- galaxy-commits - lists.galaxyproject.org

commit/galaxy-central: dan: Rewrite HbVar datasource tool.
by Bitbucket 04 May '12

04 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/1c196b8747e4/ changeset: 1c196b8747e4 user: dan date: 2012-05-04 21:35:51 summary: Rewrite HbVar datasource tool. affected #: 1 file diff -r dd777fbcc5fa1fee5939db5d914611b8b466eed6 -r 1c196b8747e4d976cbc1d294457b64a7e27fb26c tools/data_source/hbvar.xml --- a/tools/data_source/hbvar.xml +++ b/tools/data_source/hbvar.xml @@ -1,22 +1,18 @@ <?xml version="1.0"?> -<tool name="HbVar" id="hbvar"> +<tool name="HbVar" id="hbvar" tool_type="data_source" version="2.0.0"><description>Human Hemoglobin Variants and Thalassemias</description> - <command/> + <command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command><inputs action="http://globin.bx.psu.edu/cgi-bin/hbvar/query_vars3" check_values="false" method="get" target="_top"><display>go to HbVar database $GALAXY_URL $tool_id</display> - <param name="GALAXY_URL" type="baseurl" value="/tool_runner/hbvar" /> - <param name="tool_id" type="hidden" value = "hbvar"/></inputs><uihints minwidth="800"/> - <code file="hbvar_filter.py"/> - <outputs> - <data name="output" format="txt" /> + <data name="output" format="auto" /></outputs><options sanitize="False" refresh="True"/> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dan: Update GenomeSpace exporter tool to use the newly introduced /personaldirectory as the root for auto-generated export paths.
by Bitbucket 04 May '12

04 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/dd777fbcc5fa/ changeset: dd777fbcc5fa user: dan date: 2012-05-04 20:31:22 summary: Update GenomeSpace exporter tool to use the newly introduced /personaldirectory as the root for auto-generated export paths. affected #: 2 files diff -r 1eb32dbab2c1a0bc308eb4d3a069fa55ff6ecb83 -r dd777fbcc5fa1fee5939db5d914611b8b466eed6 tools/genomespace/genomespace_exporter.py --- a/tools/genomespace/genomespace_exporter.py +++ b/tools/genomespace/genomespace_exporter.py @@ -50,6 +50,7 @@ def get_directory( url_opener, dm_url, path ): url = dm_url i = None + dir_dict = {} for i, sub_path in enumerate( path ): url = "%s/%s" % ( url, sub_path ) dir_request = urllib2.Request( url, headers = { 'Content-Type': 'application/json', 'Accept': 'application/json' } ) @@ -57,7 +58,7 @@ try: dir_dict = simplejson.loads( url_opener.open( dir_request ).read() ) except urllib2.HTTPError, e: - #print "e", e, url #punting, assuming lack of permisions at this low of a level... + #print "e", e, url #punting, assuming lack of permissions at this low of a level... continue break if i is not None: @@ -69,6 +70,9 @@ def get_default_directory( url_opener, dm_url ): return get_directory( url_opener, dm_url, ["defaultdirectory"] )[0] +def get_personal_directory( url_opener, dm_url ): + return get_directory( url_opener, dm_url, [ "%s/personaldirectory" % ( GENOMESPACE_API_VERSION_STRING ) ] )[0] + def create_directory( url_opener, directory_dict, new_dir, dm_url ): payload = { "isDirectory": True } for dir_slice in new_dir: @@ -134,7 +138,9 @@ genomespace_site_dict = get_genomespace_site_urls()[ genomespace_site ] dm_url = genomespace_site_dict['dmServer'] #get default directory - directory_dict = get_default_directory( url_opener, dm_url )['directory'] + directory_dict = get_default_directory( url_opener, dm_url ).get( 'directory', None ) + if directory_dict is None: + return [] #what directory to stuff this in recurse_directory_dict( url_opener, rval, directory_dict.get( 'url' ) ) @@ -150,7 +156,7 @@ directory_dict, target_directory = get_directory( url_opener, dm_url, [ "%s/%s/%s" % ( GENOMESPACE_API_VERSION_STRING, 'file', target_directory[1] ) ] + target_directory[2:] ) directory_dict = directory_dict['directory'] else: - directory_dict = get_default_directory( url_opener, dm_url )['directory'] + directory_dict = get_personal_directory( url_opener, dm_url )['directory'] #this is the base for the auto-generated galaxy export directories #what directory to stuff this in target_directory_dict = create_directory( url_opener, directory_dict, target_directory, dm_url ) #get upload url @@ -208,6 +214,6 @@ (options, args) = parser.parse_args() - send_file_to_genomespace( options.genomespace_site, options.username, options.token, options.dataset, map( binascii.unhexlify, options.subdirectory ), options.filename, options.file_type, options.content_type, options.log ) + send_file_to_genomespace( options.genomespace_site, options.username, options.token, options.dataset, map( binascii.unhexlify, options.subdirectory ), binascii.unhexlify( options.filename ), options.file_type, options.content_type, options.log ) diff -r 1eb32dbab2c1a0bc308eb4d3a069fa55ff6ecb83 -r dd777fbcc5fa1fee5939db5d914611b8b466eed6 tools/genomespace/genomespace_exporter.xml --- a/tools/genomespace/genomespace_exporter.xml +++ b/tools/genomespace/genomespace_exporter.xml @@ -25,9 +25,9 @@ --subdirectory "${ binascii.hexlify( str( $base_url ).split( '://', 1 )[-1] ) }" ##Protocol removed by request #end if #if $filename: - --filename "${filename}" + --filename "${ binascii.hexlify( str( $filename ) ) }" #else: - --filename "Galaxy History Item ${__app__.security.encode_id( $input1.id )} (${__app__.security.encode_id( $output_log.id )}) - ${input1.hid}: ${input1.name}.${input1.ext}" + --filename "${ binascii.hexlify( "Galaxy History Item %s (%s) - %s: %s.%s" % ( $__app__.security.encode_id( $input1.id ), $__app__.security.encode_id( $output_log.id ), $input1.hid, $input1.name, $input1.ext ) ) }" #end if --file_type "${input1.ext}" --content_type "${input1.get_mime()}" @@ -36,7 +36,6 @@ <inputs><param format="data" name="input1" type="data" label="Send this dataset to GenomeSpace" /><param name="base_url" type="baseurl" /> - <param name="subdirectory" type="drill_down" display="radio" hierarchy="exact" multiple="False" label="Choose Target Directory" dynamic_options="galaxy_code_get_genomespace_folders( genomespace_site = 'prod', trans=__trans__, value=__value__, input_dataset=input1 )" help="Leave blank to generate automatically"/><param name="filename" type="text" size="80" help="Leave blank to generate automatically" /></inputs> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: greg: Clarify host string value in community_wsgi.ini.
by Bitbucket 03 May '12

03 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/1eb32dbab2c1/ changeset: 1eb32dbab2c1 user: greg date: 2012-05-03 20:00:32 summary: Clarify host string value in community_wsgi.ini. affected #: 1 file diff -r ea9f3c25a41576216f3c328e3333ebdb55250ed1 -r 1eb32dbab2c1a0bc308eb4d3a069fa55ff6ecb83 community_wsgi.ini.sample --- a/community_wsgi.ini.sample +++ b/community_wsgi.ini.sample @@ -4,7 +4,12 @@ use = egg:Paste#http port = 9009 + +# The address on which to listen. By default, only listen to localhost (the tool shed will not +# be accessible over the network). Use '0.0.0.0' to listen on all available network interfaces. +#host = 0.0.0.0 host = 127.0.0.1 + use_threadpool = true threadpool_workers = 10 Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: greg: Enhance sample file handling for installed tool shed repositories to handle more than just .loc.sample files in the tool-data directory.
by Bitbucket 03 May '12

03 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/ea9f3c25a415/ changeset: ea9f3c25a415 user: greg date: 2012-05-03 19:37:33 summary: Enhance sample file handling for installed tool shed repositories to handle more than just .loc.sample files in the tool-data directory. affected #: 4 files diff -r 71dfeecdd019554b5cccc047546ae26ed7b50afa -r ea9f3c25a41576216f3c328e3333ebdb55250ed1 lib/galaxy/tool_shed/install_manager.py --- a/lib/galaxy/tool_shed/install_manager.py +++ b/lib/galaxy/tool_shed/install_manager.py @@ -156,9 +156,15 @@ # Handle missing data table entries for tool parameters that are dynamically generated select lists. repository_tools_tups = handle_missing_data_table_entry( self.app, self.tool_path, sample_files, repository_tools_tups ) # Handle missing index files for tool parameters that are dynamically generated select lists. - repository_tools_tups = handle_missing_index_file( self.app, self.tool_path, sample_files, repository_tools_tups ) - # Handle tools that use fabric scripts to install dependencies. - handle_tool_dependencies( current_working_dir, relative_install_dir, repository_tools_tups ) + repository_tools_tups, sample_files_copied = handle_missing_index_file( self.app, self.tool_path, sample_files, repository_tools_tups ) + # Copy remaining sample files included in the repository to the ~/tool-data directory of the local Galaxy instance. + copy_sample_files( self.app, sample_files, sample_files_copied=sample_files_copied ) + if 'tool_dependencies_config' in metadata_dict: + # Install tool dependencies. + status, message = handle_tool_dependencies( self.app, repository_clone_url, metadata_dict[ 'tool_dependencies_config' ] ) + if status != 'ok' and message: + print 'The following error occurred while installing tool dependencies:' + print message add_to_tool_panel( self.app, repository_name, repository_clone_url, @@ -215,7 +221,7 @@ ctx_rev ) if 'tools' in metadata_dict: # Get the tool_versions from the tool shed for each tool in the installed change set. - url = '%s/repository/get_tool_versions?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % \ + url = '%s/repository/get_tool_versions?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy&no_reset=true' % \ ( tool_shed_url, tool_shed_repository.name, self.repository_owner, changeset_revision ) response = urllib2.urlopen( url ) text = response.read() diff -r 71dfeecdd019554b5cccc047546ae26ed7b50afa -r ea9f3c25a41576216f3c328e3333ebdb55250ed1 lib/galaxy/util/shed_util.py --- a/lib/galaxy/util/shed_util.py +++ b/lib/galaxy/util/shed_util.py @@ -1,4 +1,4 @@ -import os, tempfile, shutil, subprocess, logging, string, urllib2 +import sys, os, tempfile, shutil, subprocess, logging, string, urllib2 from datetime import date, datetime, timedelta from time import strftime, gmtime from galaxy import util @@ -7,6 +7,9 @@ from galaxy.tools.search import ToolBoxSearch from galaxy.model.orm import * +from galaxy import eggs +import pkg_resources + pkg_resources.require( 'mercurial' ) from mercurial import ui, commands @@ -215,7 +218,6 @@ # The value of proprietary_path must be an absolute path due to job_working_directory. elem.attrib[ 'proprietary_path' ] = os.path.abspath( relative_head ) elem.attrib[ 'proprietary_datatype_module' ] = proprietary_datatype_module - sniffers = datatypes_config_root.find( 'sniffers' ) else: sniffers = None @@ -270,8 +272,7 @@ return tool_shed_url.rstrip( '/' ) def clone_repository( repository_clone_url, repository_file_dir, ctx_rev ): """ - Clone the repository up to the specified changeset_revision. No subsequent revisions will be present - in the cloned repository. + Clone the repository up to the specified changeset_revision. No subsequent revisions will be present in the cloned repository. """ commands.clone( get_configured_ui(), repository_clone_url, @@ -279,17 +280,28 @@ pull=True, noupdate=False, rev=[ ctx_rev ] ) -def copy_sample_loc_file( app, filename ): - """Copy xxx.loc.sample to ~/tool-data/xxx.loc.sample and ~/tool-data/xxx.loc""" - head, sample_loc_file = os.path.split( filename ) - loc_file = sample_loc_file.replace( '.sample', '' ) - tool_data_path = os.path.abspath( app.config.tool_data_path ) +def copy_sample_file( app, filename, dest_path=None ): + """ + Copy xxx.loc.sample to dest_path/xxx.loc.sample and dest_path/xxx.loc. The default value for dest_path is ~/tool-data. + """ + if dest_path is None: + dest_path = os.path.abspath( app.config.tool_data_path ) + sample_file_path, sample_file_name = os.path.split( filename ) + copied_file = sample_file_name.replace( '.sample', '' ) # It's ok to overwrite the .sample version of the file. - shutil.copy( os.path.abspath( filename ), os.path.join( tool_data_path, sample_loc_file ) ) - # Only create the .loc file if it does not yet exist. We don't - # overwrite it in case it contains stuff proprietary to the local instance. - if not os.path.exists( os.path.join( tool_data_path, loc_file ) ): - shutil.copy( os.path.abspath( filename ), os.path.join( tool_data_path, loc_file ) ) + shutil.copy( os.path.abspath( filename ), os.path.join( dest_path, sample_file_name ) ) + # Only create the .loc file if it does not yet exist. We don't overwrite it in case it contains stuff proprietary to the local instance. + if not os.path.exists( os.path.join( dest_path, copied_file ) ): + shutil.copy( os.path.abspath( filename ), os.path.join( dest_path, copied_file ) ) +def copy_sample_files( app, sample_files, sample_files_copied=None, dest_path=None ): + """ + Copy all files to dest_path in the local Galaxy environment that have not already been copied. Those that have been copied + are contained in sample_files_copied. The default value for dest_path is ~/tool-data. + """ + sample_files_copied = util.listify( sample_files_copied ) + for filename in sample_files: + if filename not in sample_files_copied: + copy_sample_file( app, filename, dest_path=dest_path ) def create_repository_dict_for_proprietary_datatypes( tool_shed, name, owner, installed_changeset_revision, tool_dicts, converter_path=None, display_path=None ): return dict( tool_shed=tool_shed, repository_name=name, @@ -336,7 +348,7 @@ tool_shed_url = get_url_from_repository_tool_shed( trans.app, repository ) return '%s/repos/%s/%s' % ( tool_shed_url, repository.owner, repository.name ) def generate_datatypes_metadata( datatypes_config, metadata_dict ): - """Update the received metadata_dict with changes that have been applied to the received datatypes_config.""" + """Update the received metadata_dict with information from the parsed datatypes_config.""" tree = ElementTree.parse( datatypes_config ) root = tree.getroot() ElementInclude.include( root ) @@ -454,21 +466,9 @@ # Handle tool.requirements. tool_requirements = [] for tr in tool.requirements: - name=tr.name - type=tr.type - if type == 'fabfile': - version = None - fabfile = tr.fabfile - method = tr.method - else: - version = tr.version - fabfile = None - method = None - requirement_dict = dict( name=name, - type=type, - version=version, - fabfile=fabfile, - method=method ) + requirement_dict = dict( name=tr.name, + type=tr.type, + version=tr.version ) tool_requirements.append( requirement_dict ) # Handle tool.tests. tool_tests = [] @@ -732,7 +732,7 @@ break return converter_path, display_path def get_ctx_rev( tool_shed_url, name, owner, changeset_revision ): - url = '%s/repository/get_ctx_rev?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % ( tool_shed_url, name, owner, changeset_revision ) + url = '%s/repository/get_ctx_rev?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy&no_reset=true' % ( tool_shed_url, name, owner, changeset_revision ) response = urllib2.urlopen( url ) ctx_rev = response.read() response.close() @@ -893,27 +893,27 @@ return repository_tools_tups def handle_missing_index_file( app, tool_path, sample_files, repository_tools_tups ): """Inspect each tool to see if it has any input parameters that are dynamically generated select lists that depend on a .loc file.""" - missing_files_handled = [] + sample_files_copied = [] for index, repository_tools_tup in enumerate( repository_tools_tups ): tup_path, guid, repository_tool = repository_tools_tup params_with_missing_index_file = repository_tool.params_with_missing_index_file for param in params_with_missing_index_file: options = param.options - missing_head, missing_tail = os.path.split( options.missing_index_file ) - if missing_tail not in missing_files_handled: + missing_file_path, missing_file_name = os.path.split( options.missing_index_file ) + if missing_file_name not in sample_files_copied: # The repository must contain the required xxx.loc.sample file. for sample_file in sample_files: - sample_head, sample_tail = os.path.split( sample_file ) - if sample_tail == '%s.sample' % missing_tail: - copy_sample_loc_file( app, sample_file ) + sample_file_path, sample_file_name = os.path.split( sample_file ) + if sample_file_name == '%s.sample' % missing_file_name: + copy_sample_file( app, sample_file ) if options.tool_data_table and options.tool_data_table.missing_index_file: options.tool_data_table.handle_found_index_file( options.missing_index_file ) - missing_files_handled.append( missing_tail ) + sample_files_copied.append( options.missing_index_file ) break # Reload the tool into the local list of repository_tools_tups. repository_tool = app.toolbox.load_tool( os.path.join( tool_path, tup_path ), guid=guid ) repository_tools_tups[ index ] = ( tup_path, guid, repository_tool ) - return repository_tools_tups + return repository_tools_tups, sample_files_copied def handle_sample_tool_data_table_conf_file( app, filename ): """ Parse the incoming filename and add new entries to the in-memory @@ -1038,7 +1038,8 @@ # Load or deactivate proprietary datatype display applications app.datatypes_registry.load_display_applications( installed_repository_dict=repository_dict, deactivate=deactivate ) def load_repository_contents( trans, repository_name, description, owner, changeset_revision, ctx_rev, tool_path, repository_clone_url, - relative_install_dir, current_working_dir, tool_shed=None, tool_section=None, shed_tool_conf=None ): + relative_install_dir, current_working_dir, tool_shed=None, tool_section=None, shed_tool_conf=None, + install_tool_dependencies=False ): """Generate the metadata for the installed tool shed repository, among other things.""" # It is critical that the installed repository is updated to the desired changeset_revision before metadata is set because the # process for setting metadata uses the repository files on disk. This method is called when an admin is installing a new repository @@ -1063,8 +1064,9 @@ # Handle missing data table entries for tool parameters that are dynamically generated select lists. repository_tools_tups = handle_missing_data_table_entry( trans.app, tool_path, sample_files, repository_tools_tups ) # Handle missing index files for tool parameters that are dynamically generated select lists. - repository_tools_tups = handle_missing_index_file( trans.app, tool_path, sample_files, repository_tools_tups ) - # Handle tools that use fabric scripts to install dependencies. + repository_tools_tups, sample_files_copied = handle_missing_index_file( trans.app, tool_path, sample_files, repository_tools_tups ) + # Copy remaining sample files included in the repository to the ~/tool-data directory of the local Galaxy instance. + copy_sample_files( trans.app, sample_files, sample_files_copied=sample_files_copied ) handle_tool_dependencies( current_working_dir, relative_install_dir, repository_tools_tups ) add_to_tool_panel( app=trans.app, repository_name=repository_name, diff -r 71dfeecdd019554b5cccc047546ae26ed7b50afa -r ea9f3c25a41576216f3c328e3333ebdb55250ed1 lib/galaxy/webapps/community/controllers/common.py --- a/lib/galaxy/webapps/community/controllers/common.py +++ b/lib/galaxy/webapps/community/controllers/common.py @@ -5,7 +5,7 @@ from galaxy.tools import * from galaxy.util.json import from_json_string, to_json_string from galaxy.util.hash_util import * -from galaxy.util.shed_util import copy_sample_loc_file, get_configured_ui, generate_datatypes_metadata, generate_tool_metadata, generate_workflow_metadata +from galaxy.util.shed_util import copy_sample_file, get_configured_ui, generate_datatypes_metadata, generate_tool_metadata, generate_workflow_metadata from galaxy.util.shed_util import handle_sample_tool_data_table_conf_file, to_html_escaped, to_html_str, update_repository from galaxy.web.base.controller import * from galaxy.webapps.community import model @@ -209,13 +209,13 @@ if options.index_file or options.missing_index_file: # Make sure the repository contains the required xxx.loc.sample file. index_file = options.index_file or options.missing_index_file - index_head, index_tail = os.path.split( index_file ) + index_file_path, index_file_name = os.path.split( index_file ) sample_found = False for sample_file in sample_files: - sample_head, sample_tail = os.path.split( sample_file ) - if sample_tail == '%s.sample' % index_tail: - copy_sample_loc_file( trans.app, sample_file ) - options.index_file = index_tail + sample_file_path, sample_file_name = os.path.split( sample_file ) + if sample_file_name == '%s.sample' % index_file_name: + copy_sample_file( trans.app, sample_file ) + options.index_file = index_file_name options.missing_index_file = None if options.tool_data_table: options.tool_data_table.missing_index_file = None @@ -224,7 +224,7 @@ if not sample_found: can_set_metadata = False correction_msg = "This file refers to a file named <b>%s</b>. " % str( index_file ) - correction_msg += "Upload a file named <b>%s.sample</b> to the repository to correct this error." % str( index_tail ) + correction_msg += "Upload a file named <b>%s.sample</b> to the repository to correct this error." % str( index_file_name ) invalid_files.append( ( name, correction_msg ) ) return can_set_metadata, invalid_files def new_tool_metadata_required( trans, id, metadata_dict ): @@ -283,8 +283,7 @@ else: # There is no saved repository metadata, so we need to create a new repository_metadata table record. return True - # The received metadata_dict includes no metadata for workflows, so a new repository_metadata table - # record is not needed. + # The received metadata_dict includes no metadata for workflows, so a new repository_metadata table record is not needed. return False def generate_metadata_for_repository_tip( trans, id, ctx, changeset_revision, repo, repo_dir ): """ diff -r 71dfeecdd019554b5cccc047546ae26ed7b50afa -r ea9f3c25a41576216f3c328e3333ebdb55250ed1 lib/galaxy/webapps/community/controllers/upload.py --- a/lib/galaxy/webapps/community/controllers/upload.py +++ b/lib/galaxy/webapps/community/controllers/upload.py @@ -139,9 +139,8 @@ if error: message = '%s<br/>%s' % ( message, error_message ) if full_path.endswith( '.loc.sample' ): - # Handle the special case where a xxx.loc.sample file is - # being uploaded by copying it to ~/tool-data/xxx.loc. - copy_sample_loc_file( trans.app, full_path ) + # Handle the special case where a xxx.loc.sample file is being uploaded by copying it to ~/tool-data/xxx.loc. + copy_sample_file( trans.app, full_path ) # See if the content of the change set was valid. admin_only = len( repository.downloadable_revisions ) != 1 handle_email_alerts( trans, repository, content_alert_str=content_alert_str, new_repo_alert=new_repo_alert, admin_only=admin_only ) @@ -295,9 +294,8 @@ if error: return False, message, files_to_remove, content_alert_str if filename_in_archive.endswith( '.loc.sample' ): - # Handle the special case where a xxx.loc.sample file is - # being uploaded by copying it to ~/tool-data/xxx.loc. - copy_sample_loc_file( trans.app, filename_in_archive ) + # Handle the special case where a xxx.loc.sample file is being uploaded by copying it to ~/tool-data/xxx.loc. + copy_sample_file( trans.app, filename_in_archive ) try: commands.commit( repo.ui, repo, full_path, user=trans.user.username, message=commit_message ) except Exception, e: Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dan: Allow GenomeSpace importer tool to sniff filetype when GSMetadata object is not available.
by Bitbucket 03 May '12

