Merged thanhleviet's changes from PR galaxyproject#2575 here

Slugger70 · Sep 11, 2019 · ced4edf · ced4edf
2 parents ae13a8c + 31d02e0
commit ced4edf
Show file tree

Hide file tree

Showing 6 changed files with 151 additions and 33 deletions.
diff --git a/tools/snippy/snippy-core.xml b/tools/snippy/snippy-core.xml
@@ -8,19 +8,39 @@
     </macros>
     <expand macro="requirements" />
     <command detect_errors="exit_code"><![CDATA[
+        #if $reference_source.reference_source_selector == 'history'
+            ln -sf '$reference_source.ref_file' 'ref' &&
+        #elif $reference_source.reference_source_selector == 'cached'
+            ln -sf '$reference_source.ref_file.fields.path' 'ref' &&
+        #end if
         #for $indir in $indirs
             #set $sample_name = os.path.splitext(os.path.basename(str($indir.name)))[0]
             mkdir '$sample_name' && tar -xf '$indir' -C '$sample_name' --strip-components=1 &&
         #end for
         #set snippy_dirs = " ".join(["'{0}'".format(os.path.splitext(os.path.basename(str($indir.name)))[0]) for $indir in $indirs])
         snippy-core
-            --ref '$ref'
+            --ref 'ref'
             ${snippy_dirs}
     ]]></command>
 
     <inputs>
         <param name="indirs" type="data" multiple="true" format="zip" label="Snippy input zipped dirs" help="Select all the snippy inputs for alignment" />
-        <param name="ref" type="data" format="fasta,genbank" label="Reference File (either in fasta or genbank format)" help="Fasta or Genbank file to use as the reference" />
+        <conditional name="reference_source">
+            <param name="reference_source_selector" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options. See `Indexes` section of help below. If you would like to perform self-mapping select `history` here, then choose your input file as reference.">
+                <option value="cached">Use a built-in genome index</option>
+                <option value="history">Use a genome from history and build index</option>
+            </param>
+            <when value="cached">
+                <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
+                    <options from_data_table="all_fasta">
+                        <validator type="no_options" message="No reference genomes are available" />
+                    </options>
+                </param>
+            </when>
+            <when value="history">
+                <param name="ref_file" type="data" format="fasta,genbank" label="Use the following dataset as the reference sequence" help="You can upload a FASTA or FASTQ sequence to the history and use it as reference" />
+            </when>
+        </conditional>
         <param name="outputs" type="select" multiple="true" display="checkboxes" label="Output selection">
             <option value="outaln" selected="True">A core SNP alignment in the fasta format</option>
             <option value="outfull" selected="False">A whole genome SNP alignment (includes invariant sites)</option>
@@ -48,7 +68,15 @@
     <tests>
         <test><!-- Test #1 - test with 3 zipped directories -->
             <param name="indirs" value="a.tgz,b.tgz,c.tgz" />
-            <param name="ref" value="reference.fasta" />
+            <param name="reference_source|reference_source_selector" value="history"/>
+            <param name="reference_source|ref_file" value="reference.fasta" ftype="fasta"/>
+            <param name="outputs" value="outtxt" />
+            <output name="alignment_summary" ftype="txt" file="a_b_c.core.txt" />
+        </test>
+        <test><!-- Test #2 - test with 3 zipped directories -->
+            <param name="indirs" value="a.tgz,b.tgz,c.tgz" />
+            <param name="reference_source|reference_source_selector" value="cached"/>
+            <param name="reference_source|ref_file" value="test_id"/>
             <param name="outputs" value="outtxt" />
             <output name="alignment_summary" ftype="txt" file="a_b_c.core.txt" />
         </test>

diff --git a/tools/snippy/snippy.xml b/tools/snippy/snippy.xml
@@ -1,31 +1,26 @@
 <tool id="snippy" name="snippy" version="@VERSION@+galaxy3">
   <description>
       Snippy finds SNPs between a haploid reference genome and your NGS sequence reads.
-  </description>
-  <macros>
-      <import>macros.xml</import>
-  </macros>
-  <expand macro="requirements" />
-  <expand macro="version_command" />
+    </description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <expand macro="version_command" />
 
