# HG changeset patch # User matthias # Date 1560946453 14400 # Node ID 42bbbc4b4739c2931ce5428d647463d93719c344 # Parent e374299894b069c2dcf45008bc2fad01ea8d7f90 planemo upload commit 8d8a5c80b61682382aaad45f82948a9850a71e9c diff -r e374299894b0 -r 42bbbc4b4739 data_manager/.dada2_fetcher.xml.swp Binary file data_manager/.dada2_fetcher.xml.swp has changed diff -r e374299894b0 -r 42bbbc4b4739 data_manager/.data_manager.py.swp Binary file data_manager/.data_manager.py.swp has changed diff -r e374299894b0 -r 42bbbc4b4739 data_manager/dada2_fetcher.xml --- a/data_manager/dada2_fetcher.xml Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,180 +0,0 @@ - - - Download reference databases - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - 10.1093/nar/gks1219 - > - 10.1093/nar/gkt1244 - - 10.1128/AEM.03006-05 - - 10.15156/BIO/786343 - - - 10.1186/s12864-015-2265-y - - 10.1093/nar/gks1160 - - - diff -r e374299894b0 -r 42bbbc4b4739 data_manager/data_manager.py --- a/data_manager/data_manager.py Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,134 +0,0 @@ -import argparse -import json -import os -import shutil -import sys -import zipfile -try: - # For Python 3.0 and later - from urllib.request import Request, urlopen -except ImportError: - # Fall back to Python 2 imports - from urllib2 import Request, urlopen - -DEFAULT_TAXLEVELS="Kingdom,Phylum,Class,Order,Family,Genus,Species" - -FILE2NAME = { - "silva_132":"Silva version 132", - "silva_128":"Silva version 128", - "rdp_16":"RDP trainset 16", - "rdp_14":"RDP trainset 14", - "greengenes_13.84":"GreenGenes version 13.84", - "unite_8.0_fungi": "UNITE: General Fasta release 8.0 for Fungi", - "unite_8.0_fungi_singletons": "UNITE: General Fasta release 8.0 for Fungi including global and 97% singletons", - "RefSeq_RDP_2018_05": "NCBI RefSeq 16S rRNA database supplemented by RDP (05/2018)", - "gtdb_2018_11": "GTDB: Genome Taxonomy Database (Bacteria & Archaea) (11/2018)", - "hitdb_1": "HitDB version 1 (Human InTestinal 16S rRNA)", - "silva_euk_18S_132": "Silva version 132 Eukaryotic 18S", - "PR2_4.11.1": "Protist Ribosomal Reference database (PR2) 4.11.1" -} - -FILE2TAXURL = { - "silva_132":"https://zenodo.org/record/1172783/files/silva_nr_v132_train_set.fa.gz?download=1", - "silva_128":"https://zenodo.org/record/824551/files/silva_nr_v128_train_set.fa.gz?download=1", - "rdp_16":"https://zenodo.org/record/801828/files/rdp_train_set_16.fa.gz?download=1", - "rdp_14":"https://zenodo.org/record/158955/files/rdp_train_set_14.fa.gz?download=1", - "unite_8.0_fungi": "https://files.plutof.ut.ee/public/orig/EB/0C/EB0CCB3A871B77EA75E472D13926271076904A588D2E1C1EA5AFCF7397D48378.zip", - "unite_8.0_fungi_singletons": "https://files.plutof.ut.ee/doi/06/A2/06A2C86256EED64085670EB0C54B7115F6DAC8F311C656A9CB33E386CFABA0D0.zip", - "greengenes_13.84":"https://zenodo.org/record/158955/files/gg_13_8_train_set_97.fa.gz?download=1", - "RefSeq_RDP_2018_05": "https://zenodo.org/record/2541239/files/RefSeq-RDP16S_v2_May2018.fa.gz?download=1", - "gtdb_2018_11": "https://zenodo.org/record/2541239/files/GTDB_bac-arc_ssu_r86.fa.gz?download=1", - "hitdb_1": "https://zenodo.org/record/159205/files/hitdb_v1.00.fa.gz?download=1", - "silva_euk_18S_132": "https://zenodo.org/record/1447330/files/silva_132.18s.99_rep_set.dada2.fa.gz?download=1", - "PR2_4.11.1": "https://github.com/pr2database/pr2database/releases/download/4.11.1/pr2_version_4.11.1_dada2.fasta.gz" -} - -FILE2SPECIESURL = { - "silva_132":"https://zenodo.org/record/1172783/files/silva_species_assignment_v132.fa.gz?download=1", - "silva_128":"https://zenodo.org/record/824551/files/silva_species_assignment_v128.fa.gz?download=1", - "rdp_16":"https://zenodo.org/record/801828/files/rdp_species_assignment_16.fa.gz?download=1", - "rdp_14":"https://zenodo.org/record/158955/files/rdp_species_assignment_14.fa.gz?download=1" -} - -FILE2TAXLEVELS = { - "PR2_4.11.1": "Kingdom,Supergroup,Division,Class,Order,Family,Genus,Species" -} - -def url_download(url, fname, workdir): - """ - download url to workdir/fname - """ - file_path = os.path.join(workdir, fname) - if not os.path.exists(workdir): - os.makedirs(workdir) - src = None - dst = None - try: - req = Request(url) - src = urlopen(req) - with open(file_path, 'wb') as dst: - while True: - chunk = src.read(2**10) - if chunk: - dst.write(chunk) - else: - break - finally: - if src: - src.close() - - #special treatment of UNITE DBs: they are