Mercurial > repos > devteam > blast_datatypes
comparison tools/ncbi_blast_plus/ncbi_tblastn_wrapper.xml @ 2:45ba7c750bc8 draft
This update should have no functional effect. Renamed files (since xml.py will be inaccurate once BLAST databases are added in future update).
author | peterjc |
---|---|
date | Thu, 20 Sep 2012 10:12:43 -0400 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
1:10dce68b584b | 2:45ba7c750bc8 |
---|---|
1 <tool id="ncbi_tblastn_wrapper" name="NCBI BLAST+ tblastn" version="0.0.13"> | |
2 <description>Search translated nucleotide database with protein query sequence(s)</description> | |
3 <!-- If job splitting is enabled, break up the query file into parts --> | |
4 <parallelism method="multi" split_inputs="query" split_mode="to_size" split_size="1000" shared_inputs="subject" merge_outputs="output1"></parallelism> | |
5 <version_command>tblastn -version</version_command> | |
6 <command> | |
7 ## The command is a Cheetah template which allows some Python based syntax. | |
8 ## Lines starting hash hash are comments. Galaxy will turn newlines into spaces | |
9 tblastn | |
10 -query "$query" | |
11 #if $db_opts.db_opts_selector == "db": | |
12 -db "${db_opts.database.fields.path}" | |
13 #else: | |
14 -subject "$db_opts.subject" | |
15 #end if | |
16 -evalue $evalue_cutoff | |
17 -out $output1 | |
18 ##Set the extended list here so if/when we add things, saved workflows are not affected | |
19 #if str($out_format)=="ext": | |
20 -outfmt "6 std sallseqid score nident positive gaps ppos qframe sframe qseq sseq qlen slen" | |
21 #else: | |
22 -outfmt $out_format | |
23 #end if | |
24 -num_threads 8 | |
25 #if $adv_opts.adv_opts_selector=="advanced": | |
26 -db_gencode $adv_opts.db_gencode | |
27 $adv_opts.filter_query | |
28 -matrix $adv_opts.matrix | |
29 ## Need int(str(...)) because $adv_opts.max_hits is an InputValueWrapper object not a string | |
30 ## Note -max_target_seqs overrides -num_descriptions and -num_alignments | |
31 #if (str($adv_opts.max_hits) and int(str($adv_opts.max_hits)) > 0): | |
32 -max_target_seqs $adv_opts.max_hits | |
33 #end if | |
34 #if (str($adv_opts.word_size) and int(str($adv_opts.word_size)) > 0): | |
35 -word_size $adv_opts.word_size | |
36 #end if | |
37 ##Ungapped disabled for now - see comments below | |
38 ##$adv_opts.ungapped | |
39 $adv_opts.parse_deflines | |
40 ## End of advanced options: | |
41 #end if | |
42 </command> | |
43 <stdio> | |
44 <exit_code range="1:" /> | |
45 <exit_code range="://0" /> | |
46 </stdio> | |
47 <inputs> | |
48 <param name="query" type="data" format="fasta" label="Protein query sequence(s)"/> | |
49 <conditional name="db_opts"> | |
50 <param name="db_opts_selector" type="select" label="Subject database/sequences"> | |
51 <option value="db" selected="True">BLAST Database</option> | |
52 <option value="file">FASTA file (pairwise e-values)</option> | |
53 </param> | |
54 <when value="db"> | |
55 <param name="database" type="select" label="Nucleotide BLAST database"> | |
56 <options from_file="blastdb.loc"> | |
57 <column name="value" index="0"/> | |
58 <column name="name" index="1"/> | |
59 <column name="path" index="2"/> | |
60 </options> | |
61 </param> | |
62 <param name="subject" type="hidden" value="" /> | |
63 </when> | |
64 <when value="file"> | |
65 <param name="database" type="hidden" value="" /> | |
66 <param name="subject" type="data" format="fasta" label="Nucleotide FASTA file to use as database"/> | |
67 </when> | |
68 </conditional> | |
69 <param name="evalue_cutoff" type="float" size="15" value="0.001" label="Set expectation value cutoff" /> | |
70 <param name="out_format" type="select" label="Output format"> | |
71 <option value="6" selected="True">Tabular (standard 12 columns)</option> | |
72 <option value="ext">Tabular (extended 24 columns)</option> | |
