Mercurial > repos > iuc > sra_tools

changeset 1:462ee06c9358 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sra-tools commit 4defaa3ff1c21e2ec39033bfe63ee69471104ede
author iuc
date Tue, 17 May 2016 14:14:50 -0400
parents b723c120161a
children f256cb398262
files fastq_dump.xml sam_dump.xml sra_macros.xml tool_dependencies.xml
diffstat 4 files changed, 161 insertions(+), 55 deletions(-) [+]
line wrap: on
line diff
--- a/fastq_dump.xml	Sun Dec 06 09:04:37 2015 -0500
+++ b/fastq_dump.xml	Tue May 17 14:14:50 2016 -0400
@@ -1,4 +1,4 @@
-<tool id="fastq_dump" name="Extract reads" version="1.2.5">
+<tool id="fastq_dump" name="Extract reads" version="1.3.0">
     <description>in FASTQ/A format from NCBI SRA.</description>
     <macros>
         <import>sra_macros.xml</import>
@@ -10,6 +10,18 @@
     <version_command>fastq-dump --version</version_command>
     <command>
         <![CDATA[
+
+    #if $input.input_select=="file_list":
+      for acc in `cat $input.file_list` ;
+      do
+    #elif $input.input_select=="accession_number":
+      acc="$input.accession" &&
+    #end if
+
+    #if $input.input_select=="file_list" or $input.input_select=="accession_number":
+          [ ""\$acc" =~ ^[E|S|D]RR[0-9]{1,}$" ] && (
+    #end if
+    
     ## Need to set the home directory to the current working directory,
     ## else the tool tries to write to home/.ncbi and fails when used 
     ## with a cluster manager. 
@@ -24,15 +36,16 @@
         #if ( str( $adv.region ) == "" ) and ( str( $adv.minID ) == "" ) and ( str( $adv.maxID ) == "" ):
             ASCP_PATH=`command -v ascp` &&
             ASCP_KEY=`dirname \$ASCP_PATH`/asperaweb_id_dsa.openssh || true &&
-            prefetch --ascp-path "\$ASCP_PATH|\$ASCP_KEY" $input.accession &&
+            prefetch --ascp-path "\$ASCP_PATH|\$ASCP_KEY" "\$acc" &&
             ## Duplicate vdb-config, in case settings changed between prefetch and
             ## dump command.
             vdb-config -s "/repository/user/main/public/root=\$PWD" &&
-            #end if
-        fastq-dump --accession "$input.accession"
+        #end if
+        fastq-dump --accession "\$acc"
+        --split-files
     #end if
     --defline-seq '@\$sn[_\$rn]/\$ri'
-    --stdout
+
     $adv.split
     #if str( $adv.alignments ) == "aligned":
         --aligned
@@ -63,14 +76,45 @@
     #end if
     $adv.clip
     $adv.skip_technical
+    
     #if str( $outputformat ) == "fasta":
         --fasta
     #end if
     #if $input.input_select=="file":
+        --stdout
         "$input.file" > "$output_file"
+    #elif $input.input_select=="file_list":
+        "\$acc"
     #else:
-        "$input.accession" > "$output_accession"
+         --stdout
+        "\$acc" > "$output_accession" )
     #end if
+
+    #if $input.input_select=="file_list":
+    ) ; done
+
+    ;
+
+
+    #if str( $outputformat ) == "fasta":
+    
+        for f in *_2.fasta ; do   mv "\$f" "`basename \$f _2.fasta`_reverse.fasta" ;  mv "`basename \$f _2.fasta`_1.fasta" "`basename \$f _2.fasta`_forward.fasta"  ; done &&
+        for f in *_1.fasta; do mv "\$f" "`basename \$f _1.fasta`__single.fasta"; done
+        
+    #else:
+
+        for f in *_2.fastq ; do   mv "\$f" "`basename \$f _2.fastq`_reverse.fastq" ;  mv "`basename \$f _2.fastq`_1.fastq" "`basename \$f _2.fastq`_forward.fastq"  ; done &&
+        for f in *_1.fastq; do mv "\$f" "`basename \$f _1.fastq`__single.fastq"; done
+        
+    #end if
+
+
+
+
+
+    #end if
+
+    
     ]]>
     </command>
     <inputs>
@@ -105,45 +149,62 @@
         </section>
     </inputs>
     <outputs>
-        <data format="fastq" name="output_accession" label="${input.accession}.${outputformat}">
-            <filter>input['input_select'] == "accession_number"</filter>
-            <change_format>
-                <when input="outputformat" value="fasta" format="fasta"/>
