Mercurial > repos > iuc > dram_merge_annotations

diff dram_merge_annotations.xml @ 0:2675f8d7b2a5 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/dram commit df10ba86507266a6a6f83c9bbefb7191a41b46f5
author iuc
date Sat, 10 Dec 2022 21:14:28 +0000
parents
children 96c0067106ec
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/dram_merge_annotations.xml	Sat Dec 10 21:14:28 2022 +0000
@@ -0,0 +1,195 @@
+<tool id="dram_merge_annotations" name="DRAM merge multiple annotations" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
+    <description>into a single set</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <command detect_errors="exit_code"><![CDATA[
+## DRAM expects a specific file name for each file in the set.
+#set annotations_file_name = 'annotations.tsv'
+#set genbank_file_name = 'genbank'
+#set trnas_file_name = 'trnas.tsv'
+#set rrnas_file_name = 'rrnas.tsv'
+#set scaffolds_file_name = 'scaffolds.fna'
+#set genes_gff_file_name = 'genes.gff'
+#set genes_fna_file_name = 'genes.fna'
+#set genes_faa_file_name = 'genes.faa'
+
+## DRAM expects each annotation set to be in a different directory.
+#set input_dirs = list()
+#for $index, $item in enumerate($annotations_collection):
+    #set dir_name = 'input_dir_' + str($index)
+    mkdir '$dir_name' &&
+    ln -s '$item' '$dir_name/$annotations_file_name' &&
+    ln -s '$genbank_collection[$index]' '$dir_name/$genbank_file_name' &&
+    #if $trnas_collection:
+        ln -s '$trnas_collection[$index]' '$dir_name/$trnas_file_name' &&
+    #end if
+    #if $rrnas_collection
+        ln -s '$rrnas_collection[$index]' '$dir_name/$rrnas_file_name' &&
+    #end if
+    ln -s '$scaffolds_collection[$index]' '$dir_name/$scaffolds_file_name' &&
+    ln -s '$genes_gff_collection[$index]' '$dir_name/$genes_gff_file_name' &&
+    ln -s '$genes_fna_collection[$index]' '$dir_name/$genes_fna_file_name' &&
+    ln -s '$genes_faa_collection[$index]' '$dir_name/$genes_faa_file_name' &&
+    $input_dirs.append($dir_name)
+#end for
+
+DRAM.py merge_annotations
+--input_dirs 'input_dir*'
+--output_dir 'output_dir'
+&& test -f 'output_dir/genes.faa' && mv 'output_dir/genes.faa' '$output_genes_faa' || echo 'No genes.faa output produced'
+&& test -f 'output_dir/genes.fna' && mv 'output_dir/genes.fna' '$output_genes_fna' || echo 'No genes.fna output produced'
+&& test -f 'output_dir/genes.gff' && mv 'output_dir/genes.gff' '$output_genes_gff' || echo 'No genes.gff output produced'
+&& test -f 'output_dir/scaffolds.fna' && mv 'output_dir/scaffolds.fna' '$output_scaffolds_fna' || echo 'No scaffolds.fna output produced'
+#if $rrnas_collection:
+    && test -f 'output_dir/rrnas.tsv' && mv 'output_dir/rrnas.tsv' '$output_rrnas' || echo 'No rrnas.tsv output produced'
+#end if
+#if $trnas_collection:
+    && test -f 'output_dir/trnas.tsv' && mv 'output_dir/trnas.tsv' '$output_trnas' || echo 'No trnas.tsv output produced'
+#end if
+&& test -f 'output_dir/annotations.tsv' && mv 'output_dir/annotations.tsv' '$output_annotations' || echo 'No annotations.tsv output produced'
+    ]]></command>
+    <inputs>
+        <param name="annotations_collection" type="data_collection" format="tabular" collection_type="list" label="Collection of annotation files"/>
+        <param name="genbank_collection" type="data_collection" format="genbank" collection_type="list" label="Collection of genbank files"/>
+        <param name="trnas_collection" type="data_collection" format="tabular" collection_type="list" optional="true" label="Collection of trna files"/>
+        <param name="rrnas_collection" type="data_collection" format="tabular" collection_type="list" optional="true" label="Collection of rrna files"/>
+        <param name="scaffolds_collection" type="data_collection" format="fasta" collection_type="list" label="Collection of scaffolds files"/>
+        <param name="genes_gff_collection" type="data_collection" format="gff3" collection_type="list" label="Collection of genes.gff files"/>
+        <param name="genes_fna_collection" type="data_collection" format="fasta" collection_type="list" label="Collection of genes.fna files"/>
+        <param name="genes_faa_collection" type="data_collection" format="fasta" collection_type="list" label="Collection of genes.faa files"/>
+    </inputs>
+    <outputs>
+        <data name="output_genes_faa" format="fasta" label="${tool.name} on ${on_string}: genes.faa"/>
+        <data name="output_genes_fna" format="fasta" label="${tool.name} on ${on_string}: genes.fna"/>
+        <data name="output_genes_gff" format="gff3" label="${tool.name} on ${on_string}: genes.gff"/>
+        <data name="output_scaffolds_fna" format="fasta" label="${tool.name} on ${on_string}: scaffolds"/>
+        <data name="output_rrnas" format="tabular" label="${tool.name} on ${on_string}: rrnas">
+            <filter>rrnas_collection</filter>
+        </data>
+        <data name="output_trnas" format="tabular" label="${tool.name} on ${on_string}: trnas">
+            <filter>trnas_collection</filter>
+        </data>
+        <!-- DRAM just copies the genbank files to a directory -->
+        <collection name="output_genbank" type="list" label="${tool.name} on ${on_string}: genbank">
+            <discover_datasets pattern="__name__" ext="genbank" directory="output_dir/genbank"/>
+        </collection>
+        <data name="output_annotations" format="tabular" label="${tool.name} on ${on_string}: annotations"/>
+    </outputs>
+    <tests>
+        <!--
+        These tests succeed, but the outputs are empty because the DRAM
+        database is not available in the test environment.
