_set.fa.gz?download=1",
33 "silva_128":"https://zenodo.org/record/824551/files/silva_nr_v128_train_set.fa.gz?download=1",
34 "rdp_16":"https://zenodo.org/record/801828/files/rdp_train_set_16.fa.gz?download=1",
35 "rdp_14":"https://zenodo.org/record/158955/files/rdp_train_set_14.fa.gz?download=1",
36 "unite_8.0_fungi": "https://files.plutof.ut.ee/public/orig/EB/0C/EB0CCB3A871B77EA75E472D13926271076904A588D2E1C1EA5AFCF7397D48378.zip",
37 "unite_8.0_fungi_singletons": "https://files.plutof.ut.ee/doi/06/A2/06A2C86256EED64085670EB0C54B7115F6DAC8F311C656A9CB33E386CFABA0D0.zip",
38 "greengenes_13.84":"https://zenodo.org/record/158955/files/gg_13_8_train_set_97.fa.gz?download=1",
39 "RefSeq_RDP_2018_05": "https://zenodo.org/record/2541239/files/RefSeq-RDP16S_v2_May2018.fa.gz?download=1",
40 "gtdb_2018_11": "https://zenodo.org/record/2541239/files/GTDB_bac-arc_ssu_r86.fa.gz?download=1",
41 "hitdb_1": "https://zenodo.org/record/159205/files/hitdb_v1.00.fa.gz?download=1",
42 "silva_euk_18S_132": "https://zenodo.org/record/1447330/files/silva_132.18s.99_rep_set.dada2.fa.gz?download=1",
43 "PR2_4.11.1": "https://github.com/pr2database/pr2database/releases/download/4.11.1/pr2_version_4.11.1_dada2.fasta.gz"
44 }
45
46 FILE2SPECIESURL = {
47 "silva_132":"https://zenodo.org/record/1172783/files/silva_species_assignment_v132.fa.gz?download=1",
48 "silva_128":"https://zenodo.org/record/824551/files/silva_species_assignment_v128.fa.gz?download=1",
49 "rdp_16":"https://zenodo.org/record/801828/files/rdp_species_assignment_16.fa.gz?download=1",
50 "rdp_14":"https://zenodo.org/record/158955/files/rdp_species_assignment_14.fa.gz?download=1"
51 }
52
53 FILE2TAXLEVELS = {
54 "PR2_4.11.1": "Kingdom,Supergroup,Division,Class,Order,Family,Genus,Species"
55 }
56
57 def url_download(url, fname, workdir):
58 """
59 download url to workdir/fname
60 """
61 file_path = os.path.join(workdir, fname)
62 if not os.path.exists(workdir):
63 os.makedirs(workdir)
64 src = None
65 dst = None
66 try:
67 req = Request(url)
68 src = urlopen(req)
69 with open(file_path, 'wb') as dst:
70 while True:
71 chunk = src.read(2**10)
72 if chunk:
73 dst.write(chunk)
74 else:
75 break
76 finally:
77 if src:
78 src.close()
79
80 #special treatment of UNITE DBs: they are zip files containing two fasta (xyz.fasta and developer/xyz.fasta)
81 if fname.startswith("unite"):
82 import glob
83 import gzip
84 import shutil
85 import zipfile
86 # unzip download
87 zip_ref = zipfile.ZipFile(file_path, 'r')
88 zip_ref.extractall(workdir)
89 zip_ref.close()
90 # gzip top level fasta file
91 fastas = glob.glob("%s/*fasta"%workdir)
92 if len(fastas) != 1:
93 msg = "UNITE download %s contained %d fasta file(s): %s"%(url, len(fastas), " ".join(fastas))
94 raise Exception(msg)
95 with open(fastas[0], 'rb') as f_in:
96 with gzip.open(file_path, 'wb') as f_out:
97 shutil.copyfileobj(f_in, f_out)
98
99
100 def remote_dataset(dataset, outjson):
101
102 with open(outjson) as jf:
103 params = json.loads(jf.read())
104
105 workdir = params['output_data'][0]['extra_files_path']
106 os.mkdir(workdir)
107 url_download( FILE2TAXURL[dataset], dataset+".taxonomy", workdir)
108
109 data_manager_json = {"data_tables":{}}
110 data_manager_entry = {}
111 data_manager_entry['value'] = dataset
112 data_manager_entry['name'] = FILE2NAME[dataset]
113 data_manager_entry['path'] = dataset+".taxonomy"
114 data_manager_entry['taxlevels'] = FILE2TAXLEVELS.get(dataset, DEFAULT_TAXLEVELS)
115 data_manager_json["data_tables"]["dada2_taxonomy"] = data_manager_entry
116
117 if FILE2SPECIESURL.get(dataset, False ):
118 url_download( FILE2SPECIESURL[dataset], dataset+".species", workdir)
119 data_manager_entry = {}
120 data_manager_entry['value'] = dataset
121 data_manager_entry['name'] = FILE2NAME[dataset]
122 data_manager_entry['path'] = dataset+".species"
123 data_manager_json["data_tables"]["dada2_species"] = data_manager_entry
124
125 with file(outjson, 'w') as jf:
126 jf.write(json.dumps(data_manager_json))
127
128 if __name__ == '__main__':
129 parser = argparse.ArgumentParser(description='Create data manager json.')
130 parser.add_argument('--out', action='store', help='JSON filename')
131 parser.add_argument('--dataset', action='store', help='Download data set name')
132 args = parser.parse_args()
133
134 remote_dataset(args.dataset, args.out)