03 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/71dfeecdd019/ changeset: 71dfeecdd019 user: dan date: 2012-05-03 18:25:06 summary: Allow GenomeSpace importer tool to sniff filetype when GSMetadata object is not available. affected #: 1 file diff -r 4d7077d8d2b875feed71fa8c9ab7bd701957b909 -r 71dfeecdd019554b5cccc047546ae26ed7b50afa tools/genomespace/genomespace_importer.py --- a/tools/genomespace/genomespace_importer.py +++ b/tools/genomespace/genomespace_importer.py @@ -1,6 +1,6 @@ #Dan Blankenberg -import optparse, os, urllib2, urllib, cookielib, urlparse +import optparse, os, urllib2, urllib, cookielib, urlparse, tempfile, shutil from galaxy import eggs import pkg_resources @@ -8,6 +8,10 @@ pkg_resources.require( "simplejson" ) import simplejson +import galaxy.model # need to import model before sniff to resolve a circular import dependency +from galaxy.datatypes import sniff +from galaxy.datatypes.registry import Registry + GENOMESPACE_API_VERSION_STRING = "v1.0" GENOMESPACE_SERVER_URL_PROPERTIES = "http://www.genomespace.org/sites/genomespacefiles/config/serverurl.properti…" @@ -61,13 +65,13 @@ cookie_opener = urllib2.build_opener( urllib2.HTTPCookieProcessor( cj ) ) return cookie_opener -def get_galaxy_ext_from_genomespace_format_url( url_opener, file_format_url ): +def get_galaxy_ext_from_genomespace_format_url( url_opener, file_format_url, default = DEFAULT_GALAXY_EXT ): ext = GENOMESPACE_FORMAT_IDENTIFIER_TO_GENOMESPACE_EXT.get( file_format_url, None ) if ext is not None: ext = GENOMESPACE_EXT_TO_GALAXY_EXT.get( ext, None ) if ext is None: #could check content type, etc here - ext = DEFAULT_GALAXY_EXT + ext = default return ext def get_genomespace_site_urls(): @@ -94,8 +98,6 @@ def download_from_genomespace_importer( username, token, json_parameter_file, genomespace_site ): json_params = simplejson.loads( open( json_parameter_file, 'r' ).read() ) datasource_params = json_params.get( 'param_dict' ) - #username = datasource_params.get( "gs-username", None ) - #token = datasource_params.get( "gs-token", None ) assert None not in [ username, token ], "Missing GenomeSpace username or token." output_filename = datasource_params.get( "output_file1", None ) dataset_id = json_params['output_data'][0]['dataset_id'] @@ -106,17 +108,15 @@ set_genomespace_format_identifiers( url_opener, genomespace_site_dict['dmServer'] ) file_url_name = "URL" metadata_parameter_file = open( json_params['job_config']['TOOL_PROVIDED_JOB_METADATA_FILE'], 'wb' ) + #setup datatypes registry for sniffing + datatypes_registry = Registry() + datatypes_registry.load_datatypes( root_dir = json_params[ 'job_config' ][ 'GALAXY_ROOT_DIR' ], config = json_params[ 'job_config' ][ 'GALAXY_DATATYPES_CONF_FILE' ] ) url_param = datasource_params.get( file_url_name, None ) for download_url in url_param.split( ',' ): + using_temp_file = False parsed_url = urlparse.urlparse( download_url ) query_params = urlparse.parse_qs( parsed_url[4] ) - file_type = DEFAULT_GALAXY_EXT - if 'dataformat' in query_params: - file_type = query_params[ 'dataformat' ][0] - file_type = get_galaxy_ext_from_genomespace_format_url( url_opener, file_type ) - elif '.' in parsed_url[2]: - file_type = parsed_url[2].rsplit( '.', 1 )[-1] - file_type = GENOMESPACE_EXT_TO_GALAXY_EXT.get( file_type, file_type ) + #write file to disk new_file_request = urllib2.Request( download_url ) new_file_request.get_method = lambda: 'GET' target_download_url = url_opener.open( new_file_request ) @@ -130,16 +130,58 @@ query_params = urlparse.parse_qs( parsed_url[4] ) filename = urllib.unquote_plus( parsed_url[2].split( '/' )[-1] ) if output_filename is None: - output_filename = os.path.join( datasource_params['__new_file_path__'], 'primary_%i_output%s_visible_%s' % ( hda_id, ''.join( c in VALID_CHARS and c or '-' for c in filename ), file_type ) ) - else: - if dataset_id is not None: - metadata_parameter_file.write( "%s\n" % simplejson.dumps( dict( type = 'dataset', - dataset_id = dataset_id, - ext = file_type, - name = "GenomeSpace importer on %s" % ( filename ) ) ) ) + #need to use a temp file here, because we do not know the ext yet + using_temp_file = True + output_filename = tempfile.NamedTemporaryFile( prefix='tmp-genomespace-importer-' ).name output_file = open( output_filename, 'wb' ) chunk_write( target_download_url, output_file ) output_file.close() + + #determine file format + file_type = None + if 'dataformat' in query_params: #this is a converted dataset + file_type = query_params[ 'dataformat' ][0] + file_type = get_galaxy_ext_from_genomespace_format_url( url_opener, file_type ) + else: + try: + #get and use GSMetadata object + download_file_path = download_url.split( "%s/file/" % ( genomespace_site_dict['dmServer'] ), 1)[-1] #FIXME: This is a very bad way to get the path for determining metadata. There needs to be a way to query API using download URLto get to the metadata object + metadata_request = urllib2.Request( "%s/%s/filemetadata/%s" % ( genomespace_site_dict['dmServer'], GENOMESPACE_API_VERSION_STRING, download_file_path ) ) + metadata_request.get_method = lambda: 'GET' + metadata_url = url_opener.open( metadata_request ) + file_metadata_dict = simplejson.loads( metadata_url.read() ) + metadata_url.close() + file_type = file_metadata_dict.get( 'dataFormat', None ) + if file_type and file_type.get( 'url' ): + file_type = file_type.get( 'url' ) + file_type = get_galaxy_ext_from_genomespace_format_url( url_opener, file_type, default = None ) + except: + pass + if file_type is None: + #try to sniff datatype + try: + file_type = sniff.handle_uploaded_dataset_file( output_filename, datatypes_registry ) + except: + pass #sniff failed + if file_type is None and '.' in parsed_url[2]: + #still no known datatype, fall back to using extension + file_type = parsed_url[2].rsplit( '.', 1 )[-1] + file_type = GENOMESPACE_EXT_TO_GALAXY_EXT.get( file_type, file_type ) + if file_type is None: + #use default extension (e.g. 'data') + file_type = DEFAULT_GALAXY_EXT + + #save json info for single primary dataset + if dataset_id is not None: + metadata_parameter_file.write( "%s\n" % simplejson.dumps( dict( type = 'dataset', + dataset_id = dataset_id, + ext = file_type, + name = "GenomeSpace importer on %s" % ( filename ) ) ) ) + #if using tmp file, move the file to the new file path dir to get scooped up later + if using_temp_file: + shutil.move( output_filename, os.path.join( datasource_params['__new_file_path__'], 'primary_%i_output%s_visible_%s' % ( hda_id, ''.join( c in VALID_CHARS and c or '-' for c in filename ), file_type ) ) ) + + dataset_id = None #only one primary dataset available output_filename = None #only have one filename available metadata_parameter_file.close() return True Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: 2 new changesets
by Bitbucket 03 May '12

03 May '12

2 new commits in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/81e6e2f44d32/ changeset: 81e6e2f44d32 user: cjav date: 2012-05-03 01:30:11 summary: expose dataset full path through the API affected #: 1 file diff -r c5f3e218266e8b82cd509b9177461839c74971c3 -r 81e6e2f44d32845b8d48459ea779030d596c7c48 lib/galaxy/model/__init__.py --- a/lib/galaxy/model/__init__.py +++ b/lib/galaxy/model/__init__.py @@ -1167,6 +1167,7 @@ deleted = hda.deleted, visible = hda.visible, state = hda.state, + file_name = hda.file_name, file_size = int( hda.get_size() ), data_type = hda.ext, genome_build = hda.dbkey, https://bitbucket.org/galaxy/galaxy-central/changeset/4d7077d8d2b8/ changeset: 4d7077d8d2b8 user: dannon date: 2012-05-03 16:18:38 summary: Incorporation and slight update to pull request #43. The original contribution allowed access to file_path regardless of admin status and config setting. affected #: 2 files diff -r 81e6e2f44d32845b8d48459ea779030d596c7c48 -r 4d7077d8d2b875feed71fa8c9ab7bd701957b909 lib/galaxy/model/__init__.py --- a/lib/galaxy/model/__init__.py +++ b/lib/galaxy/model/__init__.py @@ -1167,7 +1167,6 @@ deleted = hda.deleted, visible = hda.visible, state = hda.state, - file_name = hda.file_name, file_size = int( hda.get_size() ), data_type = hda.ext, genome_build = hda.dbkey, diff -r 81e6e2f44d32845b8d48459ea779030d596c7c48 -r 4d7077d8d2b875feed71fa8c9ab7bd701957b909 lib/galaxy/web/api/history_contents.py --- a/lib/galaxy/web/api/history_contents.py +++ b/lib/galaxy/web/api/history_contents.py @@ -1,11 +1,9 @@ """ API operations on the contents of a history. """ -import logging, os, string, shutil, urllib, re, socket -from cgi import escape, FieldStorage -from galaxy import util, datatypes, jobs, web, util +import logging +from galaxy import web from galaxy.web.base.controller import * -from galaxy.util.sanitize_html import sanitize_html from galaxy.model.orm import * import pkg_resources @@ -56,6 +54,8 @@ return str( e ) try: item = content.get_api_value( view='element' ) + if trans.user_is_admin() or trans.app.config.expose_dataset_path: + item['file_name'] = hda.file_name if not item['deleted']: # Problem: Method url_for cannot use the dataset controller # Get the environment from DefaultWebTransaction and use default webapp mapper instead of webapp API mapper @@ -76,7 +76,6 @@ POST /api/libraries/{encoded_history_id}/contents Creates a new history content item (file, aka HistoryDatasetAssociation). """ - params = util.Params( payload ) from_ld_id = payload.get( 'from_ld_id', None ) try: Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dan: Update WormBase datasource tool to use WormBase 2.
by Bitbucket 02 May '12

02 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/c5f3e218266e/ changeset: c5f3e218266e user: dan date: 2012-05-02 23:04:33 summary: Update WormBase datasource tool to use WormBase 2. affected #: 1 file diff -r a781f132e259b60c417c674047535ac0a688b69d -r c5f3e218266e8b82cd509b9177461839c74971c3 tools/data_source/wormbase.xml --- a/tools/data_source/wormbase.xml +++ b/tools/data_source/wormbase.xml @@ -1,8 +1,8 @@ <?xml version="1.0"?> -<tool name="Wormbase" id="wormbase" tool_type="data_source"> +<tool name="WormBase" id="wormbase" tool_type="data_source" version="1.0.1"><description>server</description><command interpreter="python">data_source.py $output $__app__.config.output_size_limit</command> - <inputs action="http://www.wormbase.org/db/seq/gbgff/c_elegans/" check_values="false" target="_top"> + <inputs action="http://www.wormbase.org/tools/genome/gbrowse/c_elegans/" check_values="false" target="_top"><display>go to Wormbase server $GALAXY_URL</display><param name="GALAXY_URL" type="baseurl" value="/tool_runner?tool_id=wormbase" /></inputs> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dan: Fix typo in BAM slice tool.
by Bitbucket 02 May '12

02 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/a781f132e259/ changeset: a781f132e259 user: dan date: 2012-05-02 17:47:04 summary: Fix typo in BAM slice tool. affected #: 1 file diff -r 926c93b412beaaff5579e6faa2d052768e9408d1 -r a781f132e259b60c417c674047535ac0a688b69d tools/samtools/samtools_slice_bam.xml --- a/tools/samtools/samtools_slice_bam.xml +++ b/tools/samtools/samtools_slice_bam.xml @@ -20,7 +20,7 @@ <test><param name="input_bam" value="gatk/fake_phiX_reads_1.bam" ftype="bam" /><param name="input_interval" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" /> - <output name="output_log" file="gatk/fake_phiX_reads_1.bam" ftype="bam" /> + <output name="output_bam" file="gatk/fake_phiX_reads_1.bam" ftype="bam" /></test></tests><help> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dan: Add Slice BAM by regions tool.
by Bitbucket 02 May '12

02 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/926c93b412be/ changeset: 926c93b412be user: dan date: 2012-05-02 17:32:19 summary: Add Slice BAM by regions tool. affected #: 3 files diff -r 5e53e5d824009984629a269b9d768b99b5683310 -r 926c93b412beaaff5579e6faa2d052768e9408d1 tool_conf.xml.sample --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -384,6 +384,7 @@ <tool file="samtools/pileup_interval.xml" /><tool file="samtools/samtools_flagstat.xml" /><tool file="samtools/samtools_rmdup.xml" /> + <tool file="samtools/samtools_slice_bam.xml" /></section><section name="NGS: GATK Tools (beta)" id="gatk"><label text="Alignment Utilities" id="gatk_bam_utilities"/> diff -r 5e53e5d824009984629a269b9d768b99b5683310 -r 926c93b412beaaff5579e6faa2d052768e9408d1 tools/samtools/samtools_slice_bam.py --- /dev/null +++ b/tools/samtools/samtools_slice_bam.py @@ -0,0 +1,75 @@ +#!/usr/bin/env python +#Dan Blankenberg + +""" +A wrapper script for slicing a BAM file by provided BED file using SAMTools. +%prog input_filename.sam output_filename.bam +""" +#TODO: Confirm that the sort is necessary e.g. if input regions are out of order + + +import sys, optparse, os, tempfile, subprocess, shutil + +CHUNK_SIZE = 2**20 #1mb + +def cleanup_before_exit( tmp_dir ): + if tmp_dir and os.path.exists( tmp_dir ): + shutil.rmtree( tmp_dir ) + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + (options, args) = parser.parse_args() + + assert len( args ) == 4, "Invalid command line: samtools_slice_bam.py input.bam input.bam.bai input.interval output.bam" + input_bam_filename, input_index_filename, input_interval_filename, output_bam_filename = args + + tmp_dir = tempfile.mkdtemp( prefix='tmp-samtools_slice_bam-' ) + + tmp_input_bam_filename = os.path.join( tmp_dir, 'input_bam.bam' ) + os.symlink( input_bam_filename, tmp_input_bam_filename ) + os.symlink( input_index_filename, "%s.bai" % tmp_input_bam_filename ) + + #Slice BAM + unsorted_bam_filename = os.path.join( tmp_dir, 'unsorted.bam' ) + unsorted_stderr_filename = os.path.join( tmp_dir, 'unsorted.stderr' ) + cmd = 'samtools view -b -L "%s" "%s" > "%s"' % ( input_interval_filename, tmp_input_bam_filename, unsorted_bam_filename ) + proc = subprocess.Popen( args=cmd, stderr=open( unsorted_stderr_filename, 'wb' ), shell=True, cwd=tmp_dir ) + return_code = proc.wait() + if return_code: + stderr_target = sys.stderr + else: + stderr_target = sys.stdout + stderr = open( unsorted_stderr_filename ) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + + #sort sam, so indexing will not fail + #TODO: confirm if sorting is necessary (is original BAM order maintained, or does the output follow the order of input intervals?) + sorted_stderr_filename = os.path.join( tmp_dir, 'sorted.stderr' ) + sorting_prefix = os.path.join( tmp_dir, 'sorted_bam' ) + cmd = 'samtools sort -o "%s" "%s" > "%s"' % ( unsorted_bam_filename, sorting_prefix, output_bam_filename ) + proc = subprocess.Popen( args=cmd, stderr=open( sorted_stderr_filename, 'wb' ), shell=True, cwd=tmp_dir ) + return_code = proc.wait() + + if return_code: + stderr_target = sys.stderr + else: + stderr_target = sys.stdout + stderr = open( sorted_stderr_filename ) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + + cleanup_before_exit( tmp_dir ) + +if __name__=="__main__": __main__() diff -r 5e53e5d824009984629a269b9d768b99b5683310 -r 926c93b412beaaff5579e6faa2d052768e9408d1 tools/samtools/samtools_slice_bam.xml --- /dev/null +++ b/tools/samtools/samtools_slice_bam.xml @@ -0,0 +1,40 @@ +<tool id="samtools_slice_bam" name="Slice BAM" version="0.0.1"> + <description>by provided regions</description> + <requirements> + <requirement type="package">samtools</requirement> + </requirements> + <command interpreter="python">samtools_slice_bam.py + "${input_bam}" + "${input_bam.metadata.bam_index}" + "${input_interval}" + "${output_bam}" + </command> + <inputs> + <param name="input_bam" type="data" format="bam" label="BAM file" /> + <param name="input_interval" type="data" format="bed" label="BED file" /> + </inputs> + <outputs> + <data format="bam" name="output_bam"/> + </outputs> + <tests> + <test> + <param name="input_bam" value="gatk/fake_phiX_reads_1.bam" ftype="bam" /> + <param name="input_interval" value="gatk/fake_phiX_variant_locations.bed" ftype="bed" /> + <output name="output_log" file="gatk/fake_phiX_reads_1.bam" ftype="bam" /> + </test> + </tests> + <help> +**What it does** + + Accepts an input BAM file and an input BED file and creates an output BAM file containing only those alignments that overlap the provided BED intervals. + +------ + +**Citation** + +For the underlying tool, please cite `Li H, Handsaker B, Wysoker A, Fennell T, Ruan J, Homer N, Marth G, Abecasis G, Durbin R; 1000 Genome Project Data Processing Subgroup. The Sequence Alignment/Map format and SAMtools. Bioinformatics. 2009 Aug 15;25(16):2078-9. <http://www.ncbi.nlm.nih.gov/pubmed/19505943>`_ + +If you use this tool in Galaxy, please cite Blankenberg D, et al. *In preparation.* + + </help> +</tool> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: greg: Fix popup menu for viewing tool metadata in a tool shed repository to be compatible with new styles.
by Bitbucket 01 May '12

