Mercurial > repos > bgruening > structure_to_gspan

changeset 0:81a8f5bba747 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/mmiladi/galaxytools/blob/graphclust-gspan/tools/GraphClust/Structure_GSPAN commit 2fd74d285d0914d689ca2378ccebb501b6c775f1
author bgruening
date Thu, 18 May 2017 16:00:59 -0400
parents
children
files structure_to_gspan.xml test-data/GSPAN_Outputs/sample_3.1.group.gspan.bz2 test-data/sample_3.struct
diffstat 3 files changed, 94 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/structure_to_gspan.xml	Thu May 18 16:00:59 2017 -0400
@@ -0,0 +1,85 @@
+<tool id="structure_to_gspan" name="Structure to GSPAN" version="0.1">
+    <requirements>
+        <requirement type="package" version="0.2.0">graphclust-wrappers</requirement>
+    </requirements>
+    <command detect_errors="exit_code">
+    <![CDATA[
+        mkdir ./temp/ ./GSPAN_Outputs/ &&
+        structure_2_gspan.pl
+            --input-file '$dataFile'
+            --input-format 'rnafold'
+            $abstr
+            $stack
+            $seq_graph_t
+            -group $group
+            -tmp ./temp
+            -o ./GSPAN_Outputs/
+    ]]>
+    </command>
+    <inputs>
+        <param type="data" name="dataFile" format="dbn" label="Sequence and Structure input file in the prediction tool format" />
+        <param name="inputFormat" type="text" value="rnafold"
+            label="  Sequence Structure format of the input. Allowed format: rnafold" help="-input-format"/>
+        <param argument="-stack" truevalue="-stack" falsevalue="" checked="true"  type="boolean"
+            label="Add stacking information to graphs"/>
+        <param argument="abstr" truevalue="-abstr" falsevalue="" type="boolean"
+            label="Add abstract structure graphs to the single shrep graph instances."/>
+        <param argument="-seq-graph-t" name="seq_graph_t" truevalue="-seq-graph-t" falsevalue="" checked="true" type="boolean"
+            label="Add for each 't #' a graph which contains no structure"/>
+        <param name="group" type="integer" value="10000"
+            label="Group size" help="Default is 10000"/>
+    </inputs>
+    <outputs>
+        <collection name="gspan_compressed" type="list" label="GSPAN Groups" >
+            <discover_datasets pattern="(?P&lt;name&gt;.*)\.bz2$" directory="GSPAN_Outputs" />
+        </collection>
+    </outputs>
+    <tests>
+        <test>
+            <param name="dataFile" value="sample_3.struct"/>
+            <param name="i_stacks" value="True" />
+            <param name="i_abstr" value="False" />
+            <param name="seq_graph_t" value="True" />
+            <param name="group" value="10000" />
+            <output_collection name="gspan_compressed" type="list">
+                <element name="1.group.gspan" file="GSPAN_Outputs/sample_3.1.group.gspan.bz2"/>
+            </output_collection>
+        </test>
+    </tests>
+    <help>
+    <![CDATA[
+
+**What it does**
+For each pair of sequence and structure provided in the input file
+and convert them into GSPAN format graphs.
+
+
+**Parameters**
+
++ **input** : The sequence and structure data, the output of structure prediction tool.
+
++ **input-format** : Sequence Structure format of the input. Allowed format: "rnafold"
+                        example of input-file for rnafold format:
+                        >seq1
+                        CCGGGCGUGCUG
+                        .(((.....))) ( -0.30)
+                        >seq2
+                        GCGGUUGCCG
+                        .(((...))) ( -0.50)
+
+   
++ **stack** : This adds an additional vertex (type P) for each pair of stacked base-pairs and four edges
+  (type p) from each of the involved bases to the new vertex.
+
++ **abstr** : Add abstract structure graphs to the single shrep graph instances.
+
++ **seq-graph-t** : Add for each 't #' a graph which contains no structure
+
++ **group** : Combine/group that number of input seqs into 1 gspan file output name is then '<INT>.group.gspan.bz2'
+
+    ]]>
+    </help>
+    <citations>
+        <citation type="doi">10.1093/bioinformatics/bts224</citation>
+    </citations>
+</tool>
Binary file test-data/GSPAN_Outputs/sample_3.1.group.gspan.bz2 has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/sample_3.struct	Thu May 18 16:00:59 2017 -0400
@@ -0,0 +1,9 @@
+>SECIS_1
+AUUUUAUCCAUGAAAGUGUUUCCUCUAAACCUAUGUGGAGGAACACCUGAUGUCCAGGAAAAU
+...............(((((.((((((........)))))))))))(((.....)))...... (-14.20)
+>6S_1
+GAAACCCUAAUGUAUUCGAUAUAGUUCCUGAUAUUUUUGAACCGAACAAUUUUUUAUACCUAGGGAGCUUGGAGUUCCGGCGCGGCGCACAUGCCUUCACACGAGGAAGUGCAAACCGUUAGACAGAGCACCCACCUGCUUUAAUUGAGAGCGGGUUCAAAGGAAGGGAAUCCUAAACGGUACGAUUGGGGUUUCU
+((((((((((((((((.......((((((....((((((((((...................(((.((((...(((.....((((.((((.(.((((.....))))).))))...))))..))).)))).)))...((((((.....))))))))))))))))..)))))).......))))).))))))))))). (-59.40)
+>6S_2
+UUGUCCCUGCCGUGCUCGUGACUUGGCCAUACAUUCUCUGAACCUAUGUCUUACGGCAUAUGGGUUGCGGGAGUGUAGAGCUGGAGUGAUCGUCUACUCGUAGACGAACCCGAUGCUCUUCGGAUCGCGACCACCUUGAACCUCAGGGUUCGAGAUGCCGGCCUUGACGGCACAGGCGGGGCAUC
+.((.(((((((((((.(((.(...((((.(((((((((..(((((((((((...)).)))))))))..)))))))))(((((((.((..(((((((....))))))))))))..))))...(((((.(((..(((((((...)))))))))).))).)))))).).))))))).))))))))).. (-84.20)