/tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml

https://bitbucket.org/cistrome/cistrome-harvard/ · XML · 286 lines · 256 code · 17 blank · 13 comment · 0 complexity · c8b41a0186852dc39e809623a2dbda50 MD5 · raw file 

    

  1. <tool id="ncbi_tblastn_wrapper" name="NCBI BLAST+ tblastn" version="0.0.11">
    2. 

  2.     <description>Search translated nucleotide database with protein query sequence(s)</description>
    3. 

  3.     <version_command>tblastn -version</version_command>
    4. 

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

  5. ## The command is a Cheetah template which allows some Python based syntax.
    6. 

  6. ## Lines starting hash hash are comments. Galaxy will turn newlines into spaces
    7. 

  7. tblastn
    8. 

  8. -query "$query"
    9. 

  9. #if $db_opts.db_opts_selector == "db":
    10. 

  10.   -db "${db_opts.database.fields.path}"
    11. 

  11. #else:
    12. 

  12.   -subject "$db_opts.subject"
    13. 

  13. #end if
    14. 

  14. -evalue $evalue_cutoff
    15. 

  15. -out $output1
    16. 

  16. ##Set the extended list here so if/when we add things, saved workflows are not affected
    17. 

  17. #if str($out_format)=="ext":
    18. 

  18.     -outfmt "6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen"
    19. 

  19. #else:
    20. 

  20.     -outfmt $out_format
    21. 

  21. #end if
    22. 

  22. -num_threads 8
    23. 

  23. #if $adv_opts.adv_opts_selector=="advanced":
    24. 

  24. $adv_opts.filter_query
    25. 

  25. -matrix $adv_opts.matrix
    26. 

  26. ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string
    27. 

  27. ## Note -max_target_seqs overrides -num_descriptions and -num_alignments
    28. 

  28. #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0):
    29. 

  29. -max_target_seqs $adv_opts.max_hits
    30. 

  30. #end if
    31. 

  31. #if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0):
    32. 

  32. -word_size $adv_opts.word_size
    33. 

  33. #end if
    34. 

  34. ##Ungapped disabled for now - see comments below
    35. 

  35. ##$adv_opts.ungapped
    36. 

  36. $adv_opts.parse_deflines
    37. 

  37. ## End of advanced options:
    38. 

  38. #end if
    39. 

  39.     </command>
    40. 

  40.     <inputs>
    41. 

  41.         <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/> 
    42. 

  42.         <conditional name="db_opts">
    43. 

  43.             <param name="db_opts_selector" type="select" label="Subject database/sequences">
    44. 

  44.               <option value="db" selected="True">BLAST Database</option>
    45. 

  45.               <option value="file">FASTA file</option>
    46. 

  46.             </param>
    47. 

  47.             <when value="db">
    48. 

  48.                 <param name="database" type="select" label="Nucleotide BLAST database">
    49. 

  49.                     <options from_file="blastdb.loc">
    50. 

  50.                       <column name="value" index="0"/>
    51. 

  51.                       <column name="name" index="1"/>
    52. 

  52.                       <column name="path" index="2"/>
    53. 

  53.                     </options>
    54. 

  54.                 </param>
    55. 

  55.                 <param name="subject" type="hidden" value="" /> 
    56. 

  56.             </when>
    57. 

  57.             <when value="file">
    58. 

  58.                 <param name="database" type="hidden" value="" /> 
    59. 

  59.                 <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/> 
    60. 

  60.             </when>
    61. 

  61.         </conditional>
    62. 

  62.         <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" />
    63. 

  63.         <param name="out_format" type="select" label="Output format">
    64. 

  64.             <option value="6" selected="True">Tabular (standard 12 columns)</option>
    65. 

  65.             <option value="ext">Tabular (extended 24 columns)</option>
    66. 

  66.             <option value="5">BLAST XML</option>
    67. 

  67.             <option value="0">Pairwise text</option>
    68. 

  68.             <option value="0 -html">Pairwise HTML</option>
    69. 

  69.             <option value="2">Query-anchored text</option>
    70. 

  70.             <option value="2 -html">Query-anchored HTML</option>
    71. 

