Galaxy |

Changeset 4:f49f5a460c74 (2011-11-08)

Previous changeset 3:72ab00e732c3 (2011-10-21) Next changeset 5:f4b4c1712e39 (2011-11-08)

Commit message:
GSNAP - add and refine param options for gmap v 2011-10-16

modified:
gmap/gsnap.xml

added:
gmap/gmap_indices.loc.sample

removed:
tool-data/gmap_indices.loc.sample

diff -r 72ab00e732c3 -r f49f5a460c74 gmap/gmap_indices.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/gmap/gmap_indices.loc.sample Tue Nov 08 13:02:32 2011 -0600

@@ -0,0 +1,10 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of GMAPDB indexed sequences data files.  You will need
+#to create these data files using gmap_build and then create a gmap_indices.loc file
+#similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The gmap_indices.loc
+#file has this format (white space characters are TAB characters):
+#
+#<unique_build_id>   <dbkey>   <display_name>   <kmers> <map,map>       <snp,snp>       <file_base_path>
+#hg18   hg18    hg18 (cmet atoi)        12,13,14,15     splicesites,introns     snps    /depot/data2/galaxy/gmap/hg18
+#hg19 hg19 hg19 (cmet atoi) 12,13,14,15 splicesites,introns,snps snps,dbsnp /depot/data2/galaxy/gmap/hg19

diff -r 72ab00e732c3 -r f49f5a460c74 gmap/gsnap.xml
--- a/gmap/gsnap.xml Fri Oct 21 12:11:45 2011 -0500
+++ b/gmap/gsnap.xml Tue Nov 08 13:02:32 2011 -0600

