/tools/sr_mapping/bwa_wrapper.xml

https://bitbucket.org/cistrome/cistrome-harvard/ · XML · 474 lines · 389 code · 44 blank · 41 comment · 0 complexity · 00a9cbfaf448329ad7eb00a6d91df57a MD5 · raw file 

    

  1. <tool id="bwa_wrapper" name="Map with BWA for Illumina" version="1.2.2">
    2. 

  2.   <description></description>
    3. 

  3.   <parallelism method="basic"></parallelism>
    4. 

  4.   <command interpreter="python">
    5. 

  5.     bwa_wrapper.py 
    6. 

  6.       --threads="4"
    7. 

  7. 

  8.       #if $input1.ext == "fastqillumina":
    9. 

  9.             --illumina1.3
    10. 

  10.       #end if
    11. 

  11. 

  12.       ## reference source
    13. 

  13.       --fileSource=$genomeSource.refGenomeSource
    14. 

  14.       #if $genomeSource.refGenomeSource == "history":
    15. 

  15.         ##build index on the fly
    16. 

  16.         --ref="${genomeSource.ownFile}"
    17. 

  17.         --dbkey=$dbkey
    18. 

  18.       #else:
    19. 

  19.         ##use precomputed indexes
    20. 

  20.         --ref="${ filter( lambda x: str( x[0] ) == str( $genomeSource.indices ), $__app__.tool_data_tables[ 'bwa_indexes' ].get_fields() )[0][-1] }"
    21. 

  21.         --do_not_build_index
    22. 

  22.       #end if
    23. 

  23. 

  24.       ## input file(s)
    25. 

  25.       --input1=$paired.input1
    26. 

  26.       #if $paired.sPaired == "paired":
    27. 

  27.         --input2=$paired.input2
    28. 

  28.       #end if
    29. 

  29. 

  30.       ## output file
    31. 

  31.       --output=$output
    32. 

  32. 

  33.       ## run parameters
    34. 

  34.       --genAlignType=$paired.sPaired
    35. 

  35.       --params=$params.source_select
    36. 

  36.       #if $params.source_select != "pre_set":
    37. 

  37.         --maxEditDist=$params.maxEditDist
    38. 

  38.         --fracMissingAligns=$params.fracMissingAligns
    39. 

  39.         --maxGapOpens=$params.maxGapOpens
    40. 

  40.         --maxGapExtens=$params.maxGapExtens
    41. 

  41.         --disallowLongDel=$params.disallowLongDel
    42. 

  42.         --disallowIndel=$params.disallowIndel
    43. 

  43.         --seed=$params.seed
    44. 

  44.         --maxEditDistSeed=$params.maxEditDistSeed
    45. 

  45.         --mismatchPenalty=$params.mismatchPenalty
    46. 

  46.         --gapOpenPenalty=$params.gapOpenPenalty
    47. 

  47.         --gapExtensPenalty=$params.gapExtensPenalty
    48. 

  48.         --suboptAlign=$params.suboptAlign
    49. 

  49.         --noIterSearch=$params.noIterSearch
    50. 

  50.         --outputTopN=$params.outputTopN
    51. 

  51.         --outputTopNDisc=$params.outputTopNDisc
    52. 

  52.         --maxInsertSize=$params.maxInsertSize
    53. 

  53.         --maxOccurPairing=$params.maxOccurPairing
    54. 

  54.         #if $params.readGroup.specReadGroup == "yes"
    55. 

  55.           --rgid="$params.readGroup.rgid"
    56. 

  56.           --rgcn="$params.readGroup.rgcn"
    57. 

  57.           --rgds="$params.readGroup.rgds"
    58. 

  58.           --rgdt="$params.readGroup.rgdt"
    59. 

  59.           --rgfo="$params.readGroup.rgfo"
    60. 

  60.           --rgks="$params.readGroup.rgks"
    61. 

  61.           --rglb="$params.readGroup.rglb"
    62. 

  62.           --rgpg="$params.readGroup.rgpg"
    63. 

  63.           --rgpi="$params.readGroup.rgpi"
    64. 

  64.           --rgpl="$params.readGroup.rgpl"
    65. 

  65.           --rgpu="$params.readGroup.rgpu"
    66. 

  66.           --rgsm="$params.readGroup.rgsm"
    67. 

  67.         #end if
    68. 

  68.       #end if
    69. 

  69. 

  70.       ## suppress output SAM header
    71. 

  71.       --suppressHeader=$suppressHeader
    72. 

  72.   </command>
    73. 

  73.   <requirements>
    74. 

