changeset 18:36f3c82323e6

Use tool_data_table with key and version columns added to allow for multiple versions in a .loc file
author Jim Johnson <jj@umn.edu>
date Tue, 13 Jan 2015 13:36:11 -0600
parents 13d81e5226cd
children 2e37b58fc24d
files readme.rst repository_dependencies.xml snpEff.xml snpEff_databases.xml snpEff_download.xml snpEff_macros.xml tool-data/snpeff4_annotations.loc.sample tool-data/snpeff4_databases.loc.sample tool-data/snpeff4_genomedb.loc.sample tool-data/snpeff4_regulationdb.loc.sample tool-data/snpeffv_annotations.loc.sample tool-data/snpeffv_databases.loc.sample tool-data/snpeffv_genomedb.loc.sample tool-data/snpeffv_regulationdb.loc.sample tool_data_table_conf.xml.sample
diffstat 15 files changed, 146 insertions(+), 95 deletions(-) [+]
line wrap: on
line diff
--- a/readme.rst	Mon Nov 10 09:33:36 2014 -0600
+++ b/readme.rst	Tue Jan 13 13:36:11 2015 -0600
@@ -1,20 +1,38 @@
-These are galaxy tools for SnpEff a variant annotation and effect prediction tool by Pablo Cingolani. 
+SnpEff wrappers
+===============
+
+These are galaxy tools for SnpEff_, a variant annotation and effect prediction tool by Pablo Cingolani.
 It annotates and predicts the effects of variants on genes (such as amino acid changes).
-( http://snpeff.sourceforge.net/ )
+
+.. _SnpEff: http://snpeff.sourceforge.net/
+
+
+This repository let you automatically install SnpEff and SnpSift.
+This will use the default location for genome reference downloads from the ``snpEff.config`` file:
 
-This repository contains a tool_dependencies.xml file that will attempt to automatically install SnpEff and SnpSift.   
+  data_dir = ~/snpEff/data/
+
+You can manually edit the installed ``snpEff.config`` file and change the location, or you can create a symbolic link to the desired data location from ``~/snpEff``.
+
+The genome reference options used by the tools "SnpEff" (snpEff.xml) and "SnpEff Download" (snpEff_download.xml) are taken from the ``tool-data/snpeffect_genomedb.loc`` file.
+You can fill this file by running the following command:
 
-The genome reference options used by the tools:
-    "SnpEff"  snpEff.xml
-    "SnpEff Download" snpEff_download.xml
-are taken from: tool-data/snpeffect_genomedb.loc
+  java -jar snpEff.jar databases | tail -n +3 | cut -f 1,2 | awk '{ gsub(/_/, " ", $2); printf "%s\\t%s : %s\\n", $1, $2, $1 }' | sort -k 2 > snpeffect_genomedb.loc
+
+There are 2 datamanagers to download and install prebuilt SnpEff genome databases:
+
+* data_manager_snpeff_databases: generates a list of available SnpEff genome databases into the ``tool-data/snpeff_databases.loc`` file
+* data_manager_snpeff_download: downloads a SnpEff genome database selected from ``tool-data/snpeff_databases.loc`` and adds entries to ``snpeff_genomedb.loc``, ``snpeff_regulationdb.loc`` and ``snpeff_annotations.loc``
+
+SnpEff citation: |Cingolani2012program|_.
 
-There are 2 datamanagers to download and install prebuilt SnpEff Genome databases:
-  data_manager_snpeff_databases - generates a list of available SnpEff genome databases into the tool-data/snpeff_databases.loc 
-  data_manager_snpeff_download - downloads a SnpEff genome database selected from: tool-data/snpeff_databases.loc and adds entries to snpeff_genomedb.loc,snpeff_regulationdb.loc,snpeff_annotations.loc 
+.. |Cingolani2012program| replace:: Cingolani, P., Platts, A., Wang, L. L., Coon, M., Nguyen, T., Wang, L., Land, S. J., Lu, X., Ruden, D. M. (2012) A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of *Drosophila melanogaster* strain w1118; iso-2; iso-3. *Fly* 6(2):80-92
+.. _Cingolani2012program: https://www.landesbioscience.com/journals/fly/article/19695/
+
+SnpSift citation: |Cingolani2012using|_.
 
