# HG changeset patch # User sh477 # Date 1646039849 0 # Node ID a3dba0440f082faa1922e8bcd9d6cb60300d6d34 # Parent 97cd72b5130e31667fa374042837d05878505bfb Reformatting diff -r 97cd72b5130e -r a3dba0440f08 .shed.yml --- a/.shed.yml Wed Feb 23 12:26:11 2022 +0000 +++ b/.shed.yml Mon Feb 28 09:17:29 2022 +0000 @@ -1,11 +1,11 @@ -categories: -- Data Managers -description: Download and install annotation cache files for Ensembl VEP -long_description: | - This tool downloads given versions of VEP cache annotation files and makes - them available to Ensembl VEP in Galaxy via the "vep_versioned_caches" data - table. -name: data_manager_vep_cache_downloader -owner: sh477 -remote_repository_url: +categories: +- Data Managers +description: Download and install annotation cache files for Ensembl VEP +long_description: | + This tool downloads given versions of VEP cache annotation files and makes + them available to Ensembl VEP in Galaxy via the "vep_versioned_caches" data + table. +name: data_manager_vep_cache_downloader +owner: sh477 +remote_repository_url: type: unrestricted \ No newline at end of file diff -r 97cd72b5130e -r a3dba0440f08 data_manager/data_manager_vep_cache_download.py --- a/data_manager/data_manager_vep_cache_download.py Wed Feb 23 12:26:11 2022 +0000 +++ b/data_manager/data_manager_vep_cache_download.py Mon Feb 28 09:17:29 2022 +0000 @@ -1,56 +1,56 @@ -#!/usr/bin/env python - -import datetime -import json -import os -import re -from urllib.request import urlretrieve -import sys -import tarfile - - -def main(): - # Read in given out_file and create target directory for file download - with open(sys.argv[1]) as fh: - params = json.load(fh) - target_directory = params['output_data'][0]['extra_files_path'] - os.mkdir(target_directory) - - # Process parameters for metadata and file download - url = params['param_dict']['url'].rstrip("/") + "/" + params['param_dict']['file_name'].lstrip("/") - m = re.search(r"_([^_]*?)_vep_(\d+?)_", params['param_dict']['file_name']) - version = str(m.group(2)) - cache_type = m.group(1) if m.group(1) == "merged" or m.group(1) == "refseq" else "default" - - # Download and extract given cache archive, remove archive afterwards - final_file, headers = urlretrieve(url, os.path.join(target_directory, params['param_dict']['file_name'])) - tar = tarfile.open(final_file, "r:gz") - tar.extractall(target_directory) - tar.close() - os.remove(final_file) - - # Construct metadata for the new data table entry - data_manager_dict = { - 'data_tables': { - 'vep_versioned_caches': [ - { - 'value': params['param_dict']['file_name'].strip(".tar.gz"), - 'dbkey': params['param_dict']['dbkey'], - 'version': version, - 'cachetype': cache_type, - 'name': params['param_dict']['display_name'], - 'path': './%s' % params['param_dict']['file_name'].strip(".tar.gz") - } - ] - } - } - - #assert 42 == 0, str(data_manager_dict) - - # Save metadata to out_file - with open(sys.argv[1], 'w') as fh: - json.dump(data_manager_dict, fh, sort_keys=True) - - -if __name__ == "__main__": - main() +#!/usr/bin/env python + +import datetime +import json +import os +import re +from urllib.request import urlretrieve +import sys +import tarfile + + +def main(): + # Read in given out_file and create target directory for file download + with open(sys.argv[1]) as fh: + params = json.load(fh) + target_directory = params['output_data'][0]['extra_files_path'] + os.mkdir(target_directory) + + # Process parameters for metadata and file download + url = params['param_dict']['url'].rstrip("/") + "/" + params['param_dict']['file_name'].lstrip("/") + m = re.search(r"_([^_]*?)_vep_(\d+?)_", params['param_dict']['file_name']) + version = str(m.group(2)) + cache_type = m.group(1) if m.group(1) == "merged" or m.group(1) == "refseq" else "default" + + # Download and extract given cache archive, remove archive afterwards + final_file, headers = urlretrieve(url, os.path.join(target_directory, params['param_dict']['file_name'])) + tar = tarfile.open(final_file, "r:gz") + tar.extractall(target_directory) + tar.close() + os.remove(final_file) + + # Construct metadata for the new data table entry + data_manager_dict = { + 'data_tables': { + 'vep_versioned_caches': [ + { + 'value': params['param_dict']['file_name'].strip(".tar.gz"), + 'dbkey': params['param_dict']['dbkey'], + 'version': version, + 'cachetype': cache_type, + 'name': params['param_dict']['display_name'], + 