01 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/5e53e5d82400/ changeset: 5e53e5d82400 user: greg date: 2012-05-01 18:17:07 summary: Fix popup menu for viewing tool metadata in a tool shed repository to be compatible with new styles. affected #: 1 file diff -r 49b5dc00dfb6ef3bf0f4bb1f611db33042469181 -r 5e53e5d824009984629a269b9d768b99b5683310 templates/webapps/community/repository/common.mako --- a/templates/webapps/community/repository/common.mako +++ b/templates/webapps/community/repository/common.mako @@ -108,15 +108,13 @@ <td><b>version</b></td><td><b>requirements</b></td></tr> - %for tool_dict in tool_dicts: + %for index, tool_dict in enumerate( tool_dicts ): <tr><td> - <div style="float: left; margin-left: 1px;" class="menubutton split popup" id="tool-${tool_dict[ 'id' ].replace( ' ', '_' )}-popup"> - <a class="view-info" href="${h.url_for( controller='repository', action='display_tool', repository_id=trans.security.encode_id( repository.id ), tool_config=tool_dict[ 'tool_config' ], changeset_revision=changeset_revision, webapp=webapp )}"> - ${tool_dict[ 'name' ]} - </a> + <div style="float:left;" class="menubutton split popup" id="tool-${index}-popup"> + <a class="view-info" href="${h.url_for( controller='repository', action='display_tool', repository_id=trans.security.encode_id( repository.id ), tool_config=tool_dict[ 'tool_config' ], changeset_revision=changeset_revision, webapp=webapp )}">${tool_dict[ 'name' ]}</a></div> - <div popupmenu="tool-${tool_dict[ 'id' ].replace( ' ', '_' )}-popup"> + <div popupmenu="tool-${index}-popup"><a class="action-button" href="${h.url_for( controller='repository', action='view_tool_metadata', repository_id=trans.security.encode_id( repository.id ), changeset_revision=changeset_revision, tool_id=tool_dict[ 'id' ], webapp=webapp )}">View tool metadata</a></div></td> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: greg: Eliminate the fabfile/method type from ToolRequirement.
by Bitbucket 01 May '12

01 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/49b5dc00dfb6/ changeset: 49b5dc00dfb6 user: greg date: 2012-05-01 15:15:59 summary: Eliminate the fabfile/method type from ToolRequirement. affected #: 1 file diff -r 0090f9df64fd84a9fda73d12b816a7d4d044b822 -r 49b5dc00dfb6ef3bf0f4bb1f611db33042469181 lib/galaxy/tools/__init__.py --- a/lib/galaxy/tools/__init__.py +++ b/lib/galaxy/tools/__init__.py @@ -702,19 +702,13 @@ class ToolRequirement( object ): """ - Represents an external requirement that must be available for the tool to - run (for example, a program, package, or library). Requirements can - optionally assert a specific version, or reference a command to execute a - fabric script. If fabric is used, the type is 'fabfile' and the version - attribute is not used since the fabric script includes all necessary - information for automatic dependency installation. + Represents an external requirement that must be available for the tool to run (for example, a program, package, or library). + Requirements can optionally assert a specific version. """ - def __init__( self, name=None, type=None, version=None, fabfile=None, method=None ): + def __init__( self, name=None, type=None, version=None ): self.name = name self.type = type self.version = version - self.fabfile = fabfile - self.method = method class ToolParallelismInfo(object): """ @@ -1339,19 +1333,8 @@ for requirement_elem in requirements_elem.findall( 'requirement' ): name = util.xml_text( requirement_elem ) type = requirement_elem.get( "type", "package" ) - if type == 'fabfile': - # The fabric script will include all necessary information for - # automatically installing the tool dependencies. - fabfile = requirement_elem.get( "fabfile" ) - method = requirement_elem.get( "method" ) - version = None - else: - # For backward compatibility, requirements tag sets should not require the - # use of a fabric script. - version = requirement_elem.get( "version" ) - fabfile = None - method = None - requirement = ToolRequirement( name=name, type=type, version=version, fabfile=fabfile, method=method ) + version = requirement_elem.get( "version", None ) + requirement = ToolRequirement( name=name, type=type, version=version ) self.requirements.append( requirement ) def check_workflow_compatible( self ): """ Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: greg: Fix the instructions on the veiw request type page.
by Bitbucket 01 May '12

01 May '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/0090f9df64fd/ changeset: 0090f9df64fd user: greg date: 2012-05-01 15:11:07 summary: Fix the instructions on the veiw request type page. affected #: 1 file diff -r 1640cbaafd09a3cb4bcdea55d95c43d619a0471f -r 0090f9df64fd84a9fda73d12b816a7d4d044b822 templates/admin/request_type/view_request_type.mako --- a/templates/admin/request_type/view_request_type.mako +++ b/templates/admin/request_type/view_request_type.mako @@ -73,7 +73,7 @@ %endfor %else: <div class="form-row"> - External service login information is not set. Select the <b>Edit request type</b> option in the <b>Configuration options</b> menu. + External service login information is not set. Select the <b>Edit request type</b> option in the <b>Request type actions</b> menu. </div> %endif </div> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: natefoo: Allow for library deletion from the API (admins only).
by Bitbucket 30 Apr '12

30 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/1640cbaafd09/ changeset: 1640cbaafd09 user: natefoo date: 2012-04-30 22:27:55 summary: Allow for library deletion from the API (admins only). affected #: 2 files diff -r 4ff0dd2aa475275a13c65f183c4bb2595f001941 -r 1640cbaafd09a3cb4bcdea55d95c43d619a0471f lib/galaxy/web/api/libraries.py --- a/lib/galaxy/web/api/libraries.py +++ b/lib/galaxy/web/api/libraries.py @@ -7,18 +7,27 @@ from galaxy.web.base.controller import * from galaxy.util.sanitize_html import sanitize_html from galaxy.model.orm import * +from paste.httpexceptions import * log = logging.getLogger( __name__ ) class LibrariesController( BaseAPIController ): @web.expose_api - def index( self, trans, **kwd ): + def index( self, trans, deleted='False', **kwd ): """ GET /api/libraries + GET /api/libraries/deleted Displays a collection (list) of libraries. """ - query = trans.sa_session.query( trans.app.model.Library ).filter( trans.app.model.Library.table.c.deleted == False ) + query = trans.sa_session.query( trans.app.model.Library ) + deleted = util.string_as_bool( deleted ) + if deleted: + route = 'deleted_library' + query = query.filter( trans.app.model.Library.table.c.deleted == True ) + else: + route = 'library' + query = query.filter( trans.app.model.Library.table.c.deleted == False ) current_user_role_ids = [ role.id for role in trans.get_current_user_roles() ] library_access_action = trans.app.security_agent.permitted_actions.LIBRARY_ACCESS.action restricted_library_ids = [ lp.library_id for lp in trans.sa_session.query( trans.model.LibraryPermissions ) \ @@ -32,31 +41,32 @@ rval = [] for library in query: item = library.get_api_value() - item['url'] = url_for( 'library', id=trans.security.encode_id( library.id ) ) + item['url'] = url_for( route, id=trans.security.encode_id( library.id ) ) item['id'] = trans.security.encode_id( item['id'] ) rval.append( item ) return rval @web.expose_api - def show( self, trans, id, **kwd ): + def show( self, trans, id, deleted='False', **kwd ): """ GET /api/libraries/{encoded_library_id} + GET /api/libraries/deleted/{encoded_library_id} Displays information about a library. """ library_id = id + deleted = util.string_as_bool( deleted ) params = util.Params( kwd ) try: decoded_library_id = trans.security.decode_id( library_id ) except TypeError: - trans.response.status = 400 - return "Malformed library id ( %s ) specified, unable to decode." % str( library_id ) + raise HTTPBadRequest( detail='Malformed library id ( %s ) specified, unable to decode.' % id ) try: library = trans.sa_session.query( trans.app.model.Library ).get( decoded_library_id ) + assert library.deleted == deleted except: library = None if not library or not ( trans.user_is_admin() or trans.app.security_agent.can_access_library( trans.get_current_user_roles(), library ) ): - trans.response.status = 400 - return "Invalid library id ( %s ) specified." % str( library_id ) + raise HTTPBadRequest( detail='Invalid library id ( %s ) specified.' % id ) item = library.get_api_value( view='element' ) #item['contents_url'] = url_for( 'contents', library_id=library_id ) item['contents_url'] = url_for( 'library_contents', library_id=library_id ) @@ -69,13 +79,11 @@ Creates a new library. """ if not trans.user_is_admin(): - trans.response.status = 403 - return "You are not authorized to create a new library." + raise HTTPForbidden( detail='You are not authorized to create a new library.' ) params = util.Params( payload ) name = util.restore_text( params.get( 'name', None ) ) if not name: - trans.response.status = 400 - return "Missing required parameter 'name'." + raise HTTPBadRequest( detail="Missing required parameter 'name'." ) description = util.restore_text( params.get( 'description', '' ) ) synopsis = util.restore_text( params.get( 'synopsis', '' ) ) if synopsis in [ 'None', None ]: @@ -91,3 +99,22 @@ rval['name'] = name rval['id'] = encoded_id return [ rval ] + + @web.expose_api + def delete( self, trans, id, **kwd ): + if not trans.user_is_admin(): + raise HTTPForbidden( detail='You are not authorized to delete libraries.' ) + try: + decoded_id = trans.security.decode_id( id ) + except TypeError: + raise HTTPBadRequest( detail='Malformed library id ( %s ) specified, unable to decode.' % id ) + try: + library = trans.sa_session.query( trans.app.model.Library ).get( decoded_id ) + except: + library = None + if not library: + raise HTTPBadRequest( detail='Invalid library id ( %s ) specified.' % id ) + library.deleted = True + trans.sa_session.add( library ) + trans.sa_session.flush() + return library.get_api_value( view='element', value_mapper={ 'id' : trans.security.encode_id } ) diff -r 4ff0dd2aa475275a13c65f183c4bb2595f001941 -r 1640cbaafd09a3cb4bcdea55d95c43d619a0471f lib/galaxy/web/buildapp.py --- a/lib/galaxy/web/buildapp.py +++ b/lib/galaxy/web/buildapp.py @@ -123,7 +123,7 @@ path_prefix='/api/libraries/:library_id', parent_resources=dict( member_name='library', collection_name='libraries' ) ) webapp.api_mapper.resource( 'dataset', 'datasets', path_prefix='/api' ) - webapp.api_mapper.resource( 'library', 'libraries', path_prefix='/api' ) + webapp.api_mapper.resource_with_deleted( 'library', 'libraries', path_prefix='/api' ) webapp.api_mapper.resource( 'sample', 'samples', path_prefix='/api' ) webapp.api_mapper.resource( 'request', 'requests', path_prefix='/api' ) webapp.api_mapper.resource( 'form', 'forms', path_prefix='/api' ) Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: greg: Eliminate resetting all repository metadata on a tool shed repostiory when its not necessary.
by Bitbucket 30 Apr '12

30 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/4ff0dd2aa475/ changeset: 4ff0dd2aa475 user: greg date: 2012-04-30 20:42:39 summary: Eliminate resetting all repository metadata on a tool shed repostiory when its not necessary. affected #: 4 files diff -r 559105c554d540d8137d6583c58b2e237fe1eff4 -r 4ff0dd2aa475275a13c65f183c4bb2595f001941 lib/galaxy/tool_shed/update_manager.py --- a/lib/galaxy/tool_shed/update_manager.py +++ b/lib/galaxy/tool_shed/update_manager.py @@ -34,7 +34,7 @@ log.info( 'Transfer job restarter shutting down...' ) def check_for_update( self, repository ): tool_shed_url = get_url_from_repository_tool_shed( self.app, repository ) - url = '%s/repository/check_for_updates?name=%s&owner=%s&changeset_revision=%s&webapp=update_manager' % \ + url = '%s/repository/check_for_updates?name=%s&owner=%s&changeset_revision=%s&webapp=update_manager&no_reset=true' % \ ( tool_shed_url, repository.name, repository.owner, repository.changeset_revision ) response = urllib2.urlopen( url ) text = response.read() diff -r 559105c554d540d8137d6583c58b2e237fe1eff4 -r 4ff0dd2aa475275a13c65f183c4bb2595f001941 lib/galaxy/web/controllers/admin_toolshed.py --- a/lib/galaxy/web/controllers/admin_toolshed.py +++ b/lib/galaxy/web/controllers/admin_toolshed.py @@ -149,7 +149,7 @@ def browse_tool_shed( self, trans, **kwd ): tool_shed_url = kwd[ 'tool_shed_url' ] galaxy_url = url_for( '/', qualified=True ) - url = '%srepository/browse_valid_repositories?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) + url = '%srepository/browse_valid_repositories?galaxy_url=%s&webapp=galaxy&no_reset=true' % ( tool_shed_url, galaxy_url ) return trans.response.send_redirect( url ) @web.expose @web.require_admin @@ -167,7 +167,7 @@ # Send a request to the relevant tool shed to see if there are any updates. repository = get_repository( trans, kwd[ 'id' ] ) tool_shed_url = get_url_from_repository_tool_shed( trans.app, repository ) - url = '%s/repository/check_for_updates?galaxy_url=%s&name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % \ + url = '%s/repository/check_for_updates?galaxy_url=%s&name=%s&owner=%s&changeset_revision=%s&webapp=galaxy&no_reset=true' % \ ( tool_shed_url, url_for( '/', qualified=True ), repository.name, repository.owner, repository.changeset_revision ) return trans.response.send_redirect( url ) @web.expose @@ -218,14 +218,14 @@ def find_tools_in_tool_shed( self, trans, **kwd ): tool_shed_url = kwd[ 'tool_shed_url' ] galaxy_url = url_for( '/', qualified=True ) - url = '%srepository/find_tools?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) + url = '%srepository/find_tools?galaxy_url=%s&webapp=galaxy&no_reset=true' % ( tool_shed_url, galaxy_url ) return trans.response.send_redirect( url ) @web.expose @web.require_admin def find_workflows_in_tool_shed( self, trans, **kwd ): tool_shed_url = kwd[ 'tool_shed_url' ] galaxy_url = url_for( '/', qualified=True ) - url = '%srepository/find_workflows?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) + url = '%srepository/find_workflows?galaxy_url=%s&webapp=galaxy&no_reset=true' % ( tool_shed_url, galaxy_url ) return trans.response.send_redirect( url ) @web.expose @web.require_admin @@ -318,7 +318,7 @@ shed_tool_conf=shed_tool_conf ) if 'tools' in metadata_dict: # Get the tool_versions from the tool shed for each tool in the installed change set. - url = '%srepository/get_tool_versions?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % \ + url = '%srepository/get_tool_versions?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy&no_reset=true' % \ ( tool_shed_url, name, owner, changeset_revision ) response = urllib2.urlopen( url ) text = response.read() @@ -367,7 +367,7 @@ repo_info_tuple = decoded_repo_info_dict[ name ] description, repository_clone_url, changeset_revision, ctx_rev = repo_info_tuple owner = get_repository_owner( clean_repository_clone_url( repository_clone_url ) ) - url = '%srepository/get_readme?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % ( tool_shed_url, name, owner, changeset_revision ) + url = '%srepository/get_readme?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy&no_reset=true' % ( tool_shed_url, name, owner, changeset_revision ) response = urllib2.urlopen( url ) raw_text = response.read() response.close() @@ -564,7 +564,7 @@ # Get the tool_versions from the tool shed for each tool in the installed change set. repository = get_repository( trans, kwd[ 'id' ] ) tool_shed_url = get_url_from_repository_tool_shed( trans.app, repository ) - url = '%s/repository/get_tool_versions?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % \ + url = '%s/repository/get_tool_versions?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy&no_reset=true' % \ ( tool_shed_url, repository.name, repository.owner, repository.changeset_revision ) response = urllib2.urlopen( url ) text = response.read() diff -r 559105c554d540d8137d6583c58b2e237fe1eff4 -r 4ff0dd2aa475275a13c65f183c4bb2595f001941 lib/galaxy/web/controllers/workflow.py --- a/lib/galaxy/web/controllers/workflow.py +++ b/lib/galaxy/web/controllers/workflow.py @@ -1145,7 +1145,7 @@ import_button = True if tool_shed_url and not import_button: # Use urllib (send another request to the tool shed) to retrieve the workflow. - workflow_url = '%s/workflow/import_workflow?repository_metadata_id=%s&workflow_name=%s&webapp=%s&open_for_url=true' % \ + workflow_url = '%s/workflow/import_workflow?repository_metadata_id=%s&workflow_name=%s&webapp=%s&open_for_url=true&no_reset=true' % \ ( tool_shed_url, repository_metadata_id, tool_shed_encode( workflow_name ), webapp ) response = urllib2.urlopen( workflow_url ) workflow_text = response.read() diff -r 559105c554d540d8137d6583c58b2e237fe1eff4 -r 4ff0dd2aa475275a13c65f183c4bb2595f001941 lib/galaxy/webapps/community/controllers/hg.py --- a/lib/galaxy/webapps/community/controllers/hg.py +++ b/lib/galaxy/webapps/community/controllers/hg.py @@ -16,8 +16,10 @@ # hg clone http://test@127.0.0.1:9009/repos/test/convert_characters1 cmd = kwd.get( 'cmd', None ) wsgi_app = wsgiapplication( make_web_app ) - if cmd == 'listkeys': - # This results from an "hg push" from the command line. When doing this, the following 7 commands, in order, + # Hack: Add a parameter to requests for which we do not want all repository metadata reset. + reset_metadata = not ( kwd.get( 'no_reset', False ) ) + if cmd == 'listkeys' and reset_metadata: + # This possibly results from an "hg push" from the command line. When doing this, the following 7 commands, in order, # will be retrieved from environ: between -> capabilities -> heads -> branchmap -> unbundle -> unbundle -> listkeys path_info = kwd.get( 'path_info', None ) if path_info: Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dannon: Extract workflow - fix nested dataset input mapping.
by Bitbucket 30 Apr '12

