- galaxy-commits - lists.galaxyproject.org

galaxy-dist commit e37392b073d8: Enable datasets to use item ratings.
by commits-noreply＠bitbucket.org 08 Sep '10

08 Sep '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User jeremy goecks <jeremy.goecks(a)emory.edu> # Date 1283367569 14400 # Node ID e37392b073d89af5aea5e6206e9827ea6ad3f190 # Parent 4ee5fca864a44b2bf7e7efac7a97f564961df3f2 Enable datasets to use item ratings. --- a/lib/galaxy/web/controllers/dataset.py +++ b/lib/galaxy/web/controllers/dataset.py @@ -143,7 +143,7 @@ class HistoryDatasetAssociationListGrid( .filter( model.History.deleted==False ) \ .filter( self.model_class.visible==True ) -class DatasetInterface( BaseController, UsesAnnotations, UsesHistoryDatasetAssociation ): +class DatasetInterface( BaseController, UsesAnnotations, UsesHistoryDatasetAssociation, UsesItemRatings ): stored_list_grid = HistoryDatasetAssociationListGrid()

1 0

galaxy-dist commit 12c032ebc303: Enhance wig datatype to only use first 100 data lines to determine column type metadata if dataset filesize exceeds max_optional_metadata_filesize configured in datatypes_conf.xml.
by commits-noreply＠bitbucket.org 08 Sep '10

08 Sep '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Dan Blankenberg <dan(a)bx.psu.edu> # Date 1283371068 14400 # Node ID 12c032ebc303060b838448ad8f6e0da96cacb631 # Parent eb75925d4b9705ab8722cab41c321bf15a4b2359 Enhance wig datatype to only use first 100 data lines to determine column type metadata if dataset filesize exceeds max_optional_metadata_filesize configured in datatypes_conf.xml. --- a/lib/galaxy/datatypes/tabular.py +++ b/lib/galaxy/datatypes/tabular.py @@ -25,14 +25,21 @@ class Tabular( data.Text ): def init_meta( self, dataset, copy_from=None ): data.Text.init_meta( self, dataset, copy_from=copy_from ) - def set_meta( self, dataset, overwrite = True, skip = None, **kwd ): + def set_meta( self, dataset, overwrite = True, skip = None, max_data_lines = None, **kwd ): """ Tries to determine the number of columns as well as those columns that contain numerical values in the dataset. A skip parameter is used because various tabular data types reuse this function, and their data type classes are responsible to determine how many invalid comment lines should be skipped. Using None for skip will cause skip - to be zero, but the first line will be processed as a header. + to be zero, but the first line will be processed as a header. A + max_data_lines parameter is used because various tabular data types + reuse this function, and their data type classes are responsible to + determine how many data lines should be processed to ensure that the + non-optional metadata parameters are properly set; if used, optional + metadata parameters will be set to None, unless the entire file has + already been read. Using None (default) for max_data_lines will + process all data lines. Items of interest: 1. We treat 'overwrite' as always True (we always want to set tabular metadata when called). @@ -97,7 +104,11 @@ class Tabular( data.Text ): first_line_column_types = [default_column_type] # default value is one column of type str if dataset.has_data(): #NOTE: if skip > num_check_lines, we won't detect any metadata, and will use default - for i, line in enumerate( file ( dataset.file_name ) ): + dataset_fh = open( dataset.file_name ) + i = 0 + while True: + line = dataset_fh.readline() + if not line: break line = line.rstrip( '\r\n' ) if i < skip or not line or line.startswith( '#' ): # We'll call blank lines comments @@ -127,6 +138,14 @@ class Tabular( data.Text ): # "column_types": ["int", "int", "str", "list"] first_line_column_types = column_types column_types = [ None for col in first_line_column_types ] + if max_data_lines is not None and data_lines >= max_data_lines: + if dataset_fh.tell() != dataset.get_size(): + data_lines = None #Clear optional data_lines metadata value + comment_lines = None #Clear optional comment_lines metadata value; additional comment lines could appear below this point + break + i += 1 + dataset_fh.close() + #we error on the larger number of columns #first we pad our column_types by using data from first line if len( first_line_column_types ) > len( column_types ): --- a/lib/galaxy/datatypes/interval.py +++ b/lib/galaxy/datatypes/interval.py @@ -1079,6 +1079,7 @@ class Wiggle( Tabular, _RemoteCallMixin def make_html_table( self, dataset ): return Tabular.make_html_table( self, dataset, skipchars=['track', '#'] ) def set_meta( self, dataset, overwrite = True, **kwd ): + max_data_lines = None i = 0 for i, line in enumerate( file ( dataset.file_name ) ): line = line.rstrip('\r\n') @@ -1089,13 +1090,19 @@ class Wiggle( Tabular, _RemoteCallMixin break except: do_break = False - for str in data.col1_startswith: - if elems[0].lower().startswith(str): + for col_startswith in data.col1_startswith: + if elems[0].lower().startswith( col_startswith ): do_break = True break if do_break: break - Tabular.set_meta( self, dataset, overwrite = overwrite, skip = i ) + if self.max_optional_metadata_filesize >= 0 and dataset.get_size() > self.max_optional_metadata_filesize: + #we'll arbitrarily only use the first 100 data lines in this wig file to calculate tabular attributes (column types) + #this should be sufficient, except when we have mixed wig track types (bed, variable, fixed), + # but those cases are not a single table that would have consistant column definitions + #optional metadata values set in Tabular class will be 'None' + max_data_lines = 100 + Tabular.set_meta( self, dataset, overwrite = overwrite, skip = i, max_data_lines = max_data_lines ) def sniff( self, filename ): """ Determines wether the file is in wiggle format

