Repository 'freebayes4workflow'
hg clone https://toolshed.g2.bx.psu.edu/repos/urgi-team/freebayes4workflow

Changeset 0:874dd6c0fcde (2015-11-10)
Commit message:
Uploaded
added:
freebayes4workflow.xml
tool-data/fasta_indexes.loc.sample
tool_data_table_conf.xml.sample
tool_dependencies.xml
b
diff -r 000000000000 -r 874dd6c0fcde freebayes4workflow.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/freebayes4workflow.xml Tue Nov 10 08:51:31 2015 -0500
[
b'@@ -0,0 +1,851 @@\n+<?xml version="1.0"?>\n+<tool id="freebayes4workflow" name="Freebayes4Workflow" version="0.5">\n+  <requirements>\n+    <requirement type="package" version="1.0">freebayes</requirement>\n+    <requirement type="package" version="0.1.19">samtools</requirement>\n+  </requirements>\n+  <description> - bayesian genetic variant detector</description>\n+  <command>\n+    ##set up input files\n+\n+    #set $reference_fasta_filename = "localref.fa"\n+    \n+    #if str( $reference_source.reference_source_selector ) == "history":\n+        ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" &amp;&amp;\n+        samtools faidx "${reference_fasta_filename}" 2&gt;&amp;1 || echo "Error running samtools faidx for FreeBayes" &gt;&amp;2 &amp;&amp;\n+    #else:\n+        #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path )\n+    #end if\n+    \n+    #for $bam_count, $input_bam in enumerate( $input_bams ):\n+        ln -s "${input_bam.input_bam}" "localbam_${bam_count}.bam" &amp;&amp;\n+        ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" &amp;&amp;\n+    #end for\n+    \n+    ## Tabixize optional input_varinat_vcf file (for --variant-input option)\n+    \n+    #if ( str( $options_type.options_type_selector ) == \'cline\' or str( $options_type.options_type_selector ) == \'full\' ) and $options_type.optional_inputs.optional_inputs_selector and str( $options_type.optional_inputs.input_variant_type.input_variant_type_selector ) == "provide_vcf":\n+        ln -s "${options_type.optional_inputs.input_variant_type.input_variant_vcf}" "input_variant_vcf.vcf.gz" &amp;&amp;\n+        ln -s "${Tabixized_input}" "input_variant_vcf.vcf.gz.tbi" &amp;&amp;\n+    #end if\n+    \n+    ##finished setting up inputs\n+    \n+    ##COMMAND LINE STARTS HERE\n+    \n+    freebayes\n+    #for $bam_count, $input_bam in enumerate( $input_bams ):\n+        --bam "localbam_${bam_count}.bam"\n+    #end for\n+    --fasta-reference "${reference_fasta_filename}"\n+    \n+    ##outputs\n+    #if str( $rename_output.rename_output_selector ) == "noRename":\n+        --vcf ${output_vcf_default}\n+    #elif str( $rename_output.rename_output_selector ) == "firstBAM":\n+        --vcf "${output_vcf_firstBAM}"\n+    #elif str( $rename_output.rename_output_selector ) == "providedName":\n+\t\t--vcf "${output_vcf_rename}"\n+    #end if\n+\n+    #if str( $target_limit_type.target_limit_type_selector ) == "limit_by_target_file":\n+      --targets "${target_limit_type.input_target_bed}"\n+    #elif str( $target_limit_type.target_limit_type_selector ) == "limit_by_region":\n+      --region "${target_limit_type.region_chromosome}:${target_limit_type.region_start}..${target_limit_type.region_end}"\n+    #end if\n+    \n+    ##advanced options\n+    #if str( $options_type.options_type_selector ) == "simple":\n+      ##do nothing as command like build up to this point is sufficinet for simple diploid calling\n+      \n+    #elif str( $options_type.options_type_selector ) == "simple_w_filters":\n+  \n+    --standard-filters\n+    --min-coverage "${options_type.min_coverage}"\n+      \n+    #elif str( $options_type.options_type_selector ) == "naive":\n+    \n+      --haplotype-length 0\n+      --min-alternate-count 1\n+      --min-alternate-fraction 0\n+      --pooled-continuous\n+      --report-monomorphic\n+      \n+    #elif str( $options_type.options_type_selector ) == "naive_w_filters":\n+\n+      --haplotype-length 0\n+      --min-alternate-count 1\n+      --min-alternate-fraction 0\n+      --pooled-continuous\n+      --report-monomorphic\n+      --standard-filters\n+      --min-coverage "${options_type.min_coverage}"\n+\n+##    Command line direct text entry is not allowed at this time for security reasons\n+    \n+    #elif str( $options_type.options_type_selector ) == "full":\n+ \n+        #if $options_type.optional_inputs.optional_inputs_selector:\n+        \n+          #if $options_type.optional_inputs.output_trace_option:\n+            --trace "${output_trace}"\n+          #end if\n+ '..b'ead placement probability, strand balance probability,\n+                   and read position (5\'-3\') probability.\n+   -a --allele-balance-priors-off\n+                   Disable use of aggregate probability of observation balance between alleles\n+                   as a component of the priors.\n+\n+Genotype likelihoods::\n+\n+   --observation-bias FILE\n+                   Read length-dependent allele observation biases from FILE.\n+                   The format is [length] [alignment efficiency relative to reference]\n+                   where the efficiency is 1 if there is no relative observation bias.\n+   --base-quality-cap Q\n+                   Limit estimated observation quality by capping base quality at Q.