Add FIMO tool from MEME suite.

datatypes_conf.xml.sample

@@ -90,7 +90,7 @@
         </datatype>
         <datatype extension="picard_interval_list" type="galaxy.datatypes.data:Text" subclass="True" display_in_upload="True"/>
         <datatype extension="gatk_interval" type="galaxy.datatypes.data:Text" subclass="True" display_in_upload="True"/>
-        <datatype extension="gatk_dbsnp" type="galaxy.datatypes.data:Text" subclass="True" display_in_upload="True"/>
+        <datatype extension="gatk_dbsnp" type="galaxy.datatypes.tabular:Tabular" subclass="True" display_in_upload="True"/>
         <datatype extension="jpg" type="galaxy.datatypes.images:Jpg" mimetype="image/jpeg"/>
         <datatype extension="tiff" type="galaxy.datatypes.images:Tiff" mimetype="image/tiff"/>
         <datatype extension="bmp" type="galaxy.datatypes.images:Bmp" mimetype="image/bmp"/>
@@ -134,6 +134,7 @@
         <datatype extension="twobit" type="galaxy.datatypes.binary:TwoBit" mimetype="application/octet-stream" display_in_upload="true"/>
         <datatype extension="txt" type="galaxy.datatypes.data:Text" display_in_upload="true"/>
         <datatype extension="memexml" type="galaxy.datatypes.xml:MEMEXml" mimetype="application/xml" display_in_upload="true"/>
+        <datatype extension="cisml" type="galaxy.datatypes.xml:CisML" mimetype="application/xml" display_in_upload="true"/>
         <datatype extension="blastxml" type="galaxy.datatypes.xml:BlastXml" mimetype="application/xml" display_in_upload="true"/>
         <datatype extension="vcf" type="galaxy.datatypes.tabular:Vcf" display_in_upload="true">
             <converter file="vcf_to_bgzip_converter.xml" target_datatype="bgzip"/>

lib/galaxy/datatypes/xml.py

@@ -102,3 +102,18 @@ class MEMEXml( GenericXml ):
             dataset.blurb = 'file purged from disk'
     def sniff( self, filename ):
         return False
+
+class CisML( GenericXml ):
+    """CisML XML data""" #see: http://www.ncbi.nlm.nih.gov/pubmed/15001475
+    file_ext = "cisml"
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        """Set the peek and blurb text"""
+        if not dataset.dataset.purged:
+            dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+            dataset.blurb = 'CisML data'
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+    def sniff( self, filename ):
+        return False