  74.     <requirement type="package">bwa</requirement>
    75. 

  75.   </requirements>
    76. 

  76.   <inputs>
    77. 

  77.     <conditional name="genomeSource">
    78. 

  78.       <param name="refGenomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?">
    79. 

  79.         <option value="indexed">Use a built-in index</option>
    80. 

  80.         <option value="history">Use one from the history</option>
    81. 

  81.       </param>
    82. 

  82.       <when value="indexed">
    83. 

  83.         <param name="indices" type="select" label="Select a reference genome">
    84. 

  84.           <options from_data_table="bwa_indexes">
    85. 

  85.             <filter type="sort_by" column="2" />
    86. 

  86.             <validator type="no_options" message="No indexes are available" />
    87. 

  87.           </options>
    88. 

  88.         </param>
    89. 

  89.       </when>
    90. 

  90.       <when value="history">
    91. 

  91.         <param name="ownFile" type="data" format="fasta" metadata_name="dbkey" label="Select a reference from history" />
    92. 

  92.       </when>
    93. 

  93.     </conditional>
    94. 

  94.     <conditional name="paired">
    95. 

  95.       <param name="sPaired" type="select" label="Is this library mate-paired?">
    96. 

  96.         <option value="single">Single-end</option>
    97. 

  97.         <option value="paired">Paired-end</option>
    98. 

  98.       </param>
    99. 

  99.       <when value="single">
    100. 

  100.         <param name="input1" type="data" format="fastqsanger,fastqillumina" label="FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" />
    101. 

  101.       </when>
    102. 

  102.       <when value="paired">
    103. 

  103.         <param name="input1" type="data" format="fastqsanger,fastqillumina" label="Forward FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" />
    104. 

  104.         <param name="input2" type="data" format="fastqsanger,fastqillumina" label="Reverse FASTQ file" help="FASTQ with either Sanger-scaled quality values (fastqsanger) or Illumina-scaled quality values (fastqillumina)" />
    105. 

  105.       </when>
    106. 

  106.     </conditional>
    107. 

  107.     <conditional name="params">
    108. 

  108.       <param name="source_select" type="select" label="BWA settings to use" help="For most mapping needs use Commonly Used settings. If you want full control use Full Parameter List">
    109. 

  109.         <option value="pre_set">Commonly Used</option>
    110. 

  110.         <option value="full">Full Parameter List</option>
    111. 

  111.       </param>
    112. 

  112.       <when value="pre_set" />
    113. 

  113.       <when value="full">
    114. 

  114.         <param name="maxEditDist" type="integer" value="0" label="Maximum edit distance (aln -n)" help="Enter this value OR a fraction of missing alignments, not both" />
    115. 

  115.         <param name="fracMissingAligns" type="float" value="0.04" label="Fraction of missing alignments given 2% uniform base error rate (aln -n)" help="Enter this value OR maximum edit distance, not both" />
    116. 

  116.         <param name="maxGapOpens" type="integer" value="1" label="Maximum number of gap opens (aln -o)" />
    117. 

  117.         <param name="maxGapExtens" type="integer" value="-1" label="Maximum number of gap extensions (aln -e)" help="-1 for k-difference mode (disallowing long gaps)" />
    118. 

  118.         <param name="disallowLongDel" type="integer" value="16" label="Disallow long deletion within [value] bp towards the 3'-end (aln -d)" />
    119. 

  119.         <param name="disallowIndel" type="integer" value="5" label="Disallow insertion/deletion within [value] bp towards the end (aln -i)" />
    120. 

  120.         <param name="seed" type="integer" value="-1" label="Number of first subsequences to take as seed (aln -l)" help="Enter -1 for infinity" />
    121. 

  121.         <param name="maxEditDistSeed" type="integer" value="2" label="Maximum edit distance in the seed (aln -k)" />
    122. 

  122.         <param name="mismatchPenalty" type="integer" value="3" label="Mismatch penalty (aln -M)" help="BWA will not search for suboptimal hits with a score lower than [value]" />
    123. 

  123.         <param name="gapOpenPenalty" type="integer" value="11" label="Gap open penalty (aln -O)" />
    124. 

  124.         <param name="gapExtensPenalty" type="integer" value="4" label="Gap extension penalty (aln -E)" />
    125. 

  125.         <param name="suboptAlign" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Proceed with suboptimal alignments even if the top hit is a repeat (aln -R)" help="For paired-end reads only. By default, BWA only searches for suboptimal alignments if the top hit is unique. Using this option has no effect on accuracy for single-end reads. It is mainly designed for improving the alignment accuracy of paired-end reads. However, the pairing procedure will be slowed down, especially for very short reads (~32bp)" />
    126. 