+        -->
+        <test expect_num_outputs="8">
+            <param name="annotations_collection">
+                <collection type="list">
+                    <element name="annotated1" value="annotated1.tabular"/>
+                    <element name="annotated2" value="annotated2.tabular"/>
+                </collection>
+            </param>
+            <param name="genbank_collection">
+                <collection type="list">
+                    <element name="annotated1" value="annotated1.genbank"/>
+                    <element name="annotated2" value="annotated2.genbank"/>
+                </collection>
+            </param>
+            <param name="trnas_collection">
+                <collection type="list">
+                    <element name="annotated1" value="annotated1_trnas.tabular"/>
+                    <element name="annotated2" value="annotated2_trnas.tabular"/>
+                </collection>
+            </param>
+            <param name="rrnas_collection">
+                <collection type="list">
+                    <element name="annotated1" value="annotated1_rrnas.tabular"/>
+                    <element name="annotated2" value="annotated2_rrnas.tabular"/>
+                </collection>
+            </param>
+            <param name="scaffolds_collection">
+                <collection type="list">
+                    <element name="annotated1" value="annotated1_scaffold.fasta"/>
+                    <element name="annotated2" value="annotated2_scaffold.fasta"/>
+                </collection>
+            </param>
+            <param name="genes_gff_collection">
+                <collection type="list">
+                    <element name="annotated1" value="annotated1.gff"/>
+                    <element name="annotated2" value="annotated2.gff"/>
+                </collection>
+            </param>
+            <param name="genes_fna_collection">
+                <collection type="list">
+                    <element name="annotated1" value="annotated1_genes_fna.fasta"/>
+                    <element name="annotated2" value="annotated2_genes_fna.fasta"/>
+                </collection>
+            </param>
+            <param name="genes_faa_collection">
+                <collection type="list">
+                    <element name="annotated1" value="annotated1_genes_faa.fasta"/>
+                    <element name="annotated2" value="annotated2_genes_faa.fasta"/>
+                </collection>
+            </param>
+            <output name="output_annotations">
+                <assert_contents>
+                    <has_n_lines n="530" delta="1"/>
+                </assert_contents>
+            </output>
+            <output_collection name="output_genbank" type="list" count="2">
+                <element name="annotation_0.gbk" ftype="genbank">
+                    <assert_contents>
+                        <has_text text="LOCUS"/>
+                    </assert_contents>
+                </element>
+                <element name="annotation_1.gbk" ftype="genbank">
+                    <assert_contents>
+                        <has_text text="LOCUS"/>
+                    </assert_contents>
+                </element>
+            </output_collection>
+            <output name="output_trnas">
+                <assert_contents>
+                    <has_n_lines n="8" delta="1"/>
+                </assert_contents>
+            </output>
+            <output name="output_rrnas">
+                <assert_contents>
+                    <has_n_lines n="3" delta="1"/>
+                </assert_contents>
+            </output>
+            <output name="output_scaffolds_fna">
+                <assert_contents>
+                    <has_n_lines n="4" delta="1"/>
+                </assert_contents>
+            </output>
+            <output name="output_genes_gff">
+                <assert_contents>
+                    <has_n_lines n="23" delta="1"/>
+                </assert_contents>
+            </output>
+            <output name="output_genes_fna">
+                <assert_contents>
+                    <has_n_lines n="26" delta="1"/>
+                </assert_contents>
+            </output>
+            <output name="output_genes_faa">
+                <assert_contents>
+                    <has_n_lines n="26" delta="1"/>
+                </assert_contents>
+            </output>
+       </test>
+    </tests>
+    <help>
+**What it does**
+ 
+@WHATITDOESHEADER@
+
+This tool accepts collections of the components of a DRAM annotations (i.e., annotations, genbank files, GFF files, tRNAs,
+rRNas, etc) and, except for the genbank files which remain a collection,  merges the set of files for each component into
+a single file.
+
+@WHATITDOESFOOTER@
+    </help>
+    <expand macro="citations"/>
+</tool>