Seqtk telo (#5669)

* merge * add new output * seqtk 1.4 has a telomere finder. This adds it to the rest and bumps the version. passes lint but the CI lint seems to be failing... * better test data * single quote wrap parameters * passes lint after adding Bjoern's citation to macros * fix macro order * seqtk 1.4 has a telomere finder. This adds it to the rest and bumps the version. passes lint but the CI lint seems to be failing... * better test data * single quote wrap parameters * fix rst lint * fix help * fix redundant but beautiful code. Byebye. --------- Co-authored-by: Bjoern Gruening <[email protected]>
galaxyproject · Dec 9, 2023 · 2f75805 · 2f75805
1 parent 0331dc2
commit 2f75805
Show file tree

Hide file tree

Showing 21 changed files with 254 additions and 45 deletions.
diff --git a/tools/seqtk/.shed.yml b/tools/seqtk/.shed.yml
@@ -3,7 +3,7 @@ categories:
 description:  Toolkit for processing sequences in FASTA/Q formats
 homepage_url: https://github.com/lh3/seqtk
 long_description: |
-  Sequence Analysis toolkit provies several small utilities for working with FastA and FastQ data.
+  Sequence Analysis toolkit provides several small utilities for working with FastA and FastQ data.
 name: seqtk
 owner: iuc
 remote_repository_url: https://github.com/galaxyproject/tools-iuc/tree/master/tools/seqtk