[

b'@@ -40,8 +40,11 @@\n -V $refGenomeSource.use_snps.snpindex.extra_files_path -v $refGenomeSource.use_snps.snpindex.metadata.snps_name\n #end if\n #end if\n- #if $mode.__str__ != \'\':\n- --mode=$mode\n+ #if $refGenomeSource.mode.__str__ != \'\':\n+ --mode=$refGenomeSource.mode\n+ #end if\n+ #if $mapq_unique_score.__str__ != \'\':\n+ --mapq-unique-score=$mapq_unique_score\n #end if\n #if $computation.options == "advanced":\n #if $computation.max_mismatches.__str__ != \'\':\n@@ -76,6 +79,16 @@\n #if $computation.adapter_strip.__str__ != \'\':\n --adapter-strip=$computation.adapter_strip\n #end if\n+ #if $computation.trim_mismatch_score.__str__ != \'\':\n+ --trim-mismatch-score=$computation.trim_mismatch_score\n+ #end if\n+ ## TODO - do we need these options (Is it tally XOR runlength?):\n+ ## --tallydir= --use-tally=tally\n+ ## --runlengthdir --use-runlength=runlength\n+ #if $computation.use_tally != None and len($computation.use_tally.__str__) > 0:\n+ ##--tallydir $os.path.dirname($computation.use_tally) --use-tally $os.path.basename($computation.use_tally)\n+ --use-tally=$computation.use_tally\n+ #end if\n ## gmap options\n #if $computation.gmap_mode.__str__ != \'\' and $computation.gmap_mode.__str__ != \'None\':\n --gmap-mode=\'$computation.gmap_mode\'\n@@ -155,9 +168,22 @@\n #end if\n $result.creads_complement\n #end if\n- ## TODO - do we need these options (Is it tally XOR runlength?):\n- ## --tallydir= --use-tally=tally\n- ## --runlengthdir --use-runlength=runlength\n+ #if $results.split_output == \'yes\':\n+ --split-output=gsnap_out\n+ #if $results.fails.choice == \'nofails\':\n+ --nofails\n+ #elif $results.fails.choice == \'failsonly\':\n+ --failsonly\n+ #end if\n+ $results.fails_as_input\n+ #else\n+ #if $results.fails.choice == \'nofails\':\n+ --nofails\n+ #elif $results.fails.choice == \'failsonly\':\n+ --failsonly\n+ $results.fails.fails_as_input\n+ #end if\n+ #end if\n #if $seq.format == "gsnap_fasta":\n $seq.circularinput $seq.gsnap\n #else if $seq.format == "fastq":\n@@ -173,7 +199,7 @@\n #if $seq.filter_chastity.__str__ != \'off\':\n --filter-chastity=$seq.filter_chastity\n #end if\n- #if $seq.paired.ispaired.__str__ == "yes":\n+ #if $seq.paired.ispaired.__str__ == \'yes\':\n #if $seq.paired.pairmax_dna.__str__ != \'\':\n --pairmax-dna=$seq.paired.pairmax_dna\n #end if\n@@ -185,10 +211,14 @@\n $seq.fastq\n #end if\n #end if\n- #if $split_output == True\n+ #if $results.split_output == \'yes\':\n 2> $gsnap_stderr\n- #else\n- 2> $gsnap_stderr > $results\n+ #else:\n+ #if $results.fails.choice.__str__ == \'failsonly\' and $results.fails.fails_as_input.__str__ != \'\':\n+ 2> $gsnap_stderr > $gsnap_fq\n+ #else\n+ 2> $gsnap_stderr > $gsnap_out\n+ #end if\n #end if\n \n </command>\n@@ -197,12 +227,15 @@\n <conditional name="seq">\n <param name="format" type="select" label="<H2>Input Sequences</H2>Select the input format" help="">\n <option value="fastq">Fastq</option>\n+ \n <option value="gsnap_fasta">GNSAP fasta</option>\n </param>\n <when value="fastq">\n <param name="fastq" type="data" format="fastq" label="Select a fastq dataset" />\n <conditional name="paired">\n- <param name="ispaired" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Paired Reads"/>\n+ <param name="ispaired" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Use Paired Reads?"/>\n <when value="no"/>\n <when value="yes">\n <param name="fastq" type="data" format="fastq" label="Select the paired reads reverse dataset" />\n@@ -216,8 +249,8 @@\n '..b'ge_format>\n+ <when input="result[\'format\']" value="sam" format="sam"/>\n+ <when input="result[\'format\']" value="gsnap" format="gsnap"/>\n </change_format>\n </data>\n- <data format="txt" name="halfmapping_mult" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.halfmapping_mult">\n- <filter>(split_output == True)</filter>\n+\n+ <data format="txt" name="concordant_mult" label="${tool.name} on ${on_string} concordant_mult.${result.format}" from_work_dir="gsnap_out.concordant_mult">\n+ <filter>(results[\'split_output\'] == \'yes\' and seq[\'format\'] == \'fastq\' and seq[\'paired\'][\'ispaired\'] == True)</filter>\n <change_format>\n <when input="result[\'format\']" value="sam" format="sam"/>\n+ <when input="result[\'format\']" value="gsnap" format="gsnap"/>\n+ </change_format>\n+ </data>\n+ <data format="txt" name="concordant_uniq" label="${tool.name} on ${on_string} concordant_uniq.${result.format}" from_work_dir="gsnap_out.concordant_uniq">\n+ <filter>(results[\'split_output\'] == \'yes\' and seq[\'format\'] == \'fastq\' and seq[\'paired\'][\'ispaired\'] == True)</filter>\n+ <change_format>\n+ <when input="result[\'format\']" value="sam" format="sam"/>\n+ <when input="result[\'format\']" value="gsnap" format="gsnap"/>\n+ </change_format>\n+ </data>\n+ <data format="txt" name="concordant_transloc" label="${tool.name} on ${on_string} concordant_transloc.${result.format}" from_work_dir="gsnap_out.concordant_transloc">\n+ <filter>(results[\'split_output\'] == \'yes\' and seq[\'format\'] == \'fastq\' and seq[\'paired\'][\'ispaired\'] == True)</filter>\n+ <change_format>\n+ <when input="result[\'format\']" value="sam" format="sam"/>\n+ <when input="result[\'format\']" value="gsnap" format="gsnap"/>\n </change_format>\n </data>\n- <data format="txt" name="halfmapping_uniq" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.halfmapping_uniq">\n- <filter>(split_output == True)</filter>\n+\n+ <data format="txt" name="nomapping" label="${tool.name} on ${on_string} nomapping.${result.format}" from_work_dir="gsnap_out.nomapping">\n+ <filter>(results[\'split_output\'] == \'yes\' and results[\'fails_as_input\'] == False)</filter>\n <change_format>\n <when input="result[\'format\']" value="sam" format="sam"/>\n+ <when input="result[\'format\']" value="gsnap" format="gsnap"/>\n </change_format>\n </data>\n- <data format="txt" name="nomapping" label="${tool.name} on ${on_string} uniq.${result.format}" from_work_dir="gsnap_out.nomapping">\n- <filter>(split_output == True)</filter>\n- <change_format>\n- <when input="result[\'format\']" value="sam" format="sam"/>\n- </change_format>\n+\n+ <data format="fastq" name="nomapping_fq" label="${tool.name} on ${on_string} nomapping.fq" from_work_dir="gsnap_out.nomapping.fq">\n+ <filter>(results[\'split_output\'] == \'yes\' and seq[\'format\'] == \'fastq\' and seq[\'paired\'][\'ispaired\'] == False)</filter>\n+ </data>\n+\n+ <data format="fastq" name="nomapping_1_fq" label="${tool.name} on ${on_string} nomapping.1.fq" from_work_dir="gsnap_out.nomapping.1.fq">\n+ <filter>(results[\'split_output\'] == \'yes\' and seq[\'format\'] == \'fastq\' and seq[\'paired\'][\'ispaired\'] == True)</filter>\n </data>\n \n+ <data format="fastq" name="nomapping_2_fq" label="${tool.name} on ${on_string} nomapping.2.fq" from_work_dir="gsnap_out.nomapping.2.fq">\n+ <filter>(results[\'split_output\'] == \'yes\' and seq[\'format\'] == \'fastq\' and seq[\'paired\'][\'ispaired\'] == True)</filter>\n+ </data>\n+\n+ \n+\n </outputs>\n <tests>\n </tests> \n'

diff -r 72ab00e732c3 -r f49f5a460c74 tool-data/gmap_indices.loc.sample
--- a/tool-data/gmap_indices.loc.sample Fri Oct 21 12:11:45 2011 -0500
+++ /dev/null Thu Jan 01 00:00:00 1970 +0000

@@ -1,10 +0,0 @@
-#This is a sample file distributed with Galaxy that enables tools
-#to use a directory of GMAPDB indexed sequences data files.  You will need
-#to create these data files using gmap_build and then create a gmap_indices.loc file
-#similar to this one (store it in this directory) that points to
-#the directories in which those files are stored. The gmap_indices.loc
-#file has this format (white space characters are TAB characters):
-#
-#<unique_build_id>   <dbkey>   <display_name>   <kmers> <map,map>       <snp,snp>       <file_base_path>
-#hg18   hg18    hg18 (cmet atoi)        12,13,14,15     splicesites,introns     snps    /depot/data2/galaxy/gmap/hg18
-#hg19 hg19 hg19 (cmet atoi) 12,13,14,15 splicesites,introns,snps snps,dbsnp /depot/data2/galaxy/gmap/hg19