tools/meme/fimo.xml

@@ -0,0 +1,230 @@
+<tool id="meme_fimo" name="FIMO" version="0.0.1">
+  <description>- Find Individual Motif Occurrences</description>
+  <command interpreter="python">fimo_wrapper.py 'fimo --o "${$html_outfile.files_path}" --verbosity "1"
+  
+  #if str( $options_type.options_type_selector ) == 'advanced':
+  --max-seq-length "${options_type.max_seq_length}" 
+  --max-stored-scores "${options_type.max_stored_scores }" 
+  --motif-pseudo "${options_type.motif_pseudo}" 
+  ${options_type.norc} 
+  --output-pthresh "${options_type.output_pthresh}" 
+
+  
+  #for $motif in $options_type.motifs:
+    --motif "${motif.motif}"
+  #end for
+  
+  #if str( $options_type.bgfile_type.bgfile_type_selector ) == 'motif-file':
+    --bgfile "motif-file"
+  #elif str( $options_type.bgfile_type.bgfile_type_selector ) == 'motif-file':
+    --bgfile "${options_type.bgfile_type.bgfile}"
+  #end if
+  
+  #if str( $options_type.qvalue_type.qvalue_type_selector ) == 'no-qvalue':
+    --no-qvalue
+  #else:
+    --output-qthresh "${options_type.qvalue_type.output_qthresh}"
+  #end if
+  #end if
+  
+  "${input_motifs}" 
+  
+  #if str( $fasta_type.fasta_type_selector ) == 'history':
+    "${fasta_type.input_database}"
+  #else:
+    "${ filter( lambda x: str( x[0] ) == str( $fasta_type.input_database ), $__app__.tool_data_tables[ 'all_fasta' ].get_fields() )[0][3] }"
+  #end if
+
+  '
+  
+  '${html_outfile.files_path}'
+  
+  '${html_outfile}'
+  
+  '${interval_outfile}'
+  
+  '${txt_outfile}'
+  
+  '${xml_outfile}'
+  
+  '${gff_outfile}'
+    
+  </command>
+  <inputs>
+    <param format="memexml" name="input_motifs" type="data" label="'MEME output' formatted file"/>
+    
+    <conditional name="fasta_type">
+      <param name="fasta_type_selector" type="select" label="Source for sequence to search">
+        <option value="cached">Locally Cached sequences</option>
+        <option value="history" selected="true">Sequences from your history</option>
+      </param>
+      <when value="cached">
+        <param name="input_database" type="select" label="Genome to search">
+          <options from_data_table="all_fasta">
+          </options>
+        </param>
+      </when>
+      <when value="history">
+         <param format="fasta" name="input_database" type="data" label="Sequences"/>
+      </when>
+    </conditional>
+    
+      <conditional name="options_type">
+        <param name="options_type_selector" type="select" label="Options Configuration">
+          <option value="basic" selected="true">Basic</option>
+          <option value="advanced">Advanced</option>
+        </param>
+        <when value="basic">
+          <!-- do nothing here -->
+        </when>
+        <when value="advanced">
+    
+    <conditional name="bgfile_type">
+      <param name="bgfile_type_selector" type="select" label="Background file type">
+        <option value="motif-file">Use Frequencies from Motif File</option>
+        <option value="default" selected="true">Use frequencies from non-redundant database (default)</option>
+        <option value="bgfile">Use Frequencies from Background File</option>
+      </param>
+      <when value="motif-file">
+      <!-- do nothing here -->
+      </when>
+      <when value="default">
+      <!-- do nothing here -->
+      </when>
+      <when value="bgfile">
+        <param name="bgfile" type="data" format="txt" optional="True" label="Background Model" />
+      </when>
+    </conditional>
+    
+    <repeat name="motifs" title="Limit to specified motif">
+      <param name="motif" type="text" value="" label="Specify motif by id" />
+    </repeat>
+    
+    <param name="max_seq_length" type="integer" value="250000000" label="Maximum input sequence length" />
+    <param name="max_stored_scores" type="integer" value="100000" label="Maximum score count to store" />
+    <param name="motif_pseudo" type="float" value="0.1" label="Pseudocount to add to counts in motif matrix" />
+    <param name="norc" label="Do not check reverse complement" type="boolean" truevalue="--norc" falsevalue="" checked="False"/>
+    <param name="output_pthresh" type="float" value="1e-4" label="p-value threshold" />
+    
+    <conditional name="qvalue_type">
+      <param name="qvalue_type_selector" type="select" label="q-value options">
+        <option value="no-qvalue">Do not compute q-value</option>
+        <option value="q-value" selected="true">Compute q-value</option>
+      </param>
+      <when value="no-qvalue">
+      <!-- do nothing here -->
+      </when>
+      <when value="q-value">
+        <param name="output_qthresh" type="float" value="1.0" label="q-value threshold" />
+      </when>
+    </conditional>
+    
+      </when>
+    </conditional>