30 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/559105c554d5/ changeset: 559105c554d5 user: dannon date: 2012-04-30 18:16:09 summary: Extract workflow - fix nested dataset input mapping. affected #: 1 file diff -r c542aecc608617645d31c6ce9775f31a93c10bef -r 559105c554d540d8137d6583c58b2e237fe1eff4 lib/galaxy/web/controllers/workflow.py --- a/lib/galaxy/web/controllers/workflow.py +++ b/lib/galaxy/web/controllers/workflow.py @@ -1338,11 +1338,6 @@ tool = trans.app.toolbox.get_tool( job.tool_id ) param_values = job.get_param_values( trans.app ) associations = cleanup_param_values( tool.inputs, param_values ) - # Doing it this way breaks dynamic parameters, backed out temporarily. - # def extract_callback( input, value, prefixed_name, prefixed_label ): - # if isinstance( value, UnvalidatedValue ): - # return str( value ) - # visit_input_values( tool.inputs, param_values, extract_callback ) step = model.WorkflowStep() step.type = 'tool' step.tool_id = job.tool_id @@ -2043,13 +2038,11 @@ group_values = values[key] for i, rep_values in enumerate( group_values ): rep_index = rep_values['__index__'] - prefix = "%s_%d|" % ( key, rep_index ) - cleanup( prefix, input.inputs, group_values[i] ) + cleanup( "%s%s_%d|" % (prefix, key, rep_index ), input.inputs, group_values[i] ) elif isinstance( input, Conditional ): group_values = values[input.name] current_case = group_values['__current_case__'] - prefix = "%s|" % ( key ) - cleanup( prefix, input.cases[current_case].inputs, group_values ) + cleanup( "%s%s|" % ( prefix, key ), input.cases[current_case].inputs, group_values ) cleanup( "", inputs, values ) return associations Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: jgoecks: Revert Tophat wrapper version #.
by Bitbucket 30 Apr '12

30 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/c542aecc6086/ changeset: c542aecc6086 user: jgoecks date: 2012-04-30 17:46:43 summary: Revert Tophat wrapper version #. affected #: 1 file diff -r 62c900962bb5bd943e2717a7ba74162364b18e1e -r c542aecc608617645d31c6ce9775f31a93c10bef tools/ngs_rna/tophat_wrapper.xml --- a/tools/ngs_rna/tophat_wrapper.xml +++ b/tools/ngs_rna/tophat_wrapper.xml @@ -1,4 +1,4 @@ -<tool id="tophat" name="Tophat for Illumina" version="0.5"> +<tool id="tophat" name="Tophat for Illumina" version="1.5.0"><description>Find splice junctions using RNA-seq data</description><version_command>tophat --version</version_command> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: jgoecks: Revert Tophat wrapper due to parameter incompatibility issues.
by Bitbucket 30 Apr '12

30 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/62c900962bb5/ changeset: 62c900962bb5 user: jgoecks date: 2012-04-30 17:41:04 summary: Revert Tophat wrapper due to parameter incompatibility issues. affected #: 2 files diff -r fbe02e51b24bdb1d8861920fa984d17b3004f9bd -r 62c900962bb5bd943e2717a7ba74162364b18e1e tools/ngs_rna/tophat_wrapper.py --- a/tools/ngs_rna/tophat_wrapper.py +++ b/tools/ngs_rna/tophat_wrapper.py @@ -52,16 +52,16 @@ supplied GFF file. (ignored without -G)") parser.add_option( '', '--no-novel-indels', action="store_true", dest='no_novel_indels', help="Skip indel search. Indel search is enabled by default.") # Types of search. + parser.add_option( '', '--microexon-search', action="store_true", dest='microexon_search', help='With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.') parser.add_option( '', '--closure-search', action="store_true", dest='closure_search', help='Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the expected inner distance between mates is small (<= 50bp)') parser.add_option( '', '--no-closure-search', action="store_false", dest='closure_search' ) - parser.add_option( '', '--min-closure-exon', dest='min_closure_exon', help='Minimum length for exonic hops in potential splice graph' ) - parser.add_option( '', '--min-closure-intron', dest='min_closure_intron', help='Minimum intron length that may be found during closure search' ) - parser.add_option( '', '--max-closure-intron', dest='max_closure_intron', help='Maximum intron length that may be found during closure search' ) - parser.add_option( '', '--microexon-search', action="store_true", dest='microexon_search', help='With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.') parser.add_option( '', '--coverage-search', action="store_true", dest='coverage_search', help='Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity.') parser.add_option( '', '--no-coverage-search', action="store_false", dest='coverage_search' ) parser.add_option( '', '--min-segment-intron', dest='min_segment_intron', help='Minimum intron length that may be found during split-segment search' ) parser.add_option( '', '--max-segment-intron', dest='max_segment_intron', help='Maximum intron length that may be found during split-segment search' ) + parser.add_option( '', '--min-closure-exon', dest='min_closure_exon', help='Minimum length for exonic hops in potential splice graph' ) + parser.add_option( '', '--min-closure-intron', dest='min_closure_intron', help='Minimum intron length that may be found during closure search' ) + parser.add_option( '', '--max-closure-intron', dest='max_closure_intron', help='Maximum intron length that may be found during closure search' ) parser.add_option( '', '--min-coverage-intron', dest='min_coverage_intron', help='Minimum intron length that may be found during coverage search' ) parser.add_option( '', '--max-coverage-intron', dest='max_coverage_intron', help='Maximum intron length that may be found during coverage search' ) @@ -73,6 +73,21 @@ (options, args) = parser.parse_args() + # output version # of tool + try: + tmp = tempfile.NamedTemporaryFile().name + tmp_stdout = open( tmp, 'wb' ) + proc = subprocess.Popen( args='tophat -v', shell=True, stdout=tmp_stdout ) + tmp_stdout.close() + returncode = proc.wait() + stdout = open( tmp_stdout.name, 'rb' ).readline().strip() + if stdout: + sys.stdout.write( '%s\n' % stdout ) + else: + raise Exception + except: + sys.stdout.write( 'Could not determine Tophat version\n' ) + # Color or base space space = '' if options.color_space: @@ -166,7 +181,7 @@ opts += ' --no-closure-search' if options.microexon_search: opts += ' --microexon-search' - if options.single_paired == 'paired' and options.mate_std_dev: + if options.single_paired == 'paired': opts += ' --mate-std-dev %s' % options.mate_std_dev if options.initial_read_mismatches: opts += ' --initial-read-mismatches %d' % int( options.initial_read_mismatches ) diff -r fbe02e51b24bdb1d8861920fa984d17b3004f9bd -r 62c900962bb5bd943e2717a7ba74162364b18e1e tools/ngs_rna/tophat_wrapper.xml --- a/tools/ngs_rna/tophat_wrapper.xml +++ b/tools/ngs_rna/tophat_wrapper.xml @@ -7,111 +7,150 @@ </requirements><command interpreter="python"> tophat_wrapper.py - - ## Change this to accommodate the number of threads you have available. - --num-threads="4" + ## Change this to accommodate the number of threads you have available. + --num-threads="4" - ## Provide outputs. - --junctions-output=$junctions - --hits-output=$accepted_hits + ## Provide outputs. + --junctions-output=$junctions + --hits-output=$accepted_hits - ## Handle reference file. - #if $refGenomeSource.genomeSource == "history": - --own-file=$refGenomeSource.ownFile - #else: - --indexes-path="${refGenomeSource.index.fields.path}" - #end if - - ## Are reads single-end or paired? - --single-paired=$singlePaired.sPaired - - ## First input file always required. - --input1=$input1 - - ## Second input only if input is paired-end. - #if $singlePaired.sPaired == "paired" - --input2=$singlePaired.input2 - -r $singlePaired.mate_inner_distance - --mate-std-dev=$singlePaired.mate_std_dev - #end if - - ## Set params. - --settings=$params.settingsType - #if $params.settingsType == "full": - -a $params.anchor_length - -m $params.splice_mismatches - -i $params.min_intron_length - -I $params.max_intron_length - -g $params.max_multihits - --min-segment-intron $params.min_segment_intron - --max-segment-intron $params.max_segment_intron - --initial-read-mismatches=$params.initial_read_mismatches - --seg-mismatches=$params.seg_mismatches - --seg-length=$params.seg_length - --library-type=$params.library_type - - ## Closure search. - #if $params.closure_search.use_search == "Yes": - --closure-search - --min-closure-exon $params.closure_search.min_closure_exon - --min-closure-intron $params.closure_search.min_closure_intron - --max-closure-intron $params.closure_search.max_closure_intron + ## Handle reference file. + #if $refGenomeSource.genomeSource == "history": + --own-file=$refGenomeSource.ownFile #else: - --no-closure-search - #end if - - ## Indel search. - #if $params.indel_search.allow_indel_search == "Yes": - ## --allow-indels - --max-insertion-length $params.indel_search.max_insertion_length - --max-deletion-length $params.indel_search.max_deletion_length - #else: - --no-novel-indels + --indexes-path="${refGenomeSource.index.fields.path}" #end if - ## Supplying junctions parameters. - #if $params.own_junctions.use_junctions == "Yes": - #if $params.own_junctions.gene_model_ann.use_annotations == "Yes": - -G $params.own_junctions.gene_model_ann.gene_annotation_model + ## Are reads single-end or paired? + --single-paired=$singlePaired.sPaired + + ## First input file always required. + --input1=$input1 + + ## Set params based on whether reads are single-end or paired. + #if $singlePaired.sPaired == "single": + --settings=$singlePaired.sParams.sSettingsType + #if $singlePaired.sParams.sSettingsType == "full": + -a $singlePaired.sParams.anchor_length + -m $singlePaired.sParams.splice_mismatches + -i $singlePaired.sParams.min_intron_length + -I $singlePaired.sParams.max_intron_length + -g $singlePaired.sParams.max_multihits + --min-segment-intron $singlePaired.sParams.min_segment_intron + --max-segment-intron $singlePaired.sParams.max_segment_intron + --initial-read-mismatches=$singlePaired.sParams.initial_read_mismatches + --seg-mismatches=$singlePaired.sParams.seg_mismatches + --seg-length=$singlePaired.sParams.seg_length + --library-type=$singlePaired.sParams.library_type + + ## Indel search. + #if $singlePaired.sParams.indel_search.allow_indel_search == "Yes": + ## --allow-indels + --max-insertion-length $singlePaired.sParams.indel_search.max_insertion_length + --max-deletion-length $singlePaired.sParams.indel_search.max_deletion_length + #else: + --no-novel-indels + #end if + + ## Supplying junctions parameters. + #if $singlePaired.sParams.own_junctions.use_junctions == "Yes": + #if $singlePaired.sParams.own_junctions.gene_model_ann.use_annotations == "Yes": + -G $singlePaired.sParams.own_junctions.gene_model_ann.gene_annotation_model + #end if + #if $singlePaired.sParams.own_junctions.raw_juncs.use_juncs == "Yes": + -j $singlePaired.sParams.own_junctions.raw_juncs.raw_juncs + #end if + ## TODO: No idea why a string cast is necessary, but it is: + #if str($singlePaired.sParams.own_junctions.no_novel_juncs) == "Yes": + --no-novel-juncs + #end if + #end if + + #if $singlePaired.sParams.closure_search.use_search == "Yes": + --closure-search + --min-closure-exon $singlePaired.sParams.closure_search.min_closure_exon + --min-closure-intron $singlePaired.sParams.closure_search.min_closure_intron + --max-closure-intron $singlePaired.sParams.closure_search.max_closure_intron + #else: + --no-closure-search + #end if + #if $singlePaired.sParams.coverage_search.use_search == "Yes": + --coverage-search + --min-coverage-intron $singlePaired.sParams.coverage_search.min_coverage_intron + --max-coverage-intron $singlePaired.sParams.coverage_search.max_coverage_intron + #else: + --no-coverage-search + #end if + ## TODO: No idea why the type conversion is necessary, but it seems to be. + #if str($singlePaired.sParams.microexon_search) == "Yes": + --microexon-search + #end if #end if - #if $params.own_junctions.raw_juncs.use_juncs == "Yes": - -j $params.own_junctions.raw_juncs.raw_juncs - #end if - ## TODO: No idea why a string cast is necessary, but it is: - #if str($params.own_junctions.no_novel_juncs) == "Yes": - --no-novel-juncs + #else: + --input2=$singlePaired.input2 + -r $singlePaired.mate_inner_distance + --settings=$singlePaired.pParams.pSettingsType + #if $singlePaired.pParams.pSettingsType == "full": + --mate-std-dev=$singlePaired.pParams.mate_std_dev + -a $singlePaired.pParams.anchor_length + -m $singlePaired.pParams.splice_mismatches + -i $singlePaired.pParams.min_intron_length + -I $singlePaired.pParams.max_intron_length + -g $singlePaired.pParams.max_multihits + --min-segment-intron $singlePaired.pParams.min_segment_intron + --max-segment-intron $singlePaired.pParams.max_segment_intron + --initial-read-mismatches=$singlePaired.pParams.initial_read_mismatches + --seg-mismatches=$singlePaired.pParams.seg_mismatches + --seg-length=$singlePaired.pParams.seg_length + --library-type=$singlePaired.pParams.library_type + + ## Indel search. + #if $singlePaired.pParams.indel_search.allow_indel_search == "Yes": + ## --allow-indels + --max-insertion-length $singlePaired.pParams.indel_search.max_insertion_length + --max-deletion-length $singlePaired.pParams.indel_search.max_deletion_length + #else: + --no-novel-indels + #end if + + ## Supplying junctions parameters. + #if $singlePaired.pParams.own_junctions.use_junctions == "Yes": + #if $singlePaired.pParams.own_junctions.gene_model_ann.use_annotations == "Yes": + -G $singlePaired.pParams.own_junctions.gene_model_ann.gene_annotation_model + #end if + #if $singlePaired.pParams.own_junctions.raw_juncs.use_juncs == "Yes": + -j $singlePaired.pParams.own_junctions.raw_juncs.raw_juncs + #end if + ## TODO: No idea why type cast is necessary, but it is: + #if str($singlePaired.pParams.own_junctions.no_novel_juncs) == "Yes": + --no-novel-juncs + #end if + #end if + + #if $singlePaired.pParams.closure_search.use_search == "Yes": + --closure-search + --min-closure-exon $singlePaired.pParams.closure_search.min_closure_exon + --min-closure-intron $singlePaired.pParams.closure_search.min_closure_intron + --max-closure-intron $singlePaired.pParams.closure_search.max_closure_intron + #else: + --no-closure-search + #end if + #if $singlePaired.pParams.coverage_search.use_search == "Yes": + --coverage-search + --min-coverage-intron $singlePaired.pParams.coverage_search.min_coverage_intron + --max-coverage-intron $singlePaired.pParams.coverage_search.max_coverage_intron + #else: + --no-coverage-search + #end if + ## TODO: No idea why the type conversion is necessary, but it seems to be. + #if str ($singlePaired.pParams.microexon_search) == "Yes": + --microexon-search + #end if #end if #end if - - #if $params.coverage_search.use_search == "Yes": - --coverage-search - --min-coverage-intron $params.coverage_search.min_coverage_intron - --max-coverage-intron $params.coverage_search.max_coverage_intron - #else: - --no-coverage-search - #end if - ## TODO: No idea why the type conversion is necessary, but it seems to be. - #if str($params.microexon_search) == "Yes": - --microexon-search - #end if - #end if </command><inputs> - <conditional name="singlePaired"> - <param name="sPaired" type="select" label="Is this library mate-paired?"> - <option value="single">Single-end</option> - <option value="paired">Paired-end</option> - </param> - <when value="single"> - <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ dataset" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/> - </when> - <when value="paired"> - <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ dataset--forward reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> - <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ dataset--reverse reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> - <param name="mate_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs" /> - <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="The standard deviation for the distribution on inner distances between mate pairs."/> - </when> - </conditional> + <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /><conditional name="refGenomeSource"><param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"><option value="indexed">Use a built-in index</option> @@ -129,109 +168,221 @@ <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" /></when></conditional> - <conditional name="params"> - <param name="settingsType" type="select" label="TopHat settings to use" help="You can use the default settings or set custom values for any of Tophat's parameters."> - <option value="preSet">Use Defaults</option> - <option value="full">Full parameter list</option> + <conditional name="singlePaired"> + <param name="sPaired" type="select" label="Is this library mate-paired?"> + <option value="single">Single-end</option> + <option value="paired">Paired-end</option></param> - <when value="preSet" /> -  - <when value="full"> - <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> - <option value="fr-unstranded">FR Unstranded</option> - <option value="fr-firststrand">FR First Strand</option> - <option value="fr-secondstrand">FR Second Strand</option> - </param> - <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> - <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> - <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> - <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> - <conditional name="indel_search"> - <param name="allow_indel_search" type="select" label="Allow indel search"> + <when value="single"> + <conditional name="sParams"> + <param name="sSettingsType" type="select" label="TopHat settings to use" help="You can use the default settings or set custom values for any of Tophat's parameters."> + <option value="preSet">Use Defaults</option> + <option value="full">Full parameter list</option> + </param> + <when value="preSet" /> +  + <when value="full"> + <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> + <option value="fr-unstranded">FR Unstranded</option> + <option value="fr-firststrand">FR First Strand</option> + <option value="fr-secondstrand">FR Second Strand</option> + </param> + <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> + <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> + <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> + <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> + <conditional name="indel_search"> + <param name="allow_indel_search" type="select" label="Allow indel search"> + <option value="Yes">Yes</option> + <option value="No">No</option> + </param> + <when value="No"/> + <when value="Yes"> + <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> + <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> + </when> + </conditional> +alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" /> + <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> + <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> + <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> + <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> + <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> + <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> + +  + <conditional name="own_junctions"> + <param name="use_junctions" type="select" label="Use Own Junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="Yes"> + <conditional name="gene_model_ann"> + <param name="use_annotations" type="select" label="Use Gene Annotation Model"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" /> + <when value="Yes"> + <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> + </when> + </conditional> + <conditional name="raw_juncs"> + <param name="use_juncs" type="select" label="Use Raw Junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" /> + <when value="Yes"> + <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> + </when> + </conditional> + <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + </when> + <when value="No" /> + </conditional> + +  + <conditional name="closure_search"> + <param name="use_search" type="select" label="Use Closure Search"> + <option value="No">No</option><option value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="No"/> - <when value="Yes"> - <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> - <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> - </when> - </conditional> - alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" /> - <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> - <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> - <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> - <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> - <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> - <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> - -  - <conditional name="own_junctions"> - <param name="use_junctions" type="select" label="Use Own Junctions"> + </param> + <when value="Yes"> + <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> + <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> + <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> + </when> + <when value="No" /> + </conditional> +  + <conditional name="coverage_search"> + <param name="use_search" type="select" label="Use Coverage Search"> + <option selected="true" value="Yes">Yes</option> + <option value="No">No</option> + </param> + <when value="Yes"> + <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> + <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> + </when> + <when value="No" /> + </conditional> + <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."><option value="No">No</option><option value="Yes">Yes</option></param> - <when value="Yes"> - <conditional name="gene_model_ann"> - <param name="use_annotations" type="select" label="Use Gene Annotation Model"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> - </when> - </conditional> - <conditional name="raw_juncs"> - <param name="use_juncs" type="select" label="Use Raw Junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> - </when> - </conditional> - <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"> + </when> + </conditional> + </when> + <when value="paired"> + <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param name="mate_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs" /> + <conditional name="pParams"> + <param name="pSettingsType" type="select" label="TopHat settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list"> + <option value="preSet">Commonly used</option> + <option value="full">Full parameter list</option> + </param> + <when value="preSet" /> +  + <when value="full"> + <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> + <option value="fr-unstranded">FR Unstranded</option> + <option value="fr-firststrand">FR First Strand</option> + <option value="fr-secondstrand">FR Second Strand</option> + </param> + <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="The standard deviation for the distribution on inner distances between mate pairs."/> + <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> + <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> + <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> + <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> + <conditional name="indel_search"> + <param name="allow_indel_search" type="select" label="Allow indel search"> + <option value="Yes">Yes</option> + <option value="No">No</option> + </param> + <when value="No"/> + <when value="Yes"> + <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> + <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> + </when> + </conditional> + <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> + <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> + <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> + <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> + <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> + <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> +  + <conditional name="own_junctions"> + <param name="use_junctions" type="select" label="Use Own Junctions"><option value="No">No</option><option value="Yes">Yes</option></param> - </when> - <when value="No" /> - </conditional> - -  - <conditional name="closure_search"> - <param name="use_search" type="select" label="Use Closure Search"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> - <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> - <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> - </when> - <when value="No" /> - </conditional> - -  - <conditional name="coverage_search"> - <param name="use_search" type="select" label="Use Coverage Search"> - <option selected="true" value="Yes">Yes</option> + <when value="Yes"> + <conditional name="gene_model_ann"> + <param name="use_annotations" type="select" label="Use Gene Annotation Model"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" /> + <when value="Yes"> + <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> + </when> + </conditional> + <conditional name="raw_juncs"> + <param name="use_juncs" type="select" label="Use Raw Junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" /> + <when value="Yes"> + <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> + </when> + </conditional> + <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + </when> + <when value="No" /> + </conditional> + +  + <conditional name="closure_search"> + <param name="use_search" type="select" label="Use Closure Search"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="Yes"> + <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> + <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> + <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> + </when> + <when value="No" /> + </conditional> +  + <conditional name="coverage_search"> + <param name="use_search" type="select" label="Use Coverage Search"> + <option selected="true" value="Yes">Yes</option> + <option value="No">No</option> + </param> + <when value="Yes"> + <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> + <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> + </when> + <when value="No" /> + </conditional> + <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."><option value="No">No</option> - </param> - <when value="Yes"> - <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> - <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> - </when> - <when value="No" /> - </conditional> - <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - </conditional> + <option value="Yes">Yes</option> + </param> + </when> + </conditional> + </when> + </conditional></inputs><outputs> @@ -320,11 +471,11 @@ tophat -o tmp_dir -p 1 tophat_in1 test-data/tophat_in2.fastqsanger Rename the files in tmp_dir appropriately --> - <param name="sPaired" value="single" /><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" /><param name="genomeSource" value="indexed" /><param name="index" value="tophat_test" /> - <param name="settingsType" value="preSet" /> + <param name="sPaired" value="single" /> + <param name="sSettingsType" value="preSet" /><output name="junctions" file="tophat_out1j.bed" /><output name="accepted_hits" file="tophat_out1h.bam" compare="sim_size" /></test> @@ -335,13 +486,13 @@ tophat -o tmp_dir -p 1 -r 20 tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger Rename the files in tmp_dir appropriately --> - <param name="sPaired" value="paired" /><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" /> - <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" /><param name="genomeSource" value="history" /><param name="ownFile" ftype="fasta" value="tophat_in1.fasta" /> + <param name="sPaired" value="paired" /> + <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" /><param name="mate_inner_distance" value="20" /> - <param name="settingsType" value="preSet" /> + <param name="pSettingsType" value="preSet" /><output name="junctions" file="tophat_out2j.bed" /><output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" /></test> @@ -349,15 +500,15 @@ <test> - <param name="sPaired" value="single"/><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/><param name="genomeSource" value="history"/><param name="ownFile" value="tophat_in1.fasta"/> - <param name="settingsType" value="full"/> + <param name="sPaired" value="single"/> + <param name="sSettingsType" value="full"/><param name="library_type" value="FR Unstranded"/><param name="anchor_length" value="8"/><param name="splice_mismatches" value="0"/> @@ -395,13 +546,13 @@ Replace the + with double-dash Rename the files in tmp_dir appropriately --> - <param name="sPaired" value="paired"/><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/> - <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/><param name="genomeSource" value="indexed"/><param name="index" value="tophat_test"/> + <param name="sPaired" value="paired"/> + <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/><param name="mate_inner_distance" value="20"/> - <param name="settingsType" value="full"/> + <param name="pSettingsType" value="full"/><param name="library_type" value="FR Unstranded"/><param name="mate_std_dev" value="20"/><param name="anchor_length" value="8"/> @@ -493,15 +644,16 @@ -j/--raw-juncs [juncs file] Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-], left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive. -no-novel-juncs Only look for junctions indicated in the supplied GFF file. (ignored without -G) --no-closure-search Disables the mate pair closure-based search for junctions. Currently, has no effect - closure search is off by default. - --closure-search Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the - --min-closure-exon During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50. - --min-closure-intron The minimum intron length that may be found during closure search. The default is 50. - --max-closure-intron The maximum intron length that may be found during closure search. The default is 5000. expected inner distance between mates is small (about or less than 50bp) + --closure-search Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the expected inner distance between mates is small (about or less than 50bp) --no-coverage-search Disables the coverage based search for junctions. --coverage-search Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity. --microexon-search With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer. + --butterfly-search TopHat will use a slower but potentially more sensitive algorithm to find junctions in addition to its standard search. Consider using this if you expect that your experiment produced a lot of reads from pre-mRNA, that fall within the introns of your transcripts. --segment-mismatches Read segments are mapped independently, allowing up to this many mismatches in each segment alignment. The default is 2. --segment-length Each read is cut up into segments, each at least this long. These segments are mapped independently. The default is 25. + --min-closure-exon During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50. + --min-closure-intron The minimum intron length that may be found during closure search. The default is 50. + --max-closure-intron The maximum intron length that may be found during closure search. The default is 5000. --min-coverage-intron The minimum intron length that may be found during coverage search. The default is 50. --max-coverage-intron The maximum intron length that may be found during coverage search. The default is 20000. --min-segment-intron The minimum intron length that may be found during split-segment search. The default is 50. Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: greg: Fixes for some requests sent from Galaxy to a tool shed.
by Bitbucket 30 Apr '12

