Mercurial > repos > devteam > data_manager_gatk_picard_index_builder

--- a/data_manager/data_manager_gatk_picard_index_builder.py	Tue Apr 01 10:40:49 2014 -0400
+++ b/data_manager/data_manager_gatk_picard_index_builder.py	Fri Apr 04 15:43:20 2014 -0400
@@ -27,16 +27,27 @@
             sequence_name = dbkey
     return sequence_id, sequence_name

-def build_picard_index( data_manager_dict, fasta_filename, target_directory, dbkey, sequence_id, sequence_name, jar, data_table_name=DEFAULT_DATA_TABLE_NAME ):
+def build_picard_index( data_manager_dict, fasta_filename, target_directory, dbkey, sequence_id,
+                        sequence_name, jar, data_table_name=DEFAULT_DATA_TABLE_NAME, sort_fasta=False,
+                        sam_index_path=None ):
     fasta_base_name = os.path.split( fasta_filename )[-1]
-    gatk_sorted_fasta_filename = os.path.join( target_directory, fasta_base_name )
-    shutil.copy( fasta_filename, gatk_sorted_fasta_filename )
-    _sort_fasta_gatk( gatk_sorted_fasta_filename )
-    sam_index_filename = '%s.fai' % gatk_sorted_fasta_filename
-    if not os.path.exists( sam_index_filename ):
-        sam_command = [ 'samtools', 'faidx', gatk_sorted_fasta_filename ]
+    fasta_to_index = os.path.join( target_directory, fasta_base_name )
+    if sort_fasta:
+        shutil.copy( fasta_filename, fasta_to_index )
+        _sort_fasta_gatk( fasta_to_index )
+    else:
+        os.symlink(fasta_filename, fasta_to_index)
+    sam_index_filename = '%s.fai' % fasta_base_name
+    if sam_index_path is not None:
+        sam_index_basepath = os.path.split( sam_index_path )[0]
+    else:
+        sam_index_basepath = os.path.join( target_directory, sam_index_filename )
+    if sam_index_path is not None and os.path.exists( sam_index_path ) and os.path.exists( os.path.join( sam_index_basepath, sam_index_filename ) ):
+        os.symlink( sam_index_path + '.fai', os.path.join( target_directory, sam_index_filename ) )
+    else:
+        sam_command = [ 'samtools', 'faidx', fasta_to_index ]
         _run_command( sam_command, target_directory )
-    args = [ 'java', '-jar', jar, 'R=%s' % gatk_sorted_fasta_filename, 'O=%s.dict' % sequence_id ]
+    args = [ 'java', '-jar', jar, 'R=%s' % fasta_to_index, 'O=%s.dict' % sequence_id ]
     _run_command( args, target_directory )
     data_table_entry = dict( value=sequence_id, dbkey=dbkey, name=sequence_name, path=fasta_base_name )
     _add_data_table_entry( data_manager_dict, data_table_name, data_table_entry )
@@ -149,6 +160,8 @@
     parser.add_option( '-t', '--fasta_description', dest='fasta_description', action='store', type="string", default=None, help='fasta_description' )
     parser.add_option( '-n', '--data_table_name', dest='data_table_name', action='store', type="string", default=None, help='data_table_name' )
     parser.add_option( '-j', '--jar', dest='jar', action='store', type="string", default=None, help='GATK .jar file' )
+    parser.add_option( '-s', '--sort_fasta', dest='sort_fasta', action='store', type="string", default=False, help='Sort input FASTA' )
+    parser.add_option( '-i', '--sam_index', dest='sam_index', action='store', type="string", default=None, help='SAM index of input FASTA' )
     (options, args) = parser.parse_args()

     filename = args[0]
@@ -170,7 +183,9 @@
                         options.fasta_dbkey,
                         sequence_id,
                         sequence_name,
-                        options.jar,
+                        options.jar,
+                        sort_fasta=options.sort_fasta,
+                        sam_index_path=options.sam_index,
                         data_table_name=options.data_table_name or DEFAULT_DATA_TABLE_NAME )