-SnpEff citation:
-"A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of Drosophila melanogaster strain w1118; iso-2; iso-3.", Cingolani P, Platts A, Wang le L, Coon M, Nguyen T, Wang L, Land SJ, Lu X, Ruden DM. Fly (Austin). 2012 Apr-Jun;6(2):80-92. PMID: 22728672 [PubMed - in process]
+.. |Cingolani2012using| replace:: Cingolani, P., Patel, V. M., Coon, M., Nguyen, T., Land, S. J., Ruden, D. M., Lu, X. (2012) Using *Drosophila melanogaster* as a model for genotoxic chemical mutational studies with a new program, SnpSift. *Front. Genet.* 3:35
+.. _Cingolani2012using: http://journal.frontiersin.org/Journal/10.3389/fgene.2012.00035/
 
-SnpSift citation:
-"Using Drosophila melanogaster as a model for genotoxic chemical mutational studies with a new program, SnpSift", Cingolani, P., et. al., Frontiers in Genetics, 3, 2012.
+Wrapper authors: Jim Johnson
+
--- a/repository_dependencies.xml	Mon Nov 10 09:33:36 2014 -0600
+++ b/repository_dependencies.xml	Tue Jan 13 13:36:11 2015 -0600
@@ -1,4 +1,5 @@
 <?xml version="1.0"?>
 <repositories description="This requires the SnpEff datatype definitions.">
-    <repository name="snpeff_datatypes" owner="jjohnson" changeset_revision="b33911fdbac4" toolshed="http://testtoolshed.g2.bx.psu.edu/" />
+    <repository name="snpeff_datatypes" owner="jjohnson" changeset_revision="9efd0d32fe8a" toolshed="http://testtoolshed.g2.bx.psu.edu/" />
+    <repository name="snpeff_datatype_v4_0" owner="jjohnson" changeset_revision="dc8dfd3f9da8" toolshed="http://testtoolshed.g2.bx.psu.edu/" />
 </repositories>
--- a/snpEff.xml	Mon Nov 10 09:33:36 2014 -0600
+++ b/snpEff.xml	Tue Jan 13 13:36:11 2015 -0600
@@ -1,13 +1,14 @@
-<tool id="snpEff" name="SnpEff" version="4.0.1">
+<tool id="snpEff" name="SnpEff" version="@WRAPPER_VERSION@.2">
     <description>Variant effect and annotation</description>
     <expand macro="requirements" />
     <macros>
         <import>snpEff_macros.xml</import>
     </macros>
     <command>
+<![CDATA[
         java -Xmx6G -jar \$SNPEFF_JAR_PATH/snpEff.jar eff 
         -c \$SNPEFF_JAR_PATH/snpEff.config 
-        -i $inputFormat -o $outputFormat -upDownStreamLen $udLength 
+        -i $inputFormat -o ${outputConditional.outputFormat} -upDownStreamLen $udLength
         #if $spliceSiteSize and $spliceSiteSize.__str__ != '':
           -spliceSiteSize $spliceSiteSize
         #end if
@@ -32,7 +33,7 @@
           -interval $intervals
         #end if
         #if $statsFile:
-          -stats snpeff_report
+          -stats $statsFile 
         #end if
         #if $offset.__str__ != 'default':
           ${offset} 
@@ -66,10 +67,19 @@
           -download
           $snpDb.genome_version
         #end if
-        $input > $snpeff_output 
+        $input > $snpeff_output ;
         #if $statsFile:
-          &amp;&amp; mkdir $statsFile.extra_files_path  &amp;&amp; cp snpeff_report.genes.txt $statsFile.extra_files_path 
+            #import os
+            #set $genes_file = str($statsFile) + '.genes.txt'
+            #set $genes_file_name = os.path.split($genes_file)[-1]
+            mkdir $statsFile.files_path;
+            mv $genes_file #echo os.path.join($statsFile.files_path, $genes_file_name)#;
         #end if
+        #if $outputConditional.outputFormat == 'gatk' and $outputConditional.gatk_v1
+          ## Replace real SnpEff version with 2.0.5 to prevent this GATK 1.x error: "The version of SnpEff used to generate the SnpEff input file (x.x) is not currently supported by the GATK. Supported versions are: [2.0.5]"
+          sed -i 's/^\#\#SnpEffVersion="\(\S*\s\)/\#\#SnpEffVersion="2.0.5 - real is \1/' $snpeff_output
+        #end if
+]]>
     </command>
     <inputs>
         <param format="vcf,tabular,pileup,bed" name="input" type="data" label="Sequence changes (SNPs, MNPs, InDels)"/>
@@ -81,12 +91,22 @@
             <option value="bed">BED (Deprecated)</option>
         </param>
 
