Tophat2 wrapper updates: (a) use bowtie2-build; (b) add option to report discordant pairs; (c) update tests.

tools/ngs_rna/tophat2_wrapper.py

@@ -24,6 +24,7 @@ def __main__():
     parser.add_option( '', '--genome-read-mismatches', dest='genome_read_mismatches' )
     parser.add_option( '', '--read-mismatches', dest='read_mismatches' )
     parser.add_option( '', '--bowtie-n', action="store_true", dest='bowtie_n' )
+    parser.add_option( '', '--report-discordant-pair-alignments', action="store_true", dest='report_discordant_pairs' )
     parser.add_option( '-a', '--min-anchor-length', dest='min_anchor_length', 
                         help='The "anchor length". TopHat will report junctions spanned by reads with at least this many bases on each side of the junction.' )
     parser.add_option( '-m', '--splice-mismatches', dest='splice_mismatches', help='The maximum number of mismatches that can appear in the anchor region of a spliced alignment.' )
@@ -94,7 +95,7 @@ def __main__():
         except:
             # Tophat prefers (but doesn't require) fasta file to be in same directory, with .fa extension
             pass
-        cmd_index = 'bowtie-build %s -f %s %s' % ( space, options.own_file, index_path )
+        cmd_index = 'bowtie2-build %s -f %s %s' % ( space, options.own_file, index_path )
         try:
             tmp = tempfile.NamedTemporaryFile( dir=tmp_index_dir ).name
             tmp_stderr = open( tmp, 'wb' )
@@ -130,6 +131,8 @@ def __main__():
     opts = '-p %s %s' % ( options.num_threads, space )
     if options.single_paired == 'paired':
         opts += ' -r %s' % options.mate_inner_dist
+        if options.report_discordant_pairs:
+            opts += ' --report-discordant-pair-alignments'
     if options.settings == 'preSet':
         cmd = cmd % ( opts, index_path, reads )
     else:

tools/ngs_rna/tophat2_wrapper.xml

@@ -29,10 +29,15 @@
         --input1=$input1
         
         ## Second input only if input is paired-end.
+        ## Also set parameters specific to paired data.
         #if $singlePaired.sPaired == "paired"
             --input2=$singlePaired.input2
             -r $singlePaired.mate_inner_distance
             --mate-std-dev=$singlePaired.mate_std_dev
+            
+            #if str($singlePaired.report_discordant_pairs) == "Yes":
+                --report-discordant-pair-alignments
+            #end if
         #end if
 
         ## Set params.
@@ -114,8 +119,13 @@
             <when value="paired">
                 <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" />
                 <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" />
+                <param name="mate_inner_distance" type="integer" value="300" 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."/>
+                <!-- Discordant pairs. -->
+                <param name="report_discordant_pairs" type="select" label="Report discordant pair alignments?">
+                    <option selected="true" value="No">No</option>
+                    <option value="Yes">Yes</option>
+                </param>
             </when>
         </conditional>
         <conditional name="refGenomeSource">
@@ -125,7 +135,7 @@
           </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="tophat_indexes">
+              <options from_data_table="tophat2_indexes">
                 <filter type="sort_by" column="2"/>
                 <validator type="no_options" message="No indexes are available for the selected input dataset"/>
               </options>
@@ -334,7 +344,7 @@
         <!-- Test base-space single-end reads with pre-built index and preset parameters -->
         <test>
             <!-- TopHat commands:
-            tophat -o tmp_dir -p 1 tophat_in1 test-data/tophat_in2.fastqsanger
+            tophat2 -o tmp_dir -p 1 tophat_in1 test-data/tophat_in2.fastqsanger
             Rename the files in tmp_dir appropriately
             -->
             <param name="sPaired" value="single" />
@@ -348,8 +358,8 @@
         <!-- Test using base-space test data: paired-end reads, index from history. -->
         <test>
             <!-- TopHat commands:
-            bowtie-build -f test-data/tophat_in1.fasta tophat_in1
-            tophat -o tmp_dir -p 1 -r 20 tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger
+            bowtie2-build -f test-data/tophat_in1.fasta tophat_in1
+            tophat2 -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" />
@@ -365,8 +375,8 @@
         <!-- Test base-space single-end reads with user-supplied reference fasta and full parameters -->
         <test>
             <!-- Tophat commands:
-            bowtie-build -f test-data/tophat_in1.fasta tophat_in1
-            tophat -o tmp_dir -p 1 -a 8 -m 0 -i 70 -I 500000 -F 0.15 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger
+            bowtie2-build -f test-data/tophat_in1.fasta tophat_in1
+            tophat2 -o tmp_dir -p 1 -a 8 -m 0 -i 70 -I 500000 -F 0.15 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger
             Replace the + with double-dash
             Rename the files in tmp_dir appropriately
             -->
@@ -396,6 +406,7 @@
             <param name="use_annotations" value="No" />
             <param name="use_juncs" value="No" />
             <param name="no_novel_juncs" value="No" />
+            <param name="report_discordant_pairs" value="No" />
             <param name="use_search" value="Yes" />
             <param name="min_coverage_intron" value="50" />
             <param name="max_coverage_intron" value="20000" />
@@ -416,7 +427,7 @@
         <!-- Test base-space paired-end reads with user-supplied reference fasta and full parameters -->
         <test>
             <!-- TopHat commands:
-            tophat -o tmp_dir -r 20 -p 1 -a 8 -m 0 -i 70 -I 500000 -F 0.15 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger
+            tophat2 -o tmp_dir -r 20 -p 1 -a 8 -m 0 -i 70 -I 500000 -F 0.15 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search +report_discordant_pairs tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger
             Replace the + with double-dash
             Rename the files in tmp_dir appropriately
             -->
@@ -447,6 +458,7 @@
             <param name="use_annotations" value="No" />
             <param name="use_juncs" value="No" />
             <param name="no_novel_juncs" value="No" />
+            <param name="report_discordant_pairs" value="Yes" />
             <param name="use_search" value="No" />
             <param name="microexon_search" value="Yes" />
             <!-- Fusion search params -->