+    
+    <param name="non_commercial_use" label="I certify that I am not using this tool for commercial purposes." type="boolean" truevalue="NON_COMMERCIAL_USE" falsevalue="COMMERCIAL_USE" checked="False">
+      <validator type="expression" message="This tool is only available for non-commercial use.">value == True</validator>
+    </param>
+  
+  </inputs>
+  <outputs>
+    <data format="html" name="html_outfile" label="${tool.name} on ${on_string} (html)">
+      <actions>
+        <conditional name="fasta_type.fasta_type_selector">
+          <when value="cached">
+            <action type="metadata" name="dbkey">
+              <option type="from_data_table" name="all_fasta" column="1" offset="0">
+                <filter type="param_value" column="0" value="seq" keep="True"/>
+                <filter type="param_value" ref="fasta_type.input_database" column="1"/>
+              </option>
+            </action>
+          </when>
+        </conditional>
+      </actions>
+    </data>
+    <data format="tabular" name="txt_outfile" label="${tool.name} on ${on_string} (text)">
+      <actions>
+        <conditional name="fasta_type.fasta_type_selector">
+          <when value="cached">
+            <action type="metadata" name="dbkey">
+              <option type="from_data_table" name="all_fasta" column="1" offset="0">
+                <filter type="param_value" ref="fasta_type.input_database" column="0"/>
+              </option>
+            </action>
+          </when>
+        </conditional>
+      </actions>
+    </data>
+    <data format="tabular" name="gff_outfile" label="${tool.name} on ${on_string} (almost-gff)">
+      <actions>
+        <conditional name="fasta_type.fasta_type_selector">
+          <when value="cached">
+            <action type="metadata" name="dbkey">
+              <option type="from_data_table" name="all_fasta" column="1" offset="0">
+                <filter type="param_value" ref="fasta_type.input_database" column="0"/>
+              </option>
+            </action>
+          </when>
+        </conditional>
+      </actions>
+    </data>
+    <data format="cisml" name="xml_outfile" label="${tool.name} on ${on_string} (xml)">
+      <actions>
+        <conditional name="fasta_type.fasta_type_selector">
+          <when value="cached">
+            <action type="metadata" name="dbkey">
+              <option type="from_data_table" name="all_fasta" column="1" offset="0">
+                <filter type="param_value" ref="fasta_type.input_database" column="0"/>
+              </option>
+            </action>
+          </when>
+        </conditional>
+      </actions>
+    </data>
+    <data format="interval" name="interval_outfile" label="${tool.name} on ${on_string} (interval)">
+      <actions>
+        <conditional name="fasta_type.fasta_type_selector">
+          <when value="cached">
+            <action type="metadata" name="dbkey">
+              <option type="from_data_table" name="all_fasta" column="1" offset="0">
+                <filter type="param_value" ref="fasta_type.input_database" column="0"/>
+              </option>
+            </action>
+          </when>
+        </conditional>
+      </actions>
+    </data>
+  </outputs>
+  <tests>
+    <test>
+      <param name="input_motifs" value="meme/meme/meme_output_xml_1.xml" ftype="memexml"/>
+      <param name="fasta_type_selector" value="history"/>
+      <param name="input_database" value="phiX.fasta" ftype="fasta"/>
+      <param name="options_type_selector" value="basic"/>
+      <param name="non_commercial_use" value="True"/>
+      <output name="html_outfile" file="meme/fimo/fimo_output_html_1.html" lines_diff="12"/>
+      <output name="txt_outfile" file="meme/fimo/fimo_output_txt_1.txt" lines_diff="0"/>
+      <output name="gff_outfile" file="meme/fimo/fimo_output_almost-gff_1.txt" lines_diff="0"/>
+      <output name="xml_outfile" file="meme/fimo/fimo_output_xml_1.xml" lines_diff="8"/>
+      <output name="interval_outfile" file="meme/fimo/fimo_output_interval_1.txt" lines_diff="0"/>
+    </test>
+  </tests>
+  <help>
+
+.. class:: warningmark
+
+**WARNING: This tool is only available for non-commercial use. Use for educational, research and non-profit purposes is permitted. Before using, be sure to review, agree, and comply with the license.**
+
+.. class:: infomark
+
+**To cite FIMO:**
+`Grant CE, Bailey TL, Noble WS. FIMO: scanning for occurrences of a given motif. Bioinformatics. 2011 Apr 1;27(7):1017-8. &lt;http://www.ncbi.nlm.nih.gov/pubmed/21330290&gt;`_
+
+
+For detailed information on FIMO, click here_. To view the license_.
+
+.. _here: http://meme.nbcr.net/meme/fimo-intro.html
+.. _license: http://meme.nbcr.net/meme/COPYRIGHT.html
+
+  </help>
+</tool>