73 <option value="5">BLAST XML</option> | |
74 <option value="0">Pairwise text</option> | |
75 <option value="0 -html">Pairwise HTML</option> | |
76 <option value="2">Query-anchored text</option> | |
77 <option value="2 -html">Query-anchored HTML</option> | |
78 <option value="4">Flat query-anchored text</option> | |
79 <option value="4 -html">Flat query-anchored HTML</option> | |
80 <!-- | |
81 <option value="-outfmt 11">BLAST archive format (ASN.1)</option> | |
82 --> | |
83 </param> | |
84 <conditional name="adv_opts"> | |
85 <param name="adv_opts_selector" type="select" label="Advanced Options"> | |
86 <option value="basic" selected="True">Hide Advanced Options</option> | |
87 <option value="advanced">Show Advanced Options</option> | |
88 </param> | |
89 <when value="basic" /> | |
90 <when value="advanced"> | |
91 <param name="db_gencode" type="select" label="Database/subject genetic code"> | |
92 <!-- See http://www.ncbi.nlm.nih.gov/Taxonomy/Utils/wprintgc.cgi for details --> | |
93 <option value="1" select="True">1. Standard</option> | |
94 <option value="2">2. Vertebrate Mitochondrial</option> | |
95 <option value="3">3. Yeast Mitochondrial</option> | |
96 <option value="4">4. Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma Code</option> | |
97 <option value="5">5. Invertebrate Mitochondrial</option> | |
98 <option value="6">6. Ciliate, Dasycladacean and Hexamita Nuclear Code</option> | |
99 <option value="9">9. Echinoderm Mitochondrial</option> | |
100 <option value="10">10. Euplotid Nuclear</option> | |
101 <option value="11">11. Bacteria and Archaea</option> | |
102 <option value="12">12. Alternative Yeast Nuclear</option> | |
103 <option value="13">13. Ascidian Mitochondrial</option> | |
104 <option value="14">14. Flatworm Mitochondrial</option> | |
105 <option value="15">15. Blepharisma Macronuclear</option> | |
106 <option value="16">16. Chlorophycean Mitochondrial Code</option> | |
107 <option value="21">21. Trematode Mitochondrial Code</option> | |
108 <option value="22">22. Scenedesmus obliquus mitochondrial Code</option> | |
109 <option value="23">23. Thraustochytrium Mitochondrial Code</option> | |
110 <option value="24">24. Pterobranchia mitochondrial code</option> | |
111 </param> | |
112 <!-- Could use a select (yes, no, other) where other allows setting 'window locut hicut' --> | |
113 <param name="filter_query" type="boolean" label="Filter out low complexity regions (with SEG)" truevalue="-seg yes" falsevalue="-seg no" checked="true" /> | |
114 <param name="matrix" type="select" label="Scoring matrix"> | |
115 <option value="BLOSUM90">BLOSUM90</option> | |
116 <option value="BLOSUM80">BLOSUM80</option> | |
117 <option value="BLOSUM62" selected="true">BLOSUM62 (default)</option> | |
118 <option value="BLOSUM50">BLOSUM50</option> | |
119 <option value="BLOSUM45">BLOSUM45</option> | |
120 <option value="PAM250">PAM250</option> | |
121 <option value="PAM70">PAM70</option> | |
122 <option value="PAM30">PAM30</option> | |
123 </param> | |
124 <!-- Why doesn't optional override a validator? I want to accept an empty string OR a non-negative integer --> | |
125 <param name="max_hits" type="integer" value="0" label="Maximum hits to show" help="Use zero for default limits"> | |
126 <validator type="in_range" min="0" /> | |
127 </param> | |
128 <!-- I'd like word_size to be optional, with minimum 2 for blastp --> | |
129 <param name="word_size" type="integer" value="0" label="Word size for wordfinder algorithm" help="Use zero for default, otherwise minimum 2."> | |
130 <validator type="in_range" min="0" /> | |
131 </param> | |
132 <!-- | |
133 Can't use '-ungapped' on its own, error back is: | |
134 Composition-adjusted searched are not supported with an ungapped search, please add -comp_based_stats F or do a gapped search | |
