/tools/solid_tools/maq_cs_wrapper.xml

  1<tool id="maq_cs_wrapper" name="MAQ for SOLiD" version="1.0.0">
  2    <description> </description>
  3    <command interpreter="python">
  4    maq_cs_wrapper.py 
  5    $output1 
  6    $output2 
  7    $ref 
  8    $library_type.f3_reads 
  9    $library_type.f3_qual 
 10    $library_type.is_paired
 11    #if $library_type.is_paired == "yes":  
 12     $library_type.r3_reads 
 13     $library_type.r3_qual 
 14    #else:
 15     "None"
 16     "None"
 17    #end if
 18    $min_mapqual
 19    $max_mismatch
 20    $output3
 21    
 22    </command>
 23
 24    <inputs>
 25        <param name="ref" type="data" format="fasta" label="Target Genome"/> 
 26        <conditional name="library_type">
 27          <param name="is_paired" type="select" label="Is the library mate-paired?" multiple="false">
 28             <option value="no">No</option>
 29             <option value="yes">Yes</option>
 30         </param>
 31         <when value="no">
 32           <param name="f3_reads" type="data" format="csfasta" label="F3 reads file"/> 
 33           <param format="qualsolid" name="f3_qual" type="data" label="F3 quality file" help="If your dataset doesn't show up in the menu, click the pencil icon next to your dataset and set the datatype to 'qualsolid'" /> 
 34          </when>
 35          <when value="yes">
 36           <param name="f3_reads" type="data" format="csfasta" label="F3 reads file"/> 
 37           <param format="qualsolid" name="f3_qual" type="data" label="F3 quality file" help="If your dataset doesn't show up in the menu, click the pencil icon next to your dataset and set the datatype to 'qualsolid'" /> 
 38           <param name="r3_reads" type="data" format="csfasta" label="R3 reads file"/> 
 39           <param format="qualsolid" name="r3_qual" type="data" label="R3 quality file" help="If your dataset doesn't show up in the menu, click the pencil icon next to your dataset and set the datatype to 'qualsolid'" /> 
 40          </when>
 41      </conditional>
 42      <param name="min_mapqual" type="integer" size="3" value="0" label="Minimum mapping quality allowed for a read to be used" help="Reads below the specified mapping quality will not be considered in coverage and SNP analysis."/> 
 43      <param name="max_mismatch" type="integer" size="3" value="7" label="Maximum number of mismatches allowed for a read to be used" help="Reads above the specified threshold will not be considered in coverage and SNP analysis."/> 
 44    </inputs>
 45    <outputs>
 46        <data format="tabular" name="output1" metadata_source="ref" />
 47        <data format="tabular" name="output2" metadata_source="ref" />
 48        <data format="customtrack" name="output3" metadata_source="ref" />
 49    </outputs>
 50    
 51    <!--  "ToolTestCase does not deal with multiple outputs properly yet."
 52    <tests>
 53        
 54        <test>
 55            <param name="ref" value="phiX_mod.fasta" />
 56            <param name="is_paired" value="no" />
 57            <param name="f3_reads" value="phiX_solid.csfasta" />
 58            <param name="f3_qual" value="phiX_solid.qualsolid" />
 59            <param name="min_mapqual" value="0" />
 60            <param name="max_mismatch" value="7" />
 61            <output name="output1" file="phiX_solid_maq.map" />
 62            <output name="output2" file="phiX_solid_maq.pileup" />
 63            <output name="output3" file="phiX_solid_maq.ctrack" />
 64            
 65        </test>
 66    </tests>
 67    -->
 68<help>
 69
 70.. class:: infomark
 71
 72**What it does**
 73
 74This tool maps SOLiD color-space reads against the target genome using MAQ. It produces three output datasets: 
 75
 76
 77**ALIGNMENT INFO** : contains the read alignment information, 
 78
 79**PILEUP** : contains the coverage and SNP statistics for every nucleotide of the target genome,
 80
 81**CUSTOM TRACK** : contains the coverage and SNP statistics as custom tracks displayable in the UCSC browser. 
 82
 83-----
 84
 85**The ALIGNMENT INFO dataset will contain the following fields:**
 86
 87* column 1  = read name
 88* column 2  = chromosome
 89* column 3  = position
 90* column 4  = strand
 91* column 5  = insert size from the outer coorniates of a pair
 92* column 6  = paired flag
 93* column 7  = mapping quality
 94* column 8  = single-end mapping quality
 95* column 9  = alternative mapping quality
 96* column 10 = number of mismatches of the best hit
 97* column 11 = sum of qualities of mismatched bases of the best hit
 98* column 12 = number of 0-mismatch hits of the first 24bp
 99* column 13 = number of 1-mismatch hits of the first 24bp on the reference
100* column 14 = length of the read
101* column 15 = read sequence
102* column 16 = read quality
103
104
105**The PILEUP dataset will contain the following fields:**
106
107* column 1  = chromosome
108* column 2  = position
109* column 3  = reference nucleotide
110* column 4  = coverage (number of reads that cover this position)
111* column 5  = number of SNPs
112* column 6  = number of As
113* column 7  = number of Ts
114* column 8  = number of Gs
115* column 9  = number of Cs
116
117</help>
118<code file="maq_cs_wrapper_code.py"/>
119
120</tool>