-            </change_format>
-        </data>
-        <data format="fastq" name="output_file" label="${input.file.name}.${outputformat}">
-            <filter>input['input_select'] == "file"</filter>
-            <change_format>
-                <when input="outputformat" value="fasta" format="fasta"/>
-            </change_format>
-        </data>
+      <collection name="list_paired" type="list:paired" label="Pair-end Fast(q|a)">
+        <filter>input['input_select'] == "file_list"</filter>
+        <!-- Use named regex group to grab pattern
+             <identifier_0>_<identifier_1>.fq. Here identifier_0 is the list
+             identifier in the nested collection and identifier_1 is either
+             forward or reverse (for instance samp1_forward.fq).
+        -->
+        <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;[^_]+)\.fastq" ext="fastqsanger" visible="false" />
+        <discover_datasets pattern="(?P&lt;identifier_0&gt;[^_]+)_(?P&lt;identifier_1&gt;[^_]+)\.fasta" ext="fasta" visible="false" />
+      </collection>
+      <collection name="output_collection" type='list' label="Single-end Fast(q|a)">
+        <filter>input['input_select'] == "file_list"</filter>
+        <discover_datasets pattern="(?P&lt;designation&gt;.+)__single\.fastq" directory="." ext='fastqsanger'/>
+        <discover_datasets pattern="(?P&lt;designation&gt;.+)__single\.fasta" directory="." ext='fasta'/>
+      </collection>
+      <data format="fastqsanger" name="output_accession" >
+        <filter>input['input_select'] == "accession_number"</filter>
+        <change_format>
+          <when input="outputformat" value="fasta" format="fasta"/>
+        </change_format>
+      </data>
+      <data format="fastqsanger" name="output_file" label="${input.file.name}.${outputformat}">
+        <filter>input['input_select'] == "file"</filter>
+        <change_format>
+          <when input="outputformat" value="fasta" format="fasta"/>
+        </change_format>
+      </data>
     </outputs>
     <tests>
-        <test>
-            <param name="input_select" value="accession_number"/>
-            <param name="outputformat" value="fastqsanger"/>
-            <param name="accession" value="SRR044777"/>
-            <param name="skip_technical" value="True"/>
-            <output name="output_accession">
-                <assert_contents>
-                    <not_has_text text="rRNA_primer"/>
-                    <has_text text="F47USSH02GNP1D" />
-                </assert_contents>
-            </output>
-        </test>
-        <test>
-            <param name="input_select" value="accession_number"/>
-            <param name="outputformat" value="fastqsanger"/>
-            <param name="accession" value="SRR925743"/>
-            <param name="maxID" value="5"/>
-            <output name="output_accession" file="fastq_dump_result.fastq" ftype="fastq"/>
-        </test>
+      <test>
+        <param name="input_select" value="accession_number"/>
+        <param name="outputformat" value="fastqsanger"/>
+        <param name="accession" value="SRR044777"/>
+        <param name="skip_technical" value="True"/>
+        <output name="output_accession">
+          <assert_contents>
+            <not_has_text text="rRNA_primer"/>
+            <has_text text="F47USSH02GNP1D" />
+          </assert_contents>
+        </output>
+      </test>
+      <test>
+        <param name="input_select" value="accession_number"/>
+        <param name="outputformat" value="fastqsanger"/>
+        <param name="accession" value="SRR925743"/>
+        <param name="maxID" value="5"/>
+        <output name="output_accession" file="fastq_dump_result.fastq" ftype="fastqsanger"/>
+      </test>
     </tests>
     <help>
         This tool extracts reads from SRA archives using fastq-dump.