  126.         <param name="noIterSearch" type="boolean" truevalue="true" falsevalue="false" checked="no" label="Disable iterative search (aln -N)" help="All hits with no more than maxDiff differences will be found. This mode is much slower than the default" />
    127. 

  127.         <param name="outputTopN" type="integer" value="3" label="Maximum number of alignments to output in the XA tag for reads paired properly (samse/sampe -n)" help="If a read has more than INT hits, the XA tag will not be written" />
    128. 

  128.         <param name="outputTopNDisc" type="integer" value="10" label="Maximum number of alignments to output in the XA tag for disconcordant read pairs (excluding singletons) (sampe -N)" help="For paired-end reads only. If a read has more than INT hits, the XA tag will not be written" />
    129. 

  129.         <param name="maxInsertSize" type="integer" value="500" label="Maximum insert size for a read pair to be considered as being mapped properly (sampe -a)" help="For paired-end reads only. Only used when there are not enough good alignments to infer the distribution of insert sizes" />
    130. 

  130.         <param name="maxOccurPairing" type="integer" value="100000" label="Maximum occurrences of a read for pairing (sampe -o)" help="For paired-end reads only. A read with more occurrences will be treated as a single-end read. Reducing this parameter helps faster pairing" />
    131. 

  131.         <conditional name="readGroup">
    132. 

  132.           <param name="specReadGroup" type="select" label="Specify the read group for this file? (samse/sampe -r)">
    133. 

  133.             <option value="yes">Yes</option>
    134. 

  134.             <option value="no" selected="True">No</option>
    135. 

  135.           </param>
    136. 

  136.           <when value="yes">
    137. 

  137.             <param name="rgid" type="text" size="25" label="Read group identi?er (ID). Each @RG line must have a unique ID. The value of ID is used in the RG 
    138. 

  138. tags of alignment records. Must be unique among all read groups in header section." help="Required if RG specified. Read group 
    139. 

  139. IDs may be modi?ed when merging SAM ?les in order to handle collisions." />
    140. 

  140.             <param name="rgcn" type="text" size="25" label="Sequencing center that produced the read (CN)" help="Optional" />
    141. 

  141.             <param name="rgds" type="text" size="25" label="Description (DS)" help="Optional" />
    142. 

  142.             <param name="rgdt" type="text" size="25" label="Date that run was produced (DT)" help="Optional. ISO8601 format date or date/time, like YYYY-MM-DD" />
    143. 

  143.             <param name="rgfo" type="text" size="25" label="Flow order (FO). The array of nucleotide bases that correspond to the nucleotides used for each 
    144. 

  144. ?ow of each read." help="Optional. Multi-base ?ows are encoded in IUPAC format, and non-nucleotide ?ows by 
    145. 

  145. various other characters. Format : /\*|[ACMGRSVTWYHKDBN]+/" />
    146. 

  146.             <param name="rgks" type="text" size="25" label="The array of nucleotide bases that correspond to the key sequence of each read (KS)" help="Optional" />
    147. 

  147.             <param name="rglb" type="text" size="25" label="Library name (LB)" help="Required if RG specified" />
    148. 

  148.             <param name="rgpg" type="text" size="25" label="Programs used for processing the read group (PG)" help="Optional" />
    149. 

  149.             <param name="rgpi" type="text" size="25" label="Predicted median insert size (PI)" help="Optional" />
    150. 

  150.             <param name="rgpl" type="text" size="25" label="Platform/technology used to produce the reads (PL)" help="Required if RG specified. Valid values : CAPILLARY, LS454, ILLUMINA, 
    151. 

  151. SOLID, HELICOS, IONTORRENT and PACBIO" />
    152. 

  152.             <param name="rgpu" type="text" size="25" label="Platform unit (PU)" help="Optional. Unique identi?er (e.g. ?owcell-barcode.lane for Illumina or slide for SOLiD)" />
    153. 

  153.             <param name="rgsm" type="text" size="25" label="Sample (SM)" help="Required if RG specified. Use pool name where a pool is being sequenced" />
    154. 

  154.           </when>
    155. 

  155.           <when value="no" />
    156. 

  156.         </conditional>
    157. 

  157.       </when>
    158. 

  158.     </conditional>
    159. 

  159.     <param name="suppressHeader" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Suppress the header in the output SAM file" help="BWA produces SAM with several lines of header information" />
    160. 

  160.   </inputs>
    161. 

  161.   <outputs>
    162. 

