diff shuffle_sequences.xml @ 0:424506a8adf7 draft default tip

"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"
author erinija
date Fri, 01 May 2020 12:11:39 +0000
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/shuffle_sequences.xml	Fri May 01 12:11:39 2020 +0000
@@ -0,0 +1,70 @@
+<tool id="shuffle_sequences" name="Shuffle nucleotides in fasta" version="0.1.0">
+    <requirements>
+        <requirement type="package" version="1.2.2">ushuffle</requirement>
+    </requirements>
+    <command detect_errors="exit_code" interpreter="sh"><![CDATA[
+        shuffle_sequences.sh "$input1" "$input2" "$output1"
+    ]]></command>
+    <inputs>
+        <param type="data" name="input1" format="fasta" label="From fasta"/>
+        <param type="integer" name="input2" value="2" label="preserve frequency of k-mers" />
+    </inputs>
+    <outputs>
+        <data name="output1" format="fasta" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="input1" value="seq1000.fasta"/>
+            <param name="input2" value="2"/>
+            <output name="output1">
+                <assert_contents> 
+                    <has_text text=">chr9:42475963-42476182" />
+                    <has_text text=">chr9:42566360-42566579" />
+                    <has_n_lines n="2000" />
+                </assert_contents> 
+            </output>
+        </test>
+    </tests>
+    <help><![CDATA[
+
+        
+ CALL  
+   sh shuffle_sequences.sh input.fasta k output.fasta
+
+ INPUT
+   input.fasta   - input fasta file 
+   k             - 'preserve frequency of k letters (dinucleotide k=2)'
+
+ OUTPUT
+   output.fasta   - shuffle fasta file 
+
+ DESCRIPTION
+   Wrapper for ushuffle program written by M. Jiang.
+   The ushuffle shuffles nucleotides in fasta sequence preserving frequency
+   of k-mers, a positional order is changed. By default  k=2.
+   A sequence in fasta file is shuffled only once. The output fasta
+   in the identifier line contains the original sequence; a shuffled sequence
+   is output on the second line.
+
+ REQUIREMENT
+   ushuffle installed
+   conda install -c bioconda ushuffle
+
+
+    ]]></help>
+    <citations>
+        <citation type="bibtex">
+@article{jiang2008ushuffle,
+  title={uShuffle: a useful tool for shuffling biological sequences while preserving the k-let counts},
+  author={Jiang, Minghui and Anderson, James and Gillespie, Joel and Mayne, Martin},
+  journal={BMC bioinformatics},
+  volume={9},
+  number={1},
+  pages={192},
+  year={2008},
+  publisher={Springer},
+  url = {https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-9-192}
+}</citation>
+    </citations>
+</tool>
+