-        <param name="outputFormat" type="select" label="Output format">
-            <option value="vcf" selected="true">VCF (only if input is VCF)</option>
-            <option value="txt">Tabular</option>
-            <option value="bed">BED</option>
-            <option value="bedAnn">BED Annotations</option>
-        </param>
+        <conditional name="outputConditional">
+            <param name="outputFormat" type="select" label="Output format">
+                <option value="vcf" selected="true">VCF (only if input is VCF)</option>
+                <option value="gatk">GATK-compatible VCF (only if input is VCF)</option>
+                <option value="txt">Tabular</option>
+                <option value="bed">BED</option>
+                <option value="bedAnn">BED annotations</option>
+            </param>
+            <when value="vcf" />
+            <when value="gatk">
+                <param name="gatk_v1" type="boolean" checked="true" label="Compatible with GATK 1.x" />
+            </when>
+            <when value="txt" />
+            <when value="bed" />
+            <when value="bedAnn" />
+        </conditional>
 
         <conditional name="snpDb">
             <param name="genomeSrc" type="select" label="Genome source">
@@ -97,35 +117,36 @@
             <when value="cached">
                 <param name="genomeVersion" type="select" label="Genome">
                     <!--GENOME    DESCRIPTION-->
-                    <options from_data_table="snpeff4_genomedb">
-                           <filter type="unique_value" column="0" />
+                    <options from_data_table="snpeffv_genomedb">
+                           <filter type="static_value" name="snpeff_version" value="SnpEff4.1" column="1"/>
+                           <filter type="unique_value" column="2" />
                     </options>
                 </param>
-                <param name="extra_annotations" type="select" display="checkboxes" multiple="true" label="Additional Annotations">
+                <param name="extra_annotations" type="select" display="checkboxes" multiple="true" label="Additional annotations">
                        <help>These are available for only a few genomes</help>
-                       <options from_data_table="snpeff4_annotations">
-                           <filter type="param_value" ref="genomeVersion" key="genome" column="0" />
+                       <options from_data_table="snpeffv_annotations">
+                           <filter type="param_value" ref="genomeVersion" key="genome" column="2" />
                            <filter type="unique_value" column="1" />
                        </options>
                 </param>
-                <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory Annotation">
+                <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory annotation">
                        <help>These are available for only a few genomes</help>
-                       <options from_data_table="snpeff4_regulationdb">
-                           <filter type="param_value" ref="genomeVersion" key="genome" column="0" />
+                       <options from_data_table="snpeffv_regulationdb">
+                           <filter type="param_value" ref="genomeVersion" key="genome" column="2" />
                            <filter type="unique_value" column="1" />
                        </options>
                 </param>
             </when>
             <when value="history">
-                <param format="snpeffdbv4" name="snpeff_db" type="data" label="SnpEff Genome Version Data"/>
+                <param format="snpeffdbv41" name="snpeff_db" type="data" label="SnpEff Genome Version Data"/>
                 <!-- From metadata -->
-                <param name="extra_annotations" type="select" display="checkboxes" multiple="true" label="Additional Annotations">
+                <param name="extra_annotations" type="select" display="checkboxes" multiple="true" label="Additional annotations">
                     <help>These are available for only a few genomes</help>
                     <options>
                         <filter type="data_meta" ref="snpeff_db" key="annotation" />
                     </options>
                 </param>
-                <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory Annotation">
+                <param name="regulation" type="select" display="checkboxes" multiple="true" label="Non-coding and regulatory annotation">
                     <help>These are available for only a few genomes</help>
                     <options>
                         <filter type="data_meta" ref="snpeff_db" key="regulation" />
@@ -134,7 +155,7 @@
             </when>
             <when value="named">
                 <param name="genome_version" type="text" size="40" value="" label="Snpff Genome Version Name (e.g. GRCh38.76)">
-                    <help>http://sourceforge.net/projects/snpeff/files/databases/v4_0/</help>
+                    <help>@SNPEFF_DATABASE_URL@</help>
                     <validator type="regex" message="A genome version name is required">\S+</validator>
                 </param>
             </when>
@@ -153,7 +174,7 @@
 