  162.     <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads">
    163. 

  163.       <actions>
    164. 

  164.         <conditional name="genomeSource.refGenomeSource">
    165. 

  165.           <when value="indexed">
    166. 

  166.             <action type="metadata" name="dbkey">
    167. 

  167.               <option type="from_data_table" name="bwa_indexes" column="1">
    168. 

  168.                 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
    169. 

  169.                 <filter type="param_value" ref="genomeSource.indices" column="0"/>
    170. 

  170.               </option>
    171. 

  171.             </action>
    172. 

  172.           </when>
    173. 

  173.           <when value="history">
    174. 

  174.             <action type="metadata" name="dbkey">
    175. 

  175.               <option type="from_param" name="genomeSource.ownFile" param_attribute="dbkey" />
    176. 

  176.             </action>
    177. 

  177.           </when>
    178. 

  178.         </conditional>
    179. 

  179.       </actions>
    180. 

  180.     </data>
    181. 

  181.   </outputs>
    182. 

  182.   <tests>
    183. 

  183.     <test>
    184. 

  184.       <!--
    185. 

  185.       BWA commands:
    186. 

  186.       bwa aln -t 4 phiX.fasta test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out1.sai
    187. 

  187.       bwa samse phiX.fasta bwa_wrapper_out1.sai test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out1.sam
    188. 

  188.       phiX.fasta is the prefix for the reference files (phiX.fasta.amb, phiX.fasta.ann, phiX.fasta.bwt, ...)
    189. 

  189.       remove the comment lines (beginning with '@') from the resulting sam file
    190. 

  190.       plain old sort doesn't handle underscores like python:
    191. 

  191.       python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out1.u.sam bwa_wrapper_out1.sam
    192. 

  192.       -->
    193. 

  193.       <param name="refGenomeSource" value="indexed" />
    194. 

  194.       <param name="indices" value="phiX" />
    195. 

  195.       <param name="sPaired" value="single" />
    196. 

  196.       <param name="input1" value="bwa_wrapper_in1.fastqsanger" ftype="fastqsanger" />
    197. 

  197.       <param name="source_select" value="pre_set" />
    198. 

  198.       <param name="suppressHeader" value="true" />
    199. 

  199.       <output name="output" file="bwa_wrapper_out1.sam" ftype="sam" sort="True" />
    200. 

  200.     </test>
    201. 

  201.     <test>
    202. 

  202.       <!--
    203. 

  203.       BWA commands:
    204. 

  204.       cp test-data/phiX.fasta phiX.fasta
    205. 

  205.       bwa index -a is phiX.fasta
    206. 

  206.       bwa aln -n 0.04 -o 1 -e -1 -d 16 -i 5 -k 2 -t 4 -M 3 -O 11 -E 4 -R -N phiX.fasta test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out2.sai
    207. 

  207.       bwa samse -n 3 phiX.fasta bwa_wrapper_out2.sai test-data/bwa_wrapper_in1.fastqsanger > bwa_wrapper_out2.u.sam
    208. 

  208.       phiX.fasta is the prefix for the reference files (phiX.fasta.amb, phiX.fasta.ann, phiX.fasta.bwt, ...)
    209. 

  209.       remove the comment lines (beginning with '@') from the resulting sam file
    210. 

  210.       plain old sort doesn't handle underscores like python:
    211. 

  211.       python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out2.u.sam bwa_wrapper_out2.sam
    212. 

  212.       -->
    213. 

  213.       <param name="refGenomeSource" value="history" />
    214. 

  214.       <param name="ownFile" value="phiX.fasta" />
    215. 

  215.       <param name="sPaired" value="single" />
    216. 

  216.       <param name="input1" value="bwa_wrapper_in1.fastqsanger" ftype="fastqsanger" />
    217. 

  217.       <param name="source_select" value="full" />
    218. 

  218.       <param name="maxEditDist" value="0" />  
    219. 

  219.       <param name="fracMissingAligns" value="0.04" />
    220. 

  220.       <param name="maxGapOpens" value="1" />
    221. 

  221.       <param name="maxGapExtens" value="-1" />
    222. 

  222.       <param name="disallowLongDel" value="16" />
    223. 

  223.       <param name="disallowIndel" value="5" />
    224. 

  224.       <param name="seed" value="-1" />
    225. 

  225.       <param name="maxEditDistSeed" value="2" />
    226. 

  226.       <param name="mismatchPenalty" value="3" />
    227. 

  227.       <param name="gapOpenPenalty" value="11" />
    228. 