zip files containing two fasta (xyz.fasta and developer/xyz.fasta) - if fname.startswith("unite"): - import glob - import gzip - import shutil - import zipfile - # unzip download - zip_ref = zipfile.ZipFile(file_path, 'r') - zip_ref.extractall(workdir) - zip_ref.close() - # gzip top level fasta file - fastas = glob.glob("%s/*fasta"%workdir) - if len(fastas) != 1: - msg = "UNITE download %s contained %d fasta file(s): %s"%(url, len(fastas), " ".join(fastas)) - raise Exception(msg) - with open(fastas[0], 'rb') as f_in: - with gzip.open(file_path, 'wb') as f_out: - shutil.copyfileobj(f_in, f_out) - - -def remote_dataset(dataset, outjson): - - with open(outjson) as jf: - params = json.loads(jf.read()) - - workdir = params['output_data'][0]['extra_files_path'] - os.mkdir(workdir) - url_download( FILE2TAXURL[dataset], dataset+".taxonomy", workdir) - - data_manager_json = {"data_tables":{}} - data_manager_entry = {} - data_manager_entry['value'] = dataset - data_manager_entry['name'] = FILE2NAME[dataset] - data_manager_entry['path'] = dataset+".taxonomy" - data_manager_entry['taxlevels'] = FILE2TAXLEVELS.get(dataset, DEFAULT_TAXLEVELS) - data_manager_json["data_tables"]["dada2_taxonomy"] = data_manager_entry - - if FILE2SPECIESURL.get(dataset, False ): - url_download( FILE2SPECIESURL[dataset], dataset+".species", workdir) - data_manager_entry = {} - data_manager_entry['value'] = dataset - data_manager_entry['name'] = FILE2NAME[dataset] - data_manager_entry['path'] = dataset+".species" - data_manager_json["data_tables"]["dada2_species"] = data_manager_entry - - with file(outjson, 'w') as jf: - jf.write(json.dumps(data_manager_json)) - -if __name__ == '__main__': - parser = argparse.ArgumentParser(description='Create data manager json.') - parser.add_argument('--out', action='store', help='JSON filename') - parser.add_argument('--dataset', action='store', help='Download data set name') - args = parser.parse_args() - - remote_dataset(args.dataset, args.out) diff -r e374299894b0 -r 42bbbc4b4739 data_manager_conf.xml --- a/data_manager_conf.xml Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,34 +0,0 @@ - - - - - - - - - - ${path} - dada2/${path} - - ${GALAXY_DATA_MANAGER_DATA_PATH}/dada2/${path} - abspath - - - - - - - - - - - ${path} - dada2/${path} - - ${GALAXY_DATA_MANAGER_DATA_PATH}/dada2/${path} - abspath - - - - - diff -r e374299894b0 -r 42bbbc4b4739 test-data/PR24.11.1_json --- a/test-data/PR24.11.1_json Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"dada2_taxonomy": {"path": "PR2_4.11.1.taxonomy", "name": "Protist Ribosomal Reference database (PR2) 4.11.1", "value": "PR2_4.11.1", "taxlevels": "Kingdom,Supergroup,Division,Class,Order,Family,Genus,Species"}}} \ No newline at end of file diff -r e374299894b0 -r 42bbbc4b4739 test-data/RefSeq_RDP2018_json --- a/test-data/RefSeq_RDP2018_json Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"dada2_taxonomy": {"path": "RefSeq_RDP_2018_05.taxonomy", "name": "NCBI RefSeq 16S rRNA database supplemented by RDP (05/2018)", "value": "RefSeq_RDP_2018_05", "taxlevels": "Kingdom,Phylum,Class,Order,Family,Genus,Species"}}} \ No newline at end of file diff -r e374299894b0 -r 42bbbc4b4739 test-data/dada2_species.loc --- a/test-data/dada2_species.loc Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,9 +0,0 @@ -# This is a sample file distributed with Galaxy that is used to define a -# list of dada2 reference data sets for species assignment, using three -# tab separated columns: -# -# -# -# Datasets can be retrieved from http://busco.ezlab.org/frame_wget.html -# -# Datasets can be retrieved from https://benjjneb.github.io/dada2/training.html diff -r e374299894b0 -r 42bbbc4b4739 test-data/dada2_taxonomy.loc --- a/test-data/dada2_taxonomy.loc Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,9 +0,0 @@ -# This is a sample file distributed with Galaxy that is used to define a -# list of dada2 reference data sets for taxonomy assignment, using three -# tab separated columns: -# -# -# -# Datasets can be retrieved from https://benjjneb.github.io/dada2/training.html -# -# taxlevels is a comma separated list of taxonomy levels diff -r e374299894b0 -r 42bbbc4b4739 test-data/greengenes13.84_json --- a/test-data/greengenes13.84_json Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"dada2_taxonomy": {"path": "greengenes_13.84.taxonomy", "name": "GreenGenes version 