         <param name="spliceSiteSize" type="select" optional="true" label="Set size for splice sites (donor and acceptor) in bases" help="Default: 2">
             <option value="1">1 base</option>
-            <option value="2">2 bases</option>
+            <option value="2" selected="true">2 bases</option>
             <option value="3">3 bases</option>
             <option value="4">4 bases</option>
             <option value="5">5 bases</option>
@@ -165,24 +186,24 @@
 
         <param name="filterHomHet" type="select" display="radio" label="Filter homozygous / heterozygous changes">
             <option value="no_filter" selected="true">No filter (analyze everything)</option>
-            <option value="-hom">Analyze homozygous sequence changes only </option>
-            <option value="-het">Analyze heterozygous sequence changes only </option>
+            <option value="-hom">Analyze homozygous sequence changes only</option>
+            <option value="-het">Analyze heterozygous sequence changes only</option>
         </param>
 
         <!-- The tool testing code can not handle select,radio,check boxes values that start with '-', so the '-' is added in the command generation -->
         <param name="filterIn" type="select" display="radio" label="Filter sequence changes">
             <option value="no_filter" selected="true">No filter (analyze everything)</option>
-            <option value="-del">Analyze deletions only </option>
-            <option value="-ins">Analyze insertions only </option>
-            <option value="-mnp">Only MNPs (multiple nucleotide polymorphisms) </option>
-            <option value="-snp">Only SNPs (single nucleotide polymorphisms) </option>
+            <option value="-del">Analyze deletions only</option>
+            <option value="-ins">Analyze insertions only</option>
+            <option value="-mnp">Only MNPs (multiple nucleotide polymorphisms)</option>
+            <option value="-snp">Only SNPs (single nucleotide polymorphisms)</option>
         </param>
 