diff --git a/tools/seqtk/macros.xml b/tools/seqtk/macros.xml
@@ -12,7 +12,8 @@
             <xref type="bio.tools">seqtk</xref>
         </xrefs>
     </xml>
-    <token name="@TOOL_VERSION@">1.3</token>
+    <token name="@TOOL_VERSION@">1.4</token>
+    <token name="@VERSION_SUFFIX@">0</token>
     <token name="@AWK_VERSION@">4.2.1</token>
     <xml name="stdio">
         <stdio>
@@ -41,6 +42,17 @@ This Galaxy tool relies on the seqtk toolkit from  `lh3/seqtk
     ]]></token>
     <xml name="citation">
         <citations>
+            <citation type="bibtex">
+                @misc{seqtk,
+                  author = {Heng Li},
+                  year = {2023},
+                  title = {seqtk},
+                  publisher = {GitHub},
+                  journal = {GitHub repository},
+                  howpublished{\url{https://github.com/lh3/seqtk}},
+                }
+            </citation>
         </citations>
     </xml>
+
 </macros>
diff --git a/tools/seqtk/seqtk_comp.xml b/tools/seqtk/seqtk_comp.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_comp" name="seqtk_comp" version="@TOOL_VERSION@.1">
+<tool id="seqtk_comp" name="seqtk_comp" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>get the nucleotide composition of FASTA/Q</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements">
         <requirement type="package" version="@AWK_VERSION@">gawk</requirement>
     </expand>
@@ -22,7 +22,7 @@ seqtk comp
         <param name="in_bed" type="data" format="bed" optional="true" label="BED file"/>
     </inputs>
     <outputs>
-        <data name="default" format="tabular" label="Nucleotide composition of $in_file.name"/>
+        <data name="default" format="tabular" label="${tool.name} on ${on_string}: Nucleotide composition"/>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_cutN.xml b/tools/seqtk/seqtk_cutN.xml
@@ -1,10 +1,9 @@
-<?xml version="1.0"?>
-<tool id="seqtk_cutN" name="seqtk_cutN" version="@[email protected]">
+<tool id="seqtk_cutN" name="seqtk_cutN" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>cut sequence at long N</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements"/>
     <expand macro="stdio"/>
     <command><![CDATA[
@@ -22,7 +21,11 @@ $g
         <param argument="-g" type="boolean" truevalue="-g" falsevalue="" checked="false" label="Print gaps only, no sequence" />
     </inputs>
     <outputs>
-        <data name="default" format_source="in_file" label="$in_file.name split on N runs longer than $n"/>
+       <data name="default" format_source="in_file" label="${tool.name} on ${on_string}: split on N runs longer than $n">
+            <change_format>
+                <when input="g" value="-g" format="bed" />
+            </change_format>
+        </data>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_dropse.xml b/tools/seqtk/seqtk_dropse.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_dropse" name="seqtk_dropse" version="@TOOL_VERSION@.1">
+<tool id="seqtk_dropse" name="seqtk_dropse" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>drop unpaired from interleaved Paired End FASTA/Q</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements"/>
     <expand macro="stdio"/>
     <command><![CDATA[
@@ -16,7 +16,7 @@ seqtk dropse
         <expand macro="in_faq"/>
     </inputs>
     <outputs>
-        <data name="default" format_source="in_file" label="Only paired-end reads from $in_file.name"/>
+        <data name="default" format_source="in_file" label="${tool.name} on ${on_string}: only paired-end reads"/>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_fqchk.xml b/tools/seqtk/seqtk_fqchk.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_fqchk" name="seqtk_fqchk" version="@TOOL_VERSION@.1">
+<tool id="seqtk_fqchk" name="seqtk_fqchk" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>fastq QC (base/quality summary)</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements">
         <requirement type="package" version="@AWK_VERSION@">gawk</requirement>
     </expand>
@@ -20,7 +20,7 @@ seqtk fqchk
         <param argument="-q" type="integer" value="20" label="Quality values" help="Use 0 to get the distribution of all quality values"/>
     </inputs>
     <outputs>
-        <data name="default" format="tabular" label="Quality information for $in_file.name"/>
+        <data name="default" format="tabular" label="${tool.name} on ${on_string}: Quality information"/>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_hety.xml b/tools/seqtk/seqtk_hety.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_hety" name="seqtk_hety" version="@TOOL_VERSION@.1">
+<tool id="seqtk_hety" name="seqtk_hety" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>regional heterozygosity</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements">
         <requirement type="package" version="@AWK_VERSION@">gawk</requirement>
     </expand>
@@ -24,7 +24,7 @@ $m
         <param argument="-m" type="boolean" truevalue="-m" falsevalue="" checked="false" label="Treat lowercases as masked" />
     </inputs>
     <outputs>
-        <data name="default" format="tabular" label="Heterozygous regions in $in_file.name"/>
+        <data name="default" format="tabular" label="${tool.name} on ${on_string}: Heterozygous regions"/>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_listhet.xml b/tools/seqtk/seqtk_listhet.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_listhet" name="seqtk_listhet" version="@TOOL_VERSION@.1">
+<tool id="seqtk_listhet" name="seqtk_listhet" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>extract the position of each het</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements">
         <requirement type="package" version="@AWK_VERSION@">gawk</requirement>
     </expand>
@@ -18,7 +18,7 @@ seqtk listhet
         <expand macro="in_faq"/>
     </inputs>
     <outputs>
-        <data name="default" format="tabular" label="Positions of heterozygous bases in $in_file.name"/>
+        <data name="default" format="tabular" label="${tool.name} on ${on_string}: Positions of heterozygous bases"/>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_mergefa.xml b/tools/seqtk/seqtk_mergefa.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_mergefa" name="seqtk_mergefa" version="@TOOL_VERSION@.1">
+<tool id="seqtk_mergefa" name="seqtk_mergefa" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>merge two FASTA/Q files</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements"/>
     <expand macro="stdio"/>
     <command><![CDATA[
@@ -28,7 +28,7 @@ $h
         <param argument="-h" type="boolean" truevalue="-h" falsevalue="" checked="false" label="Suppress hets in the input" />
     </inputs>
     <outputs>
-        <data name="default" format_source="in_fa1" label="Merger of $in_fa1.name and $in_fa2.name"/>
+        <data name="default" format_source="in_fa1" label="${tool.name} on ${on_string}"/>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_mergepe.xml b/tools/seqtk/seqtk_mergepe.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_mergepe" name="seqtk_mergepe" version="@TOOL_VERSION@.1">
+<tool id="seqtk_mergepe" name="seqtk_mergepe" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>interleave two unpaired FASTA/Q files for a paired-end file</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements"/>
     <expand macro="stdio"/>
     <command><![CDATA[
@@ -18,7 +18,7 @@ seqtk mergepe
         <param name="in_fq2" type="data" format="fasta,fastq,fasta.gz,fastq.gz" label="Input FASTA/Q file #2"/>
     </inputs>
     <outputs>
-        <data name="default" format_source="in_fq1" label="$in_fq1.name and $in_fq2.name as interleaved paired-end"/>
+        <data name="default" format_source="in_fq1" label="${tool.name} on ${on_string}: interleaved paired-end"/>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_mutfa.xml b/tools/seqtk/seqtk_mutfa.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_mutfa" name="seqtk_mutfa" version="@TOOL_VERSION@.1">
+<tool id="seqtk_mutfa" name="seqtk_mutfa" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>point mutate FASTA at specified positions</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements"/>
     <expand macro="stdio"/>
     <command><![CDATA[
@@ -18,7 +18,7 @@ seqtk mutfa
         <param name="in_snp" type="data" format="tabular" label="Input SNP file"/>
     </inputs>
     <outputs>
-        <data name="default" format_source="in_file" label="Mutated $in_file.name"/>
+        <data name="default" format_source="in_file" label="${tool.name} on ${on_string}: Mutated"/>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_randbase.xml b/tools/seqtk/seqtk_randbase.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_randbase" name="seqtk_randbase" version="@TOOL_VERSION@.1">
+<tool id="seqtk_randbase" name="seqtk_randbase" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>choose a random base from hets</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements"/>
     <expand macro="stdio"/>
     <command><![CDATA[
@@ -16,7 +16,7 @@ seqtk randbase
         <expand macro="in_faq"/>
     </inputs>
     <outputs>
-        <data name="default" format_source="in_file" label="Unambiguous $in_file.name"/>
+        <data name="default" format_source="in_file" label="${tool.name} on ${on_string}: Unambiguous"/>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_sample.xml b/tools/seqtk/seqtk_sample.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_sample" name="seqtk_sample" version="@TOOL_VERSION@.2">
+<tool id="seqtk_sample" name="seqtk_sample" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>random subsample of fasta or fastq sequences</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements"/>
     <expand macro="stdio"/>
     <command><![CDATA[
@@ -24,7 +24,7 @@ $subsample_size
         </section>
     </inputs>
     <outputs>
-        <data name="default" format_source="in_file" label="Subsample of reads from $in_file.name"/>
+        <data name="default" format_source="in_file" label="${tool.name} on ${on_string}: Subsample of reads"/>
     </outputs>
     <tests>
         <test>