1 0

galaxy-dist commit 4ee5fca864a4: lims: find samples
by commits-noreply＠bitbucket.org 08 Sep '10

08 Sep '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User rc # Date 1283367408 14400 # Node ID 4ee5fca864a44b2bf7e7efac7a97f564961df3f2 # Parent f41f4ace420a58e7316fbeddacd301ff6d5dfaf1 lims: find samples - the search settings are saved after the search - search now case insensitive and wildcard support added - masthead problem fixed when showing find samples page in user mode --- a/templates/requests/common/find.mako +++ b/templates/requests/common/find.mako @@ -54,47 +54,60 @@ <div class="toolFormBody"><form name="find_request" id="find_request" action="${h.url_for( controller='requests_common', action='find', cntrller=cntrller)}" method="post" ><div class="form-row"> - <label>Find in sequencing requests in state:</label> - <select name="request_state"> - <option value="In Progress" selected>In-Progress</option> - <option value="Complete">Complete</option> - <option value="Both">Both</option> - </select> + <label>Find sample(s) using:</label> + ${search_type.get_html()} + <div class="toolParamHelp" style="clear: both;"> + Select a sample attribute to search through all the samples.<br/> + To search for a sample with a dataset name, select the dataset + option above. This will return all the sample(s) which has a + dataset with the given name associated with it. To search for + all samples created on a certain date select the 'date created' + option above. Enter date in 'YYYY-MM-DD' format. + </div></div><div class="form-row"> - <label>Find by sample:</label> - <select name="search_type"> - <option value="name" selected>name</option> - <option value="bar_code">barcode</option> - </select> + <label>Filter sequencing requests in state:</label> + ${request_states.get_html()} + <div class="toolParamHelp" style="clear: both;"> + This will filter the search results to show only those sample(s) <br/> + whose parent sequencing request is in the selected state. + </div></div><div class="form-row"> - <input type="text" name="search_string" size="40" value=""> - <input type="submit" name="go_button" value="Go"/> + ${search_box.get_html()} + <input type="submit" name="go_button" value="Find"/> + <div class="toolParamHelp" style="clear: both;"> + Wildcard search (%) can be used as placeholder for any sequence of characters or words.<br/> + For example, to search for samples starting with 'mysample' use 'mysample%' as the search string. + </div></div> %if results: <div class="form-row"><label><i>${results}</i></label> + <div class="toolParamHelp" style="clear: both;"> + The search results are sorted by the date the samples where created. + </div></div> %endif <div class="form-row"> %if samples: %for s in samples: <div class="form-row"> - <a href="${h.url_for( controller=cntrller, action='list', operation='show', id=trans.security.encode_id(s.request.id))}"><label>Sequencing request: ${s.request.name} | Type: ${s.request.type.name} | State: ${s.request.state()}</label></a> + + Sample: ${s.name} | Barcode: ${s.bar_code}<br/> + State: ${s.current_state().name}<br/> + Datasets: <a href="${h.url_for(controller='requests_common', cntrller=cntrller, action='show_datatx_page', sample_id=trans.security.encode_id(s.id))}">${s.transferred_dataset_files()}/${len(s.datasets)}</a><br/> %if cntrller == 'requests_admin': <i>User: ${s.request.user.email}</i> %endif - <div class="toolParamHelp" style="clear: both;"> - Sample: ${s.name}<br/> - Barcode: ${s.bar_code}<br/> - State: ${s.current_state().name} - </div> + <div class="toolParamHelp" style="clear: both;"> + <a href="${h.url_for( controller=cntrller, action='list', operation='show', id=trans.security.encode_id(s.request.id))}">Sequencing request: ${s.request.name} | Type: ${s.request.type.name} | State: ${s.request.state()}</a> + </div> + </div><br/> %endfor %endif - </div></form></div> --- /dev/null +++ b/templates/requests/find_index.mako @@ -0,0 +1,16 @@ +<%inherit file="/webapps/galaxy/base_panels.mako"/> + +<%def name="init()"> +<% + self.has_left_panel=False + self.has_right_panel=False + self.active_view="requests" + self.message_box_visible=False +%> +</%def> + +<%def name="center_panel()"> + + <iframe name="galaxy_main" id="galaxy_main" frameborder="0" style="position: absolute; width: 100%; height: 100%;" src="${h.url_for( controller="requests_common", action="find" )}"></iframe> + +</%def> --- a/lib/galaxy/web/controllers/requests.py +++ b/lib/galaxy/web/controllers/requests.py @@ -135,6 +135,11 @@ class Requests( BaseController ): @web.require_login( "create/submit sequencing requests" ) def index( self, trans ): return trans.fill_template( "requests/index.mako" ) + + @web.expose + @web.require_login( "create/submit sequencing requests" ) + def find_index( self, trans ): + return trans.fill_template( "requests/find_index.mako" ) @web.expose @web.require_login( "create/submit sequencing requests" ) --- a/lib/galaxy/web/controllers/requests_common.py +++ b/lib/galaxy/web/controllers/requests_common.py @@ -1256,6 +1256,25 @@ class RequestsCommon( BaseController, Us # # Find sequencing requests & samples # + def __find_widgets(self, trans, **kwd): + params = util.Params( kwd ) + request_states = SelectField('request_states', multiple=True, display="checkboxes") + sel_op = kwd.get('request_states', trans.app.model.Request.states.SUBMITTED) + for i, s in trans.app.model.Request.states.items(): + if s in sel_op: + request_states.add_option(s, s, True) + else: + request_states.add_option(s, s) + search_type = SelectField('search_type') + sel_op = kwd.get('search_type', 'sample name') + for s in ['sample name', 'barcode', 'dataset']: + if s in sel_op: + search_type.add_option(s, s, True) + else: + search_type.add_option(s, s) + search_box = TextField('search_box', 50, kwd.get('search_box', '')) + return request_states, search_type, search_box + @web.expose @web.require_admin def find( self, trans, **kwd ): @@ -1263,26 +1282,31 @@ class RequestsCommon( BaseController, Us cntrller = params.get( 'cntrller', 'requests' ) message = util.restore_text( params.get( 'message', '' ) ) status = params.get( 'status', 'done' ) - search_string = kwd.get( 'search_string', '' ) - search_type = params.get( 'search_type', '' ) - if params.get( 'request_state', 'In Progress' ) == 'Both': - request_states = ['In Progress', 'Complete'] - else: - request_states = [params.get( 'request_state', 'In Progress' )] - - samples_list = [] results = '' - if params.get('go_button', '') == 'Go': - if search_type == 'bar_code': + if params.get('go_button', '') == 'Find': + search_string = kwd.get( 'search_box', '' ) + search_type = params.get( 'search_type', '' ) + request_states = params.get( 'request_states', '' ) + samples = [] + if search_type == 'barcode': samples = trans.sa_session.query( trans.app.model.Sample ) \ .filter( and_( trans.app.model.Sample.table.c.deleted==False, trans.app.model.Sample.table.c.bar_code.like(search_string) ) )\ + .order_by( trans.app.model.Sample.table.c.create_time.desc())\ .all() - elif search_type == 'name': + elif search_type == 'sample name': samples = trans.sa_session.query( trans.app.model.Sample ) \ .filter( and_( trans.app.model.Sample.table.c.deleted==False, - trans.app.model.Sample.table.c.name.like(search_string) ) )\ + trans.app.model.Sample.table.c.name.ilike(search_string) ) )\ + .order_by( trans.app.model.Sample.table.c.create_time.desc())\ + .all() + elif search_type == 'dataset': + samples = trans.sa_session.query( trans.app.model.Sample ) \ + .filter( and_( trans.app.model.Sample.table.c.deleted==False, + trans.app.model.SampleDataset.table.c.sample_id==trans.app.model.Sample.table.c.id, + trans.app.model.SampleDataset.table.c.name.ilike(search_string) ) )\ + .order_by( trans.app.model.Sample.table.c.create_time.desc())\ .all() if cntrller == 'requests': for s in samples: @@ -1295,11 +1319,12 @@ class RequestsCommon( BaseController, Us if not s.request.deleted \ and s.request.state() in request_states: samples_list.append(s) - results = 'There are %i sequencing requests matching the search parameters.' % len(samples_list) + results = 'There are %i sample(s) matching the search parameters.' % len(samples_list) + request_states, search_type, search_box = self.__find_widgets(trans, **kwd) return trans.fill_template( '/requests/common/find.mako', - cntrller=cntrller, - samples=samples_list, - results=results ) + cntrller=cntrller, request_states=request_states, + samples=samples_list, search_type=search_type, + results=results, search_box=search_box ) --- a/templates/webapps/galaxy/base_panels.mako +++ b/templates/webapps/galaxy/base_panels.mako @@ -82,7 +82,7 @@ <% menu_options = [ [ 'Sequencing Requests', h.url_for( controller='/requests', action='index' ) ], - [ 'Find Samples', h.url_for( controller='/requests_common', action='find' ) ], + [ 'Find Samples', h.url_for( controller='/requests', action='find_index' ) ], [ 'Help', app.config.get( "lims_doc_url", "http://main.g2.bx.psu.edu/u/rkchak/p/sts" ), "galaxy_main" ] ] tab( "lab", "Lab", None, menu_options=menu_options )