  228.       <param name="gapExtensPenalty" value="4" />
    229. 

  229.       <param name="suboptAlign" value="true" />
    230. 

  230.       <param name="noIterSearch" value="true" />
    231. 

  231.       <param name="outputTopN" value="3" />
    232. 

  232.       <param name="outputTopNDisc" value="10" />
    233. 

  233.       <param name="maxInsertSize" value="500" />
    234. 

  234.       <param name="maxOccurPairing" value="100000" />
    235. 

  235.       <param name="specReadGroup" value="no" />
    236. 

  236.       <param name="suppressHeader" value="true" />
    237. 

  237.       <output name="output" file="bwa_wrapper_out2.sam" ftype="sam" sort="True" />
    238. 

  238.     </test>
    239. 

  239.     <test>
    240. 

  240.       <!--
    241. 

  241.       BWA commands:
    242. 

  242.       bwa aln -n 0.04 -o 1 -e -1 -d 16 -i 5 -k 2 -t 4 -M 3 -O 11 -E 4 -R -N phiX.fasta test-data/bwa_wrapper_in2.fastqsanger > bwa_wrapper_out3a.sai
    243. 

  243.       bwa aln -n 0.04 -o 1 -e -1 -d 16 -i 5 -k 2 -t 4 -M 3 -O 11 -E 4 -R -N phiX.fasta test-data/bwa_wrapper_in3.fastqsanger > bwa_wrapper_out3b.sai
    244. 

  244.       bwa sampe -a 500 -o 100000 -n 3 -N 10 -r "@RG\tID:abcdefg\tDS:descrip\tDT:2010-11-01\tLB:lib-mom-A\tPI:400\tPL:ILLUMINA\tSM:mom" phiX.fasta bwa_wrapper_out3a.sai bwa_wrapper_out3b.sai test-data/bwa_wrapper_in2.fastqsanger test-data/bwa_wrapper_in3.fastqsanger > bwa_wrapper_out3.u.sam
    245. 

  245.       phiX.fasta is the prefix for the reference
    246. 

  246.       plain old sort doesn't handle underscores like python:
    247. 

  247.       python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out3.u.sam bwa_wrapper_out3.sam
    248. 

  248.       -->
    249. 

  249.       <param name="refGenomeSource" value="indexed" />
    250. 

  250.       <param name="indices" value="phiX" />
    251. 

  251.       <param name="sPaired" value="paired" />
    252. 

  252.       <param name="input1" value="bwa_wrapper_in2.fastqsanger" ftype="fastqsanger" />
    253. 

  253.       <param name="input2" value="bwa_wrapper_in3.fastqsanger" ftype="fastqsanger" />
    254. 

  254.       <param name="source_select" value="full" />
    255. 

  255.       <param name="maxEditDist" value="0" />
    256. 

  256.       <param name="fracMissingAligns" value="0.04" />
    257. 

  257.       <param name="maxGapOpens" value="1" />
    258. 

  258.       <param name="maxGapExtens" value="-1" />
    259. 

  259.       <param name="disallowLongDel" value="16" />
    260. 

  260.       <param name="disallowIndel" value="5" />
    261. 

  261.       <param name="seed" value="-1" />
    262. 

  262.       <param name="maxEditDistSeed" value="2" />
    263. 

  263.       <param name="mismatchPenalty" value="3" />
    264. 

  264.       <param name="gapOpenPenalty" value="11" />
    265. 

  265.       <param name="gapExtensPenalty" value="4" />
    266. 

  266.       <param name="suboptAlign" value="true" />
    267. 

  267.       <param name="noIterSearch" value="true" />
    268. 

  268.       <param name="outputTopN" value="3" />
    269. 

  269.       <param name="outputTopNDisc" value="10" />
    270. 

  270.       <param name="maxInsertSize" value="500" />
    271. 

  271.       <param name="maxOccurPairing" value="100000" />
    272. 

  272.       <param name="specReadGroup" value="yes" />
    273. 

  273.       <param name="rgid" value="abcdefg" />
    274. 

  274.       <param name="rgcn" value="" />
    275. 

  275.       <param name="rgds" value="descrip" />
    276. 

  276.       <param name="rgdt" value="2010-11-01" />
    277. 

  277.       <param name="rgfo" value="" />
    278. 

  278.       <param name="rgks" value="" />
    279. 

  279.       <param name="rglb" value="lib-mom-A" />
    280. 

  280.       <param name="rgpg" value="" />
    281. 

  281.       <param name="rgpi" value="400" />
    282. 

  282.       <param name="rgpl" value="ILLUMINA" />
    283. 

