PageRenderTime 34ms CodeModel.GetById 22ms RepoModel.GetById 1ms app.codeStats 0ms

XML | 110 lines | 85 code | 25 blank | 0 comment | 0 complexity | 5b49caafe1bbeb5b94821859d6312ffb MD5 | raw file
  1. <tool id="rgQC1" name="QC reports:">
  2. <description>Marker and Subject measures</description>
  3. <command interpreter="python">
  4. -i '$input_file.extra_files_path/$input_file.metadata.base_name' -o "$title"
  5. -s '$html_file' -p '$html_file.files_path'
  6. </command>
  7. <inputs>
  8. <param name="input_file" type="data" label="RGenetics genotype file in compressed Plink format"
  9. size="80" format="pbed" />
  10. <param name="title" size="80" type="text" value="RgQC report" label="Descriptive report title"/>
  11. </inputs>
  12. <outputs>
  13. <data format="html" name="html_file" metadata_source="input_file" label="${title}.html"/>
  14. </outputs>
  15. <tests>
  16. <test>
  17. <param name='input_file' value='tinywga' ftype='pbed' >
  18. <metadata name='base_name' value='tinywga' />
  19. <composite_data value='tinywga.bim' />
  20. <composite_data value='tinywga.bed' />
  21. <composite_data value='tinywga.fam' />
  22. <edit_attributes type='name' value='tinywga' />
  23. </param>
  24. <param name='title' value='rgQCtest1' />
  25. <output name='html_file' file='rgtestouts/rgQC/rgQCtest1.html' ftype='html' lines_diff='300'>
  26. <param name="dbkey" value="hg18" />
  27. <extra_files type="file" name='tinywga_All_Paged.pdf' value="rgtestouts/rgQC/tinywga_All_Paged.pdf" compare="sim_size" delta = "100000"/>
  28. <extra_files type="file" name='tinywga.log' value="rgtestouts/rgQC/tinywga.log" compare="diff" lines_diff="15"/>
  29. <extra_files type="file" name='tinywga.frq' value="rgtestouts/rgQC/tinywga.frq" compare="diff" />
  30. <extra_files type="file" name='tinywga.het' value="rgtestouts/rgQC/tinywga.het" compare="diff" lines_diff="90"/>
  31. <extra_files type="file" name='tinywga.hwe' value="rgtestouts/rgQC/tinywga.hwe" compare="diff" lines_diff="90"/>
  32. <extra_files type="file" name='tinywga.imendel' value="rgtestouts/rgQC/tinywga.imendel" compare="diff"/>
  33. <extra_files type="file" name='tinywga.imiss' value="rgtestouts/rgQC/tinywga.imiss" compare="diff" />
  34. <extra_files type="file" name='tinywga.lmendel' value="rgtestouts/rgQC/tinywga.lmendel" compare="diff" />
  35. <extra_files type="file" name='tinywga.lmiss' value="rgtestouts/rgQC/tinywga.lmiss" compare="diff" />
  36. <extra_files type="file" name='tinywga_All_3x3.pdf' value="rgtestouts/rgQC/tinywga_All_3x3.pdf" compare="sim_size" delta="100000"/>
  37. <extra_files type="file" name='ldp_tinywga.bed' value="rgtestouts/rgQC/ldp_tinywga.bed" compare="diff" lines_diff="10" />
  38. <extra_files type="file" name='ldp_tinywga.bim' value="rgtestouts/rgQC/ldp_tinywga.bim" compare="sim_size" delta="1000" />
  39. <extra_files type="file" name='ldp_tinywga.fam' value="rgtestouts/rgQC/ldp_tinywga.fam" compare="diff" />
  40. <extra_files type="file" name='ldp_tinywga.log' value="rgtestouts/rgQC/ldp_tinywga.log" compare="diff" lines_diff="20"/>
  41. <extra_files type="file" name='Ranked_Marker_HWE.xls' value="rgtestouts/rgQC/Ranked_Marker_HWE.xls" compare="diff" />
  42. <extra_files type="file" name='Ranked_Marker_MAF.xls' value="rgtestouts/rgQC/Ranked_Marker_MAF.xls" compare="diff" />
  43. <extra_files type="file" name='Ranked_Marker_Missing_Genotype.xls' value="rgtestouts/rgQC/Ranked_Marker_Missing_Genotype.xls" compare="diff" lines_diff="5"/>
  44. <extra_files type="file" name='Ranked_Subject_Missing_Genotype.xls' value="rgtestouts/rgQC/Ranked_Subject_Missing_Genotype.xls" compare="diff" lines_diff="40"/>
  45. <extra_files type="file" name='tinywga_fracmiss_cum.jpg' value="rgtestouts/rgQC/tinywga_fracmiss_cum.jpg" compare="sim_size" delta = "20000"/>
  46. <extra_files type="file" name='tinywga_fracmiss_cum.pdf' value="rgtestouts/rgQC/tinywga_fracmiss_cum.pdf" compare="sim_size" delta = "100000"/>
  47. </output>
  48. </test>
  49. </tests>
  50. <help>
  51. .. class:: infomark
  52. **Summary**
  53. This tool prepares an extensive and comprehensive series of reports for quality control checking of SNP genotypes from any arbitrary
  54. genotyping experiment. Designed for family based data, so includes optional reports on Mendelian errors by
  55. subject and by marker.
  56. The outputs include histograms and boxplots for missingness, maf, mendel counts and hwe by marker, and the ones that make sense by
  57. subject. The report is built as a single web page containing links to the summary marker and subject files.
  58. The F (inbreeding) statistic is calculated using a somewhat LD independent group of genotypes
  59. The Plink used is --indep-pairwise 40 20 0.5 until we make it configurable.
  60. High heterozygosity might mean contaminated sample - more than one DNA. Low heterozygosity might mean inbreeding as in strains
  61. of mice.
  62. If the data file you want is missing from the option list above,
  63. you will first need to "import" it so it will be available here. Files available in the system library
  64. can be imported by selecting and completing the "Import ped/map" choice from the Get Data tool group at the top of the Galaxy
  65. menu. Your system administrator will be responsible for adding files to the system library.
  66. -----
  67. .. class:: infomark
  68. **Syntax**
  69. - **Genotype file** is the input pedfile -
  70. - **Prefix** is a string used to name all of the outputs
  71. -----
  72. **Attribution**
  73. This Galaxy tool was written by Ross Lazarus for the Rgenetics project
  74. The current version uses Plink for most calculations and R for plotting - for full Plink attribution, source code and documentation,
  75. please see while R attribution and source code can be found at
  76. Shaun Purcell provides the documentation you need specific to those settings, at
  78. Tool and Galaxy datatypes originally designed and written for the Rgenetics
  79. series of whole genome scale statistical genetics tools by ross lazarus (
  80. Shaun Purcell created and maintains Plink, while a cast of many maintain R.
  81. Please acknowledge your use of this tool, Galaxy, R and Plink in your publications and let
  82. us know so we can keep track. These tools all rely on highly competitive grant funding
  83. so your letting us know about publications is important to our ongoing support.
  84. </help>
  85. </tool>