/tools/solid_tools/maq_cs_wrapper.xml
https://bitbucket.org/cistrome/cistrome-harvard/ · XML · 120 lines · 85 code · 18 blank · 17 comment · 0 complexity · f8c57906fdcb55430d2d9a6feeda840b MD5 · raw file
- <tool id="maq_cs_wrapper" name="MAQ for SOLiD" version="1.0.0">
- <description> </description>
- <command interpreter="python">
- maq_cs_wrapper.py
- $output1
- $output2
- $ref
- $library_type.f3_reads
- $library_type.f3_qual
- $library_type.is_paired
- #if $library_type.is_paired == "yes":
- $library_type.r3_reads
- $library_type.r3_qual
- #else:
- "None"
- "None"
- #end if
- $min_mapqual
- $max_mismatch
- $output3
-
- </command>
- <inputs>
- <param name="ref" type="data" format="fasta" label="Target Genome"/>
- <conditional name="library_type">
- <param name="is_paired" type="select" label="Is the library mate-paired?" multiple="false">
- <option value="no">No</option>
- <option value="yes">Yes</option>
- </param>
- <when value="no">
- <param name="f3_reads" type="data" format="csfasta" label="F3 reads file"/>
- <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'" />
- </when>
- <when value="yes">
- <param name="f3_reads" type="data" format="csfasta" label="F3 reads file"/>
- <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'" />
- <param name="r3_reads" type="data" format="csfasta" label="R3 reads file"/>
- <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'" />
- </when>
- </conditional>
- <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."/>
- <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."/>
- </inputs>
- <outputs>
- <data format="tabular" name="output1" metadata_source="ref" />
- <data format="tabular" name="output2" metadata_source="ref" />
- <data format="customtrack" name="output3" metadata_source="ref" />
- </outputs>
-
- <!-- "ToolTestCase does not deal with multiple outputs properly yet."
- <tests>
-
- <test>
- <param name="ref" value="phiX_mod.fasta" />
- <param name="is_paired" value="no" />
- <param name="f3_reads" value="phiX_solid.csfasta" />
- <param name="f3_qual" value="phiX_solid.qualsolid" />
- <param name="min_mapqual" value="0" />
- <param name="max_mismatch" value="7" />
- <output name="output1" file="phiX_solid_maq.map" />
- <output name="output2" file="phiX_solid_maq.pileup" />
- <output name="output3" file="phiX_solid_maq.ctrack" />
-
- </test>
- </tests>
- -->
- <help>
- .. class:: infomark
- **What it does**
- This tool maps SOLiD color-space reads against the target genome using MAQ. It produces three output datasets:
- **ALIGNMENT INFO** : contains the read alignment information,
- **PILEUP** : contains the coverage and SNP statistics for every nucleotide of the target genome,
- **CUSTOM TRACK** : contains the coverage and SNP statistics as custom tracks displayable in the UCSC browser.
- -----
- **The ALIGNMENT INFO dataset will contain the following fields:**
- * column 1 = read name
- * column 2 = chromosome
- * column 3 = position
- * column 4 = strand
- * column 5 = insert size from the outer coorniates of a pair
- * column 6 = paired flag
- * column 7 = mapping quality
- * column 8 = single-end mapping quality
- * column 9 = alternative mapping quality
- * column 10 = number of mismatches of the best hit
- * column 11 = sum of qualities of mismatched bases of the best hit
- * column 12 = number of 0-mismatch hits of the first 24bp
- * column 13 = number of 1-mismatch hits of the first 24bp on the reference
- * column 14 = length of the read
- * column 15 = read sequence
- * column 16 = read quality
- **The PILEUP dataset will contain the following fields:**
- * column 1 = chromosome
- * column 2 = position
- * column 3 = reference nucleotide
- * column 4 = coverage (number of reads that cover this position)
- * column 5 = number of SNPs
- * column 6 = number of As
- * column 7 = number of Ts
- * column 8 = number of Gs
- * column 9 = number of Cs
- </help>
- <code file="maq_cs_wrapper_code.py"/>
- </tool>