1 0

galaxy-dist commit 397241b761ab: Fix filenames problem in 'extract genomic dna' GFF functional tests that was introduced in 4200:291183d3896b .
by commits-noreply＠bitbucket.org 08 Sep '10

08 Sep '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User jeremy goecks <jeremy.goecks(a)emory.edu> # Date 1283346658 14400 # Node ID 397241b761abe9a0cdad1f815e0a83328e3a665c # Parent c79aa66e7fd2b69c73a1937a0a58aec2f98e06e2 Fix filenames problem in 'extract genomic dna' GFF functional tests that was introduced in 4200:291183d3896b . --- a/tools/extract/extract_genomic_dna.xml +++ b/tools/extract/extract_genomic_dna.xml @@ -43,12 +43,12 @@ </test><test> - <param name="input" value="gff_filtering_out1.gff" dbkey="mm9" ftype="gff" /> + <param name="input" value="gff_filter_by_attribute_out1.gff" dbkey="mm9" ftype="gff" /><param name="out_format" value="interval"/><output name="out_file1" file="extract_genomic_dna_out4.gff" /></test><test> - <param name="input" value="gff_filtering_out1.gff" dbkey="mm9" ftype="gff" /> + <param name="input" value="gff_filter_by_attribute_out1.gff" dbkey="mm9" ftype="gff" /><param name="out_format" value="fasta"/><output name="out_file1" file="extract_genomic_dna_out5.fasta" /></test>

1 0

galaxy-dist commit f41f4ace420a: For UI tab generation, only create link if there is an href.
by commits-noreply＠bitbucket.org 08 Sep '10

08 Sep '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User jeremy goecks <jeremy.goecks(a)emory.edu> # Date 1283364901 14400 # Node ID f41f4ace420a58e7316fbeddacd301ff6d5dfaf1 # Parent 5f87abcf4854c6e5603a5b937865d3e8bdc9190d For UI tab generation, only create link if there is an href. --- a/templates/webapps/galaxy/base_panels.mako +++ b/templates/webapps/galaxy/base_panels.mako @@ -26,7 +26,12 @@ if not visible: style = "display: none;" %> - <td class="${cls}" style="${style}"><a target="${target}" href="${href}">${display}</a> + <td class="${cls}" style="${style}"> + %if href: + <a target="${target}" href="${href}">${display}</a> + %else: + ${display} + %endif %if menu_options: <div class="submenu"><ul>

1 0

galaxy-dist commit 5f87abcf4854: fix for the menu item bug intriduced in changeset 4223:03d06d05bf62
by commits-noreply＠bitbucket.org 08 Sep '10