135 Tried using '-ungapped -comp_based_stats F' and tblastn crashed with 'Attempt to access NULL pointer.' | |
136 <param name="ungapped" type="boolean" label="Perform ungapped alignment only?" truevalue="-ungapped -comp_based_stats F" falsevalue="" checked="false" /> | |
137 --> | |
138 <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"/> | |
139 </when> | |
140 </conditional> | |
141 </inputs> | |
142 <outputs> | |
143 <data name="output1" format="tabular" label="tblastn on ${db_opts.db_opts_selector}"> | |
144 <change_format> | |
145 <when input="out_format" value="0" format="txt"/> | |
146 <when input="out_format" value="0 -html" format="html"/> | |
147 <when input="out_format" value="2" format="txt"/> | |
148 <when input="out_format" value="2 -html" format="html"/> | |
149 <when input="out_format" value="4" format="txt"/> | |
150 <when input="out_format" value="4 -html" format="html"/> | |
151 <when input="out_format" value="5" format="blastxml"/> | |
152 </change_format> | |
153 </data> | |
154 </outputs> | |
155 <requirements> | |
156 <requirement type="binary">tblastn</requirement> | |
157 </requirements> | |
158 <tests> | |
159 <test> | |
160 <param name="query" value="four_human_proteins.fasta" ftype="fasta" /> | |
161 <param name="db_opts_selector" value="file" /> | |
162 <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" /> | |
163 <param name="database" value="" /> | |
164 <param name="evalue_cutoff" value="1e-10" /> | |
165 <param name="out_format" value="5" /> | |
166 <param name="adv_opts_selector" value="advanced" /> | |
167 <param name="filter_query" value="false" /> | |
168 <param name="matrix" value="BLOSUM80" /> | |
169 <param name="max_hits" value="0" /> | |
170 <param name="word_size" value="0" /> | |
171 <param name="parse_deflines" value="false" /> | |
172 <output name="output1" file="tblastn_four_human_vs_rhodopsin.xml" ftype="blastxml" /> | |
173 </test> | |
174 <test> | |
175 <param name="query" value="four_human_proteins.fasta" ftype="fasta" /> | |
176 <param name="db_opts_selector" value="file" /> | |
177 <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" /> | |
178 <param name="database" value="" /> | |
179 <param name="evalue_cutoff" value="1e-10" /> | |
180 <param name="out_format" value="ext" /> | |
181 <param name="adv_opts_selector" value="advanced" /> | |
182 <param name="filter_query" value="false" /> | |
183 <param name="matrix" value="BLOSUM80" /> | |
184 <param name="max_hits" value="0" /> | |
185 <param name="word_size" value="0" /> | |
186 <param name="parse_deflines" value="false" /> | |
187 <output name="output1" file="tblastn_four_human_vs_rhodopsin_ext.tabular" ftype="tabular" /> | |
188 </test> | |
189 <test> | |
190 <param name="query" value="four_human_proteins.fasta" ftype="fasta" /> | |
191 <param name="db_opts_selector" value="file" /> | |
192 <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" /> | |
193 <param name="database" value="" /> | |
194 <param name="evalue_cutoff" value="1e-10" /> | |
195 <param name="out_format" value="6" /> | |
196 <param name="adv_opts_selector" value="advanced" /> | |
197 <param name="filter_query" value="false" /> | |
198 <param name="matrix" value="BLOSUM80" /> | |
199 <param name="max_hits" value="0" /> | |
200 <param name="word_size" value="0" /> | |
201 <param name="parse_deflines" value="false" /> | |
202 <output name="output1" file="tblastn_four_human_vs_rhodopsin.tabular" ftype="tabular" /> | |
203 </test> | |
204 <test> | |
205 <!-- Same as above, but parse deflines - on BLAST 2.2.25+ makes no difference --> | |
206 <param name="query" value="four_human_proteins.fasta" ftype="fasta" /> | |
207 <param name="db_opts_selector" value="file" /> | |
208 <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" /> | |
209 <param name="database" value="" /> | |
