Mercurial > repos > iuc > sina

changeset 4:482052b30b78 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/sina commit f670d67c5943709ec6bd406becd60954621e4585"
author iuc
date Fri, 02 Oct 2020 08:18:09 +0000
parents 8afa8799d50f
children 56d7dc39eec8
files sina.xml
diffstat 1 files changed, 131 insertions(+), 145 deletions(-) [+]
line wrap: on
line diff
--- a/sina.xml	Fri Oct 02 08:01:21 2020 +0000
+++ b/sina.xml	Fri Oct 02 08:18:09 2020 +0000
@@ -1,100 +1,97 @@
-<tool id="sina" name="SINA" version="@TOOL_VERSION@+@WRAPPER_VERSION@" profile="18.01">
+<tool id="sina" name="SINA" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="18.01">
     <description>reference based multiple sequence alignment</description>
     <macros>
-        <token name="@TOOL_VERSION@">1.6.1</token>
-        <token name="@WRAPPER_VERSION@">galaxy0</token>
-        <xml name="minidty">
-            <param name="minidty" type="float" value="0.7" min="0.0" max="1.0" label="Exclude sequences sharing less than this value fractional identity with any of the alignment reference sequences from the output?" help="(--min-idty)"/>
-        </xml>
+        <token name="@TOOL_VERSION@">1.7.1</token>
+        <token name="@VERSION_SUFFIX@">0</token>
     </macros>
     <requirements>
         <requirement type="package" version="@TOOL_VERSION@">sina</requirement>
     </requirements>
     <version_command>sina --version</version_command>
     <command detect_errors="exit_code"><![CDATA[
-        ## initialize
-        ## parse custom reference from fasta to arb file format
-        #if $db.select == 'custom'
-            #if $db.custom.ext == 'fasta'
-                sina -i '$db.custom' --prealigned -o 'reference.arb' &&
-            #else
-                ln -s '$db.custom' 'reference.arb' &&
-            #end if
-        #elif $db.select == 'local'
-            ln -s '$db.arb_databases.fields.path' 'reference.arb' &&
-        #end if
+## initialize
+#if $db.select == 'custom'
+    ## parse custom reference from fasta to arb file format
+    #if $db.custom.ext == 'fasta'
+        sina -i '$db.custom' --prealigned -o 'reference.arb' &&
+    #else
+        ln -s '$db.custom' 'reference.arb' &&
+    #end if
+#elif $db.select == 'local'
+    ln -s '$db.arb_databases.fields.path' 'reference.arb' &&
+#end if
 