'path': './%s' % params['param_dict']['file_name'].strip(".tar.gz") + } + ] + } + } + + #assert 42 == 0, str(data_manager_dict) + + # Save metadata to out_file + with open(sys.argv[1], 'w') as fh: + json.dump(data_manager_dict, fh, sort_keys=True) + + +if __name__ == "__main__": + main() diff -r 97cd72b5130e -r a3dba0440f08 data_manager/data_manager_vep_cache_download.xml --- a/data_manager/data_manager_vep_cache_download.xml Wed Feb 23 12:26:11 2022 +0000 +++ b/data_manager/data_manager_vep_cache_download.xml Mon Feb 28 09:17:29 2022 +0000 @@ -1,42 +1,42 @@ - - ToDo:the cache files required by VEP - - python - - - python '$__tool_directory__/data_manager_vep_cache_download.py' '$out_file' - - - - - - - - - - - - - - - - - - - - -This tool downloads given versions of VEP cache annotation files and makes them available to Ensembl VEP in Galaxy via the -"vep_versioned_caches" data table. You should use the indexed version of the cache files and it is strongly recommended to -use the cache files which version number matches the VEP version number. Note that for most genomes there are three versions -of cache data available: default, refseq and merged (combining the former two). Choose the one suitable for your usage. - -A general introduction to the VEP cache and download links can be found on the official website: -https://www.ensembl.org/info/docs/tools/vep/script/vep_cache.html - - - 10.1186/s13059-016-0974-4 - - + + versioned annotation files for VEP + + python + + + python '$__tool_directory__/data_manager_vep_cache_download.py' '$out_file' + + + + + + + + + + + + + + + + + + + + +This tool downloads given versions of VEP cache annotation files and makes them available to Ensembl VEP in Galaxy via the +"vep_versioned_caches" data table. You should use the indexed version of the cache files and it is strongly recommended to +use the cache files which version number matches the VEP version number. Note that for most genomes there are three versions +of cache data available: default, refseq and merged (combining the former two). Choose the one suitable for your usage. + +A general introduction to the VEP cache and download links can be found on the official website: +https://www.ensembl.org/info/docs/tools/vep/script/vep_cache.html + + + 10.1186/s13059-016-0974-4 + + \ No newline at end of file diff -r 97cd72b5130e -r a3dba0440f08 data_manager_conf.xml --- a/data_manager_conf.xml Wed Feb 23 12:26:11 2022 +0000 +++ b/data_manager_conf.xml Mon Feb 28 09:17:29 2022 +0000 @@ -1,21 +1,21 @@ - - - - - - - - - - - - - vep/${version}/${dbkey}/${cachetype} - - ${GALAXY_DATA_MANAGER_DATA_PATH}/vep/${version}/${dbkey}/${cachetype}/ - abspath - - - - - + + + + + + + + + + + + + vep/${version}/${dbkey}/${cachetype} + + ${GALAXY_DATA_MANAGER_DATA_PATH}/vep/${version}/${dbkey}/${cachetype}/ + abspath + + + + + \ No newline at end of file diff -r 97cd72b5130e -r a3dba0440f08 data_manager_conf.xml.sample --- a/data_manager_conf.xml.sample Wed Feb 23 12:26:11 2022 +0000 +++ b/data_manager_conf.xml.sample Mon Feb 28 09:17:29 2022 +0000 @@ -1,12 +1,12 @@ - - - - value, dbkey, version, cachetype, name, path - -
- - - value, name, len_path - -
-
+ + + + value, dbkey, version, cachetype, name, path + +
+ + + value, name, len_path + +
+
\ No newline at end of file diff -r 97cd72b5130e -r a3dba0440f08 data_manager_conf.xml.test --- a/data_manager_conf.xml.test Wed Feb 23 12:26:11 2022 +0000 +++ b/data_manager_conf.xml.test Mon Feb 28 09:17:29 2022 +0000 @@ -1,12 +1,12 @@ - - - - value, dbkey, version, cachetype, name, path - -
- - - value, name, len_path - -
-
+ + + + value, dbkey, version, cachetype, name, path + +
+ + + value, name, len_path + +
+
\ No newline at end of file diff -r 97cd72b5130e -r a3dba0440f08 test-data/dbkeys.loc --- a/test-data/dbkeys.loc Wed Feb 23 12:26:11 2022 +0000 +++ b/test-data/dbkeys.loc Mon Feb 28 09:17:29 2022 +0000 @@ -1,3 +1,3 @@ # hg38 Human hg38 a_path -ce11 C. elegans ce11 a_path +ce11 C. elegans ce11 a_path \ No newline at end of file diff -r 97cd72b5130e -r a3dba0440f08 test-data/vep_versioned_caches.loc --- a/test-data/vep_versioned_caches.loc Wed Feb 23 12:26:11 2022 +0000 +++ b/test-data/vep_versioned_caches.loc Mon Feb 28 09:17:29 2022 +0000 @@ -1,2 +1,2 @@ -# -# +# +# diff -r 97cd72b5130e -r a3dba0440f08 tool-data/dbkeys.loc.sample --- a/tool-data/dbkeys.loc.sample Wed Feb 23 12:26:11 2022 +0000 +++ b/tool-data/dbkeys.loc.sample Mon Feb 28 09:17:29 2022 +0000 @@ -1,1 +1,1 @@ -# +# \ No newline at end of file