         The fastq-dump program is developed at NCBI, and is available at
         http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software.
+        
+        NB: Single-end or pair-end collections may be empty if given SRRs LibraryLayout contains only either SINGLE or PAIRED respectively
         @SRATOOLS_ATTRRIBUTION@
     </help>
     <expand macro="citation"/>
-</tool>
+  </tool>
--- a/sam_dump.xml	Sun Dec 06 09:04:37 2015 -0500
+++ b/sam_dump.xml	Tue May 17 14:14:50 2016 -0400
@@ -1,4 +1,4 @@
-<tool id="sam_dump" name="Extract reads" version="1.2.5">
+<tool id="sam_dump" name="Extract reads" version="1.3.0">
     <description>in SAM or BAM format from NCBI SRA.</description>
     <macros>
         <import>sra_macros.xml</import>
@@ -7,6 +7,19 @@
     <version_command>sam-dump --version</version_command>
     <command>
         <![CDATA[
+    #if $input.input_select=="file_list":
+      for acc in `cat $input.file_list` ;
+      do
+    #elif $input.input_select=="accession_number":
+      acc="$input.accession" &&
+    #end if
+
+    #if $input.input_select=="file_list" or $input.input_select=="accession_number":
+          [ ""\$acc" =~ ^[E|S|D]RR[0-9]{1,}$" ] && (
+    #end if
+
+
+
         ## Need to set the home directory to the current working directory,
         ## else the tool tries to write to home/.ncbi and fails when used 
         ## with a cluster manager. 
@@ -18,7 +31,7 @@
         #if ( str( $adv.region ) == "" ):
             ASCP_PATH=`command -v ascp` &&
             ASCP_KEY=`dirname \$ASCP_PATH`/asperaweb_id_dsa.openssh || true &&
-            prefetch --ascp-path "\$ASCP_PATH|\$ASCP_KEY" "$input.accession" &&
+            prefetch --ascp-path "\$ASCP_PATH|\$ASCP_KEY" "\$acc" &&
             ## Duplicate vdb-config, in case settings changed between prefetch and
             ## dump command.
             vdb-config -s "/repository/user/main/public/root=\$PWD" &&
@@ -50,16 +63,30 @@
         #if $input.input_select == "file":
             "$input.file"
         #elif $input.input_select == "accession_number":
-            "$input.accession"
+            "\$acc"
+        #elif $input.input_select=="file_list":
+            "\$acc"
         #end if
+        
         #if str( $outputformat ) == "bam":
             | samtools view -Sb - 2> /dev/null
         #end if
         #if $input.input_select == "file":
             > "$output_file"
         #elif $input.input_select == "accession_number":
-            > "$output_accession"
+            > "$output_accession" )
         #end if
+
+        #if $input.input_select=="file_list":
+                 #if str( $outputformat ) == "bam":
+                      > "\$acc.bam"
+                 #elif str( $outputformat ) == "sam":
+                      > "\$acc.sam"
+                 #end if
+        ) ; done
+        #end if
+
+
         ]]>
     </command>
     <inputs>
@@ -86,6 +113,11 @@
         </section>
     </inputs>
     <outputs>
+        <collection name="output_collection" type='list'>
+          <filter>input['input_select'] == "file_list"</filter>
+          <discover_datasets pattern="(?P&lt;designation&gt;.+)\.bam" directory="." ext='bam'/>
+          <discover_datasets pattern="(?P&lt;designation&gt;.+)\.sam" directory="." ext='sam'/>
+        </collection>      
         <data name="output_accession" format="bam" label="${input.accession}.${outputformat}">
             <filter>input['input_select'] == "accession_number"</filter>
             <change_format>
--- a/sra_macros.xml	Sun Dec 06 09:04:37 2015 -0500
+++ b/sra_macros.xml	Tue May 17 14:14:50 2016 -0400
@@ -1,9 +1,10 @@
 <macros>
     <macro name="requirements">
         <requirements>
-            <requirement type="package" version="1.1.3">ngs_sdk</requirement>
-            <requirement type="package" version="2.5.2">ncbi_vdb</requirement>
-            <requirement type="package" version="2.5.2">sra_toolkit</requirement>
+            <requirement type="package" version="1.2.3">ngs_sdk</requirement>
+            <requirement type="package" version="2.6.2">ncbi_vdb</requirement>