-        ## run
-        sina
-            --in='$in'
-            --db='reference.arb'
-            -p \${GALAXY_SLOTS:-4}
-            --num-pts=\${GALAXY_SLOTS:-4}
-            #if $os.type == 'arb'
-                --outtype='arb'
-                --out='output.arb'
-            #elif $os.type == 'fasta'
-                --outtype='fasta'
-                --out='output.fasta'
-                --min-idty=$os.minidty
-            #elif $os.type == 'fasta_meta'
-                --outtype='fasta'
-                --out='output.fasta'
-                --min-idty=$os.minidty
-                --meta-fmt='csv'
-            #end if
-            #if $log == 'yes'
-                --log-file='$logfile'
-            #elif $log == 'yes_meta'
-                --log-file='$logfile'
-                --show-diff
-            #end if
-            ## Advanced alignment parameters
-            --overhang=$ap.overhang
-            --insertion=$ap.insertion
-            #if $ap.turn == 'yes'
-                -t
-            #elif $ap.turn == 'all'
-                -t all
-            #end if
-            ## Expert Alignment Parameters
-            --fs-min=$eap.fsmin
-            --fs-max=$eap.fsmax
-            --fs-msc=$eap.fsmsc
-            --fs-weight=$eap.fsweight
-            --fs-req=$eap.fsreq
-            --fs-req-full=$eap.fsreqfull
-            --fs-full-len=$eap.fsfulllen
-            --gene-start=$eap.genestart
-            --gene-end=$eap.geneend
-            --fs-cover-gene=$eap.fscovergene
-            --match-score=$eap.matchscore
-            --mismatch-score=$eap.mismatchscore
-            --pen-gap=$eap.pengap
-            --pen-gapext=$eap.pengapext
-            --fs-kmer-len=$eap.fskmerlen
-            --fs-kmer-mm=$eap.fskmermm
-            $eap.fskmernofast
-            $eap.fskmernorel
-            ## Advanced search and classification parameters
-            #if $asacp.activate == 'yes'
-                --search
-                --search-kmer-candidates=$asacp.searchkmercandidates
-                --lca-quorum=$asacp.lcaquorum
-                --search-kmer-len=$asacp.searchkmerlen
-                --search-kmer-mm=$asacp.searchkmermm
-                --search-max-result=$asacp.searchmaxresult
-                $asacp.searchnofast
-                $asacp.searchkmernorel
-            #end if
-            ## convert meta file to tabular
-            #if $os.type == 'fasta_meta'
-                && cat output.csv | sed 's/,/\t/g' > output.tsv
-            #end if
+## run
+sina
+--in='$in'
+--db='reference.arb'
+--threads=\${GALAXY_SLOTS:-4}
+--num-pts=\${GALAXY_SLOTS:-4}
+--show-conf
+## Output options
+#if 'arb' in $oo.out
+    --out='output.arb'
+#end if
+#if 'fasta' in $oo.out
+    --out='output.fasta'
+    --min-idty=$oo.minidty
+#end if
+#if 'tsv' in $oo.out
+    --out='output.csv' ## parsed into tabular in postprocessing step
+#end if
+#if 'log' in $oo.out
+    --log-file='$logfile'
+    --show-diff
+    --show-dist
+#end if
+## Advanced alignment parameters
+--overhang=$ap.overhang
+--insertion=$ap.insertion
+#if $ap.turn == 'yes'
+    -t
+#elif $ap.turn == 'all'
+    -t all
+#end if
+## Expert alignment parameters
+--fs-min=$eap.fsmin
+--fs-max=$eap.fsmax
+--fs-msc=$eap.fsmsc
+--fs-weight=$eap.fsweight
+--fs-req=$eap.fsreq
+--fs-req-full=$eap.fsreqfull
+--fs-full-len=$eap.fsfulllen
+--gene-start=$eap.genestart
+--gene-end=$eap.geneend
+--fs-cover-gene=$eap.fscovergene
+--match-score=$eap.matchscore
+--mismatch-score=$eap.mismatchscore
+--pen-gap=$eap.pengap
+--pen-gapext=$eap.pengapext
+--fs-kmer-len=$eap.fskmerlen
+--fs-kmer-mm=$eap.fskmermm
+$eap.fskmernofast
+$eap.fskmernorel
+## Advanced search and classification parameters
+#if $asacp.activate == 'yes'
+    --search
+    --search-kmer-candidates=$asacp.searchkmercandidates
+    --lca-quorum=$asacp.lcaquorum
+    --search-kmer-len=$asacp.searchkmerlen
+    --search-kmer-mm=$asacp.searchkmermm
+    --search-max-result=$asacp.searchmaxresult
+    $asacp.searchnofast
+    $asacp.searchkmernorel
+#end if
+
+## postprocessing
+## convert csv to tabular
+#if 'tsv' in $oo.out
+    && test -f 'output.csv' && cat 'output.csv' | sed 's/,/\t/g' > 'output.tsv' || echo 'No additional meta data file.'
+#end if
     ]]></command>
-    <!-- Sections and default parameters are based on https://www.arb-silva.de/aligner -->
     <inputs>
-        <param argument="--in" type="data" format="fasta" label="Select sequence file" help="FASTA file format"/>
+        <!-- Included paramaters, sections and default values are based on https://www.arb-silva.de/aligner -->
+        <param argument="--in" type="data" format="fasta" label="Select sequence file"/>
         <conditional name="db">
             <param name="select" type="select" label="Select reference library type">
                 <option value="custom" selected="true">Custom</option>
@@ -127,25 +124,6 @@
                 <param name="searchmaxresult" type="integer" value="10" min="0" label="Set maximum number of search results to return for each query sequence" help="(--search-max-result)"/>
             </when>
         </conditional>
-        <conditional name="os">
-            <param name="type" type="select" label="Select output file type" help="(--outtype)">
-                <option value="fasta">FASTA</option>
-                <option value="fasta_meta">FASTA with meta-file</option>
-                <option value="arb">ARB</option>
-            </param>
-            <when value="fasta">
-                <expand macro="minidty"/>
-            </when>
-            <when value="fasta_meta">
-                <expand macro="minidty"/>
-            </when>
-            <when value="arb"/>