08 Sep '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User rc # Date 1283357789 14400 # Node ID 5f87abcf4854c6e5603a5b937865d3e8bdc9190d # Parent 37cbea4bf8c7995eea2b202fe3fcfbc72d0307a7 fix for the menu item bug intriduced in changeset 4223:03d06d05bf62 now the Lab menu appears correctly for sample tracking users --- a/templates/webapps/galaxy/base_panels.mako +++ b/templates/webapps/galaxy/base_panels.mako @@ -74,18 +74,20 @@ ## Lab menu. %if trans.user and trans.user.accessible_request_types(trans): - menu_options = [ - [ 'Sequencing Requests', h.url_for( controller='/requests', action='index' ) ], - [ 'Find Samples', h.url_for( controller='/requests_common', action='find' ) ], - [ 'Help', app.config.get( "lims_doc_url", "http://main.g2.bx.psu.edu/u/rkchak/p/sts" )}, "galaxy_main" ], - ] - tab( "lab", "Lab", None, menu_options=menu_options ) + <% + menu_options = [ + [ 'Sequencing Requests', h.url_for( controller='/requests', action='index' ) ], + [ 'Find Samples', h.url_for( controller='/requests_common', action='find' ) ], + [ 'Help', app.config.get( "lims_doc_url", "http://main.g2.bx.psu.edu/u/rkchak/p/sts" ), "galaxy_main" ] + ] + tab( "lab", "Lab", None, menu_options=menu_options ) + %> %endif ## Visualization menu. %if app.config.get_bool( 'enable_tracks', False ): <% - menu_options = [ + menu_options = [ ['New Track Browser', h.url_for( controller='/tracks', action='index' ) ], ['Saved Visualizations', h.url_for( controller='/visualization', action='list' ) ] ]

1 0

galaxy-dist commit 37cbea4bf8c7: Added tool_conf.xml.main with BAM-to-SAM tool
by commits-noreply＠bitbucket.org 08 Sep '10

08 Sep '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Kelly Vincent <kpvincent(a)bx.psu.edu> # Date 1283350216 14400 # Node ID 37cbea4bf8c7995eea2b202fe3fcfbc72d0307a7 # Parent 09a684e9e0d42a3704e0093a15e54ad339da6329 Added tool_conf.xml.main with BAM-to-SAM tool --- a/tool_conf.xml.main +++ b/tool_conf.xml.main @@ -327,6 +327,7 @@ <tool file="samtools/sam_bitwise_flag_filter.xml" /><tool file="samtools/sam2interval.xml" /><tool file="samtools/sam_to_bam.xml" /> + <tool file="samtools/bam_to_sam.xml" /><tool file="samtools/sam_merge.xml" /><tool file="samtools/sam_pileup.xml" /><tool file="samtools/pileup_parser.xml" />

1 0

galaxy-dist commit 09a684e9e0d4: Added BAM-to-SAM tool
by commits-noreply＠bitbucket.org 08 Sep '10