  283.       <param name="rgpu" value="" />
    284. 

  284.       <param name="rgsm" value="mom" />
    285. 

  285.       <param name="suppressHeader" value="false" />
    286. 

  286.       <output name="output" file="bwa_wrapper_out3.sam" ftype="sam" sort="True" lines_diff="2" />
    287. 

  287.     </test>
    288. 

  288.     <test>
    289. 

  289.       <!--
    290. 

  290.       BWA commands:
    291. 

  291.       cp test-data/phiX.fasta phiX.fasta
    292. 

  292.       bwa index -a is phiX.fasta
    293. 

  293.       bwa aln -t 4 phiX.fasta test-data/bwa_wrapper_in2.fastqsanger > bwa_wrapper_out8a.sai
    294. 

  294.       bwa aln -t 4 phiX.fasta test-data/bwa_wrapper_in3.fastqsanger > bwa_wrapper_out8b.sai
    295. 

  295.       bwa sampe -a 500 -o 100000 phiX.fasta bwa_wrapper_out8a.sai bwa_wrapper_out8b.sai test-data/bwa_wrapper_in2.fastqsanger test-data/bwa_wrapper_in3.fastqsanger > bwa_wrapper_out8.u.sam
    296. 

  296.       phiX.fa is the prefix for the reference
    297. 

  297.       remove the comment lines (beginning with '@') from the resulting sam file
    298. 

  298.       python -c "import sys; lines=file(sys.argv[1],'rb').readlines(); lines.sort(); file(sys.argv[2],'wb').write(''.join(lines))" bwa_wrapper_out8.u.sam bwa_wrapper_out8.sam
    299. 

  299.       -->
    300. 

  300.       <param name="refGenomeSource" value="history" />
    301. 

  301.       <!-- this is the backwards-compatible "unique value" for this index, not an actual path -->
    302. 

  302.       <param name="ownFile" value="phiX.fasta" />
    303. 

  303.       <param name="sPaired" value="paired" />
    304. 

  304.       <param name="input1" value="bwa_wrapper_in2.fastqsanger" ftype="fastqsanger" />
    305. 

  305.       <param name="input2" value="bwa_wrapper_in3.fastqsanger" ftype="fastqsanger" />
    306. 

  306.       <param name="source_select" value="preSet" />
    307. 

  307.       <param name="suppressHeader" value="true" />
    308. 

  308.       <output name="output" file="bwa_wrapper_out8.sam" ftype="sam" sort="True" />
    309. 

  309.     </test>
    310. 

  310.   </tests> 
    311. 

  311.   <help>
    312. 

  312. 

  313. **What it does**
    314. 

  314. 

  315. BWA is a fast light-weighted tool that aligns relatively short sequences (queries) to a sequence database (large), such as the human reference genome. It is developed by Heng Li at the Sanger Insitute. Li H. and Durbin R. (2009) Fast and accurate short read alignment with Burrows-Wheeler transform. Bioinformatics, 25, 1754-60. 
    316. 

  316. 

  317. ------
    318. 

  318. 

  319. **Know what you are doing**
    320. 

  320. 

  321. .. class:: warningmark
    322. 

  322. 

  323. There is no such thing (yet) as an automated gearshift in short read mapping. It is all like stick-shift driving in San Francisco. In other words = running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.
    324. 

  324. 

  325.  .. __: http://bio-bwa.sourceforge.net/
    326. 

  326. 

  327. ------
    328. 

  328. 

  329. **Input formats**
    330. 

  330. 

  331. BWA accepts files in either Sanger FASTQ format (galaxy type *fastqsanger*) or Illumina FASTQ format (galaxy type *fastqillumina*). Use the FASTQ Groomer to prepare your files.
    332. 

  332. 

  333. ------
    334. 

  334. 

  335. **A Note on Built-in Reference Genomes**
    336. 

  336. 

  337. Some genomes have multiple variants. If only one "type" of genome is listed, it is the Full version, which means that everything that came in the original genome data download (possibly with mitochondrial and plasmid DNA added if it wasn't already included). The Full version is available for every genome. Some genomes also come in the Canonical variant, which contains only the "canonical" (well-defined) chromosomes or segments, such as chr1-chr22, chrX, chrY, and chrM for human. Other variations include gender. These will come in the canonical form only, so the general Canonical variant is actually Canonical Female and the other is Canonical Male (identical to female excluding chrX).
    338. 

    339. 

  339. ------
    340. 

  340. 

  341. **Outputs**
    342. 

  342. 

  343. The output is in SAM format, and has the following columns::
    344. 

  344. 