30 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/fbe02e51b24b/ changeset: fbe02e51b24b user: greg date: 2012-04-30 17:00:07 summary: Fixes for some requests sent from Galaxy to a tool shed. affected #: 1 file diff -r dd01d42e4da3f2bd8535707cdd6d4322ae9d516c -r fbe02e51b24bdb1d8861920fa984d17b3004f9bd lib/galaxy/web/controllers/admin_toolshed.py --- a/lib/galaxy/web/controllers/admin_toolshed.py +++ b/lib/galaxy/web/controllers/admin_toolshed.py @@ -149,7 +149,7 @@ def browse_tool_shed( self, trans, **kwd ): tool_shed_url = kwd[ 'tool_shed_url' ] galaxy_url = url_for( '/', qualified=True ) - url = '%s/repository/browse_valid_repositories?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) + url = '%srepository/browse_valid_repositories?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) return trans.response.send_redirect( url ) @web.expose @web.require_admin @@ -218,14 +218,14 @@ def find_tools_in_tool_shed( self, trans, **kwd ): tool_shed_url = kwd[ 'tool_shed_url' ] galaxy_url = url_for( '/', qualified=True ) - url = '%s/repository/find_tools?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) + url = '%srepository/find_tools?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) return trans.response.send_redirect( url ) @web.expose @web.require_admin def find_workflows_in_tool_shed( self, trans, **kwd ): tool_shed_url = kwd[ 'tool_shed_url' ] galaxy_url = url_for( '/', qualified=True ) - url = '%s/repository/find_workflows?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) + url = '%srepository/find_workflows?galaxy_url=%s&webapp=galaxy' % ( tool_shed_url, galaxy_url ) return trans.response.send_redirect( url ) @web.expose @web.require_admin @@ -318,7 +318,7 @@ shed_tool_conf=shed_tool_conf ) if 'tools' in metadata_dict: # Get the tool_versions from the tool shed for each tool in the installed change set. - url = '%s/repository/get_tool_versions?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % \ + url = '%srepository/get_tool_versions?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % \ ( tool_shed_url, name, owner, changeset_revision ) response = urllib2.urlopen( url ) text = response.read() @@ -367,7 +367,7 @@ repo_info_tuple = decoded_repo_info_dict[ name ] description, repository_clone_url, changeset_revision, ctx_rev = repo_info_tuple owner = get_repository_owner( clean_repository_clone_url( repository_clone_url ) ) - url = '%s/repository/get_readme?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % ( tool_shed_url, name, owner, changeset_revision ) + url = '%srepository/get_readme?name=%s&owner=%s&changeset_revision=%s&webapp=galaxy' % ( tool_shed_url, name, owner, changeset_revision ) response = urllib2.urlopen( url ) raw_text = response.read() response.close() Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: 2 new changesets
by Bitbucket 30 Apr '12