08 Sep '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User Kelly Vincent <kpvincent(a)bx.psu.edu> # Date 1283348652 14400 # Node ID 09a684e9e0d42a3704e0093a15e54ad339da6329 # Parent 397241b761abe9a0cdad1f815e0a83328e3a665c Added BAM-to-SAM tool --- /dev/null +++ b/test-data/bam_to_sam_out1.sam @@ -0,0 +1,10 @@ +HWI-EAS91_1_30788AAXX:1:1:1698:516 16 * 2735 25 36M * 0 0 TTTACACTCAGAGGTTCAACTCCTCTCNNTAACAAC I9IIIII5IIIIIIIIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1398:854 16 * 3921 25 36M * 0 0 CACCCTTCCCGTACTAATAAATCCCCTNNTCTTCAC IIIII=AIIIIIIIIIIIIIIBIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1716:413 0 * 6040 25 36M * 0 0 GATCCAANNCTTTATCAACACCTATTCTGATTCTTC IIIIIII""IIIIIIIIIIIIIIIIIIIIIIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1634:211 0 * 9350 25 36M * 0 0 GAAGCAGNNGCTTGATACTGACACTTCGTCGACGTA IIIIIII""IIIIIIIIIIIIIIIIIIIIII9IIDF NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1513:715 16 * 9563 25 36M * 0 0 CTGACTACCACAACTAAACATCTATGCNNAAAAAAC I+-II?IDIIIIIIIIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1310:991 16 * 10002 25 36M * 0 0 CTCCTATGCCTAGAAGGAATAATACTANNACTATTC I:2IEI:IIDIIIIII4IIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1711:249 16 * 10617 25 36M * 0 0 ACCAAACAGAACGCCTGAACGCAGGCCNNTACTTCC IIIIIIIIIIIIIIIIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1491:637 16 * 10864 25 36M * 0 0 TGTAGAAGCCCCAATTGCCGGATCCATNNTGCTAGC DBAIIIIIIIIIIIFIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1630:59 16 * 12387 25 36M * 0 0 TCATACTCGACCCCAACCTTACCAACCNNCCGCTCC FIIHII;IIIIIIIIIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1218:141 16 * 14062 25 36M * 0 0 ACAAAACTAACAACAAAAATAACACTCNNAATAAAC I+IIII1IIIIIIIIIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 --- /dev/null +++ b/tools/samtools/bam_to_sam.py @@ -0,0 +1,66 @@ +#!/usr/bin/env python +""" +Converts BAM data to sorted SAM data. +usage: bam_to_sam.py [options] + --input1: SAM file to be converted + --output1: output dataset in bam format +""" + +import optparse, os, sys, subprocess, tempfile, shutil +from galaxy import eggs +import pkg_resources; pkg_resources.require( "bx-python" ) +from bx.cookbook import doc_optparse +#from galaxy import util + +def stop_err( msg ): + sys.stderr.write( '%s\n' % msg ) + sys.exit() + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + parser.add_option( '', '--input1', dest='input1', help='The input SAM dataset' ) + parser.add_option( '', '--output1', dest='output1', help='The output BAM dataset' ) + ( options, args ) = parser.parse_args() + + tmp_dir = tempfile.mkdtemp() + try: + # exit if input file empty + if os.path.getsize( options.input1 ) == 0: + raise Exception, 'Initial BAM file empty' + # Extract all alignments from the input BAM file to SAM format ( since no region is specified, all the alignments will be extracted ). + command = 'samtools view -o %s %s' % ( options.output1, options.input1 ) + tmp = tempfile.NamedTemporaryFile( dir=tmp_dir ).name + tmp_stderr = open( tmp, 'wb' ) + proc = subprocess.Popen( args=command, shell=True, cwd=tmp_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: + #clean up temp files + if os.path.exists( tmp_dir ): + shutil.rmtree( tmp_dir ) + stop_err( 'Error extracting alignments from (%s), %s' % ( options.input1, str( e ) ) ) + #clean up temp files + if os.path.exists( tmp_dir ): + shutil.rmtree( tmp_dir ) + # check that there are results in the output file + if os.path.getsize( options.output1 ) > 0: + sys.stdout.write( 'BAM file converted to SAM' ) + else: + stop_err( 'The output file is empty, there may be an error with your input file.' ) + +if __name__=="__main__": __main__() --- a/tool_conf.xml.sample +++ b/tool_conf.xml.sample @@ -286,6 +286,7 @@ <tool file="samtools/sam_bitwise_flag_filter.xml" /><tool file="samtools/sam2interval.xml" /><tool file="samtools/sam_to_bam.xml" /> + <tool file="samtools/bam_to_sam.xml" /><tool file="samtools/sam_merge.xml" /><tool file="samtools/sam_pileup.xml" /><tool file="samtools/pileup_parser.xml" /> --- /dev/null +++ b/tools/samtools/bam_to_sam.xml @@ -0,0 +1,37 @@ +<tool id="bam_to_sam" name="BAM-to-SAM" version="1.0.0"> + <description>converts BAM format to SAM format</description> + <command interpreter="python">bam_to_sam.py --input1=$input1 --output1=$output1</command> + <inputs> + <param name="input1" type="data" format="bam" label="BAM File to Convert" /> + </inputs> + <outputs> + <data name="output1" format="sam" /> + </outputs> + <tests> + <test> +  + <param name="input1" value="1.bam" ftype="bam" /> + <output name="output1" file="bam_to_sam_out1.sam" /> + </test> + <test> +  + <param name="input1" value="3.bam" ftype="bam" /> + <param name="output1" file="bam_to_sam_out2.sam" /> + </test> + </tests> + <help> + +**What it does** + +This tool uses the SAMTools_ toolkit to produce a SAM file from a BAM file. + +.. _SAMTools: http://samtools.sourceforge.net/samtools.shtml + + </help> +</tool> --- /dev/null +++ b/test-data/bam_to_sam_out2.sam @@ -0,0 +1,10 @@ +HWI-EAS91_1_30788AAXX:1:1:1095:605 0 chrM 23 25 36M * 0 0 AAGCAAGNNACTGAAAATGCCTAGATGAGTATTCTT IIIIIII""IIIIIIIIIIIIIIIEIIIIIIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1650:1185 0 chrM 14956 25 36M * 0 0 ACCCCAGNNAACCCTCTCAGCACTCCCCCTCATATT IIIIIII""IIIIIIIIIIII6IIIIIIIII5I-II NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:799:192 16 chrM 8421 25 36M * 0 0 CCTGTAGCCCTAGCCGTGCGGCTAACCNNTAACATT II%::I<IIIIIEIII8IIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1082:719 16 chrM 7191 25 36M * 0 0 TAAATTAACCCATACCAGCACCATAGANNCTCAAGA <III0EII3+3I29I>III8AIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1746:1180 16 chrM 12013 25 36M * 0 0 CCTAAGCTTCAAACTAGATTACTTCTCNNTAATTTT IIIIIIIIFIIIIIIIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:606:460 0 chrM 4552 25 36M * 0 0 TTAATTTNNATTATAATAACACTCACAATATTCATA IIIIIII""IIIIIIIIIIIIIIIIII?I6IIIII6 NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1059:362 16 chrM 7348 25 36M * 0 0 GGCCACCAATGATACTGAAGCTACGAGNNTACCGAT II/<)2IIIIIIIIIIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1483:1161 16 chrM 15080 25 36M * 0 0 TCCTGATCCTAGCACTCATCCCCACCCNNCACATAT HIIIIIFIIAIHIIIIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1273:600 16 chrM 13855 25 36M * 0 0 GTATTAGACACCCATACCTCAGGATACNNCTCAGTA IIIIIIIIIIIIIIIIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27 +HWI-EAS91_1_30788AAXX:1:1:1190:1283 16 chrM 15338 25 36M * 0 0 TATATCGCACATTACCCTGGTCTTGTANNCCAGAAA EIII?-IIIIIAIIIIIIIIIIIIIII""IIIIIII NM:i:1 X1:i:1 MD:Z:7N0N27

