/tools/human_genome_variation/freebayes.xml

https://bitbucket.org/cistrome/cistrome-harvard/ · XML · 124 lines · 122 code · 0 blank · 2 comment · 0 complexity · 604a1821c46fc2f1ca39ab539367516a MD5 · raw file

  1. <?xml version="1.0"?>
  2. <tool id="freebayes_wrapper" name="Call SNPS with Freebayes" version="0.5.0">
  3. <requirements>
  4. <requirement type="package">freebayes</requirement>
  5. </requirements>
  6. <description>Bayesian genetic variant detector</description>
  7. <command>
  8. ln -s $reference localref.fa;
  9. ln -s $bamfile localbam.bam;
  10. samtools faidx localref.fa;
  11. samtools sort localbam.bam localbam.bam;
  12. samtools index localbam.bam;
  13. freebayes --fasta-reference localref.fa localbam.bam --vcf $output
  14. #if $params.source_select == "full":
  15. $params.showRefRepeats
  16. -T $params.theta
  17. -p $params.ploidy
  18. $params.pooled
  19. $params.mnps
  20. $params.nosnps
  21. -n $params.bestAlleles
  22. $params.allAlleles
  23. $params.duplicateReads
  24. -M $params.refMapQuality
  25. $params.ignoreRefAllele
  26. $params.haploidReference
  27. -m $params.minMapQuality
  28. -q $params.minBaseQuality
  29. $params.noFilters
  30. -x $params.indelExclusionWindow
  31. <!-- -D $readDependenceFactor -->
  32. -V $params.diffusionPriorScalar
  33. -W $params.postIntegBandwidth
  34. -Y $params.postIntegBanddepth
  35. -F $params.minAltFraction
  36. -C $params.minAltCount
  37. -G $params.minAltTotal
  38. --min-coverage $params.minCoverage
  39. #end if
  40. </command>
  41. <inputs>
  42. <param format="fasta" name="reference" type="data" metadata_name="dbkey" label="Reference File"/>
  43. <param format="bam" name="bamfile" type="data" label="Bam Alignment File"/>
  44. <conditional name="params">
  45. <param name="source_select" type="select" label="Freebayes Settings to Use" help="For straight forward mapping needs use Commonly Used settings. If you want full control use Full Parameter List">
  46. <option value="pre_set">Commonly Used</option>
  47. <option value="full">Full Parameter List</option>
  48. </param>
  49. <when value="pre_set"/>
  50. <when value="full">
  51. <param name="indels" type="select" label="Include insertion and deletion alleles in the analysis">
  52. <option value="">No</option>
  53. <option value="-i -N --report-all-alternates --left-align-indels">Yes</option>
  54. </param>
  55. <param name="theta" size="5" type="float" value="0.001" label="Theta" help="The expected mutation rate or pairwise nucleotide diversity among the population under analysis. This serves as the single parameter to the Ewens Sampling Formula prior model"/>
  56. <param name="showRefRepeats" type="select" label="Show Reference Repeats" help="Calculate and show information about reference repeats in the VCF output">
  57. <option value="">No</option>
  58. <option value="-_">Yes</option>
  59. </param>
  60. <param name="ploidy" size="5" type="integer" value="2" label="Ploidy" help="Sets the default ploidy for the analysis"/>
  61. <param name="pooled" type="select" label="Pooled" help="Assume that samples result from pooled sequencing. When using this flag, set --ploidy to the number of alleles in each sample">
  62. <option value="">No</option>
  63. <option value="-J">Yes</option>
  64. </param>
  65. <param name="mnps" type="select" label="Include multi-nuceotide polymorphisms in the analysis">
  66. <option value="">No</option>
  67. <option value="--mnps">Yes</option>
  68. </param>
  69. <param name="nosnps" type="select" label="Ignore SNP alleles">
  70. <option value="">No</option>
  71. <option value="--no-snps">Yes</option>
  72. </param>
  73. <param name="duplicateReads" type="select" label="Include duplicate-marked alignments in the analysis">
  74. <option value="">No</option>
  75. <option value="--use-duplicate-reads">Yes</option>
  76. </param>
  77. <param name="bestAlleles" size="5" type="integer" value="2" label="Use Best N Alleles" help="Evaluate only the best N alleles, ranked by sum of supporting quality scores"/>
  78. <param name="allAlleles" type="select" label="Evaluate all possible alleles">
  79. <option value="">No</option>
  80. <option value="--use-all-alleles">Yes</option>
  81. </param>