30 Apr '12

2 new commits in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/1d6324d630ed/ changeset: 1d6324d630ed user: jgoecks date: 2012-04-29 04:21:30 summary: Update Cuffdiff min-alignment-count default. affected #: 1 file diff -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 -r 1d6324d630ed3c9109d6240d7186c9f99d778005 tools/ngs_rna/cuffdiff_wrapper.xml --- a/tools/ngs_rna/cuffdiff_wrapper.xml +++ b/tools/ngs_rna/cuffdiff_wrapper.xml @@ -89,7 +89,7 @@ </conditional><param name="fdr" type="float" value="0.05" label="False Discovery Rate" help="The allowed false discovery rate."/> - <param name="min_alignment_count" type="integer" value="1000" label="Min Alignment Count" help="The minimum number of alignments in a locus for needed to conduct significance testing on changes in that locus observed between samples."/> + <param name="min_alignment_count" type="integer" value="10" label="Min Alignment Count" help="The minimum number of alignments in a locus for needed to conduct significance testing on changes in that locus observed between samples."/><param name="do_normalization" type="select" label="Perform quartile normalization" help="Removes top 25% of genes from FPKM denominator to improve accuracy of differential expression calls for low abundance transcripts."><option value="No">No</option><option value="Yes">Yes</option> https://bitbucket.org/galaxy/galaxy-central/changeset/dd01d42e4da3/ changeset: dd01d42e4da3 user: jgoecks date: 2012-04-30 02:34:39 summary: Merge affected #: 4 files diff -r 1d6324d630ed3c9109d6240d7186c9f99d778005 -r dd01d42e4da3f2bd8535707cdd6d4322ae9d516c lib/galaxy/datatypes/converters/sam_to_bam.py --- /dev/null +++ b/lib/galaxy/datatypes/converters/sam_to_bam.py @@ -0,0 +1,69 @@ +#!/usr/bin/env python +#Dan Blankenberg + +""" +A wrapper script for converting SAM to BAM, with sorting. +%prog input_filename.sam output_filename.bam +""" + +import sys, optparse, os, tempfile, subprocess, shutil + +CHUNK_SIZE = 2**20 #1mb + + +def cleanup_before_exit( tmp_dir ): + if tmp_dir and os.path.exists( tmp_dir ): + shutil.rmtree( tmp_dir ) + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + (options, args) = parser.parse_args() + + assert len( args ) == 2, 'You must specify the input and output filenames' + input_filename, output_filename = args + + tmp_dir = tempfile.mkdtemp( prefix='tmp-sam_to_bam_converter-' ) + + #convert to SAM + unsorted_bam_filename = os.path.join( tmp_dir, 'unsorted.bam' ) + unsorted_stderr_filename = os.path.join( tmp_dir, 'unsorted.stderr' ) + cmd = 'samtools view -bS "%s" > "%s"' % ( input_filename, unsorted_bam_filename ) + proc = subprocess.Popen( args=cmd, stderr=open( unsorted_stderr_filename, 'wb' ), shell=True, cwd=tmp_dir ) + return_code = proc.wait() + if return_code: + stderr_target = sys.stderr + else: + stderr_target = sys.stdout + stderr = open( unsorted_stderr_filename ) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + + #sort sam, so indexing will not fail + sorted_stderr_filename = os.path.join( tmp_dir, 'sorted.stderr' ) + sorting_prefix = os.path.join( tmp_dir, 'sorted_bam' ) + cmd = 'samtools sort -o "%s" "%s" > "%s"' % ( unsorted_bam_filename, sorting_prefix, output_filename ) + proc = subprocess.Popen( args=cmd, stderr=open( sorted_stderr_filename, 'wb' ), shell=True, cwd=tmp_dir ) + return_code = proc.wait() + + if return_code: + stderr_target = sys.stderr + else: + stderr_target = sys.stdout + stderr = open( sorted_stderr_filename ) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + + cleanup_before_exit( tmp_dir ) + +if __name__=="__main__": __main__() diff -r 1d6324d630ed3c9109d6240d7186c9f99d778005 -r dd01d42e4da3f2bd8535707cdd6d4322ae9d516c lib/galaxy/datatypes/converters/sam_to_bam.xml --- a/lib/galaxy/datatypes/converters/sam_to_bam.xml +++ b/lib/galaxy/datatypes/converters/sam_to_bam.xml @@ -1,11 +1,11 @@ -<tool id="CONVERTER_sam_to_bam" name="Convert SAM to BAM" version="1.0.0"> +<tool id="CONVERTER_sam_to_bam" name="Convert SAM to BAM" version="2.0.0"> - <command>samtools view -bS $input1 > $output 2> /dev/null </command> + <command interpreter="python">sam_to_bam.py $input1 $output</command><inputs><param name="input1" type="data" format="sam" label="SAM file"/></inputs> diff -r 1d6324d630ed3c9109d6240d7186c9f99d778005 -r dd01d42e4da3f2bd8535707cdd6d4322ae9d516c tools/ngs_rna/tophat_wrapper.py --- a/tools/ngs_rna/tophat_wrapper.py +++ b/tools/ngs_rna/tophat_wrapper.py @@ -52,16 +52,16 @@ supplied GFF file. (ignored without -G)") parser.add_option( '', '--no-novel-indels', action="store_true", dest='no_novel_indels', help="Skip indel search. Indel search is enabled by default.") # Types of search. - parser.add_option( '', '--microexon-search', action="store_true", dest='microexon_search', help='With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.') parser.add_option( '', '--closure-search', action="store_true", dest='closure_search', help='Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the expected inner distance between mates is small (<= 50bp)') parser.add_option( '', '--no-closure-search', action="store_false", dest='closure_search' ) + parser.add_option( '', '--min-closure-exon', dest='min_closure_exon', help='Minimum length for exonic hops in potential splice graph' ) + parser.add_option( '', '--min-closure-intron', dest='min_closure_intron', help='Minimum intron length that may be found during closure search' ) + parser.add_option( '', '--max-closure-intron', dest='max_closure_intron', help='Maximum intron length that may be found during closure search' ) + parser.add_option( '', '--microexon-search', action="store_true", dest='microexon_search', help='With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.') parser.add_option( '', '--coverage-search', action="store_true", dest='coverage_search', help='Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity.') parser.add_option( '', '--no-coverage-search', action="store_false", dest='coverage_search' ) parser.add_option( '', '--min-segment-intron', dest='min_segment_intron', help='Minimum intron length that may be found during split-segment search' ) parser.add_option( '', '--max-segment-intron', dest='max_segment_intron', help='Maximum intron length that may be found during split-segment search' ) - parser.add_option( '', '--min-closure-exon', dest='min_closure_exon', help='Minimum length for exonic hops in potential splice graph' ) - parser.add_option( '', '--min-closure-intron', dest='min_closure_intron', help='Minimum intron length that may be found during closure search' ) - parser.add_option( '', '--max-closure-intron', dest='max_closure_intron', help='Maximum intron length that may be found during closure search' ) parser.add_option( '', '--min-coverage-intron', dest='min_coverage_intron', help='Minimum intron length that may be found during coverage search' ) parser.add_option( '', '--max-coverage-intron', dest='max_coverage_intron', help='Maximum intron length that may be found during coverage search' ) @@ -166,7 +166,7 @@ opts += ' --no-closure-search' if options.microexon_search: opts += ' --microexon-search' - if options.single_paired == 'paired': + if options.single_paired == 'paired' and options.mate_std_dev: opts += ' --mate-std-dev %s' % options.mate_std_dev if options.initial_read_mismatches: opts += ' --initial-read-mismatches %d' % int( options.initial_read_mismatches ) diff -r 1d6324d630ed3c9109d6240d7186c9f99d778005 -r dd01d42e4da3f2bd8535707cdd6d4322ae9d516c tools/ngs_rna/tophat_wrapper.xml --- a/tools/ngs_rna/tophat_wrapper.xml +++ b/tools/ngs_rna/tophat_wrapper.xml @@ -7,150 +7,111 @@ </requirements><command interpreter="python"> tophat_wrapper.py - ## Change this to accommodate the number of threads you have available. - --num-threads="4" + + ## Change this to accommodate the number of threads you have available. + --num-threads="4" - ## Provide outputs. - --junctions-output=$junctions - --hits-output=$accepted_hits + ## Provide outputs. + --junctions-output=$junctions + --hits-output=$accepted_hits - ## Handle reference file. - #if $refGenomeSource.genomeSource == "history": - --own-file=$refGenomeSource.ownFile + ## Handle reference file. + #if $refGenomeSource.genomeSource == "history": + --own-file=$refGenomeSource.ownFile + #else: + --indexes-path="${refGenomeSource.index.fields.path}" + #end if + + ## Are reads single-end or paired? + --single-paired=$singlePaired.sPaired + + ## First input file always required. + --input1=$input1 + + ## Second input only if input is paired-end. + #if $singlePaired.sPaired == "paired" + --input2=$singlePaired.input2 + -r $singlePaired.mate_inner_distance + --mate-std-dev=$singlePaired.mate_std_dev + #end if + + ## Set params. + --settings=$params.settingsType + #if $params.settingsType == "full": + -a $params.anchor_length + -m $params.splice_mismatches + -i $params.min_intron_length + -I $params.max_intron_length + -g $params.max_multihits + --min-segment-intron $params.min_segment_intron + --max-segment-intron $params.max_segment_intron + --initial-read-mismatches=$params.initial_read_mismatches + --seg-mismatches=$params.seg_mismatches + --seg-length=$params.seg_length + --library-type=$params.library_type + + ## Closure search. + #if $params.closure_search.use_search == "Yes": + --closure-search + --min-closure-exon $params.closure_search.min_closure_exon + --min-closure-intron $params.closure_search.min_closure_intron + --max-closure-intron $params.closure_search.max_closure_intron #else: - --indexes-path="${refGenomeSource.index.fields.path}" + --no-closure-search + #end if + + ## Indel search. + #if $params.indel_search.allow_indel_search == "Yes": + ## --allow-indels + --max-insertion-length $params.indel_search.max_insertion_length + --max-deletion-length $params.indel_search.max_deletion_length + #else: + --no-novel-indels #end if - ## Are reads single-end or paired? - --single-paired=$singlePaired.sPaired - - ## First input file always required. - --input1=$input1 - - ## Set params based on whether reads are single-end or paired. - #if $singlePaired.sPaired == "single": - --settings=$singlePaired.sParams.sSettingsType - #if $singlePaired.sParams.sSettingsType == "full": - -a $singlePaired.sParams.anchor_length - -m $singlePaired.sParams.splice_mismatches - -i $singlePaired.sParams.min_intron_length - -I $singlePaired.sParams.max_intron_length - -g $singlePaired.sParams.max_multihits - --min-segment-intron $singlePaired.sParams.min_segment_intron - --max-segment-intron $singlePaired.sParams.max_segment_intron - --initial-read-mismatches=$singlePaired.sParams.initial_read_mismatches - --seg-mismatches=$singlePaired.sParams.seg_mismatches - --seg-length=$singlePaired.sParams.seg_length - --library-type=$singlePaired.sParams.library_type - - ## Indel search. - #if $singlePaired.sParams.indel_search.allow_indel_search == "Yes": - ## --allow-indels - --max-insertion-length $singlePaired.sParams.indel_search.max_insertion_length - --max-deletion-length $singlePaired.sParams.indel_search.max_deletion_length - #else: - --no-novel-indels - #end if - - ## Supplying junctions parameters. - #if $singlePaired.sParams.own_junctions.use_junctions == "Yes": - #if $singlePaired.sParams.own_junctions.gene_model_ann.use_annotations == "Yes": - -G $singlePaired.sParams.own_junctions.gene_model_ann.gene_annotation_model - #end if - #if $singlePaired.sParams.own_junctions.raw_juncs.use_juncs == "Yes": - -j $singlePaired.sParams.own_junctions.raw_juncs.raw_juncs - #end if - ## TODO: No idea why a string cast is necessary, but it is: - #if str($singlePaired.sParams.own_junctions.no_novel_juncs) == "Yes": - --no-novel-juncs - #end if - #end if - - #if $singlePaired.sParams.closure_search.use_search == "Yes": - --closure-search - --min-closure-exon $singlePaired.sParams.closure_search.min_closure_exon - --min-closure-intron $singlePaired.sParams.closure_search.min_closure_intron - --max-closure-intron $singlePaired.sParams.closure_search.max_closure_intron - #else: - --no-closure-search - #end if - #if $singlePaired.sParams.coverage_search.use_search == "Yes": - --coverage-search - --min-coverage-intron $singlePaired.sParams.coverage_search.min_coverage_intron - --max-coverage-intron $singlePaired.sParams.coverage_search.max_coverage_intron - #else: - --no-coverage-search - #end if - ## TODO: No idea why the type conversion is necessary, but it seems to be. - #if str($singlePaired.sParams.microexon_search) == "Yes": - --microexon-search - #end if + ## Supplying junctions parameters. + #if $params.own_junctions.use_junctions == "Yes": + #if $params.own_junctions.gene_model_ann.use_annotations == "Yes": + -G $params.own_junctions.gene_model_ann.gene_annotation_model #end if - #else: - --input2=$singlePaired.input2 - -r $singlePaired.mate_inner_distance - --settings=$singlePaired.pParams.pSettingsType - #if $singlePaired.pParams.pSettingsType == "full": - --mate-std-dev=$singlePaired.pParams.mate_std_dev - -a $singlePaired.pParams.anchor_length - -m $singlePaired.pParams.splice_mismatches - -i $singlePaired.pParams.min_intron_length - -I $singlePaired.pParams.max_intron_length - -g $singlePaired.pParams.max_multihits - --min-segment-intron $singlePaired.pParams.min_segment_intron - --max-segment-intron $singlePaired.pParams.max_segment_intron - --initial-read-mismatches=$singlePaired.pParams.initial_read_mismatches - --seg-mismatches=$singlePaired.pParams.seg_mismatches - --seg-length=$singlePaired.pParams.seg_length - --library-type=$singlePaired.pParams.library_type - - ## Indel search. - #if $singlePaired.pParams.indel_search.allow_indel_search == "Yes": - ## --allow-indels - --max-insertion-length $singlePaired.pParams.indel_search.max_insertion_length - --max-deletion-length $singlePaired.pParams.indel_search.max_deletion_length - #else: - --no-novel-indels - #end if - - ## Supplying junctions parameters. - #if $singlePaired.pParams.own_junctions.use_junctions == "Yes": - #if $singlePaired.pParams.own_junctions.gene_model_ann.use_annotations == "Yes": - -G $singlePaired.pParams.own_junctions.gene_model_ann.gene_annotation_model - #end if - #if $singlePaired.pParams.own_junctions.raw_juncs.use_juncs == "Yes": - -j $singlePaired.pParams.own_junctions.raw_juncs.raw_juncs - #end if - ## TODO: No idea why type cast is necessary, but it is: - #if str($singlePaired.pParams.own_junctions.no_novel_juncs) == "Yes": - --no-novel-juncs - #end if - #end if - - #if $singlePaired.pParams.closure_search.use_search == "Yes": - --closure-search - --min-closure-exon $singlePaired.pParams.closure_search.min_closure_exon - --min-closure-intron $singlePaired.pParams.closure_search.min_closure_intron - --max-closure-intron $singlePaired.pParams.closure_search.max_closure_intron - #else: - --no-closure-search - #end if - #if $singlePaired.pParams.coverage_search.use_search == "Yes": - --coverage-search - --min-coverage-intron $singlePaired.pParams.coverage_search.min_coverage_intron - --max-coverage-intron $singlePaired.pParams.coverage_search.max_coverage_intron - #else: - --no-coverage-search - #end if - ## TODO: No idea why the type conversion is necessary, but it seems to be. - #if str ($singlePaired.pParams.microexon_search) == "Yes": - --microexon-search - #end if + #if $params.own_junctions.raw_juncs.use_juncs == "Yes": + -j $params.own_junctions.raw_juncs.raw_juncs + #end if + ## TODO: No idea why a string cast is necessary, but it is: + #if str($params.own_junctions.no_novel_juncs) == "Yes": + --no-novel-juncs #end if #end if + + #if $params.coverage_search.use_search == "Yes": + --coverage-search + --min-coverage-intron $params.coverage_search.min_coverage_intron + --max-coverage-intron $params.coverage_search.max_coverage_intron + #else: + --no-coverage-search + #end if + ## TODO: No idea why the type conversion is necessary, but it seems to be. + #if str($params.microexon_search) == "Yes": + --microexon-search + #end if + #end if </command><inputs> - <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <conditional name="singlePaired"> + <param name="sPaired" type="select" label="Is this library mate-paired?"> + <option value="single">Single-end</option> + <option value="paired">Paired-end</option> + </param> + <when value="single"> + <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ dataset" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/> + </when> + <when value="paired"> + <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ dataset--forward reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ dataset--reverse reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param name="mate_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs" /> + <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="The standard deviation for the distribution on inner distances between mate pairs."/> + </when> + </conditional><conditional name="refGenomeSource"><param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"><option value="indexed">Use a built-in index</option> @@ -168,221 +129,109 @@ <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" /></when></conditional> - <conditional name="singlePaired"> - <param name="sPaired" type="select" label="Is this library mate-paired?"> - <option value="single">Single-end</option> - <option value="paired">Paired-end</option> + <conditional name="params"> + <param name="settingsType" type="select" label="TopHat settings to use" help="You can use the default settings or set custom values for any of Tophat's parameters."> + <option value="preSet">Use Defaults</option> + <option value="full">Full parameter list</option></param> - <when value="single"> - <conditional name="sParams"> - <param name="sSettingsType" type="select" label="TopHat settings to use" help="You can use the default settings or set custom values for any of Tophat's parameters."> - <option value="preSet">Use Defaults</option> - <option value="full">Full parameter list</option> - </param> - <when value="preSet" /> -  - <when value="full"> - <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> - <option value="fr-unstranded">FR Unstranded</option> - <option value="fr-firststrand">FR First Strand</option> - <option value="fr-secondstrand">FR Second Strand</option> + <when value="preSet" /> +  + <when value="full"> + <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> + <option value="fr-unstranded">FR Unstranded</option> + <option value="fr-firststrand">FR First Strand</option> + <option value="fr-secondstrand">FR Second Strand</option> + </param> + <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> + <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> + <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> + <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> + <conditional name="indel_search"> + <param name="allow_indel_search" type="select" label="Allow indel search"> + <option value="Yes">Yes</option> + <option value="No">No</option></param> - <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> - <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> - <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> - <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> - <conditional name="indel_search"> - <param name="allow_indel_search" type="select" label="Allow indel search"> - <option value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="No"/> - <when value="Yes"> - <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> - <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> - </when> - </conditional> -alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" /> - <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> - <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> - <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> - <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> - <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> - <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> - -  - <conditional name="own_junctions"> - <param name="use_junctions" type="select" label="Use Own Junctions"> + <when value="No"/> + <when value="Yes"> + <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> + <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> + </when> + </conditional> + alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" /> + <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> + <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> + <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> + <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> + <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> + <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> + +  + <conditional name="own_junctions"> + <param name="use_junctions" type="select" label="Use Own Junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="Yes"> + <conditional name="gene_model_ann"> + <param name="use_annotations" type="select" label="Use Gene Annotation Model"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" /> + <when value="Yes"> + <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> + </when> + </conditional> + <conditional name="raw_juncs"> + <param name="use_juncs" type="select" label="Use Raw Junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" /> + <when value="Yes"> + <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> + </when> + </conditional> + <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"><option value="No">No</option><option value="Yes">Yes</option></param> - <when value="Yes"> - <conditional name="gene_model_ann"> - <param name="use_annotations" type="select" label="Use Gene Annotation Model"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> - </when> - </conditional> - <conditional name="raw_juncs"> - <param name="use_juncs" type="select" label="Use Raw Junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> - </when> - </conditional> - <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - <when value="No" /> - </conditional> - -  - <conditional name="closure_search"> - <param name="use_search" type="select" label="Use Closure Search"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> - <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> - <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> - </when> - <when value="No" /> - </conditional> -  - <conditional name="coverage_search"> - <param name="use_search" type="select" label="Use Coverage Search"> - <option selected="true" value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="Yes"> - <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> - <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> - </when> - <when value="No" /> - </conditional> - <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."> + </when> + <when value="No" /> + </conditional> + +  + <conditional name="closure_search"> + <param name="use_search" type="select" label="Use Closure Search"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="Yes"> + <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> + <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> + <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> + </when> + <when value="No" /> + </conditional> + +  + <conditional name="coverage_search"> + <param name="use_search" type="select" label="Use Coverage Search"> + <option selected="true" value="Yes">Yes</option><option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - </conditional> - </when> - <when value="paired"> - <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> - <param name="mate_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs" /> - <conditional name="pParams"> - <param name="pSettingsType" type="select" label="TopHat settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list"> - <option value="preSet">Commonly used</option> - <option value="full">Full parameter list</option></param> - <when value="preSet" /> -  - <when value="full"> - <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> - <option value="fr-unstranded">FR Unstranded</option> - <option value="fr-firststrand">FR First Strand</option> - <option value="fr-secondstrand">FR Second Strand</option> - </param> - <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="The standard deviation for the distribution on inner distances between mate pairs."/> - <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> - <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> - <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> - <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> - <conditional name="indel_search"> - <param name="allow_indel_search" type="select" label="Allow indel search"> - <option value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="No"/> - <when value="Yes"> - <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> - <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> - </when> - </conditional> - <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> - <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> - <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> - <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> - <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> - <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> -  - <conditional name="own_junctions"> - <param name="use_junctions" type="select" label="Use Own Junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <conditional name="gene_model_ann"> - <param name="use_annotations" type="select" label="Use Gene Annotation Model"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> - </when> - </conditional> - <conditional name="raw_juncs"> - <param name="use_juncs" type="select" label="Use Raw Junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> - </when> - </conditional> - <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - <when value="No" /> - </conditional> - -  - <conditional name="closure_search"> - <param name="use_search" type="select" label="Use Closure Search"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> - <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> - <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> - </when> - <when value="No" /> - </conditional> -  - <conditional name="coverage_search"> - <param name="use_search" type="select" label="Use Coverage Search"> - <option selected="true" value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="Yes"> - <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> - <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> - </when> - <when value="No" /> - </conditional> - <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - </conditional> - </when> - </conditional> + <when value="Yes"> + <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> + <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> + </when> + <when value="No" /> + </conditional> + <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + </when> + </conditional></inputs><outputs> @@ -471,11 +320,11 @@ tophat -o tmp_dir -p 1 tophat_in1 test-data/tophat_in2.fastqsanger Rename the files in tmp_dir appropriately --> + <param name="sPaired" value="single" /><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" /><param name="genomeSource" value="indexed" /><param name="index" value="tophat_test" /> - <param name="sPaired" value="single" /> - <param name="sSettingsType" value="preSet" /> + <param name="settingsType" value="preSet" /><output name="junctions" file="tophat_out1j.bed" /><output name="accepted_hits" file="tophat_out1h.bam" compare="sim_size" /></test> @@ -486,13 +335,13 @@ tophat -o tmp_dir -p 1 -r 20 tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger Rename the files in tmp_dir appropriately --> + <param name="sPaired" value="paired" /><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" /> + <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" /><param name="genomeSource" value="history" /><param name="ownFile" ftype="fasta" value="tophat_in1.fasta" /> - <param name="sPaired" value="paired" /> - <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" /><param name="mate_inner_distance" value="20" /> - <param name="pSettingsType" value="preSet" /> + <param name="settingsType" value="preSet" /><output name="junctions" file="tophat_out2j.bed" /><output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" /></test> @@ -500,15 +349,15 @@ <test> + <param name="sPaired" value="single"/><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/><param name="genomeSource" value="history"/><param name="ownFile" value="tophat_in1.fasta"/> - <param name="sPaired" value="single"/> - <param name="sSettingsType" value="full"/> + <param name="settingsType" value="full"/><param name="library_type" value="FR Unstranded"/><param name="anchor_length" value="8"/><param name="splice_mismatches" value="0"/> @@ -546,13 +395,13 @@ Replace the + with double-dash Rename the files in tmp_dir appropriately --> + <param name="sPaired" value="paired"/><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/> + <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/><param name="genomeSource" value="indexed"/><param name="index" value="tophat_test"/> - <param name="sPaired" value="paired"/> - <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/><param name="mate_inner_distance" value="20"/> - <param name="pSettingsType" value="full"/> + <param name="settingsType" value="full"/><param name="library_type" value="FR Unstranded"/><param name="mate_std_dev" value="20"/><param name="anchor_length" value="8"/> @@ -644,16 +493,15 @@ -j/--raw-juncs [juncs file] Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-], left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive. -no-novel-juncs Only look for junctions indicated in the supplied GFF file. (ignored without -G) --no-closure-search Disables the mate pair closure-based search for junctions. Currently, has no effect - closure search is off by default. - --closure-search Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the expected inner distance between mates is small (about or less than 50bp) + --closure-search Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the + --min-closure-exon During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50. + --min-closure-intron The minimum intron length that may be found during closure search. The default is 50. + --max-closure-intron The maximum intron length that may be found during closure search. The default is 5000. expected inner distance between mates is small (about or less than 50bp) --no-coverage-search Disables the coverage based search for junctions. --coverage-search Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity. --microexon-search With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer. - --butterfly-search TopHat will use a slower but potentially more sensitive algorithm to find junctions in addition to its standard search. Consider using this if you expect that your experiment produced a lot of reads from pre-mRNA, that fall within the introns of your transcripts. --segment-mismatches Read segments are mapped independently, allowing up to this many mismatches in each segment alignment. The default is 2. --segment-length Each read is cut up into segments, each at least this long. These segments are mapped independently. The default is 25. - --min-closure-exon During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50. - --min-closure-intron The minimum intron length that may be found during closure search. The default is 50. - --max-closure-intron The maximum intron length that may be found during closure search. The default is 5000. --min-coverage-intron The minimum intron length that may be found during coverage search. The default is 50. --max-coverage-intron The maximum intron length that may be found during coverage search. The default is 20000. --min-segment-intron The minimum intron length that may be found during split-segment search. The default is 50. Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: dan: Have implicit SAM to BAM converter sort the output BAM file so that indexing will not fail.
by Bitbucket 27 Apr '12

27 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/605eb591503a/ changeset: 605eb591503a user: dan date: 2012-04-27 21:33:10 summary: Have implicit SAM to BAM converter sort the output BAM file so that indexing will not fail. affected #: 2 files diff -r 5293f1bf1dba762cae71983e40304d1d8e4ae5b5 -r 605eb591503a73ed9fdc939f71c14e6c74762673 lib/galaxy/datatypes/converters/sam_to_bam.py --- /dev/null +++ b/lib/galaxy/datatypes/converters/sam_to_bam.py @@ -0,0 +1,69 @@ +#!/usr/bin/env python +#Dan Blankenberg + +""" +A wrapper script for converting SAM to BAM, with sorting. +%prog input_filename.sam output_filename.bam +""" + +import sys, optparse, os, tempfile, subprocess, shutil + +CHUNK_SIZE = 2**20 #1mb + + +def cleanup_before_exit( tmp_dir ): + if tmp_dir and os.path.exists( tmp_dir ): + shutil.rmtree( tmp_dir ) + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + (options, args) = parser.parse_args() + + assert len( args ) == 2, 'You must specify the input and output filenames' + input_filename, output_filename = args + + tmp_dir = tempfile.mkdtemp( prefix='tmp-sam_to_bam_converter-' ) + + #convert to SAM + unsorted_bam_filename = os.path.join( tmp_dir, 'unsorted.bam' ) + unsorted_stderr_filename = os.path.join( tmp_dir, 'unsorted.stderr' ) + cmd = 'samtools view -bS "%s" > "%s"' % ( input_filename, unsorted_bam_filename ) + proc = subprocess.Popen( args=cmd, stderr=open( unsorted_stderr_filename, 'wb' ), shell=True, cwd=tmp_dir ) + return_code = proc.wait() + if return_code: + stderr_target = sys.stderr + else: + stderr_target = sys.stdout + stderr = open( unsorted_stderr_filename ) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + + #sort sam, so indexing will not fail + sorted_stderr_filename = os.path.join( tmp_dir, 'sorted.stderr' ) + sorting_prefix = os.path.join( tmp_dir, 'sorted_bam' ) + cmd = 'samtools sort -o "%s" "%s" > "%s"' % ( unsorted_bam_filename, sorting_prefix, output_filename ) + proc = subprocess.Popen( args=cmd, stderr=open( sorted_stderr_filename, 'wb' ), shell=True, cwd=tmp_dir ) + return_code = proc.wait() + + if return_code: + stderr_target = sys.stderr + else: + stderr_target = sys.stdout + stderr = open( sorted_stderr_filename ) + while True: + chunk = stderr.read( CHUNK_SIZE ) + if chunk: + stderr_target.write( chunk ) + else: + break + stderr.close() + + cleanup_before_exit( tmp_dir ) + +if __name__=="__main__": __main__() diff -r 5293f1bf1dba762cae71983e40304d1d8e4ae5b5 -r 605eb591503a73ed9fdc939f71c14e6c74762673 lib/galaxy/datatypes/converters/sam_to_bam.xml --- a/lib/galaxy/datatypes/converters/sam_to_bam.xml +++ b/lib/galaxy/datatypes/converters/sam_to_bam.xml @@ -1,11 +1,11 @@ -<tool id="CONVERTER_sam_to_bam" name="Convert SAM to BAM" version="1.0.0"> +<tool id="CONVERTER_sam_to_bam" name="Convert SAM to BAM" version="2.0.0"> - <command>samtools view -bS $input1 > $output 2> /dev/null </command> + <command interpreter="python">sam_to_bam.py $input1 $output</command><inputs><param name="input1" type="data" format="sam" label="SAM file"/></inputs> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: jgoecks: More cleaning of Tophat wrapper.
by Bitbucket 27 Apr '12