         <param name="annotations" type="select" display="checkboxes" multiple="true" label="Annotation options">
-            <option value="-cancer">Perform 'cancer' comparissons (Somatic vs Germline)</option>
+            <option value="-cancer">Perform 'cancer' comparisons (somatic vs. germline)</option>
             <option value="-canon">Only use canonical transcripts</option>
             <option value="-geneId">Use gene ID instead of gene name (VCF output)</option>
-            <option value="-lof">Add loss of function (LOF) and Nonsense mediated decay (NMD) tags</option>
+            <option value="-lof">Add loss of function (LOF) and nonsense mediated decay (NMD) tags</option>
             <option value="-oicr">Add OICR tag in VCF file</option>
             <option value="-onlyReg">Only use regulation tracks</option>
             <option value="-classic">Use Classic Effect names and amino acid variant annotations (NON_SYNONYMOUS_CODING vs missense_variant and G180R vs p.Gly180Arg/c.538G>C)</option>
@@ -217,13 +238,12 @@
     <outputs>
         <data format="vcf" name="snpeff_output" >
             <change_format>
-                <when input="outputFormat" value="vcf" format="vcf" />
-                <when input="outputFormat" value="txt" format="tabular" />
-                <when input="outputFormat" value="bed" format="bed" />
-                <when input="outputFormat" value="bedAnn" format="bed" />
+                <when input="outputConditional.outputFormat" value="txt" format="tabular" />
+                <when input="outputConditional.outputFormat" value="bed" format="bed" />
+                <when input="outputConditional.outputFormat" value="bedAnn" format="bed" />
             </change_format>
         </data>
-        <data format="html" name="statsFile" label="{tool.name} on ${on_string} Summary Report" from_work_dir="snpeff_report">
+        <data format="html" name="statsFile" label="${tool.name} on ${on_string} - stats">
             <filter>generate_stats == True</filter>
         </data>
     </outputs>
@@ -287,7 +307,7 @@
         <param name="genome_version" value="testCase"/>
         <param name="udLength" value="0"/>
         <param name="filterHomHet" value="no_filter"/>
-        <param name="filterIn" value="del"/>
+        <param name="filterIn" value="+-del"/>
         <!--
         <param name="filterOut" value=""/>
         -->
@@ -333,5 +353,6 @@
 @CITATION_SECTION@
 
     </help>
+    <expand macro="citations" />
 </tool>
 
--- a/snpEff_databases.xml	Mon Nov 10 09:33:36 2014 -0600
+++ b/snpEff_databases.xml	Tue Jan 13 13:36:11 2015 -0600
@@ -1,11 +1,13 @@
-<tool id="snpEff_databases" name="SnpEff Available Databases" version="4.0.0">
+<tool id="snpEff_databases" name="SnpEff Available Databases" version="@WRAPPER_VERSION@.0">
     <description></description>
     <expand macro="requirements" />
     <macros>
         <import>snpEff_macros.xml</import>
     </macros>
     <command>
+<![CDATA[
     java -jar \$SNPEFF_JAR_PATH/snpEff.jar databases |  grep -v '^---' | sed 's/^Genome/#Genome/' | sed  's/  *//g' > $snpeff_dbs 
+]]>
     </command>
     <inputs>
     </inputs>
--- a/snpEff_download.xml	Mon Nov 10 09:33:36 2014 -0600
+++ b/snpEff_download.xml	Tue Jan 13 13:36:11 2015 -0600
@@ -1,21 +1,22 @@
-<tool id="snpEff_download" name="SnpEff Download" version="4.0.1">
+<tool id="snpEff_download" name="SnpEff Download" version="@WRAPPER_VERSION@.2">
     <description>Download a new database</description>
     <expand macro="requirements" />
     <macros>
         <import>snpEff_macros.xml</import>
     </macros>
     <command>
-    java -jar \$SNPEFF_JAR_PATH/snpEff.jar download -c \$SNPEFF_JAR_PATH/snpEff.config -dataDir $snpeff_db.extra_files_path -v $genome_version > $logfile 
+<![CDATA[
+    java -jar \$SNPEFF_JAR_PATH/snpEff.jar download -c \$SNPEFF_JAR_PATH/snpEff.config -dataDir $snpeff_db.files_path -v $genome_version 
+]]>
     </command>
     <inputs>
-        <param name="genome_version" type="text" size="40" value="" label="Snpff Genome Version Name (e.g. GRCh37.74)">
-            <help>http://sourceforge.net/projects/snpeff/files/databases/</help>
+        <param name="genome_version" type="text" size="40" value="" label="Select the genome version you want to download (e.g. GRCh37.74)">
+            <help>@SNPEFF_DATABASE_URL@</help>
             <validator type="regex" message="A genome version name is required">\S+</validator>
         </param>
     </inputs>
     <outputs>
-        <data format="txt" name="logfile" />
-        <data format="snpeffdbv4" name="snpeff_db" label="${tool.name} ${genome_version}" />
+        <data format="snpeffdbv41" name="snpeff_db" label="${tool.name} ${genome_version}" />
     </outputs>
     <expand macro="stdio" />
     <help>
@@ -25,5 +26,6 @@
 @CITATION_SECTION@
 