diff --git a/tools/seqtk/seqtk_seq.xml b/tools/seqtk/seqtk_seq.xml
@@ -1,10 +1,10 @@
 <?xml version="1.0"?>
-<tool id="seqtk_seq" name="seqtk_seq" version="@TOOL_VERSION@.3">
+<tool id="seqtk_seq" name="seqtk_seq" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>common transformation of FASTA/Q</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements"/>
     <expand macro="stdio"/>
     <command><![CDATA[
@@ -54,7 +54,7 @@ $x2
         <param name="x2" argument="-2" type="boolean" truevalue="-2" falsevalue="" checked="false" label="Output the 2n reads only" />
     </inputs>
     <outputs>
-        <data name="default" format_source="in_file" />
+        <data name="default" format_source="in_file" label="${tool.name} on ${on_string}" />
     </outputs>
     <tests>
         <!-- This is a sorry excuse for a test for a tool which does way more

diff --git a/tools/seqtk/seqtk_subseq.xml b/tools/seqtk/seqtk_subseq.xml
@@ -1,11 +1,11 @@
 <?xml version="1.0"?>
-<tool id="seqtk_subseq" name="seqtk_subseq" version="@TOOL_VERSION@.1">
+<tool id="seqtk_subseq" name="seqtk_subseq" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
     <description>extract subsequences from FASTA/Q files</description>
-    <expand macro="bio_tools"/>
     <macros>
         <import>macros.xml</import>
         <requirement type="package" version="@AWK_VERSION@">gawk</requirement>
     </macros>
+    <expand macro="bio_tools"/>
     <expand macro="requirements"/>
     <expand macro="stdio"/>
     <command><![CDATA[
@@ -41,7 +41,7 @@ $t
         <param argument="-l" type="integer" value="0" label="Sequence line length" />
     </inputs>
     <outputs>
-        <data name="default" format_source="in_file" label="Selected sequences from $in_file.name">
+        <data name="default" format_source="in_file" label="${tool.name} on ${on_string}: Selected sequences">
             <change_format>
                 <when input="t" value="-t" format="tabular"/>
             </change_format>

diff --git a/tools/seqtk/seqtk_telo.xml b/tools/seqtk/seqtk_telo.xml
@@ -0,0 +1,61 @@
+<?xml version="1.0"?>
+<tool id="seqtk_telo" name="seqtk_telo" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="22.05">
+    <description>find telomeres</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="bio_tools"/>
+    <expand macro="requirements"/>
+    <expand macro="stdio"/>
+    <command><![CDATA[
+seqtk telo
+-m '$m'
+-p '$p'
+-d '$d'
+-s '$s'
+$P
+'$in_file'
+> '$default'
+    ]]></command>
+    <inputs>
+        <expand macro="in_faq"/>
+        <param argument="-m" type="text" value="CCCTAA" label="Telomere repeat to search for. Default is vertebrate" />
+        <param argument="-p" type="integer" value="1" label="Penalty for a non-repeat" />
+        <param argument="-d" type="integer" value="2000" label="Maximum drop" />
+        <param argument="-s" type="integer" value="300" label="Minimum score" />
+        <param argument="-P" type="boolean" truevalue="-P" falsevalue="" checked="false" label="Print scoring" />
+    </inputs>
+    <outputs>
+        <data name="default" format="bed" label="${tool.name} on ${on_string}: telomers"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="in_file" value="seqtk_telo.fa"/>
+            <output name="default" file="seqtk_telo.out" ftype="bed"/>
+        </test>
+        <test>
+            <param name="in_file" value="seqtk_telo.fa.gz" ftype="fasta.gz"/>
+            <output name="default" file="seqtk_telogz.out" ftype="bed"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+**What it does**
+
+Identifies telomeres using a default vertebrate repeat sequence CCCTAA, or a user supplied one
+
+
+::
+
+     Usage: seqtk telo [options] <in.fq>
+     Options:
+     -m STR     motif [CCCTAA]
+     -p INT     penalty [1]
+     -d INT     max drop [2000]
+     -s INT     min score [300]
+     -P         print scoring
+
+
+@ATTRIBUTION@
+    ]]></help>
+    <expand macro="citation" />
+</tool>