  71.             <option value="4">Flat query-anchored text</option>
    72. 

  72.             <option value="4 -html">Flat query-anchored HTML</option>
    73. 

  73.             <!--
    74. 

  74.             <option value="-outfmt 11">BLAST archive format (ASN.1)</option>
    75. 

  75.             -->
    76. 

  76.         </param>
    77. 

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

  78.             <param name="adv_opts_selector" type="select" label="Advanced Options">
    79. 

  79.               <option value="basic" selected="True">Hide Advanced Options</option>
    80. 

  80.               <option value="advanced">Show Advanced Options</option>
    81. 

  81.             </param>
    82. 

  82.             <when value="basic" />
    83. 

  83.             <when value="advanced">
    84. 

  84.                 <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' -->
    85. 

  85.                 <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" />
    86. 

  86.                 <param name="matrix" type="select" label="Scoring matrix">
    87. 

  87.                     <option value="BLOSUM90">BLOSUM90</option>
    88. 

  88.                     <option value="BLOSUM80">BLOSUM80</option>
    89. 

  89.                     <option value="BLOSUM62" selected="true">BLOSUM62 (default)</option>
    90. 

  90.                     <option value="BLOSUM50">BLOSUM50</option> 
    91. 

  91.                     <option value="BLOSUM45">BLOSUM45</option>
    92. 

  92.                     <option value="PAM250">PAM250</option>
    93. 

  93.                     <option value="PAM70">PAM70</option>
    94. 

  94.                     <option value="PAM30">PAM30</option>
    95. 

  95.                 </param>
    96. 

  96.                 <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer -->
    97. 

  97.                 <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits">
    98. 

  98.                     <validator type="in_range" min="0" />
    99. 

  99.                 </param>
    100. 

  100.                 <!-- I'd like word_size to be optional, with minimum 2 for blastp -->
    101. 

  101.                 <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2.">
    102. 

  102.                     <validator type="in_range" min="0" />
    103. 

  103.                 </param>
    104. 

  104.                 <!--
    105. 

  105.                 Can't use '-ungapped' on its own, error back is:
    106. 

  106.                 Composition-adjusted searched are not supported with an ungapped search, please add -comp_based_stats F or do a gapped search
    107. 

  107.                 Tried using '-ungapped -comp_based_stats F' and tblastn crashed with 'Attempt to access NULL pointer.'
    108. 

  108.                 <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped -comp_based_stats F" falsevalue="" checked="false" />
    109. 

  109.                 -->
    110. 

  110.                 <param name="parse_deflines" type="boolean" label="Should the query and subject defline(s) be parsed?" truevalue="-parse_deflines" falsevalue="" checked="false" help="This affects the formatting of the query/subject ID strings"/>
    111. 

  111.             </when>
    112. 

  112.         </conditional>
    113. 

  113.     </inputs>
    114. 

  114.     <outputs>
    115. 

  115.         <data name="output1" format="tabular" label="tblastn on ${db_opts.db_opts_selector}">
    116. 

  116.             <change_format>
    117. 

  117.                 <when input="out_format" value="0" format="txt"/>
    118. 

  118.                 <when input="out_format" value="0 -html" format="html"/>
    119. 

  119.                 <when input="out_format" value="2" format="txt"/>
    120. 

  120.                 <when input="out_format" value="2 -html" format="html"/>
    121. 

  121.                 <when input="out_format" value="4" format="txt"/>
    122. 

  122.                 <when input="out_format" value="4 -html" format="html"/>
    123. 

  123.                 <when input="out_format" value="5" format="blastxml"/>
    124. 

  124.             </change_format>
    125. 

  125.         </data>
    126. 

  126.     </outputs>
    127. 

  127.     <requirements>
    128. 

  128.         <requirement type="binary">tblastn</requirement>
    129. 

  129.     </requirements>
    130. 

  130.     <tests>
    131. 

  131.         <test>
    132. 

  132.             <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
    133. 

  133.             <param name="db_opts_selector" value="file" />
    134. 

  134.             <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" />
    135. 

  135.             <param name="database" value="" />
    136. 

  136.             <param name="evalue_cutoff" value="1e-10" />
    137. 