-        </conditional>
-        <param name="log" type="select" label="Create log file?" help="(--log-file, --show-diff)">
-            <option value="no">no</option>
-            <option value="yes">yes</option>
-            <option value="yes_meta">yes with differences between the inferred alignment and the original alignment</option>
-        </param>
         <section name="ap" title="Alignment parameters">
             <param argument="--overhang" type="select" label="Bases remaining unaligned at the ends should be">
                 <option value="attach">attached to the last aligned base</option>
@@ -180,44 +158,52 @@
             <param name="pengap" type="integer" value="5" min="0" label="Set penalty subtracted from the score for opening a gap" help="(--pen-gap)"/>
             <param name="pengapext" type="integer" value="2" min="0" label="Set penalty subtracted from the score for extending a gap" help="(--pen-gapext)"/>
             <param name="fskmerlen" type="integer" value="10" min="0" label="Set size of k for the reference search" help="For SSU rRNA sequences, the default of 10 is a good value. For different sequence types, different values may perform better. For 5S, for example, 6 has shown to be more effective. (--fs-kmer-len)"/>
-            <param name="fskmermm" type="integer" value="0" min="0" label="Set k-mer matches in the reference database to contain this number of mismatches" help=" (--fs-kmer-mm)"/>
+            <param name="fskmermm" type="integer" value="0" min="0" label="Set k-mer matches in the reference database to contain this number of mismatches" help="(--fs-kmer-mm)"/>
             <param name="fskmernofast" type="boolean" truevalue="--fs-kmer-no-fast" falsevalue="" label="Use all k-mers occurring in the query sequence in the search?" help="By default, only k-mers starting with an A are used for extra performance. (--fs-kmer-no-fast)"/>
             <param name="fskmernorel" type="boolean" truevalue="--fs-kmer-norel" falsevalue="" label="Use absolute match scores in the kmer search?" help="Absolute (number of shared k-mers) rather than relative (number or shared k-mers divided by length of reference sequence) (--fs-kmer-norel)"/>
         </section>
+        <section name="oo" title="Output options">
+            <param name="out" type="select" multiple="true" optional="false" label="Select output file(s)">
+                <option value="arb" selected="true">Alignment (ARB)</option>
+                <option value="fasta" selected="true">Alignment (FASTA)</option>
+                <option value="tsv">Additional meta data (Tabular)</option>
+                <option value="log">Log</option>
+            </param>
+            <param name="minidty" type="float" value="0.7" min="0.0" max="1.0" label="Exclude sequences sharing less than this value fractional identity with any of the alignment reference sequences from the output?" help="Only relevant for FASTA output. (--min-idty)"/>
+        </section>
     </inputs>
     <outputs>
-        <data name="output_fasta" format="fasta" from_work_dir="output.fasta" label="${tool.name} on ${on_string}: alignment">
-            <filter>os['type'] == 'fasta' or os['type'] == 'fasta_meta'</filter>
+        <data name="out_fasta" format="fasta" from_work_dir="output.fasta" label="${tool.name} on ${on_string}: Alignment (FASTA)">
+            <filter>'fasta' in oo['out']</filter>
         </data>
-        <data name="output_arb" format="data" from_work_dir="output.arb" label="${tool.name} on ${on_string}: alignment">
-            <filter>os['type'] == 'arb'</filter>
+        <data name="out_arb" format="data" from_work_dir="output.arb" label="${tool.name} on ${on_string}: Alignment (ARB)">
+            <filter>'arb' in oo['out']</filter>
         </data>
-        <data name="output_meta" format="csv" from_work_dir="output.tsv" label="${tool.name} on ${on_string}: meta information">
-            <filter>os['type'] == 'fasta_meta'</filter>
+        <data name="out_tsv" format="tabular" from_work_dir="output.tsv" label="${tool.name} on ${on_string}: Additional meta data (Tabular)">
+            <filter>'tsv' in oo['out']</filter>
         </data>
-        <data name="logfile" format="txt" label="${tool.name} on ${on_string}: log">
-            <filter>log == 'yes' or log == 'yes_meta'</filter>
+        <data name="out_log" format="txt" label="${tool.name} on ${on_string}: Log">
+            <filter>'log' in oo['out']</filter>
         </data>
     </outputs>
     <tests>
-        <!-- name pattern of outputfile: output_<in_filetype>_<db_filetype>.<os.type>" -->
-        <!-- #1 in: *.fasta; db: *.fasta; out: *.fasta; standard parameters -->
+        <!-- #1 in: *.fasta; db: *.fasta; out: *.fasta; default parameters -->
         <test>
             <param name="in" value="sequence.fasta"/>
             <conditional name="db">
                 <param name="custom" value="reference.fasta"/>
             </conditional>
-            <section name="os">
-                <param name="type" value="fasta_meta"/>
+            <section name="oo">
+                <param name="out" value="fasta,tsv"/>
                 <param name="minidty" value="0.0"/>
             </section>
-            <output name="output_meta">
+            <output name="out_tsv">
                 <assert_contents>
                     <has_text text="FJ203641.1"/>
                     <has_n_lines n="18"/>
                 </assert_contents>
             </output>
-            <output name="output_fasta">
+            <output name="out_fasta">
                 <assert_contents>
                     <has_line line=">FJ203641.1"/>
