root/galaxy-central/tools/fastx_toolkit/fastx_clipper.xml

<tool id="cshl_fastx_clipper" name="Clip" version="1.0.1" >
  <description>adapter sequences</description>
        <requirements><requirement type="package">fastx_toolkit</requirement></requirements>
  <command>
    zcat -f $input | fastx_clipper -l $minlength -a $clip_source.clip_sequence -d $keepdelta -o $output -v $KEEP_N $DISCARD_OPTIONS
  </command>
  
  <inputs>
    <param format="fasta,fastqsolexa" name="input" type="data" label="Library to clip" />
  
    <param name="minlength" size="4" type="integer" value="15">
      <label>Minimum sequence length (after clipping, sequences shorter than this length will be discarded)</label>
    </param>

        <conditional name="clip_source">
                <param name="clip_source_list" type="select" label="Source">
                        <option value="prebuilt" selected="true">Standard (select from the list below)</option>
                        <option value="user">Enter custom sequence</option>
                </param>

                <when value="user">
                        <param name="clip_sequence" size="30" label="Enter custom clipping sequence" type="text" value="AATTGGCC" />
                </when>

                <when value="prebuilt">
                        <param name="clip_sequence" type="select" label="Choose Adapter">
                                <options from_file="fastx_clipper_sequences.txt">
                                        <column name="name" index="1"/>
                                        <column name="value" index="0"/>
                                </options>
                        </param> 
                </when>
        </conditional>

        <param name="keepdelta" size="2" type="integer" value="0">
                <label>enter non-zero value to keep the adapter sequence and x bases that follow it</label>
                <help>use this for hairpin barcoding. keep at 0 unless you know what you're doing.</help>
        </param>

        <param name="KEEP_N" type="select" label="Discard sequences with unknown (N) bases">
                <option value="">Yes</option>
                <option value="-n">No</option>
        </param>

        <param name="DISCARD_OPTIONS" type="select" label="Output options">
                <option value="-c">Output only clipped sequences (i.e. sequences which contained the adapter)</option>
                <option value="-C">Output only non-clipped sequences (i.e. sequences which did not contained the adapter)</option>
                <option value="">Output both clipped and non-clipped sequences</option>
        </param>

  </inputs>
        <!--
        #functional test with param value starting with - fails.        
        <tests>
                <test>
                        <param name="input" value="fastx_clipper1.fastq" />
                        <param name="maxmismatches" value="2" />
                        <param name="minlength" value="15" />
                        <param name="clip_source_list" value="user" />
                        <param name="clip_sequence" value="CAATTGGTTAATCCCCCTATATA" />
                        <param name="keepdelta" value="0" />
                        <param name="KEEP_N" value="-n" />
                        <param name="DISCARD_OPTIONS" value="-c" />
                        <output name="output" file="fastx_clipper1a.out" />
                </test>
        </tests>
        -->
  <outputs>
    <data format="input" name="output" metadata_source="input" />
  </outputs>
  
<help>
**What it does**

This tool clips adapters from the 3'-end of the sequences in a FASTA/FASTQ file.

--------


**Clipping Illustration:**

.. image:: ./static/fastx_icons/fastx_clipper_illustration.png 
 
 
 
 
 
 
 

**Clipping Example:**

.. image:: ./static/fastx_icons/fastx_clipper_example.png 


    
**In the above example:**

* Sequence no. 1 was discarded since it wasn't clipped (i.e. didn't contain the adapter sequence). (**Output** parameter).
* Sequence no. 5 was discarded --- it's length (after clipping) was shorter than 15 nt (**Minimum Sequence Length** parameter).



    
</help>
</tool>