     <command detect_errors="exit_code"><![CDATA[
 
-        #if $ref.is_of_type("fasta")
-            cp '$ref' 'ref.fna' &&
-        #end if
-        #if $ref.is_of_type("genbank")
-            cp '$ref' 'ref.gbk' &&
+        #if $reference_source.reference_source_selector == 'history'
+            ln -sf '$reference_source.ref_file' 'ref' &&
+        #elif $reference_source.reference_source_selector == 'cached'
+            ln -sf '$reference_source.ref_file.fields.path' 'ref' &&
         #end if
+
         snippy
             --outdir 'out'
             --cpus \${GALAXY_SLOTS:-1}
             --ram \$((\${GALAXY_MEMORY_MB:-4096}/1024))
-            #if $ref.is_of_type("fasta")
-                --ref 'ref.fna'
-            #end if
-            #if $ref.is_of_type("genbank")
-                --ref 'ref.gbk'
-            #end if
+            --ref 'ref'
             --mapqual $adv.mapqual
             --mincov $adv.mincov
             --minfrac $adv.minfrac
@@ -69,12 +64,26 @@
         #end if
 
 
-    ]]></command>
+    ]]>    </command>
 
     <inputs>
 
-        <param name="ref" type="data" format="fasta,genbank" label="Reference File (either in fasta or genbank format)" help="Fasta or Genbank file to use as the reference" />
-
+        <conditional name="reference_source">
+            <param name="reference_source_selector" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options. See `Indexes` section of help below. If you would like to perform self-mapping select `history` here, then choose your input file as reference.">
+                <option value="cached">Use a built-in genome index</option>
+                <option value="history">Use a genome from history and build index</option>
+            </param>
+            <when value="cached">
+                <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
+                    <options from_data_table="all_fasta">
+                        <validator type="no_options" message="No reference genomes are available" />
+                    </options>
+                </param>
+            </when>
+            <when value="history">
+                <param name="ref_file" type="data" format="fasta" label="Use the following dataset as the reference sequence" help="You can upload a FASTA or FASTQ sequence to the history and use it as reference" />
+            </when>
+        </conditional>
         <conditional name="fastq_input">
             <param name="fastq_input_selector" type="select" label="Single or Paired-end reads" help="Select between paired and single end data">
                 <option value="paired">Paired</option>
@@ -155,8 +164,12 @@
 
     <tests>
 
-        <test> <!-- test 0 - fasta ref no snps -->
-            <param name="ref" value="reference.fasta" ftype="fasta" />
+        <test>            <!-- test 0 - fasta ref no snps -->
+            <!-- <param name="ref" value="reference.fasta" ftype="fasta" /> -->
+            <conditional name="reference_source">
+              <param name="reference_source_selector" value="history"/>
+              <param name="ref_file" value="reference.fasta" ftype="fasta"/>
+            </conditional>
             <param name="fastq_input_selector" value="paired" />
             <param name="fastq_input1" ftype="fastqsanger" value="a_1.fastq" />
             <param name="fastq_input2" ftype="fastqsanger" value="a_2.fastq" />
@@ -167,8 +180,11 @@
             <output name="snpgff" ftype="gff3" file="a_fna_ref_mincov_2_minqual_60.snps.gff" />
         </test>
 
-        <test> <!-- test 1 - fasta ref one snp -->
-            <param name="ref" value="reference.fasta" ftype="fasta" />
+        <test>            <!-- test 1 - fasta ref one snp -->
+            <conditional name="reference_source">
+                <param name="reference_source_selector" value="history"/>
+                <param name="ref_file" value="reference.fasta" ftype="fasta"/>
+            </conditional>
             <param name="fastq_input_selector" value="paired" />
             <param name="fastq_input1" ftype="fastqsanger" value="b_1.fastq" />
             <param name="fastq_input2" ftype="fastqsanger" value="b_2.fastq" />
@@ -179,8 +195,11 @@
             <output name="snpgff" ftype="gff3" file="b_fna_ref_mincov_2_minqual_60.snps.gff" />
         </test>
 
-        <test> <!-- test 2 - fasta ref one snp paired_collection -->
-            <param name="ref" value="reference.fasta" ftype="fasta" />
+        <test>            <!-- test 2 - fasta ref one snp paired_collection -->
+            <conditional name="reference_source">
+                <param name="reference_source_selector" value="history"/>
+                <param name="ref_file" value="reference.fasta" ftype="fasta"/>
+            </conditional>
             <param name="fastq_input_selector" value="paired_collection" />
             <param name="fastq_input">
                 <collection type="paired">
@@ -195,8 +214,25 @@
             <output name="snpgff" ftype="gff3" file="b_fna_ref_mincov_2_minqual_60.snps.gff" />
         </test>
 