                     <has_line line=">WH051F03"/>
@@ -225,38 +211,38 @@
                 </assert_contents>
             </output>
         </test>
-        <!-- #2 in: *.fasta; db: *.fasta; out: *.arb; standard parameters -->
+        <!-- #2 in: *.fasta; db: *.fasta; out: *.arb; default parameters -->
         <test>
             <param name="in" value="sequence.fasta"/>
             <conditional name="db">
                 <param name="custom" value="reference.fasta"/>
             </conditional>
-            <section name="os">
-                <param name="type" value="arb"/>
+            <section name="oo">
+                <param name="out" value="arb"/>
             </section>
-            <output name="output_arb">
+            <output name="out_arb">
                 <assert_contents>
-                    <has_size value="21369"/>
+                    <has_size value="21106"/>
                 </assert_contents>
             </output>
         </test>
-        <!-- #3 in: *.fasta; db: *.arb; out: *.fasta; standard parameters -->
+        <!-- #3 in: *.fasta; db: *.arb; out: *.fasta; default parameters -->
         <test>
             <param name="in" value="sequence.fasta"/>
             <conditional name="db">
                 <param name="custom" value="reference.arb"/>
             </conditional>
-            <section name="os">
-                <param name="type" value="fasta_meta"/>
+            <section name="oo">
+                <param name="out" value="fasta,tsv"/>
                 <param name="minidty" value="0.0"/>
             </section>
-            <output name="output_meta">
+            <output name="out_tsv">
                 <assert_contents>
                     <has_text text="FJ203641.1"/>
                     <has_n_lines n="18"/>
                 </assert_contents>
             </output>
-            <output name="output_fasta">
+            <output name="out_fasta">
                 <assert_contents>
                     <has_line line=">FJ203641.1"/>
                     <has_line line=">WH051F03"/>
@@ -264,18 +250,18 @@
                 </assert_contents>
             </output>
         </test>
-        <!-- #4 in: *.fasta; db: *.arb; out: *.arb; standard parameters -->
+        <!-- #4 in: *.fasta; db: *.arb; out: *.arb; default parameters -->
         <test>
             <param name="in" value="sequence.fasta"/>
             <conditional name="db">
                 <param name="custom" value="reference.arb"/>
             </conditional>
-            <section name="os">
-                <param name="type" value="arb"/>
+            <section name="oo">
+                <param name="out" value="arb"/>
             </section>
-            <output name="output_arb">
+            <output name="out_arb">
                 <assert_contents>
-                    <has_size value="19999"/>
+                    <has_size value="19736"/>
                 </assert_contents>
             </output>
         </test>
@@ -285,8 +271,8 @@
             <conditional name="db">
                 <param name="custom" value="reference.arb"/>
             </conditional>
-            <section name="os">
-                <param name="type" value="fasta"/>
+            <section name="oo">
+                <param name="out" value="fasta"/>
                 <param name="minidty" value="0.0"/>
             </section>
             <section name="ap">
@@ -323,7 +309,7 @@
                 <param name="searchkmernorel" value="--search-kmer-norel"/>
                 <param name="searchmaxresult" value="10"/>
             </section>
-            <output name="output_fasta">
+            <output name="out_fasta">
                 <assert_contents>
                     <has_line line=">FJ203641.1"/>
                     <has_line line=">WH051F03"/>
@@ -331,19 +317,19 @@
                 </assert_contents>
             </output>
         </test>
-        <!-- #6 in: *.fasta; db: <arb_databases>.arb; out: *.fasta; standard parameters -->
+        <!-- #6 in: *.fasta; db: <arb_databases>.arb; out: *.fasta; default parameters -->
         <test>
             <param name="in" value="sequence.fasta"/>
             <conditional name="db">
                 <param name="select" value="local"/>
                 <param name="arb_databases" value="testarb"/>
             </conditional>
-            <section name="os">
-                <param name="type" value="arb"/>
+            <section name="oo">
+                <param name="out" value="arb"/>
             </section>
-            <output name="output_arb">
+            <output name="out_arb">
                 <assert_contents>
-                    <has_size value="19999"/>
+                    <has_size value="19736"/>
                 </assert_contents>
             </output>
         </test>
@@ -365,13 +351,13 @@
 
 **Output**
 
-Results are provided in FASTA or ARB file format, whereas additional metadata is provided as CSV.
+Results are provided in FASTA or ARB file format, whereas additional metadata is provided as tabular text file.
 
 .. class:: infomark
 
 **References**
 
-More information can be found on the `project website <https://sina.readthedocs.io/en/latest>`_, and on `github <https://github.com/epruesse/SINA>`_.  An `online version <https://www.arb-silva.de/aligner>`_ of SINA is provided by the SILVA project.
+More information can be found on the `project website <https://sina.readthedocs.io/en/latest>`_ and on `GitHub <https://github.com/epruesse/SINA>`_.  An `online version <https://www.arb-silva.de/aligner>`_ of SINA is provided by the SILVA project.
     ]]></help>
     <citations>
         <citation type="doi">10.1093/bioinformatics/bts252</citation>