  137.             <param name="out_format" value="5" />
    138. 

  138.             <param name="adv_opts_selector" value="advanced" />
    139. 

  139.             <param name="filter_query" value="false" />
    140. 

  140.             <param name="matrix" value="BLOSUM80" />
    141. 

  141.             <param name="max_hits" value="0" />
    142. 

  142.             <param name="word_size" value="0" />
    143. 

  143.             <param name="parse_deflines" value="false" />
    144. 

  144.             <output name="output1" file="tblastn_four_human_vs_rhodopsin.xml" ftype="blastxml" />
    145. 

  145.         </test>
    146. 

  146.         <test>
    147. 

  147.             <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
    148. 

  148.             <param name="db_opts_selector" value="file" />
    149. 

  149.             <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" />
    150. 

  150.             <param name="database" value="" />
    151. 

  151.             <param name="evalue_cutoff" value="1e-10" />
    152. 

  152.             <param name="out_format" value="ext" />
    153. 

  153.             <param name="adv_opts_selector" value="advanced" />
    154. 

  154.             <param name="filter_query" value="false" />
    155. 

  155.             <param name="matrix" value="BLOSUM80" />
    156. 

  156.             <param name="max_hits" value="0" />
    157. 

  157.             <param name="word_size" value="0" />
    158. 

  158.             <param name="parse_deflines" value="false" />
    159. 

  159.             <output name="output1" file="tblastn_four_human_vs_rhodopsin_ext.tabular" ftype="tabular" />
    160. 

  160.         </test>
    161. 

  161.         <test>
    162. 

  162.             <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
    163. 

  163.             <param name="db_opts_selector" value="file" />
    164. 

  164.             <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" />
    165. 

  165.             <param name="database" value="" />
    166. 

  166.             <param name="evalue_cutoff" value="1e-10" />
    167. 

  167.             <param name="out_format" value="6" />
    168. 

  168.             <param name="adv_opts_selector" value="advanced" />
    169. 

  169.             <param name="filter_query" value="false" />
    170. 

  170.             <param name="matrix" value="BLOSUM80" />
    171. 

  171.             <param name="max_hits" value="0" />
    172. 

  172.             <param name="word_size" value="0" />
    173. 

  173.             <param name="parse_deflines" value="false" />
    174. 

  174.             <output name="output1" file="tblastn_four_human_vs_rhodopsin.tabular" ftype="tabular" />
    175. 

  175.         </test>
    176. 

  176.         <test>
    177. 

  177.             <!-- Same as above, but parse deflines - on BLAST 2.2.25+ makes no difference -->
    178. 

  178.             <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
    179. 

  179.             <param name="db_opts_selector" value="file" />
    180. 

  180.             <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" />
    181. 

  181.             <param name="database" value="" />
    182. 

  182.             <param name="evalue_cutoff" value="1e-10" />
    183. 

  183.             <param name="out_format" value="6" />
    184. 

  184.             <param name="adv_opts_selector" value="advanced" />
    185. 

  185.             <param name="filter_query" value="false" />
    186. 

  186.             <param name="matrix" value="BLOSUM80" />
    187. 

  187.             <param name="max_hits" value="0" />
    188. 

  188.             <param name="word_size" value="0" />
    189. 

  189.             <param name="parse_deflines" value="true" />
    190. 

  190.             <output name="output1" file="tblastn_four_human_vs_rhodopsin.tabular" ftype="tabular" />
    191. 

  191.         </test>
    192. 

  192.         <test>
    193. 

  193.             <param name="query" value="four_human_proteins.fasta" ftype="fasta" />
    194. 

  194.             <param name="db_opts_selector" value="file" />
    195. 

  195.             <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" />
    196. 

  196.             <param name="database" value="" />
    197. 

  197.             <param name="evalue_cutoff" value="1e-10" />
    198. 

  198.             <param name="out_format" value="0 -html" />
    199. 

  199.             <param name="adv_opts_selector" value="advanced" />
    200. 

  200.             <param name="filter_query" value="false" />
    201. 

  201.             <param name="matrix" value="BLOSUM80" />
    202. 