     </help>
+    <expand macro="citations" />
 </tool>
 
--- a/snpEff_macros.xml	Mon Nov 10 09:33:36 2014 -0600
+++ b/snpEff_macros.xml	Tue Jan 13 13:36:11 2015 -0600
@@ -10,6 +10,8 @@
         <exit_code range="1:"  level="fatal" description="Error" />
     </stdio>
   </xml>
+  <token name="@WRAPPER_VERSION@">4.0</token>
+  <token name="@SNPEFF_DATABASE_URL@">http://sourceforge.net/projects/snpeff/files/databases/v4_1/</token>
   <token name="@EXTERNAL_DOCUMENTATION@">
 
 For details about this tool, please go to:
@@ -23,10 +25,13 @@
 For the underlying tool, please cite the following two publications:
 
 SnpEff citation:
-"A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of Drosophila melanogaster strain w1118; iso-2; iso-3.", Cingolani P, Platts A, Wang le L, Coon M, Nguyen T, Wang L, Land SJ, Lu X, Ruden DM. Fly (Austin). 2012 Apr-Jun;6(2):80-92. PMID: 22728672 [PubMed - in process]
-
-SnpSift citation:
-"Using Drosophila melanogaster as a model for genotoxic chemical mutational studies with a new program, SnpSift", Cingolani, P., et. al., Frontiers in Genetics, 3, 2012.
+"A program for annotating and predicting the effects of single nucleotide polymorphisms, SnpEff: SNPs in the genome of Drosophila melanogaster strain w1118; iso-2; iso-3.", Cingolani P, Platts A, Wang le L, Coon M, Nguyen T, Wang L, Land SJ, Lu X, Ruden DM. Fly 6(2):80-92, 2012
 