27 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/5293f1bf1dba/ changeset: 5293f1bf1dba user: jgoecks date: 2012-04-27 21:22:11 summary: More cleaning of Tophat wrapper. affected #: 2 files diff -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 -r 5293f1bf1dba762cae71983e40304d1d8e4ae5b5 tools/ngs_rna/tophat_wrapper.py --- a/tools/ngs_rna/tophat_wrapper.py +++ b/tools/ngs_rna/tophat_wrapper.py @@ -52,16 +52,16 @@ supplied GFF file. (ignored without -G)") parser.add_option( '', '--no-novel-indels', action="store_true", dest='no_novel_indels', help="Skip indel search. Indel search is enabled by default.") # Types of search. - parser.add_option( '', '--microexon-search', action="store_true", dest='microexon_search', help='With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.') parser.add_option( '', '--closure-search', action="store_true", dest='closure_search', help='Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the expected inner distance between mates is small (<= 50bp)') parser.add_option( '', '--no-closure-search', action="store_false", dest='closure_search' ) + parser.add_option( '', '--min-closure-exon', dest='min_closure_exon', help='Minimum length for exonic hops in potential splice graph' ) + parser.add_option( '', '--min-closure-intron', dest='min_closure_intron', help='Minimum intron length that may be found during closure search' ) + parser.add_option( '', '--max-closure-intron', dest='max_closure_intron', help='Maximum intron length that may be found during closure search' ) + parser.add_option( '', '--microexon-search', action="store_true", dest='microexon_search', help='With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.') parser.add_option( '', '--coverage-search', action="store_true", dest='coverage_search', help='Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity.') parser.add_option( '', '--no-coverage-search', action="store_false", dest='coverage_search' ) parser.add_option( '', '--min-segment-intron', dest='min_segment_intron', help='Minimum intron length that may be found during split-segment search' ) parser.add_option( '', '--max-segment-intron', dest='max_segment_intron', help='Maximum intron length that may be found during split-segment search' ) - parser.add_option( '', '--min-closure-exon', dest='min_closure_exon', help='Minimum length for exonic hops in potential splice graph' ) - parser.add_option( '', '--min-closure-intron', dest='min_closure_intron', help='Minimum intron length that may be found during closure search' ) - parser.add_option( '', '--max-closure-intron', dest='max_closure_intron', help='Maximum intron length that may be found during closure search' ) parser.add_option( '', '--min-coverage-intron', dest='min_coverage_intron', help='Minimum intron length that may be found during coverage search' ) parser.add_option( '', '--max-coverage-intron', dest='max_coverage_intron', help='Maximum intron length that may be found during coverage search' ) @@ -166,7 +166,7 @@ opts += ' --no-closure-search' if options.microexon_search: opts += ' --microexon-search' - if options.single_paired == 'paired': + if options.single_paired == 'paired' and options.mate_std_dev: opts += ' --mate-std-dev %s' % options.mate_std_dev if options.initial_read_mismatches: opts += ' --initial-read-mismatches %d' % int( options.initial_read_mismatches ) diff -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 -r 5293f1bf1dba762cae71983e40304d1d8e4ae5b5 tools/ngs_rna/tophat_wrapper.xml --- a/tools/ngs_rna/tophat_wrapper.xml +++ b/tools/ngs_rna/tophat_wrapper.xml @@ -7,150 +7,111 @@ </requirements><command interpreter="python"> tophat_wrapper.py - ## Change this to accommodate the number of threads you have available. - --num-threads="4" + + ## Change this to accommodate the number of threads you have available. + --num-threads="4" - ## Provide outputs. - --junctions-output=$junctions - --hits-output=$accepted_hits + ## Provide outputs. + --junctions-output=$junctions + --hits-output=$accepted_hits - ## Handle reference file. - #if $refGenomeSource.genomeSource == "history": - --own-file=$refGenomeSource.ownFile + ## Handle reference file. + #if $refGenomeSource.genomeSource == "history": + --own-file=$refGenomeSource.ownFile + #else: + --indexes-path="${refGenomeSource.index.fields.path}" + #end if + + ## Are reads single-end or paired? + --single-paired=$singlePaired.sPaired + + ## First input file always required. + --input1=$input1 + + ## Second input only if input is paired-end. + #if $singlePaired.sPaired == "paired" + --input2=$singlePaired.input2 + -r $singlePaired.mate_inner_distance + --mate-std-dev=$singlePaired.mate_std_dev + #end if + + ## Set params. + --settings=$params.settingsType + #if $params.settingsType == "full": + -a $params.anchor_length + -m $params.splice_mismatches + -i $params.min_intron_length + -I $params.max_intron_length + -g $params.max_multihits + --min-segment-intron $params.min_segment_intron + --max-segment-intron $params.max_segment_intron + --initial-read-mismatches=$params.initial_read_mismatches + --seg-mismatches=$params.seg_mismatches + --seg-length=$params.seg_length + --library-type=$params.library_type + + ## Closure search. + #if $params.closure_search.use_search == "Yes": + --closure-search + --min-closure-exon $params.closure_search.min_closure_exon + --min-closure-intron $params.closure_search.min_closure_intron + --max-closure-intron $params.closure_search.max_closure_intron #else: - --indexes-path="${refGenomeSource.index.fields.path}" + --no-closure-search + #end if + + ## Indel search. + #if $params.indel_search.allow_indel_search == "Yes": + ## --allow-indels + --max-insertion-length $params.indel_search.max_insertion_length + --max-deletion-length $params.indel_search.max_deletion_length + #else: + --no-novel-indels #end if - ## Are reads single-end or paired? - --single-paired=$singlePaired.sPaired - - ## First input file always required. - --input1=$input1 - - ## Set params based on whether reads are single-end or paired. - #if $singlePaired.sPaired == "single": - --settings=$singlePaired.sParams.sSettingsType - #if $singlePaired.sParams.sSettingsType == "full": - -a $singlePaired.sParams.anchor_length - -m $singlePaired.sParams.splice_mismatches - -i $singlePaired.sParams.min_intron_length - -I $singlePaired.sParams.max_intron_length - -g $singlePaired.sParams.max_multihits - --min-segment-intron $singlePaired.sParams.min_segment_intron - --max-segment-intron $singlePaired.sParams.max_segment_intron - --initial-read-mismatches=$singlePaired.sParams.initial_read_mismatches - --seg-mismatches=$singlePaired.sParams.seg_mismatches - --seg-length=$singlePaired.sParams.seg_length - --library-type=$singlePaired.sParams.library_type - - ## Indel search. - #if $singlePaired.sParams.indel_search.allow_indel_search == "Yes": - ## --allow-indels - --max-insertion-length $singlePaired.sParams.indel_search.max_insertion_length - --max-deletion-length $singlePaired.sParams.indel_search.max_deletion_length - #else: - --no-novel-indels - #end if - - ## Supplying junctions parameters. - #if $singlePaired.sParams.own_junctions.use_junctions == "Yes": - #if $singlePaired.sParams.own_junctions.gene_model_ann.use_annotations == "Yes": - -G $singlePaired.sParams.own_junctions.gene_model_ann.gene_annotation_model - #end if - #if $singlePaired.sParams.own_junctions.raw_juncs.use_juncs == "Yes": - -j $singlePaired.sParams.own_junctions.raw_juncs.raw_juncs - #end if - ## TODO: No idea why a string cast is necessary, but it is: - #if str($singlePaired.sParams.own_junctions.no_novel_juncs) == "Yes": - --no-novel-juncs - #end if - #end if - - #if $singlePaired.sParams.closure_search.use_search == "Yes": - --closure-search - --min-closure-exon $singlePaired.sParams.closure_search.min_closure_exon - --min-closure-intron $singlePaired.sParams.closure_search.min_closure_intron - --max-closure-intron $singlePaired.sParams.closure_search.max_closure_intron - #else: - --no-closure-search - #end if - #if $singlePaired.sParams.coverage_search.use_search == "Yes": - --coverage-search - --min-coverage-intron $singlePaired.sParams.coverage_search.min_coverage_intron - --max-coverage-intron $singlePaired.sParams.coverage_search.max_coverage_intron - #else: - --no-coverage-search - #end if - ## TODO: No idea why the type conversion is necessary, but it seems to be. - #if str($singlePaired.sParams.microexon_search) == "Yes": - --microexon-search - #end if + ## Supplying junctions parameters. + #if $params.own_junctions.use_junctions == "Yes": + #if $params.own_junctions.gene_model_ann.use_annotations == "Yes": + -G $params.own_junctions.gene_model_ann.gene_annotation_model #end if - #else: - --input2=$singlePaired.input2 - -r $singlePaired.mate_inner_distance - --settings=$singlePaired.pParams.pSettingsType - #if $singlePaired.pParams.pSettingsType == "full": - --mate-std-dev=$singlePaired.pParams.mate_std_dev - -a $singlePaired.pParams.anchor_length - -m $singlePaired.pParams.splice_mismatches - -i $singlePaired.pParams.min_intron_length - -I $singlePaired.pParams.max_intron_length - -g $singlePaired.pParams.max_multihits - --min-segment-intron $singlePaired.pParams.min_segment_intron - --max-segment-intron $singlePaired.pParams.max_segment_intron - --initial-read-mismatches=$singlePaired.pParams.initial_read_mismatches - --seg-mismatches=$singlePaired.pParams.seg_mismatches - --seg-length=$singlePaired.pParams.seg_length - --library-type=$singlePaired.pParams.library_type - - ## Indel search. - #if $singlePaired.pParams.indel_search.allow_indel_search == "Yes": - ## --allow-indels - --max-insertion-length $singlePaired.pParams.indel_search.max_insertion_length - --max-deletion-length $singlePaired.pParams.indel_search.max_deletion_length - #else: - --no-novel-indels - #end if - - ## Supplying junctions parameters. - #if $singlePaired.pParams.own_junctions.use_junctions == "Yes": - #if $singlePaired.pParams.own_junctions.gene_model_ann.use_annotations == "Yes": - -G $singlePaired.pParams.own_junctions.gene_model_ann.gene_annotation_model - #end if - #if $singlePaired.pParams.own_junctions.raw_juncs.use_juncs == "Yes": - -j $singlePaired.pParams.own_junctions.raw_juncs.raw_juncs - #end if - ## TODO: No idea why type cast is necessary, but it is: - #if str($singlePaired.pParams.own_junctions.no_novel_juncs) == "Yes": - --no-novel-juncs - #end if - #end if - - #if $singlePaired.pParams.closure_search.use_search == "Yes": - --closure-search - --min-closure-exon $singlePaired.pParams.closure_search.min_closure_exon - --min-closure-intron $singlePaired.pParams.closure_search.min_closure_intron - --max-closure-intron $singlePaired.pParams.closure_search.max_closure_intron - #else: - --no-closure-search - #end if - #if $singlePaired.pParams.coverage_search.use_search == "Yes": - --coverage-search - --min-coverage-intron $singlePaired.pParams.coverage_search.min_coverage_intron - --max-coverage-intron $singlePaired.pParams.coverage_search.max_coverage_intron - #else: - --no-coverage-search - #end if - ## TODO: No idea why the type conversion is necessary, but it seems to be. - #if str ($singlePaired.pParams.microexon_search) == "Yes": - --microexon-search - #end if + #if $params.own_junctions.raw_juncs.use_juncs == "Yes": + -j $params.own_junctions.raw_juncs.raw_juncs + #end if + ## TODO: No idea why a string cast is necessary, but it is: + #if str($params.own_junctions.no_novel_juncs) == "Yes": + --no-novel-juncs #end if #end if + + #if $params.coverage_search.use_search == "Yes": + --coverage-search + --min-coverage-intron $params.coverage_search.min_coverage_intron + --max-coverage-intron $params.coverage_search.max_coverage_intron + #else: + --no-coverage-search + #end if + ## TODO: No idea why the type conversion is necessary, but it seems to be. + #if str($params.microexon_search) == "Yes": + --microexon-search + #end if + #end if </command><inputs> - <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <conditional name="singlePaired"> + <param name="sPaired" type="select" label="Is this library mate-paired?"> + <option value="single">Single-end</option> + <option value="paired">Paired-end</option> + </param> + <when value="single"> + <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ dataset" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/> + </when> + <when value="paired"> + <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ dataset--forward reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ dataset--reverse reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param name="mate_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs" /> + <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="The standard deviation for the distribution on inner distances between mate pairs."/> + </when> + </conditional><conditional name="refGenomeSource"><param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"><option value="indexed">Use a built-in index</option> @@ -168,221 +129,109 @@ <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" /></when></conditional> - <conditional name="singlePaired"> - <param name="sPaired" type="select" label="Is this library mate-paired?"> - <option value="single">Single-end</option> - <option value="paired">Paired-end</option> + <conditional name="params"> + <param name="settingsType" type="select" label="TopHat settings to use" help="You can use the default settings or set custom values for any of Tophat's parameters."> + <option value="preSet">Use Defaults</option> + <option value="full">Full parameter list</option></param> - <when value="single"> - <conditional name="sParams"> - <param name="sSettingsType" type="select" label="TopHat settings to use" help="You can use the default settings or set custom values for any of Tophat's parameters."> - <option value="preSet">Use Defaults</option> - <option value="full">Full parameter list</option> - </param> - <when value="preSet" /> -  - <when value="full"> - <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> - <option value="fr-unstranded">FR Unstranded</option> - <option value="fr-firststrand">FR First Strand</option> - <option value="fr-secondstrand">FR Second Strand</option> + <when value="preSet" /> +  + <when value="full"> + <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> + <option value="fr-unstranded">FR Unstranded</option> + <option value="fr-firststrand">FR First Strand</option> + <option value="fr-secondstrand">FR Second Strand</option> + </param> + <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> + <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> + <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> + <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> + <conditional name="indel_search"> + <param name="allow_indel_search" type="select" label="Allow indel search"> + <option value="Yes">Yes</option> + <option value="No">No</option></param> - <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> - <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> - <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> - <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> - <conditional name="indel_search"> - <param name="allow_indel_search" type="select" label="Allow indel search"> - <option value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="No"/> - <when value="Yes"> - <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> - <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> - </when> - </conditional> -alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" /> - <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> - <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> - <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> - <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> - <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> - <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> - -  - <conditional name="own_junctions"> - <param name="use_junctions" type="select" label="Use Own Junctions"> + <when value="No"/> + <when value="Yes"> + <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> + <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> + </when> + </conditional> + alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" /> + <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> + <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> + <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> + <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> + <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> + <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> + +  + <conditional name="own_junctions"> + <param name="use_junctions" type="select" label="Use Own Junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="Yes"> + <conditional name="gene_model_ann"> + <param name="use_annotations" type="select" label="Use Gene Annotation Model"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" /> + <when value="Yes"> + <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> + </when> + </conditional> + <conditional name="raw_juncs"> + <param name="use_juncs" type="select" label="Use Raw Junctions"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="No" /> + <when value="Yes"> + <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> + </when> + </conditional> + <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"><option value="No">No</option><option value="Yes">Yes</option></param> - <when value="Yes"> - <conditional name="gene_model_ann"> - <param name="use_annotations" type="select" label="Use Gene Annotation Model"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> - </when> - </conditional> - <conditional name="raw_juncs"> - <param name="use_juncs" type="select" label="Use Raw Junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> - </when> - </conditional> - <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - <when value="No" /> - </conditional> - -  - <conditional name="closure_search"> - <param name="use_search" type="select" label="Use Closure Search"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> - <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> - <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> - </when> - <when value="No" /> - </conditional> -  - <conditional name="coverage_search"> - <param name="use_search" type="select" label="Use Coverage Search"> - <option selected="true" value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="Yes"> - <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> - <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> - </when> - <when value="No" /> - </conditional> - <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."> + </when> + <when value="No" /> + </conditional> + +  + <conditional name="closure_search"> + <param name="use_search" type="select" label="Use Closure Search"> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + <when value="Yes"> + <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> + <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> + <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> + </when> + <when value="No" /> + </conditional> + +  + <conditional name="coverage_search"> + <param name="use_search" type="select" label="Use Coverage Search"> + <option selected="true" value="Yes">Yes</option><option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - </conditional> - </when> - <when value="paired"> - <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> - <param name="mate_inner_distance" type="integer" value="20" label="Mean Inner Distance between Mate Pairs" /> - <conditional name="pParams"> - <param name="pSettingsType" type="select" label="TopHat settings to use" help="For most mapping needs use Commonly used settings. If you want full control use Full parameter list"> - <option value="preSet">Commonly used</option> - <option value="full">Full parameter list</option></param> - <when value="preSet" /> -  - <when value="full"> - <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol."> - <option value="fr-unstranded">FR Unstranded</option> - <option value="fr-firststrand">FR First Strand</option> - <option value="fr-secondstrand">FR Second Strand</option> - </param> - <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="The standard deviation for the distribution on inner distances between mate pairs."/> - <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." /> - <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" /> - <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." /> - <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." /> - <conditional name="indel_search"> - <param name="allow_indel_search" type="select" label="Allow indel search"> - <option value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="No"/> - <when value="Yes"> - <param name="max_insertion_length" type="integer" value="3" label="Max insertion length." help="The maximum insertion length." /> - <param name="max_deletion_length" type="integer" value="3" label="Max deletion length." help="The maximum deletion length." /> - </when> - </conditional> - <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" /> - <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" /> - <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" /> - <param name="initial_read_mismatches" type="integer" min="0" value="2" label="Number of mismatches allowed in the initial read mapping" /> - <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" /> - <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" /> -  - <conditional name="own_junctions"> - <param name="use_junctions" type="select" label="Use Own Junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <conditional name="gene_model_ann"> - <param name="use_annotations" type="select" label="Use Gene Annotation Model"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="gtf" name="gene_annotation_model" type="data" label="Gene Model Annotations" help="TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping."/> - </when> - </conditional> - <conditional name="raw_juncs"> - <param name="use_juncs" type="select" label="Use Raw Junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="No" /> - <when value="Yes"> - <param format="interval" name="raw_juncs" type="data" label="Raw Junctions" help="Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-] left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive."/> - </when> - </conditional> - <param name="no_novel_juncs" type="select" label="Only look for supplied junctions"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - <when value="No" /> - </conditional> - -  - <conditional name="closure_search"> - <param name="use_search" type="select" label="Use Closure Search"> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - <when value="Yes"> - <param name="min_closure_exon" type="integer" value="50" label="During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50." /> - <param name="min_closure_intron" type="integer" value="50" label="Minimum intron length that may be found during closure search" /> - <param name="max_closure_intron" type="integer" value="5000" label="Maximum intron length that may be found during closure search" /> - </when> - <when value="No" /> - </conditional> -  - <conditional name="coverage_search"> - <param name="use_search" type="select" label="Use Coverage Search"> - <option selected="true" value="Yes">Yes</option> - <option value="No">No</option> - </param> - <when value="Yes"> - <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> - <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> - </when> - <when value="No" /> - </conditional> - <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."> - <option value="No">No</option> - <option value="Yes">Yes</option> - </param> - </when> - </conditional> - </when> - </conditional> + <when value="Yes"> + <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" /> + <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" /> + </when> + <when value="No" /> + </conditional> + <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer."> + <option value="No">No</option> + <option value="Yes">Yes</option> + </param> + </when> + </conditional></inputs><outputs> @@ -471,11 +320,11 @@ tophat -o tmp_dir -p 1 tophat_in1 test-data/tophat_in2.fastqsanger Rename the files in tmp_dir appropriately --> + <param name="sPaired" value="single" /><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" /><param name="genomeSource" value="indexed" /><param name="index" value="tophat_test" /> - <param name="sPaired" value="single" /> - <param name="sSettingsType" value="preSet" /> + <param name="settingsType" value="preSet" /><output name="junctions" file="tophat_out1j.bed" /><output name="accepted_hits" file="tophat_out1h.bam" compare="sim_size" /></test> @@ -486,13 +335,13 @@ tophat -o tmp_dir -p 1 -r 20 tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger Rename the files in tmp_dir appropriately --> + <param name="sPaired" value="paired" /><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" /> + <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" /><param name="genomeSource" value="history" /><param name="ownFile" ftype="fasta" value="tophat_in1.fasta" /> - <param name="sPaired" value="paired" /> - <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" /><param name="mate_inner_distance" value="20" /> - <param name="pSettingsType" value="preSet" /> + <param name="settingsType" value="preSet" /><output name="junctions" file="tophat_out2j.bed" /><output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" /></test> @@ -500,15 +349,15 @@ <test> + <param name="sPaired" value="single"/><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/><param name="genomeSource" value="history"/><param name="ownFile" value="tophat_in1.fasta"/> - <param name="sPaired" value="single"/> - <param name="sSettingsType" value="full"/> + <param name="settingsType" value="full"/><param name="library_type" value="FR Unstranded"/><param name="anchor_length" value="8"/><param name="splice_mismatches" value="0"/> @@ -546,13 +395,13 @@ Replace the + with double-dash Rename the files in tmp_dir appropriately --> + <param name="sPaired" value="paired"/><param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/> + <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/><param name="genomeSource" value="indexed"/><param name="index" value="tophat_test"/> - <param name="sPaired" value="paired"/> - <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/><param name="mate_inner_distance" value="20"/> - <param name="pSettingsType" value="full"/> + <param name="settingsType" value="full"/><param name="library_type" value="FR Unstranded"/><param name="mate_std_dev" value="20"/><param name="anchor_length" value="8"/> @@ -644,16 +493,15 @@ -j/--raw-juncs [juncs file] Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-], left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive. -no-novel-juncs Only look for junctions indicated in the supplied GFF file. (ignored without -G) --no-closure-search Disables the mate pair closure-based search for junctions. Currently, has no effect - closure search is off by default. - --closure-search Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the expected inner distance between mates is small (about or less than 50bp) + --closure-search Enables the mate pair closure-based search for junctions. Closure-based search should only be used when the + --min-closure-exon During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50. + --min-closure-intron The minimum intron length that may be found during closure search. The default is 50. + --max-closure-intron The maximum intron length that may be found during closure search. The default is 5000. expected inner distance between mates is small (about or less than 50bp) --no-coverage-search Disables the coverage based search for junctions. --coverage-search Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity. --microexon-search With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer. - --butterfly-search TopHat will use a slower but potentially more sensitive algorithm to find junctions in addition to its standard search. Consider using this if you expect that your experiment produced a lot of reads from pre-mRNA, that fall within the introns of your transcripts. --segment-mismatches Read segments are mapped independently, allowing up to this many mismatches in each segment alignment. The default is 2. --segment-length Each read is cut up into segments, each at least this long. These segments are mapped independently. The default is 25. - --min-closure-exon During closure search for paired end reads, exonic hops in the potential splice graph must be at least this long. The default is 50. - --min-closure-intron The minimum intron length that may be found during closure search. The default is 50. - --max-closure-intron The maximum intron length that may be found during closure search. The default is 5000. --min-coverage-intron The minimum intron length that may be found during coverage search. The default is 50. --max-coverage-intron The maximum intron length that may be found during coverage search. The default is 20000. --min-segment-intron The minimum intron length that may be found during split-segment search. The default is 50. Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: jgoecks: Skeleton wrapper for Bowtie2.
by Bitbucket 26 Apr '12