tools/meme/fimo_wrapper.py

@@ -0,0 +1,73 @@
+#!/usr/bin/env python
+#Dan Blankenberg
+
+"""
+Read text output from FIMO and create an interval file.
+"""
+import sys, tempfile, subprocess, shutil, os
+from galaxy_utils.sequence.transform import DNA_reverse_complement
+
+buffsize = 1048576
+
+def stop_err( msg ):
+    sys.stderr.write( msg )
+    sys.exit()
+
+def main():
+    assert len( sys.argv ) == 8, "Wrong number of arguments"
+    sys.argv.pop(0)
+    fimo_cmd = sys.argv.pop(0)
+    html_path = sys.argv.pop(0)
+    html_out = sys.argv.pop(0)
+    interval_out = sys.argv.pop(0)
+    txt_out = sys.argv.pop(0)
+    xml_out = sys.argv.pop(0)
+    gff_out = sys.argv.pop(0)
+    
+    #run fimo
+    try:
+        tmp_stderr = tempfile.NamedTemporaryFile()
+        #tmp_stderr = open( tmp_filename, 'wb' )
+        proc = subprocess.Popen( args=fimo_cmd, shell=True, stderr=tmp_stderr )
+        returncode = proc.wait()
+        #tmp_stderr.close()
+        # get stderr, allowing for case where it's very large
+        #tmp_stderr = open( tmp, 'rb' )
+        tmp_stderr.seek(0)
+        stderr = ''
+        try:
+            while True:
+                stderr += tmp_stderr.read( buffsize )
+                if not stderr or len( stderr ) % buffsize != 0:
+                    break
+        except OverflowError:
+            pass
+        
+        if returncode != 0:
+            raise Exception, stderr
+    except Exception, e:
+        raise Exception, 'Error running FIMO:\n' + str( e )
+
+    shutil.move( os.path.join( html_path, 'fimo.txt' ), txt_out )
+    shutil.move( os.path.join( html_path, 'fimo.gff' ), gff_out )
+    shutil.move( os.path.join( html_path, 'fimo.xml' ), xml_out )
+    shutil.move( os.path.join( html_path, 'fimo.html' ), html_out )
+    
+    out_file = open( interval_out, 'wb' )
+    out_file.write( "#%s\n" % "\t".join( ( "chr", "start", "end", "pattern name", "score", "strand", "matched sequence", "p-value", "q-value" ) ) )
+    for line in open( txt_out ):
+        if line.startswith( '#' ): continue
+        fields = line.rstrip( "\n\r" ).split( "\t" )
+        start, end = int( fields[2] ), int( fields[3] )
+        sequence = fields[7]
+        if start > end:
+            start, end = end, start #flip start and end, and set strand
+            strand = "-"
+            sequence = DNA_reverse_complement( sequence ) #we want sequences relative to strand; FIMO always provides + stranded sequence
+        else:
+            strand = "+"
+        start -= 1 #make 0-based start position
+        out_file.write( "%s\n" % "\t".join( [ fields[1], str( start ), str( end ), fields[0], fields[4], strand, sequence, fields[5], fields[6] ] ) )
+    out_file.close()
+
+if __name__ == "__main__": main()

tools/meme/meme.xml

@@ -316,7 +316,7 @@
   </outputs>
   <tests>
     <test>
-      <param name="input1" value="meme_input_1.fasta" ftype="fasta" dbkey="hg19"/>
+      <param name="input1" value="meme/meme/meme_input_1.fasta" ftype="fasta" dbkey="hg19"/>
       <param name="options_type_selector" value="basic"/>
       <param name="non_commercial_use" value="True"/>
       <output name="html_outfile" file="meme/meme/meme_output_html_1.html" lines_diff="12"/>