\n+   --experimental-gls\n+                   Generate genotype likelihoods using \'effective base depth\' metric\n+                   qual = 1-BaseQual * 1-MapQual.  Incorporate partial observations.\n+                   This is the default when contamination estimates are provided.\n+                   Optimized for diploid samples.\n+   --prob-contamination F\n+                   An estimate of contamination to use for all samples.  default: 10e-9\n+   --contamination-estimates FILE\n+                   A file containing per-sample estimates of contamination, such as\n+                   those generated by VerifyBamID.  The format should be:\n+                       sample p(read=R|genotype=AR) p(read=A|genotype=AA)\n+                   Sample \'*\' can be used to set default contamination estimates.\n+\n+Algorithmic features::\n+\n+   --report-genotype-likelihood-max\n+                   Report genotypes using the maximum-likelihood estimate provided\n+                   from genotype likelihoods.\n+   -B --genotyping-max-iterations N\n+                   Iterate no more than N times during genotyping step. default: 1000.\n+   --genotyping-max-banddepth N\n+                   Integrate no deeper than the Nth best genotype by likelihood when\n+                   genotyping. default: 6.\n+   -W --posterior-integration-limits N,M\n+                   Integrate all genotype combinations in our posterior space\n+                   which include no more than N samples with their Mth best\n+                   data likelihood. default: 1,3.\n+   -N --exclude-unobserved-genotypes\n+                   Skip sample genotypings for which the sample has no supporting reads.\n+   -S --genotype-variant-threshold N\n+                   Limit posterior integration to samples where the second-best\n+                   genotype likelihood is no more than log(N) from the highest\n+                   genotype likelihood for the sample.  default: ~unbounded\n+   -j --use-mapping-quality\n+                   Use mapping quality of alleles when calculating data likelihoods.\n+   -H --harmonic-indel-quality\n+                   Use a weighted sum of base qualities around an indel, scaled by the\n+                   distance from the indel.  By default use a minimum BQ in flanking sequence.\n+   -D --read-dependence-factor N\n+                   Incorporate non-independence of reads by scaling successive\n+                   observations by this factor during data likelihood\n+                   calculations.  default: 0.9\n+   -= --genotype-qualities\n+                   Calculate the marginal probability of genotypes and report as GQ in\n+                   each sample field in the VCF output.\n+\n+\n+------\n+\n+**Citation**\n+\n+For the underlying tool, please cite `Erik Garrison and Gabor Marth. Haplotype-based variant detection from short-read sequencing &lt;http://arxiv.org/abs/1207.3907&gt;`_.\n+\n+The initial version of the wrapper was produced by Dan Blankenberg and upgraded by Anton Nekrutenko.\n+\n+  </help>\n+  \n+  <citations>\n+    <citation type="bibtex">@misc{1207.3907,\n+Author = {Erik Garrison},\n+Title = {Haplotype-based variant detection from short-read sequencing},\n+Year = {2012},\n+Eprint = {arXiv:1207.3907},\n+url = {http://arxiv.org/abs/1207.3907},\n+}</citation>\n+  </citations>\n+</tool>\n'
b
diff -r 000000000000 -r 874dd6c0fcde tool-data/fasta_indexes.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/fasta_indexes.loc.sample Tue Nov 10 08:51:31 2015 -0500
b
@@ -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
b
diff -r 000000000000 -r 874dd6c0fcde tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Tue Nov 10 08:51:31 2015 -0500
b
@@ -0,0 +1,8 @@
+<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc-->
+<tables>
+    <!-- Location of SAMTools indexes for FASTA files -->
+    <table name="fasta_indexes" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/fasta_indexes.loc" />
+    </table>
+</tables>
b
diff -r 000000000000 -r 874dd6c0fcde tool_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml Tue Nov 10 08:51:31 2015 -0500
b
@@ -0,0 +1,22 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="freebayes" version="1.0">
+        <install version="1.0">
+            <actions_group>
+                <actions architecture="x86_64" os="linux">
+                    <action type="download_by_url">http://depot.galaxyproject.org/package/linux/x86_64/freebayes/freebayes-0.9.20_b040236.tar.gz</action>
+                    <action type="move_directory_files">
+                        <source_directory>.</source_directory>
+                        <destination_directory>$INSTALL_DIR/bin</destination_directory>
+                    </action>       
+                </actions>                
+                <action type="set_environment">
+                    <environment_variable action="prepend_to" name="PATH">$INSTALL_DIR/bin</environment_variable>
+                </action>
+            </actions_group>
+        </install>
+    </package>
+    <package name="samtools" version="0.1.19">
+     <repository changeset_revision="95d2c4aefb5f" name="package_samtools_0_1_19" owner="devteam" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>