-        <test> <!-- test 3 - fasta ref one snp single -->
-            <param name="ref" value="reference.fasta" ftype="fasta" />
+        <test>            <!-- test 3 - fasta ref one snp single -->
+            <conditional name="reference_source">
+                <param name="reference_source_selector" value="history"/>
+                <param name="ref_file" value="reference.fasta" ftype="fasta"/>
+            </conditional>
+            <param name="fastq_input_selector" value="single" />
+            <param name="fastq_input_single" value="b_2.fastq" ftype="fastqsanger" />
+            <param name="mincov" value="2" />
+            <param name="minqual" value="60" />
+            <param name="outputs" value="outgff,outsum" />
+            <output name="snpsum" ftype="tabular" file="b_fna_ref_mincov_2_minqual_60.snps.txt" lines_diff="6" />
+            <output name="snpgff" ftype="gff3" file="b_2_fna_ref_mincov_2_minqual_60.snps.gff" />
+        </test>
+
+        <test>            <!-- test 4 - reference source as cached -->
+            <conditional name="reference_source">
+                <param name="reference_source_selector" value="cached"/>
+                <param name="ref_file" value="test_id"/>
+            </conditional>
             <param name="fastq_input_selector" value="single" />
             <param name="fastq_input_single" value="b_2.fastq" ftype="fastqsanger" />
             <param name="mincov" value="2" />
@@ -243,7 +279,7 @@ If the reference file is supplied in genbank format, snpeff will be called to de
 
     For a much more in depth description of snippy and how it works, see https://github.com/tseemann/snippy
 
-    ]]></help>
-  <expand macro="citations"/>
+    ]]>    </help>
+    <expand macro="citations"/>
 
 </tool>
diff --git a/tools/snippy/test-data/all_fasta.loc b/tools/snippy/test-data/all_fasta.loc
@@ -0,0 +1,20 @@
+#This file lists the locations and dbkeys of all the fasta files
+#under the "genome" directory (a directory that contains a directory
+#for each build). The script extract_fasta.py will generate the file
+#all_fasta.loc. This file has the format (white space characters are
+#TAB characters):
+#
+#<unique_build_id>	<dbkey>	<display_name>	<file_path>
+#
+#So, all_fasta.loc could look something like this:
+#
+#apiMel3	apiMel3	Honeybee (Apis mellifera): apiMel3	/path/to/genome/apiMel3/apiMel3.fa
+#hg19canon	hg19	Human (Homo sapiens): hg19 Canonical	/path/to/genome/hg19/hg19canon.fa
+#hg19full	hg19	Human (Homo sapiens): hg19 Full	/path/to/genome/hg19/hg19full.fa
+#
+#Your all_fasta.loc file should contain an entry for each individual
+#fasta file. So there will be multiple fasta files for each build,
+#such as with hg19 above.
+#
+test_id	test_dbkey	test display name	${__HERE__}/ref.fna
+
diff --git a/tools/snippy/tool-data/all_fasta.loc b/tools/snippy/tool-data/all_fasta.loc
@@ -0,0 +1,18 @@
+#This file lists the locations and dbkeys of all the fasta files
+#under the "genome" directory (a directory that contains a directory
+#for each build). The script extract_fasta.py will generate the file
+#all_fasta.loc. This file has the format (white space characters are
+#TAB characters):
+#
+#<unique_build_id>	<dbkey>	<display_name>	<file_path>
+#
+#So, all_fasta.loc could look something like this:
+#
+#apiMel3	apiMel3	Honeybee (Apis mellifera): apiMel3	/path/to/genome/apiMel3/apiMel3.fa
+#hg19canon	hg19	Human (Homo sapiens): hg19 Canonical	/path/to/genome/hg19/hg19canon.fa
+#hg19full	hg19	Human (Homo sapiens): hg19 Full	/path/to/genome/hg19/hg19full.fa
+#
+#Your all_fasta.loc file should contain an entry for each individual
+#fasta file. So there will be multiple fasta files for each build,
+#such as with hg19 above.
+#
diff --git a/tools/snippy/tool_data_table_conf.xml.sample b/tools/snippy/tool_data_table_conf.xml.sample
@@ -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>
+    <!-- Locations of all fasta files under genome directory -->
+    <table name="all_fasta" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/all_fasta.loc" />
+    </table>
+</tables>
diff --git a/tools/snippy/tool_data_table_conf.xml.test b/tools/snippy/tool_data_table_conf.xml.test
@@ -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>
+    <!-- Locations of all fasta files under genome directory -->
+    <table name="all_fasta" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, name, path</columns>
+        <file path="${__HERE__}/test-data/all_fasta.loc" />
+    </table>
+</tables>