     #save info to json file
--- a/data_manager/data_manager_gatk_picard_index_builder.xml	Tue Apr 01 10:40:49 2014 -0400
+++ b/data_manager/data_manager_gatk_picard_index_builder.xml	Fri Apr 04 15:43:20 2014 -0400
@@ -1,5 +1,5 @@
-<tool id="gatk_picard_index_builder" name="Generate GATK-sorted Picard indexes" tool_type="manage_data" version="0.0.1">
-    <description>builder</description>
+<tool id="gatk_picard_index_builder" name="Generate Picard indexes" tool_type="manage_data" version="0.0.2">
+    <description>sorted for GATK</description>
     <requirements>
         <requirement type="package" version="0.1.18">samtools</requirement>
         <requirement type="package" version="1.56.0">picard</requirement>
@@ -10,19 +10,37 @@
             --fasta_filename "${all_fasta_source.fields.path}" \
             --fasta_dbkey "${all_fasta_source.fields.dbkey}" \
             --fasta_description "${all_fasta_source.fields.name}" \
+            #if $input_fasta_sorting.sort_input_fasta == 'sort_fasta':
+                --sort_fasta \
+            #else:
+                --sam_index "${input_fasta_sorting.sam_index_source.fields.path}" \
+            #end if
             --data_table_name "gatk_picard_indexes"
     </command>
     <inputs>
         <param name="all_fasta_source" type="select" label="Source FASTA Sequence">
-            <options from_data_table="all_fasta"/>
+            <options from_data_table="all_fasta" />
         </param>
+        <conditional name="input_fasta_sorting">
+            <param name="sort_input_fasta" type="select" label="Input fasta sorting">
+                <option value="input_order" selected="True">As-is</option>
+                <option value="sort_fasta">Sort for GATK</option>
+            </param>
+            <when value="input_order">
+                <param name="sam_index_source" type="select" label="SAM index of FASTA">
+                    <options from_data_table="fasta_indexes">
+                        <filter type="param_value" column="0" key="value" ref="all_fasta_source" />
+                        <validator type="no_options" message="This FASTA file does not have SAM indexes."/>
+                    </options>
+                </param>
+            </when>
+        </conditional>
         <param type="text" name="sequence_name" value="" label="Name of sequence" />
         <param type="text" name="sequence_id" value="" label="ID for sequence" />
     </inputs>
     <outputs>
         <data name="out_file" format="data_manager_json"/>
     </outputs>
-
     <help>

 .. class:: infomark
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/fasta_indexes.loc.sample	Fri Apr 04 15:43:20 2014 -0400
@@ -0,0 +1,29 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of Samtools indexed sequences data files.  You will need
+#to create these data files and then create a fasta_indexes.loc file
+#similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The fasta_indexes.loc
+#file has this format (white space characters are TAB characters):
+#
+# <unique_build_id>	<dbkey>	<display_name>	<file_base_path>
+#
+#So, for example, if you had hg19 Canonical indexed stored in
+#
+# /depot/data2/galaxy/hg19/sam/,
+#
+#then the fasta_indexes.loc entry would look like this:
+#
+#hg19canon	hg19	Human (Homo sapiens): hg19 Canonical	/depot/data2/galaxy/hg19/sam/hg19canon.fa
+#
+#and your /depot/data2/galaxy/hg19/sam/ directory
+#would contain hg19canon.fa and hg19canon.fa.fai files.
+#
+#Your fasta_indexes.loc file should include an entry per line for
+#each index set you have stored.  The file in the path does actually
+#exist, but it should never be directly used. Instead, the name serves
+#as a prefix for the index file.  For example:
+#
+#hg18canon	hg18	Human (Homo sapiens): hg18 Canonical	/depot/data2/galaxy/hg18/sam/hg18canon.fa
+#hg18full	hg18	Human (Homo sapiens): hg18 Full	/depot/data2/galaxy/hg18/sam/hg18full.fa
+#hg19canon	hg19	Human (Homo sapiens): hg19 Canonical	/depot/data2/galaxy/hg19/sam/hg19canon.fa
+#hg19full	hg19	Human (Homo sapiens): hg19 Full	/depot/data2/galaxy/hg19/sam/hg19full.fa
--- a/tool_data_table_conf.xml.sample	Tue Apr 01 10:40:49 2014 -0400
+++ b/tool_data_table_conf.xml.sample	Fri Apr 04 15:43:20 2014 -0400
@@ -10,4 +10,9 @@
         <columns>value, dbkey, name, path</columns>
         <file path="tool-data/gatk_sorted_picard_index.loc" />
     </table>
+    <!-- Location of SAMTools indexes and other files -->
+    <table name="fasta_indexes" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/fasta_indexes.loc" />
+    </table>
 </tables>
--- a/tool_dependencies.xml	Tue Apr 01 10:40:49 2014 -0400
+++ b/tool_dependencies.xml	Fri Apr 04 15:43:20 2014 -0400
@@ -1,9 +1,9 @@
 <?xml version="1.0"?>
 <tool_dependency>
   <package name="picard" version="1.56.0">
-      <repository changeset_revision="7206dbf34dcd" name="package_picard_1_56_0" owner="devteam" prior_installation_required="False" toolshed="http://testtoolshed.g2.bx.psu.edu" />
+      <repository changeset_revision="7206dbf34dcd" name="package_picard_1_56_0" owner="devteam" toolshed="http://testtoolshed.g2.bx.psu.edu" />
     </package>
     <package name="samtools" version="0.1.18">
-      <repository changeset_revision="c0f72bdba484" name="package_samtools_0_1_18" owner="devteam" prior_installation_required="False" toolshed="http://testtoolshed.g2.bx.psu.edu" />
+      <repository changeset_revision="c0f72bdba484" name="package_samtools_0_1_18" owner="devteam" toolshed="http://testtoolshed.g2.bx.psu.edu" />
     </package>
 </tool_dependency>