+            <requirement type="package" version="2.6.2">sra_toolkit</requirement>
+            <requirement type="package" version="2.6.2">sra-tools</requirement>
             <requirement type="package" version="5.18.1">perl</requirement>
         </requirements>
     </macro>
@@ -12,13 +13,17 @@
             <param name="input_select" type="select" label="select input type">
                 <option value="accession_number">SRR accession</option>
                 <option value="file">SRA archive in current history</option>
+                <option value="file_list">List of SRA accession, one per line</option>
             </param>
             <when value="accession_number">
-                <param name="accession" type="text" label="SRR accession" help="Must start with SRR, e.g. SRR925743"/>
+                <param name="accession" type="text" label="SRR accession" help="Must start with SRR,DRR or ERR, e.g. SRR925743 , ERR343809"/>
             </when>
             <when value="file">
                 <param format="sra" name="file" type="data" label="sra archive"/>
             </when>
+            <when value="file_list">
+                <param format="txt" name="file_list" type="data" label="sra accession list"/>
+            </when>            
         </conditional>
     </macro>
     <macro name="alignments">
@@ -45,8 +50,16 @@
             <citation type="doi">10.1093/nar/gkq1019</citation>
         </citations>
     </macro>
-    <token name="@SRATOOLS_ATTRRIBUTION@">Browse the NCBI SRA for SRR accessions at http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=studies.
+    <token name="@SRATOOLS_ATTRRIBUTION@">
+        Browse the NCBI SRA for SRR accessions at http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=studies.
+        
         Galaxy tool wrapper originally written by Matt Shirley (mdshw5 at gmail.com).
+
+        Wrapper modified by Philip Mabon ( philip.mabon at phac-aspc.gc.ca ). 
+        
         Tool dependencies, clean-up and bug-fixes by Marius van den Beek (m.vandenbeek at gmail.com).
-        For support and bug reports contact Matt Shirley or Marius van den Beek or go to https://github.com/galaxyproject/tools-iuc.</token>
+        
+        For support and bug reports contact Matt Shirley or Marius van den Beek or go to https://github.com/galaxyproject/tools-iuc.
+        
+    </token>
 </macros>
--- a/tool_dependencies.xml	Sun Dec 06 09:04:37 2015 -0500
+++ b/tool_dependencies.xml	Tue May 17 14:14:50 2016 -0400
@@ -1,15 +1,15 @@
 <?xml version="1.0"?>
 <tool_dependency>
-    <package name="ncbi_vdb" version="2.5.2">
-        <repository changeset_revision="b980182ad267" name="package_ncbi_vdb_2_5_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+    <package name="ncbi_vdb" version="2.6.2">
+        <repository changeset_revision="be38d36c735d" name="package_ncbi_vdb_2_6_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
     </package>
-    <package name="ngs_sdk" version="1.1.3">
-        <repository changeset_revision="1197d3c98375" name="package_ngs_sdk_1_1_3" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+    <package name="ngs_sdk" version="1.2.3">
+        <repository changeset_revision="3da0f4d34e92" name="package_ngs_sdk_1_2_3" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
     </package>
-    <package name="sra_toolkit" version="2.5.2">
-        <repository changeset_revision="ab06c0240705" name="package_sra_toolkit_2_5_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+    <package name="sra_toolkit" version="2.6.2">
+        <repository changeset_revision="98414d1f9480" name="package_sra_toolkit_2_6_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
     </package>
     <package name="perl" version="5.18.1">
-        <repository changeset_revision="8b3509930a44" name="package_perl_5_18" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+        <repository changeset_revision="35f117d7396b" name="package_perl_5_18" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
     </package>
 </tool_dependency>