  345.     Column  Description
    346. 

  346.   --------  --------------------------------------------------------
    347. 

  347.   1  QNAME  Query (pair) NAME
    348. 

  348.   2  FLAG   bitwise FLAG
    349. 

  349.   3  RNAME  Reference sequence NAME
    350. 

  350.   4  POS    1-based leftmost POSition/coordinate of clipped sequence
    351. 

  351.   5  MAPQ   MAPping Quality (Phred-scaled)
    352. 

  352.   6  CIGAR  extended CIGAR string
    353. 

  353.   7  MRNM   Mate Reference sequence NaMe ('=' if same as RNAME)
    354. 

  354.   8  MPOS   1-based Mate POSition
    355. 

  355.   9  ISIZE  Inferred insert SIZE
    356. 

  356.   10 SEQ    query SEQuence on the same strand as the reference
    357. 

  357.   11 QUAL   query QUALity (ASCII-33 gives the Phred base quality)
    358. 

  358.   12 OPT    variable OPTional fields in the format TAG:VTYPE:VALU
    359. 

  359.   
    360. 

  360. The flags are as follows::
    361. 

  361. 

  362.     Flag  Description
    363. 

  363.   ------  -------------------------------------
    364. 

  364.   0x0001  the read is paired in sequencing
    365. 

  365.   0x0002  the read is mapped in a proper pair
    366. 

  366.   0x0004  the query sequence itself is unmapped
    367. 

  367.   0x0008  the mate is unmapped
    368. 

  368.   0x0010  strand of the query (1 for reverse)
    369. 

  369.   0x0020  strand of the mate
    370. 

  370.   0x0040  the read is the first read in a pair
    371. 

  371.   0x0080  the read is the second read in a pair
    372. 

  372.   0x0100  the alignment is not primary
    373. 

  373. 

  374. It looks like this (scroll sideways to see the entire example)::
    375. 

  375. 

  376.   QNAME	FLAG	RNAME	POS	MAPQ	CIAGR	MRNM	MPOS	ISIZE	SEQ	QUAL	OPT
    377. 

  377.   HWI-EAS91_1_30788AAXX:1:1:1761:343	4	*	0	0	*	*	0	0	AAAAAAANNAAAAAAAAAAAAAAAAAAAAAAAAAAACNNANNGAGTNGNNNNNNNGCTTCCCACAGNNCTGG	hhhhhhh;;hhhhhhhhhhh^hOhhhhghhhfhhhgh;;h;;hhhh;h;;;;;;;hhhhhhghhhh;;Phhh
    378. 

  378.   HWI-EAS91_1_30788AAXX:1:1:1578:331	4	*	0	0	*	*	0	0	GTATAGANNAATAAGAAAAAAAAAAATGAAGACTTTCNNANNTCTGNANNNNNNNTCTTTTTTCAGNNGTAG	hhhhhhh;;hhhhhhhhhhhhhhhhhhhhhhhhhhhh;;h;;hhhh;h;;;;;;;hhhhhhhhhhh;;hhVh
    379. 

  379. 

  380. -------
    381. 

  381. 

  382. **BWA settings**
    383. 

  383. 

  384. All of the options have a default value. You can change any of them. All of the options in BWA have been implemented here.
    385. 

  385. 

  386. ------
    387. 

  387. 

  388. **BWA parameter list**
    389. 

  389. 

  390. This is an exhaustive list of BWA options:
    391. 

  391. 

  392. For **aln**::
    393. 

  393. 

  394.   -n NUM  Maximum edit distance if the value is INT, or the fraction of missing
    395. 

  395.           alignments given 2% uniform base error rate if FLOAT. In the latter
    396. 

  396.           case, the maximum edit distance is automatically chosen for different 
    397. 

  397.           read lengths. [0.04]
    398. 

  398.   -o INT  Maximum number of gap opens [1]
    399. 

  399.   -e INT  Maximum number of gap extensions, -1 for k-difference mode
    400. 

  400.           (disallowing long gaps) [-1]
    401. 

  401.   -d INT  Disallow a long deletion within INT bp towards the 3'-end [16]
    402. 

  402.   -i INT  Disallow an indel within INT bp towards the ends [5]
    403. 

  403.   -l INT  Take the first INT subsequence as seed. If INT is larger than the
    404. 

  404.           query sequence, seeding will be disabled. For long reads, this option 
    405. 

  405.           is typically ranged from 25 to 35 for '-k 2'. [inf]
    406. 

  406.   -k INT  Maximum edit distance in the seed [2]
    407. 