1 0

galaxy-dist commit c79aa66e7fd2: Another small tweak - no idea what combination of plink and other dependencies
by commits-noreply＠bitbucket.org 08 Sep '10

08 Sep '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User fubar: ross Lazarus at gmail period com # Date 1283313090 14400 # Node ID c79aa66e7fd2b69c73a1937a0a58aec2f98e06e2 # Parent ce299d78b5670aa548b9ecad47754f6b5ce8584f Another small tweak - no idea what combination of plink and other dependencies will have on lines_diff at other sites...but buildbot seems fussy Still missing scipy and haploview seems unhappy too. --- a/tools/rgenetics/rgQC.xml +++ b/tools/rgenetics/rgQC.xml @@ -30,7 +30,7 @@ <param name='out_prefix' value='rgQCtest1' /><output name='html_file' file='rgtestouts/rgQC/rgQCtest1.html' ftype='html' lines_diff='280'><extra_files type="file" name='tinywga_All_Paged.pdf' value="rgtestouts/rgQC/tinywga_All_Paged.pdf" compare="sim_size" delta = "5000"/> - <extra_files type="file" name='tinywga.log' value="rgtestouts/rgQC/tinywga.log" compare="diff" lines_diff="10"/> + <extra_files type="file" name='tinywga.log' value="rgtestouts/rgQC/tinywga.log" compare="diff" lines_diff="15"/><extra_files type="file" name='tinywga.frq' value="rgtestouts/rgQC/tinywga.frq" compare="diff" /><extra_files type="file" name='tinywga.het' value="rgtestouts/rgQC/tinywga.het" compare="diff" lines_diff="90"/><extra_files type="file" name='tinywga.hwe' value="rgtestouts/rgQC/tinywga.hwe" compare="diff" lines_diff="90"/> @@ -39,13 +39,13 @@ <extra_files type="file" name='tinywga.lmendel' value="rgtestouts/rgQC/tinywga.lmendel" compare="diff" /><extra_files type="file" name='tinywga.lmiss' value="rgtestouts/rgQC/tinywga.lmiss" compare="diff" /><extra_files type="file" name='tinywga_All_3x3.pdf' value="rgtestouts/rgQC/tinywga_All_3x3.pdf" compare="sim_size" delta="5000"/> - <extra_files type="file" name='ldp_tinywga.bed' value="rgtestouts/rgQC/ldp_tinywga.bed" compare="diff" /> + <extra_files type="file" name='ldp_tinywga.bed' value="rgtestouts/rgQC/ldp_tinywga.bed" compare="diff" lines_diff="10" /><extra_files type="file" name='ldp_tinywga.bim' value="rgtestouts/rgQC/ldp_tinywga.bim" compare="sim_size" delta="1000" /><extra_files type="file" name='ldp_tinywga.fam' value="rgtestouts/rgQC/ldp_tinywga.fam" compare="diff" /> - <extra_files type="file" name='ldp_tinywga.log' value="rgtestouts/rgQC/ldp_tinywga.log" compare="diff" lines_diff="17"/> + <extra_files type="file" name='ldp_tinywga.log' value="rgtestouts/rgQC/ldp_tinywga.log" compare="diff" lines_diff="20"/><extra_files type="file" name='Ranked_Marker_HWE.xls' value="rgtestouts/rgQC/Ranked_Marker_HWE.xls" compare="diff" /><extra_files type="file" name='Ranked_Marker_MAF.xls' value="rgtestouts/rgQC/Ranked_Marker_MAF.xls" compare="diff" /> - <extra_files type="file" name='Ranked_Marker_Missing_Genotype.xls' value="rgtestouts/rgQC/Ranked_Marker_Missing_Genotype.xls" compare="diff" /> + <extra_files type="file" name='Ranked_Marker_Missing_Genotype.xls' value="rgtestouts/rgQC/Ranked_Marker_Missing_Genotype.xls" compare="diff" lines_diff="5"/><extra_files type="file" name='Ranked_Subject_Missing_Genotype.xls' value="rgtestouts/rgQC/Ranked_Subject_Missing_Genotype.xls" compare="diff" lines_diff="10"/><extra_files type="file" name='tinywga_fracmiss_cum.jpg' value="rgtestouts/rgQC/tinywga_fracmiss_cum.jpg" compare="sim_size" delta = "1000"/><extra_files type="file" name='tinywga_fracmiss_cum.pdf' value="rgtestouts/rgQC/tinywga_fracmiss_cum.pdf" compare="sim_size" delta = "1000"/>