  202.             <param name="max_hits" value="0" />
    203. 

  203.             <param name="word_size" value="0" />
    204. 

  204.             <param name="parse_deflines" value="false" />
    205. 

  205.             <output name="output1" file="tblastn_four_human_vs_rhodopsin.html" ftype="html" />
    206. 

  206.         </test>
    207. 

  207.     </tests>
    208. 

  208.     <help>
    209. 

  209.     
    210. 

  210. .. class:: warningmark
    211. 

  211. 

  212. **Note**. Database searches may take a substantial amount of time.
    213. 

  213. For large input datasets it is advisable to allow overnight processing.  
    214. 

  214. 

  215. -----
    216. 

  216. 

  217. **What it does**
    218. 

  218. 

  219. Search a *translated nucleotide database* using a *protein query*,
    220. 

  220. using the NCBI BLAST+ tblastn command line tool.
    221. 

  221. 

  222. -----
    223. 

  223. 

  224. **Output format**
    225. 

  225. 

  226. Because Galaxy focuses on processing tabular data, the default output of this
    227. 

  227. tool is tabular. The standard BLAST+ tabular output contains 12 columns:
    228. 

  228. 

  229. ====== ========= ============================================
    230. 

  230. Column NCBI name Description
    231. 

  231. ------ --------- --------------------------------------------
    232. 

  232.      1 qseqid    Query Seq-id (ID of your sequence)
    233. 

  233.      2 sseqid    Subject Seq-id (ID of the database hit)
    234. 

  234.      3 pident    Percentage of identical matches
    235. 

  235.      4 length    Alignment length
    236. 

  236.      5 mismatch  Number of mismatches
    237. 

  237.      6 gapopen   Number of gap openings
    238. 

  238.      7 qstart    Start of alignment in query
    239. 

  239.      8 qend      End of alignment in query
    240. 

  240.      9 sstart    Start of alignment in subject (database hit)
    241. 

  241.     10 send      End of alignment in subject (database hit)
    242. 

  242.     11 evalue    Expectation value (E-value)
    243. 

  243.     12 bitscore  Bit score
    244. 

  244. ====== ========= ============================================
    245. 

  245. 

  246. The BLAST+ tools can optionally output additional columns of information,
    247. 

  247. but this takes longer to calculate. Most (but not all) of these columns are
    248. 

  248. included by selecting the extended tabular output. The extra columns are
    249. 

  249. included *after* the standard 12 columns. This is so that you can write
    250. 

  250. workflow filtering steps that accept either the 12 or 24 column tabular
    251. 

  251. BLAST output.
    252. 

  252. 

  253. ====== ============= ===========================================
    254. 

  254. Column NCBI name     Description
    255. 

  255. ------ ------------- -------------------------------------------
    256. 

  256.     13 sallseqid     All subject Seq-id(s), separated by a ';'
    257. 

  257.     14 score         Raw score
    258. 

  258.     15 nident        Number of identical matches
    259. 

  259.     16 positive      Number of positive-scoring matches
    260. 

  260.     17 gaps          Total number of gaps
    261. 

  261.     18 ppos          Percentage of positive-scoring matches
    262. 

  262.     19 qframe        Query frame
    263. 

  263.     20 sframe        Subject frame
    264. 

  264.     21 qseq          Aligned part of query sequence
    265. 

  265.     22 sseq          Aligned part of subject sequence
    266. 

  266.     23 qlen          Query sequence length
    267. 

  267.     24 slen          Subject sequence length
    268. 

  268. ====== ============= ===========================================
    269. 

  269. 

  270. The third option is BLAST XML output, which is designed to be parsed by
    271. 

  271. another program, and is understood by some Galaxy tools.
    272. 

  272. 

  273. You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program).
    274. 

  274. The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website.
    275. 

  275. The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query.
    276. 

  276. The two query anchored outputs show a multiple sequence alignment between the query and all the matches,
    277. 

  277. and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences).
    278. 

  278. 

  279. -------
    280. 

  280. 

  281. **References**
    282. 

  282. 

  283. Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402.
    284. 

  284. 

  285.     </help>
    286. 

  286. </tool>
    287.