  407.   -t INT  Number of threads (multi-threading mode) [1]
    408. 

  408.   -M INT  Mismatch penalty. BWA will not search for suboptimal hits with a score
    409. 

  409.           lower than (bestScore-misMsc). [3]
    410. 

  410.   -O INT  Gap open penalty [11]
    411. 

  411.   -E INT  Gap extension penalty [4]
    412. 

  412.   -c      Reverse query but not complement it, which is required for alignment
    413. 

  413.           in the color space.
    414. 

  414.   -R      Proceed with suboptimal alignments even if the top hit is a repeat. By
    415. 

  415.           default, BWA only searches for suboptimal alignments if the top hit is
    416. 

  416.           unique. Using this option has no effect on accuracy for single-end
    417. 

  417.           reads. It is mainly designed for improving the alignment accuracy of
    418. 

  418.           paired-end reads. However, the pairing procedure will be slowed down,
    419. 

  419.           especially for very short reads (~32bp).
    420. 

  420.   -N      Disable iterative search. All hits with no more than maxDiff
    421. 

  421.           differences will be found. This mode is much slower than the default.
    422. 

  422. 

  423. For **samse**::
    424. 

  424. 

  425.   -n INT  Maximum number of alignments to output in the XA tag for reads paired
    426. 

  426.           properly. If a read has more than INT hits, the XA tag will not be
    427. 

  427.           written. [3]
    428. 

  428.   -r STR  Specify the read group in a format like '@RG\tID:foo\tSM:bar' [null]
    429. 

  429. 

  430. For **sampe**::
    431. 

  431. 

  432.   -a INT  Maximum insert size for a read pair to be considered as being mapped
    433. 

  433.           properly. Since version 0.4.5, this option is only used when there
    434. 

  434.           are not enough good alignment to infer the distribution of insert
    435. 

  435.           sizes. [500]
    436. 

  436.   -n INT  Maximum number of alignments to output in the XA tag for reads paired
    437. 

  437.           properly. If a read has more than INT hits, the XA tag will not be
    438. 

  438.           written. [3]
    439. 

  439.   -N INT  Maximum number of alignments to output in the XA tag for disconcordant
    440. 

  440.           read pairs (excluding singletons). If a read has more than INT hits,
    441. 

  441.           the XA tag will not be written. [10]
    442. 

  442.   -o INT  Maximum occurrences of a read for pairing. A read with more
    443. 

  443.           occurrences will be treated as a single-end read. Reducing this
    444. 

  444.           parameter helps faster pairing. [100000]
    445. 

  445.   -r STR  Specify the read group in a format like '@RG\tID:foo\tSM:bar' [null]
    446. 

  446. 

  447. For specifying the read group in **samse** or **sampe**, use the following::
    448. 

  448. 

  449.   @RG   Read group. Unordered multiple @RG lines are allowed. 
    450. 

  450.   ID    Read group identi?er. Each @RG line must have a unique ID. The value of
    451. 

  451.         ID is used in the RG tags of alignment records. Must be unique among all
    452. 

  452.         read groups in header section. Read group IDs may be modi?ed when
    453. 

  453.         merging SAM ?les in order to handle collisions. 
    454. 

  454.   CN    Name of sequencing center producing the read. 
    455. 

  455.   DS    Description. 
    456. 

  456.   DT    Date the run was produced (ISO8601 date or date/time). 
    457. 

  457.   FO    Flow order. The array of nucleotide bases that correspond to the
    458. 

  458.         nucleotides used for each ?ow of each read. Multi-base ?ows are encoded
    459. 

  459.         in IUPAC format, and non-nucleotide ?ows by various other characters.
    460. 

  460.         Format : /\*|[ACMGRSVTWYHKDBN]+/ 
    461. 

  461.   KS    The array of nucleotide bases that correspond to the key sequence of each read. 
    462. 

  462.   LB    Library. 
    463. 

  463.   PG    Programs used for processing the read group. 
    464. 

  464.   PI    Predicted median insert size. 
    465. 

  465.   PL    Platform/technology used to produce the reads. Valid values : CAPILLARY,
    466. 

  466.         LS454, ILLUMINA, SOLID, HELICOS, IONTORRENT and PACBIO. 
    467. 

  467.   PU    Platform unit (e.g. ?owcell-barcode.lane for Illumina or slide for
    468. 

  468.         SOLiD). Unique identi?er. 
    469. 

  469.   SM    Sample. Use pool name where a pool is being sequenced. 
    470. 

  470. 

  471.   </help>
    472. 

  472. </tool>
    473.