  82. <param name="refMapQuality" size="5" type="integer" value="100" label="Assign mapping quality of Q to the reference allele at each site"/>
  83. <param name="refBaseQuality" size="5" type="integer" value="60" label="Reference Base Quality" help="Assign a base quality of Q to the reference allele at each site"/>
  84. <param name="minMapQuality" size="5" type="integer" value="10" label="Minimum Mapping Quality" help="Exclude alignments from analysis if they have a mapping quality less than Q"/>
  85. <param name="minBaseQuality" size="5" type="integer" value="5" label="Minimum Base Quality" help="Exclude alleles from analysis if their supporting base quality is less than Q"/>
  86. <param name="indelExclusionWindow" size="5" type="integer" value="0" label="Indel Exclusion Window" help="Ignore portions of alignments N bases from a putative insertion or deletion allele"/>
  87. <param name="ignoreRefAllele" type="select" label="Ignore Reference Allele" help="By default, the reference allele is considered as another sample. This flag excludes it from the analysis">
  88. <option value="">No</option>
  89. <option value="--ignore-reference-allele">Yes</option>
  90. </param>
  91. <param name="haploidReference" type="select" label="Haploid Reference" help="If using the reference sequence as a sample, consider it to be haploid">
  92. <option value="">No</option>
  93. <option value="--haploid-reference">Yes</option>
  94. </param>
  95. <param name="noFilters" type="select" label="No Filters" help="Do not use any input base and mapping quality filters. Equivalent to -m 0 -q 0 -R 0 -S 0">
  96. <option value="">No</option>
  97. <option value="--no-filters">Yes</option>
  98. </param>
  99. <!-- <param name="readDependenceFactor" size="5" type="float" value="0.9" label="Read Dependence Factor" help="Incorporate non-independence of reads by scaling successive observations by this factor during data likelihood calculations"/> -->
  100. <param name="diffusionPriorScalar" size="5" type="float" value="1" label="Diffusion Prior Scalar" help="Downgrade the significance of P(genotype combo | allele frequency) by taking the Nth root of this component of the prior"/>
  101. <param name="postIntegBandwidth" size="5" type="integer" value="2" label="Posterior Integratoin Bandwidth" help="Integrate all genotype combinations in our posterior space which lie no more than N steps from the most likely combination in terms of data likelihoods, taking the N steps from the most to least likely genotype for each individual"/>
  102. <param name="postIntegBanddepth" size="5" type="integer" value="2" label="Posterior Integratoin Banddepth" help="Generate all genotype combinations for which up to this number of samples have up to their -W'th worst genotype according to data likelihood"/>
  103. <param name="minAltFraction" size="5" type="integer" value="0" label="Minimum Alternative Fraction" help="Require at least this fraction of observations supporting an alternate allele within a single individual in the in order to evaluate the position"/>
  104. <param name="minAltCount" size="5" type="integer" value="1" label="Minimum Alternative Count" help="Require at least this count of observations supporting an alternate allele within a single individual in order to evaluate the position"/>
  105. <param name="minAltTotal" size="5" type="integer" value="1" label="Minimum Alternative Total" help="Require at least this count of observations supporting an alternate allele within the total population in order to use the allele in analysis"/>
  106. <param name="minCoverage" size="5" type="integer" value="0" label="Minimum Coverage" help="Require at least this coverage to process a site"/>
  107. </when>
  108. </conditional>
  109. </inputs>
  110. <outputs>
  111. <data format="vcf" name="output" metadata_source="reference" />
  112. </outputs>
  113. <tests>
  114. <test>
  115. <param name="reference" ftype="fasta" value="mosaik_test_ref.fasta"/>
  116. <param name="bamfile" ftype="bam" value="freebayes_in.bam"/>
  117. <param name="source_select" value="pre_set"/>
  118. <output name="output" file="freebayes_out.vcf" lines_diff="4"/>
  119. </test>
  120. </tests>
  121. <help>
  122. This tool uses Freebayes to call SNPS given a reference sequence and a BAM alignment file.
  123. </help>
  124. </tool>