13.84", "value": "greengenes_13.84", "taxlevels": "Kingdom,Phylum,Class,Order,Family,Genus,Species"}}} \ No newline at end of file diff -r e374299894b0 -r 42bbbc4b4739 test-data/gtdb2018_json --- a/test-data/gtdb2018_json Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"dada2_taxonomy": {"path": "gtdb_2018_11.taxonomy", "name": "GTDB: Genome Taxonomy Database (Bacteria & Archaea) (11/2018)", "value": "gtdb_2018_11", "taxlevels": "Kingdom,Phylum,Class,Order,Family,Genus,Species"}}} \ No newline at end of file diff -r e374299894b0 -r 42bbbc4b4739 test-data/hitdb1_json --- a/test-data/hitdb1_json Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"dada2_taxonomy": {"path": "hitdb_1.taxonomy", "name": "HitDB version 1 (Human InTestinal 16S rRNA)", "value": "hitdb_1", "taxlevels": "Kingdom,Phylum,Class,Order,Family,Genus,Species"}}} \ No newline at end of file diff -r e374299894b0 -r 42bbbc4b4739 test-data/rdp16_json --- a/test-data/rdp16_json Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"dada2_species": {"path": "rdp_16.species", "name": "RDP trainset 16", "value": "rdp_16"}, "dada2_taxonomy": {"path": "rdp_16.taxonomy", "name": "RDP trainset 16", "value": "rdp_16", "taxlevels": "Kingdom,Phylum,Class,Order,Family,Genus,Species"}}} \ No newline at end of file diff -r e374299894b0 -r 42bbbc4b4739 test-data/silva132_json --- a/test-data/silva132_json Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"dada2_species": {"path": "silva_132.species", "name": "Silva version 132", "value": "silva_132"}, "dada2_taxonomy": {"path": "silva_132.taxonomy", "name": "Silva version 132", "value": "silva_132", "taxlevels": "Kingdom,Phylum,Class,Order,Family,Genus,Species"}}} \ No newline at end of file diff -r e374299894b0 -r 42bbbc4b4739 test-data/silvaeuk132_json --- a/test-data/silvaeuk132_json Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"dada2_taxonomy": {"path": "silva_euk_18S_132.taxonomy", "name": "Silva version 132 Eukaryotic 18S", "value": "silva_euk_18S_132", "taxlevels": "Kingdom,Phylum,Class,Order,Family,Genus,Species"}}} \ No newline at end of file diff -r e374299894b0 -r 42bbbc4b4739 test-data/unite8fungi_json --- a/test-data/unite8fungi_json Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"dada2_taxonomy": {"path": "unite_8.0_fungi.taxonomy", "name": "UNITE: General Fasta release 8.0 for Fungi", "value": "unite_8.0_fungi", "taxlevels": "Kingdom,Phylum,Class,Order,Family,Genus,Species"}}} \ No newline at end of file diff -r e374299894b0 -r 42bbbc4b4739 test-data/unite8fungisingletons_json --- a/test-data/unite8fungisingletons_json Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,1 +0,0 @@ -{"data_tables": {"dada2_taxonomy": {"path": "unite_8.0_fungi_singletons.taxonomy", "name": "UNITE: General Fasta release 8.0 for Fungi including global and 97% singletons", "value": "unite_8.0_fungi_singletons", "taxlevels": "Kingdom,Phylum,Class,Order,Family,Genus,Species"}}} \ No newline at end of file diff -r e374299894b0 -r 42bbbc4b4739 tool-data/dada2_species.loc.sample --- a/tool-data/dada2_species.loc.sample Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,9 +0,0 @@ -# This is a sample file distributed with Galaxy that is used to define a -# list of dada2 reference data sets for species assignment, using three -# tab separated columns: -# -# -# -# Datasets can be retrieved from http://busco.ezlab.org/frame_wget.html -# -# Datasets can be retrieved from https://benjjneb.github.io/dada2/training.html diff -r e374299894b0 -r 42bbbc4b4739 tool-data/dada2_taxonomy.loc.sample --- a/tool-data/dada2_taxonomy.loc.sample Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,9 +0,0 @@ -# This is a sample file distributed with Galaxy that is used to define a -# list of dada2 reference data sets for taxonomy assignment, using three -# tab separated columns: -# -# -# -# Datasets can be retrieved from https://benjjneb.github.io/dada2/training.html -# -# taxlevels is a comma separated list of taxonomy levels diff -r e374299894b0 -r 42bbbc4b4739 tool_data_table_conf.xml.sample --- a/tool_data_table_conf.xml.sample Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,11 +0,0 @@ - - - - value, name, path - -
- - value, name, path, taxlevels - -
-
diff -r e374299894b0 -r 42bbbc4b4739 tool_data_table_conf.xml.test --- a/tool_data_table_conf.xml.test Thu Jun 06 07:59:19 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,11 +0,0 @@ - - - - value, name, path - -
- - value, name, path, taxlevels - -
-