26 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/51fccbc2e9bc/ changeset: 51fccbc2e9bc user: jgoecks date: 2012-04-26 21:28:17 summary: Skeleton wrapper for Bowtie2. affected #: 5 files diff -r 1c8eb226af94b29ef8484c4fbed557282170259e -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 tool-data/bowtie2_indices.loc.sample --- /dev/null +++ b/tool-data/bowtie2_indices.loc.sample @@ -0,0 +1,37 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of Bowtie2 indexed sequences data files. You will +#need to create these data files and then create a bowtie_indices.loc +#file similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The bowtie2_indices.loc +#file has this format (longer white space characters are TAB characters): +# +#<unique_build_id><dbkey><display_name><file_base_path> +# +#So, for example, if you had hg18 indexed stored in +#/depot/data2/galaxy/bowtie2/hg18/, +#then the bowtie2_indices.loc entry would look like this: +# +#hg18 hg18 hg18 /depot/data2/galaxy/bowtie2/hg18/hg18 +# +#and your /depot/data2/galaxy/bowtie2/hg18/ directory +#would contain hg18.*.ebwt files: +# +#-rw-r--r-- 1 james universe 830134 2005-09-13 10:12 hg18.1.ebwt +#-rw-r--r-- 1 james universe 527388 2005-09-13 10:12 hg18.2.ebwt +#-rw-r--r-- 1 james universe 269808 2005-09-13 10:12 hg18.3.ebwt +#...etc... +# +#Your bowtie2_indices.loc file should include an entry per line for each +#index set you have stored. The "file" in the path does not actually +#exist, but it is the prefix for the actual index files. For example: +# +#hg18canon hg18 hg18 Canonical /depot/data2/galaxy/bowtie2/hg18/hg18canon +#hg18full hg18 hg18 Full /depot/data2/galaxy/bowtie2/hg18/hg18full +#/orig/path/hg19 hg19 hg19 /depot/data2/galaxy/bowtie2/hg19/hg19 +#...etc... +# +#Note that for backwards compatibility with workflows, the unique ID of +#an entry must be the path that was in the original loc file, because that +#is the value stored in the workflow for that parameter. That is why the +#hg19 entry above looks odd. New genomes can be better-looking. +# diff -r 1c8eb226af94b29ef8484c4fbed557282170259e -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 tool_conf.xml.sample --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -336,6 +336,7 @@ <tool file="sr_mapping/lastz_wrapper.xml" /><tool file="sr_mapping/lastz_paired_reads_wrapper.xml" /><tool file="sr_mapping/bowtie_wrapper.xml" /> + <tool file="sr_mapping/bowtie2_wrapper.xml" /><tool file="sr_mapping/bowtie_color_wrapper.xml" /><tool file="sr_mapping/bwa_wrapper.xml" /><tool file="sr_mapping/bwa_color_wrapper.xml" /> diff -r 1c8eb226af94b29ef8484c4fbed557282170259e -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 tool_data_table_conf.xml.sample --- a/tool_data_table_conf.xml.sample +++ b/tool_data_table_conf.xml.sample @@ -25,6 +25,11 @@ <columns>value, dbkey, name, path</columns><file path="tool-data/bowtie_indices.loc" /></table> +  + <table name="bowtie2_indexes" comment_char="#"> + <columns>value, dbkey, name, path</columns> + <file path="tool-data/bowtie2_indices.loc" /> + </table><table name="bowtie_indexes_color" comment_char="#"><columns>value, dbkey, name, path</columns> diff -r 1c8eb226af94b29ef8484c4fbed557282170259e -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 tools/sr_mapping/bowtie2_wrapper.py --- /dev/null +++ b/tools/sr_mapping/bowtie2_wrapper.py @@ -0,0 +1,115 @@ +#!/usr/bin/env python + +import optparse, os, shutil, subprocess, sys, tempfile, fileinput + +def stop_err( msg ): + sys.stderr.write( "%s\n" % msg ) + sys.exit() + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + parser.add_option( '-p', '--num-threads', dest='num_threads', help='Use this many threads to align reads. The default is 1.' ) + parser.add_option( '', '--own-file', dest='own_file', help='' ) + parser.add_option( '-D', '--indexes-path', dest='index_path', help='Indexes directory; location of .ebwt and .fa files.' ) + + # Wrapper options. + parser.add_option( '-O', '--output', dest='output' ) + parser.add_option( '-1', '--input1', dest='input1', help='The (forward or single-end) reads file in Sanger FASTQ format' ) + parser.add_option( '-2', '--input2', dest='input2', help='The reverse reads file in Sanger FASTQ format' ) + parser.add_option( '', '--single-paired', dest='single_paired', help='' ) + parser.add_option( '', '--settings', dest='settings', help='' ) + + (options, args) = parser.parse_args() + + # Creat bowtie index if necessary. + tmp_index_dir = tempfile.mkdtemp() + if options.own_file: + index_path = os.path.join( tmp_index_dir, '.'.join( os.path.split( options.own_file )[1].split( '.' )[:-1] ) ) + try: + os.link( options.own_file, index_path + '.fa' ) + except: + # Bowtie prefers (but doesn't require) fasta file to be in same directory, with .fa extension + pass + cmd_index = 'bowtie2-build -f %s %s' % ( options.own_file, index_path ) + try: + tmp = tempfile.NamedTemporaryFile( dir=tmp_index_dir ).name + tmp_stderr = open( tmp, 'wb' ) + proc = subprocess.Popen( args=cmd_index, shell=True, cwd=tmp_index_dir, stderr=tmp_stderr.fileno() ) + returncode = proc.wait() + tmp_stderr.close() + # get stderr, allowing for case where it's very large + tmp_stderr = open( tmp, 'rb' ) + stderr = '' + buffsize = 1048576 + try: + while True: + stderr += tmp_stderr.read( buffsize ) + if not stderr or len( stderr ) % buffsize != 0: + break + except OverflowError: + pass + tmp_stderr.close() + if returncode != 0: + raise Exception, stderr + except Exception, e: + if os.path.exists( tmp_index_dir ): + shutil.rmtree( tmp_index_dir ) + stop_err( 'Error indexing reference sequence\n' + str( e ) ) + else: + index_path = options.index_path + + # Build bowtie command. + cmd = 'bowtie2 %s -x %s %s -S %s' + + # Set up reads. + if options.single_paired == 'paired': + reads = " -1 %s -2 %s" % ( options.input1, options.input2 ) + else: + reads = " -U %s" % ( options.input1 ) + + # Set up options. + opts = '-p %s' % ( options.num_threads ) + if options.settings == 'preSet': + pass + else: + pass + + # Final command: + cmd = cmd % ( opts, index_path, reads, options.output ) + print cmd + + # Run + try: + tmp_out = tempfile.NamedTemporaryFile().name + tmp_stdout = open( tmp_out, 'wb' ) + tmp_err = tempfile.NamedTemporaryFile().name + tmp_stderr = open( tmp_err, 'wb' ) + proc = subprocess.Popen( args=cmd, shell=True, cwd=".", stdout=tmp_stdout, stderr=tmp_stderr ) + returncode = proc.wait() + tmp_stderr.close() + # get stderr, allowing for case where it's very large + tmp_stderr = open( tmp_err, 'rb' ) + stderr = '' + buffsize = 1048576 + try: + while True: + stderr += tmp_stderr.read( buffsize ) + if not stderr or len( stderr ) % buffsize != 0: + break + except OverflowError: + pass + tmp_stdout.close() + tmp_stderr.close() + if returncode != 0: + raise Exception, stderr + + # TODO: look for errors in program output. + except Exception, e: + stop_err( 'Error in bowtie2:\n' + str( e ) ) + + # Clean up temp dirs + if os.path.exists( tmp_index_dir ): + shutil.rmtree( tmp_index_dir ) + +if __name__=="__main__": __main__() diff -r 1c8eb226af94b29ef8484c4fbed557282170259e -r 51fccbc2e9bc401c83b52447b513e201fe776ba2 tools/sr_mapping/bowtie2_wrapper.xml --- /dev/null +++ b/tools/sr_mapping/bowtie2_wrapper.xml @@ -0,0 +1,109 @@ +<tool id="bowtie2" name="Bowtie2" version="0.1"> +  + <description>is a short-read mapper</description> + <version_command>bowtie2 --version</version_command> + <requirements> + <requirement type="package">bowtie2</requirement> + </requirements> + <command interpreter="python"> + bowtie2_wrapper.py + + ## Change this to accommodate the number of threads you have available. + --num-threads="4" + + ## Outputs. + --output=$output + + ## Handle reference file. + #if $refGenomeSource.genomeSource == "history": + --own-file=$refGenomeSource.ownFile + #else: + --indexes-path="${refGenomeSource.index.fields.path}" + #end if + + ## Are reads single-end or paired? + --single-paired=$singlePaired.sPaired + + ## First input file always required. + --input1=$input1 + + ## Second input only if input is paired-end. + #if $singlePaired.sPaired == "paired" + --input2=$singlePaired.input2 + #end if + + ## Set params. + --settings=$params.settingsType + </command> + <inputs> + <conditional name="singlePaired"> + <param name="sPaired" type="select" label="Is this library mate-paired?"> + <option value="single">Single-end</option> + <option value="paired">Paired-end</option> + </param> + <when value="single"> + <param format="fastqsanger" name="input1" type="data" label="FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/> + </when> + <when value="paired"> + <param format="fastqsanger" name="input1" type="data" label="FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> + <param format="fastqsanger" name="input2" type="data" label="FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" /> +  + </when> + </conditional> + <conditional name="refGenomeSource"> + <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options"> + <option value="indexed">Use a built-in index</option> + <option value="history">Use one from the history</option> + </param> + <when value="indexed"> + <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact the Galaxy team"> + <options from_data_table="bowtie2_indexes"> + <filter type="sort_by" column="2"/> + <validator type="no_options" message="No indexes are available for the selected input dataset"/> + </options> + </param> + </when> + <when value="history"> + <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select the reference genome" /> + </when> + </conditional> + <conditional name="params"> + <param name="settingsType" type="select" label="Bowtie settings to use" help="You can use the default settings or set custom values for any of Bowtie's parameters."> + <option value="preSet">Use Defaults</option> + <option value="full">Full parameter list</option> + </param> + <when value="preSet" /> +  + <when value="full"> + </when> + </conditional> + </inputs> + + <outputs> + <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads"> + <actions> + <conditional name="refGenomeSource.genomeSource"> + <when value="indexed"> + <action type="metadata" name="dbkey"> + <option type="from_data_table" name="bowtie2_indexes" column="1" offset="0"> + <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> + <filter type="param_value" ref="refGenomeSource.index" column="0"/> + </option> + </action> + </when> + <when value="history"> + <action type="metadata" name="dbkey"> + <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" /> + </action> + </when> + </conditional> + </actions> + </data> + </outputs> + + <tests> + </tests> + + <help> + </help> +</tool> Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: jgoecks: Remove version code from tophat wrappers as this is now handled by <version> tag.
by Bitbucket 26 Apr '12

26 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/1c8eb226af94/ changeset: 1c8eb226af94 user: jgoecks date: 2012-04-26 20:25:01 summary: Remove version code from tophat wrappers as this is now handled by <version> tag. affected #: 2 files diff -r c16adb4630e58fe4001e488367e27e911d7ec0cb -r 1c8eb226af94b29ef8484c4fbed557282170259e tools/ngs_rna/tophat2_wrapper.py --- a/tools/ngs_rna/tophat2_wrapper.py +++ b/tools/ngs_rna/tophat2_wrapper.py @@ -80,21 +80,6 @@ (options, args) = parser.parse_args() - # output version # of tool - try: - tmp = tempfile.NamedTemporaryFile().name - tmp_stdout = open( tmp, 'wb' ) - proc = subprocess.Popen( args='tophat -v', shell=True, stdout=tmp_stdout ) - tmp_stdout.close() - returncode = proc.wait() - stdout = open( tmp_stdout.name, 'rb' ).readline().strip() - if stdout: - sys.stdout.write( '%s\n' % stdout ) - else: - raise Exception - except: - sys.stdout.write( 'Could not determine Tophat version\n' ) - # Color or base space space = '' if options.color_space: diff -r c16adb4630e58fe4001e488367e27e911d7ec0cb -r 1c8eb226af94b29ef8484c4fbed557282170259e tools/ngs_rna/tophat_wrapper.py --- a/tools/ngs_rna/tophat_wrapper.py +++ b/tools/ngs_rna/tophat_wrapper.py @@ -73,21 +73,6 @@ (options, args) = parser.parse_args() - # output version # of tool - try: - tmp = tempfile.NamedTemporaryFile().name - tmp_stdout = open( tmp, 'wb' ) - proc = subprocess.Popen( args='tophat -v', shell=True, stdout=tmp_stdout ) - tmp_stdout.close() - returncode = proc.wait() - stdout = open( tmp_stdout.name, 'rb' ).readline().strip() - if stdout: - sys.stdout.write( '%s\n' % stdout ) - else: - raise Exception - except: - sys.stdout.write( 'Could not determine Tophat version\n' ) - # Color or base space space = '' if options.color_space: Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: jgoecks: Fix version references in tophat2 wrapper.
by Bitbucket 26 Apr '12

26 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/c16adb4630e5/ changeset: c16adb4630e5 user: jgoecks date: 2012-04-26 19:59:03 summary: Fix version references in tophat2 wrapper. affected #: 1 file diff -r 9884af7d49189f1af3f8ae60931064d2abcc62cc -r c16adb4630e58fe4001e488367e27e911d7ec0cb tools/ngs_rna/tophat2_wrapper.xml --- a/tools/ngs_rna/tophat2_wrapper.xml +++ b/tools/ngs_rna/tophat2_wrapper.xml @@ -1,9 +1,9 @@ <tool id="tophat2" name="Tophat2" version="0.5"><description>Gapped-read mapper for RNA-seq data</description> - <version_command>tophat --version</version_command> + <version_command>tophat2 --version</version_command><requirements> - <requirement type="package">tophat</requirement> + <requirement type="package">tophat2</requirement></requirements><command interpreter="python"> tophat2_wrapper.py Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0

commit/galaxy-central: jgoecks: Make history export work for optional data inputs.
by Bitbucket 26 Apr '12

26 Apr '12

1 new commit in galaxy-central: https://bitbucket.org/galaxy/galaxy-central/changeset/9884af7d4918/ changeset: 9884af7d4918 user: jgoecks date: 2012-04-26 19:32:04 summary: Make history export work for optional data inputs. affected #: 1 file diff -r 0a0b01a980eac2f4c98d317bbde3ff572aca13e9 -r 9884af7d49189f1af3f8ae60931064d2abcc62cc lib/galaxy/tools/imp_exp/__init__.py --- a/lib/galaxy/tools/imp_exp/__init__.py +++ b/lib/galaxy/tools/imp_exp/__init__.py @@ -415,8 +415,13 @@ params_dict[ name ] = value job_attrs[ 'params' ] = params_dict - # Get input, output datasets. - input_datasets = [ assoc.dataset.hid for assoc in job.input_datasets ] + # -- Get input, output datasets. -- + + input_datasets = [] + for assoc in job.input_datasets: + # Optional data inputs will not have a dataset. + if assoc.dataset: + input_datasets.append( assoc.dataset.hid ) job_attrs[ 'input_datasets' ] = input_datasets output_datasets = [ assoc.dataset.hid for assoc in job.output_datasets ] job_attrs[ 'output_datasets' ] = output_datasets Repository URL: https://bitbucket.org/galaxy/galaxy-central/ -- This is a commit notification from bitbucket.org. You are receiving this because you have the service enabled, addressing the recipient of this email.

1 0