   </token>
+  <xml name="citations">
+      <citations>
+        <citation type="doi">10.4161/fly.19695</citation>
+        <yield />
+      </citations>
+  </xml>
 </macros>
--- a/tool-data/snpeff4_annotations.loc.sample	Mon Nov 10 09:33:36 2014 -0600
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,5 +0,0 @@
-## Regulation Databases for SnpEff 
-## These are from the list on: http://snpeff.sourceforge.net/download.html
-#genome	annotation_name description
-#GRCh37.71	nextprot	nextprot
-#GRCh37.71	motif	motif
--- a/tool-data/snpeff4_databases.loc.sample	Mon Nov 10 09:33:36 2014 -0600
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,5 +0,0 @@
-## Available Databases for SnpEff 
-## These are from the list on: http://snpeff.sourceforge.net/download.html
-## the Description field in this sample is "Genome : Version" 
-#Version	Description
-#GRCh37.68	Homo sapiens : GRCh37.68
--- a/tool-data/snpeff4_genomedb.loc.sample	Mon Nov 10 09:33:36 2014 -0600
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,5 +0,0 @@
-## Downloaded Databases for SnpEff 
-## These are from the list on: http://snpeff.sourceforge.net/download.html
-## the Description field in this sample is "Genome : Version" 
-#Version        Description	data_dir path
-#GRCh37.68      Homo sapiens : GRCh37.68	/home/galaxy/snpEff/data
--- a/tool-data/snpeff4_regulationdb.loc.sample	Mon Nov 10 09:33:36 2014 -0600
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,4 +0,0 @@
-## Regulation Databases for SnpEff 
-## These are from the list on: http://snpeff.sourceforge.net/download.html
-#genome	regulation_name description
-#GRCh37.70	CD4	CD4
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/snpeffv_annotations.loc.sample	Tue Jan 13 13:36:11 2015 -0600
@@ -0,0 +1,5 @@
+## Regulation Databases for SnpEff 
+## These are from the list on: http://snpeff.sourceforge.net/download.html
+#key	snpeff_version	genome	annotation_name description
+#SnpEff4.0_GRCh37.75	SnpEff4.0	GRCh37.75	nextprot	nextprot
+#SnpEff4.0_GRCh38.76	SnpEff4.1	GRCh38.76	motif	motif
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/snpeffv_databases.loc.sample	Tue Jan 13 13:36:11 2015 -0600
@@ -0,0 +1,5 @@
+## Available Databases for SnpEff 
+## These are from the list on: http://snpeff.sourceforge.net/download.html
+## the Description field in this sample is "Genome : Version" 
+#key	snpeff_version	Version	Description
+#SnpEff4.0_GRCh37.75	SnpEff4.0	GRCh37.75	Homo sapiens : GRCh37.75
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/snpeffv_genomedb.loc.sample	Tue Jan 13 13:36:11 2015 -0600
@@ -0,0 +1,6 @@
+## Downloaded Databases for SnpEff 
+## These are from the list on: http://snpeff.sourceforge.net/download.html
+## the Description field in this sample is "Genome : Version" 
+#Key	snpeff_version	Version	Description	data_dir	path
+#SnpEff4.0_GRCh37.74	SnpEff4.0	GRCh37.74	Homo sapiens : GRCh37.74	/home/galaxy/snpEff/v4_0/data
+#SnpEff4.1_GRCh38.76	SnpEff4.1	GRCh38.76	Homo sapiens : GRCh38.76	/home/galaxy/snpEff/v4_1/data
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/snpeffv_regulationdb.loc.sample	Tue Jan 13 13:36:11 2015 -0600
@@ -0,0 +1,5 @@
+## Regulation Databases for SnpEff 
+## These are from the list on: http://snpeff.sourceforge.net/download.html
+#Key	snpeff_version	genome	regulation_name description
+#SnpEff4.0_GRCh37.74	SnpEff4.0	GRCh37.74	CD4	CD4
+#SnpEff4.1_GRCh38.76	SnpEff4.1	GRCh38.76	CD4	CD4
--- a/tool_data_table_conf.xml.sample	Mon Nov 10 09:33:36 2014 -0600
+++ b/tool_data_table_conf.xml.sample	Tue Jan 13 13:36:11 2015 -0600
@@ -1,19 +1,19 @@
 <tables>
-    <table name="snpeff4_databases" comment_char="#">
-        <columns>value, name</columns>
-        <file path="tool-data/snpeff4_databases.loc" />
+    <table name="snpeffv_databases" comment_char="#">
+        <columns>key, version, value, name</columns>
+        <file path="tool-data/snpeffv_databases.loc" />
     </table>
-    <table name="snpeff4_genomedb" comment_char="#">
-        <columns>value, name, path</columns>
-        <file path="tool-data/snpeff4_genomedb.loc" />
+    <table name="snpeffv_genomedb" comment_char="#">
+        <columns>key, version, value, name, path</columns>
+        <file path="tool-data/snpeffv_genomedb.loc" />
     </table>
-    <table name="snpeff4_regulationdb" comment_char="#">
-        <columns>genome, value, name</columns>
-        <file path="tool-data/snpeff4_regulationdb.loc" />
+    <table name="snpeffv_regulationdb" comment_char="#">
+        <columns>key, version, genome, value, name</columns>
+        <file path="tool-data/snpeffv_regulationdb.loc" />
     </table>
-    <table name="snpeff4_annotations" comment_char="#">
-        <columns>genome, value, name</columns>
-        <file path="tool-data/snpeff4_annotations.loc" />
+    <table name="snpeffv_annotations" comment_char="#">
+        <columns>key, version, genome, value, name</columns>
+        <file path="tool-data/snpeffv_annotations.loc" />
     </table>
 </tables>