/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

  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. </command>
  22. <inputs>
  23. <param name="ref" type="data" format="fasta" label="Target Genome"/>
  24. <conditional name="library_type">
  25. <param name="is_paired" type="select" label="Is the library mate-paired?" multiple="false">
  26. <option value="no">No</option>
  27. <option value="yes">Yes</option>
  28. </param>
  29. <when value="no">
  30. <param name="f3_reads" type="data" format="csfasta" label="F3 reads file"/>
  31. <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'" />
  32. </when>
  33. <when value="yes">
  34. <param name="f3_reads" type="data" format="csfasta" label="F3 reads file"/>
  35. <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'" />
  36. <param name="r3_reads" type="data" format="csfasta" label="R3 reads file"/>
  37. <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'" />
  38. </when>
  39. </conditional>
  40. <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."/>
  41. <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."/>
  42. </inputs>
  43. <outputs>
  44. <data format="tabular" name="output1" metadata_source="ref" />
  45. <data format="tabular" name="output2" metadata_source="ref" />
  46. <data format="customtrack" name="output3" metadata_source="ref" />
  47. </outputs>
  48. <!-- "ToolTestCase does not deal with multiple outputs properly yet."
  49. <tests>
  50. <test>
  51. <param name="ref" value="phiX_mod.fasta" />
  52. <param name="is_paired" value="no" />
  53. <param name="f3_reads" value="phiX_solid.csfasta" />
  54. <param name="f3_qual" value="phiX_solid.qualsolid" />
  55. <param name="min_mapqual" value="0" />
  56. <param name="max_mismatch" value="7" />
  57. <output name="output1" file="phiX_solid_maq.map" />
  58. <output name="output2" file="phiX_solid_maq.pileup" />
  59. <output name="output3" file="phiX_solid_maq.ctrack" />
  60. </test>
  61. </tests>
  62. -->
  63. <help>
  64. .. class:: infomark
  65. **What it does**
  66. This tool maps SOLiD color-space reads against the target genome using MAQ. It produces three output datasets:
  67. **ALIGNMENT INFO** : contains the read alignment information,
  68. **PILEUP** : contains the coverage and SNP statistics for every nucleotide of the target genome,
  69. **CUSTOM TRACK** : contains the coverage and SNP statistics as custom tracks displayable in the UCSC browser.
  70. -----
  71. **The ALIGNMENT INFO dataset will contain the following fields:**
  72. * column 1 = read name
  73. * column 2 = chromosome
  74. * column 3 = position
  75. * column 4 = strand
  76. * column 5 = insert size from the outer coorniates of a pair
  77. * column 6 = paired flag
  78. * column 7 = mapping quality
  79. * column 8 = single-end mapping quality
  80. * column 9 = alternative mapping quality
  81. * column 10 = number of mismatches of the best hit
  82. * column 11 = sum of qualities of mismatched bases of the best hit
  83. * column 12 = number of 0-mismatch hits of the first 24bp
  84. * column 13 = number of 1-mismatch hits of the first 24bp on the reference
  85. * column 14 = length of the read
  86. * column 15 = read sequence
  87. * column 16 = read quality
  88. **The PILEUP dataset will contain the following fields:**
  89. * column 1 = chromosome
  90. * column 2 = position
  91. * column 3 = reference nucleotide
  92. * column 4 = coverage (number of reads that cover this position)
  93. * column 5 = number of SNPs
  94. * column 6 = number of As
  95. * column 7 = number of Ts
  96. * column 8 = number of Gs
  97. * column 9 = number of Cs
  98. </help>
  99. <code file="maq_cs_wrapper_code.py"/>
  100. </tool>