diff blat.xml @ 1:eb7fcec3fdba draft

planemo upload commit 78ad97a2be3ed2c75777ec97ef9489f819cbc471
author yating-l
date Thu, 01 Jun 2017 14:17:51 -0400
parents 951076264957
children a1b3d24b55a1
line wrap: on
line diff
--- a/blat.xml	Wed Apr 12 17:47:43 2017 -0400
+++ b/blat.xml	Thu Jun 01 14:17:51 2017 -0400
@@ -5,21 +5,47 @@
       <requirement type="package" version="1.0">ucsc_tools_340_for_BLAT</requirement>
     </requirements>
     <command detect_errors="exit_code"><![CDATA[
-    blat 
-        #if $noHead == "yes"
-          -noHead
-        #end if
-        -q=$query_type
-        -t=$database_type
-        -mask=$mask
-        '${database}'
-        '${query}'
-        output
-    && sort -k 10,10 -k 12,12n output > '${output_sorted}'
+      #if str($reference_source.reference_source_selector) == "history":
+            #set $reference_fasta_filename = "localref.fa" 
+            ln -s '${reference_source.database}' '${reference_fasta_filename}' &&
+      #else:
+            #set $reference_fasta_filename = str($reference_source.database.fields.path)
+      #end if
+      blat 
+            #if $noHead == "yes"
+            -noHead
+            #end if
+            -q=$query_type
+            -t=$database_type
+            #if $mask_type.mask == "file.out":
+                  -mask=$mask_type.mask_file
+            #else:
+                  -mask=$mask_type.mask
+            #end if
+            '$reference_fasta_filename'
+            '${query}'
+            output
+      && sort -k 10,10 -k 12,12n output > '${output_sorted}'
 ]]></command>
       <inputs>
-            <param type="data" name="database" format="fasta" />
-            <param type="data" name="query" format="fasta" />
+            <conditional name="reference_source">
+                  <param name="reference_source_selector" type="select" label="Choose the source for the database">
+                        <option value="cached">Locally cached</option>
+                        <option value="history">History</option>
+                  </param>
+                  <when value="cached">
+                        <param name="database" type="select" label="Select database">
+                              <options from_data_table="all_fasta">
+                                    <filter type="sort_by" column="2" />
+                              </options>
+                              <validator type="no_options" message="A built-in database is not available" />
+                        </param>
+                  </when>
+                  <when value="history">
+                        <param name="database" type="data" format="fasta, twobit" label="Using database file, either a .fa, .nib or .2bit file" />
+                  </when>
+            </conditional>
+            <param type="data" name="query" format="fasta, twobit" label="Query data, either a .fa, .nib or .2bit file"/>
             <param type="select" name="database_type" format="text" multiple="false" label="database type" help="Choose your database type, the default is dnax" argument="-t">
                   <option value="dna">dna - DNA sequence</option>
                   <option value="prot">prot - protein sequence</option>
@@ -36,37 +62,61 @@
                   <option value="yes" selected="true">Yes, suppresses .psl header</option>
                   <option value="no">No, do not suppresses .psl header</option>
             </param>
-            <param name="mask" type="select" label="Mask out repeats" help="Alignments won't be started in masked region
+            <conditional name="mask_type">
+                  <param name="mask" type="select" label="Mask out repeats" help="Alignments won't be started in masked region
                   but may extend through it in nucleotide searches.  Masked areas
                   are ignored entirely in protein or translated searches. Default is lower" argument="-mask">
-                  <option value="lower" selected="true">lower - mask out lower-cased sequence</option>
-                  <option value="upper">upper - mask out upper-cased sequence</option>
-                  <option value="out">out - mask according to database.out RepeatMasker .out file</option>
-                  <option value="file.out">file.out - mask database according to RepeatMasker file.out</option>
-            </param>
+                        <option value="lower" selected="true">lower - mask out lower-cased sequence</option>
+                        <option value="upper">upper - mask out upper-cased sequence</option>
+                        <option value="out">out - mask according to database.out RepeatMasker .out file</option>
+                        <option value="file.out">file.out - mask database according to RepeatMasker file.out</option>
+                  </param>
+                  <when value="lower" />
+                  <when value="upper" />
+                  <when value="out" />
+                  <when value="file.out">
+                        <param name="mask_file" type="data" format="txt" label="RepeatMasker file.out" />
+                  </when>  
+            </conditional>
       </inputs>
       <outputs>
             <data format="psl" name="output_sorted" label="${tool.name} on ${on_string}"></data>
       </outputs>
   <tests>
+      <!-- test on query of GenBank RefSeq records for Gallus gallus and database of Amazona vittata -->
       <test>
+            <param name="reference_source_selector" value="history" />
             <param name="database" value="amaVit1_Gallus/amaVit1.fa" />
             <param name="query" value="amaVit1_Gallus/Gallus_gallus_RefSeq.fa" />
             <param name="database_type" value="dnax" />    
             <param name="query_type" value="rnax" />     
-            <param name="noHead" value="true" />
+            <param name="noHead" value="yes" />
             <param name="mask" value="lower" />
             <output name="output_sorted" value="amaVit1_Gallus/amaVit1_Gallus_gallus.psl" />
       </test>
+      <!-- test on query of partial mRNA of Drosophila melanogaster and the database of Drosophila biamipes dot chromosome -->
       <test>
+            <param name="reference_source_selector" value="history" />
             <param name="database" value="dbia3/dbia3.fa" />
-            <param name="query" value="dbia3/dmel-all-transcript-r6.13.fasta" />
+            <param name="query" value="dbia3/dmel-transcript.fa" />
             <param name="database_type" value="dnax" />    
             <param name="query_type" value="rnax" />     
-            <param name="noHead" value="true" />
+            <param name="noHead" value="yes" />
             <param name="mask" value="lower" />
             <output name="output_sorted" value="dbia3/dbia3.sorted.psl" />
       </test>
+      <!-- test on the database masked by repeat masker -->
+      <test>
+            <param name="reference_source_selector" value="history" />
+            <param name="database" value="dbia3/dbia3_masked.2bit" />
+            <param name="query" value="dbia3/dmel-transcript.fa" />
+            <param name="database_type" value="dnax" />    
+            <param name="query_type" value="rnax" />     
+            <param name="noHead" value="yes" />
+            <param name="mask" value="file.out" />
+            <param name="mask_file" value="dbia3/dbia3_RM.out" />
+            <output name="output_sorted" value="dbia3/dbia3_masked.sorted.psl" />
+      </test>
 
   </tests> 
   <help>
@@ -103,16 +153,7 @@
 
 ]]></help>  
 <citations>
-      <citation type="bibtex">@article{kent2002blat,
-  title={BLAT—the BLAST-like alignment tool},
-  author={Kent, W James},
-  journal={Genome research},
-  volume={12},
-  number={4},
-  pages={656--664},
-  year={2002},
-  publisher={Cold Spring Harbor Lab}
-      }</citation>
+      <citation type="doi">10.1101/gr.229202</citation>
 </citations> 
 </tool>