1 0

galaxy-dist commit ce299d78b567: Tweaks to lines_diff in 2 rg tests to account for different versions of R and plink
by commits-noreply＠bitbucket.org 08 Sep '10

08 Sep '10

# HG changeset patch -- Bitbucket.org # Project galaxy-dist # URL http://bitbucket.org/galaxy/galaxy-dist/overview # User fubar: ross Lazarus at gmail period com # Date 1283301008 14400 # Node ID ce299d78b5670aa548b9ecad47754f6b5ce8584f # Parent 03d06d05bf62a6444f1a652910708fde17fa189b Tweaks to lines_diff in 2 rg tests to account for different versions of R and plink --- a/tools/rgenetics/rgManQQ.xml +++ b/tools/rgenetics/rgManQQ.xml @@ -42,7 +42,7 @@ <param name='chrom_col' value='1' /><param name='offset_col' value='2' /><param name='grey' value='0' /> - <output name='out_html' file='rgtestouts/rgManQQ/rgManQQtest1.html' ftype='html' lines_diff='30'> + <output name='out_html' file='rgtestouts/rgManQQ/rgManQQtest1.html' ftype='html' lines_diff='40'><extra_files type="file" name='Allelep_manhattan.png' value='rgtestouts/rgManQQ/Allelep_manhattan.png' compare="sim_size" delta = "10000"/><extra_files type="file" name='Allelep_qqplot.png' value='rgtestouts/rgManQQ/Allelep_qqplot.png' compare="sim_size" --- a/tools/rgenetics/rgQC.xml +++ b/tools/rgenetics/rgQC.xml @@ -32,8 +32,8 @@ <extra_files type="file" name='tinywga_All_Paged.pdf' value="rgtestouts/rgQC/tinywga_All_Paged.pdf" compare="sim_size" delta = "5000"/><extra_files type="file" name='tinywga.log' value="rgtestouts/rgQC/tinywga.log" compare="diff" lines_diff="10"/><extra_files type="file" name='tinywga.frq' value="rgtestouts/rgQC/tinywga.frq" compare="diff" /> - <extra_files type="file" name='tinywga.het' value="rgtestouts/rgQC/tinywga.het" compare="diff" /> - <extra_files type="file" name='tinywga.hwe' value="rgtestouts/rgQC/tinywga.hwe" compare="diff" /> + <extra_files type="file" name='tinywga.het' value="rgtestouts/rgQC/tinywga.het" compare="diff" lines_diff="90"/> + <extra_files type="file" name='tinywga.hwe' value="rgtestouts/rgQC/tinywga.hwe" compare="diff" lines_diff="90"/><extra_files type="file" name='tinywga.imendel' value="rgtestouts/rgQC/tinywga.imendel" compare="diff"/><extra_files type="file" name='tinywga.imiss' value="rgtestouts/rgQC/tinywga.imiss" compare="diff" /><extra_files type="file" name='tinywga.lmendel' value="rgtestouts/rgQC/tinywga.lmendel" compare="diff" />

1 0