210 <param name="evalue_cutoff" value="1e-10" /> | |
211 <param name="out_format" value="6" /> | |
212 <param name="adv_opts_selector" value="advanced" /> | |
213 <param name="filter_query" value="false" /> | |
214 <param name="matrix" value="BLOSUM80" /> | |
215 <param name="max_hits" value="0" /> | |
216 <param name="word_size" value="0" /> | |
217 <param name="parse_deflines" value="true" /> | |
218 <output name="output1" file="tblastn_four_human_vs_rhodopsin.tabular" ftype="tabular" /> | |
219 </test> | |
220 <test> | |
221 <param name="query" value="four_human_proteins.fasta" ftype="fasta" /> | |
222 <param name="db_opts_selector" value="file" /> | |
223 <param name="subject" value="rhodopsin_nucs.fasta" ftype="fasta" /> | |
224 <param name="database" value="" /> | |
225 <param name="evalue_cutoff" value="1e-10" /> | |
226 <param name="out_format" value="0 -html" /> | |
227 <param name="adv_opts_selector" value="advanced" /> | |
228 <param name="filter_query" value="false" /> | |
229 <param name="matrix" value="BLOSUM80" /> | |
230 <param name="max_hits" value="0" /> | |
231 <param name="word_size" value="0" /> | |
232 <param name="parse_deflines" value="false" /> | |
233 <output name="output1" file="tblastn_four_human_vs_rhodopsin.html" ftype="html" /> | |
234 </test> | |
235 </tests> | |
236 <help> | |
237 | |
238 .. class:: warningmark | |
239 | |
240 **Note**. Database searches may take a substantial amount of time. | |
241 For large input datasets it is advisable to allow overnight processing. | |
242 | |
243 ----- | |
244 | |
245 **What it does** | |
246 | |
247 Search a *translated nucleotide database* using a *protein query*, | |
248 using the NCBI BLAST+ tblastn command line tool. | |
249 | |
250 ----- | |
251 | |
252 **Output format** | |
253 | |
254 Because Galaxy focuses on processing tabular data, the default output of this | |
255 tool is tabular. The standard BLAST+ tabular output contains 12 columns: | |
256 | |
257 ====== ========= ============================================ | |
258 Column NCBI name Description | |
259 ------ --------- -------------------------------------------- | |
260 1 qseqid Query Seq-id (ID of your sequence) | |
261 2 sseqid Subject Seq-id (ID of the database hit) | |
262 3 pident Percentage of identical matches | |
263 4 length Alignment length | |
264 5 mismatch Number of mismatches | |
265 6 gapopen Number of gap openings | |
266 7 qstart Start of alignment in query | |
267 8 qend End of alignment in query | |
268 9 sstart Start of alignment in subject (database hit) | |
269 10 send End of alignment in subject (database hit) | |
270 11 evalue Expectation value (E-value) | |
271 12 bitscore Bit score | |
272 ====== ========= ============================================ | |
273 | |
274 The BLAST+ tools can optionally output additional columns of information, | |
275 but this takes longer to calculate. Most (but not all) of these columns are | |
276 included by selecting the extended tabular output. The extra columns are | |
277 included *after* the standard 12 columns. This is so that you can write | |
278 workflow filtering steps that accept either the 12 or 24 column tabular | |
279 BLAST output. | |
280 | |
281 ====== ============= =========================================== | |
282 Column NCBI name Description | |
283 ------ ------------- ------------------------------------------- | |
284 13 sallseqid All subject Seq-id(s), separated by a ';' | |
285 14 score Raw score | |
286 15 nident Number of identical matches | |
287 16 positive Number of positive-scoring matches | |
288 17 gaps Total number of gaps | |
289 18 ppos Percentage of positive-scoring matches | |
290 19 qframe Query frame | |
291 20 sframe Subject frame | |
292 21 qseq Aligned part of query sequence | |
293 22 sseq Aligned part of subject sequence | |
294 23 qlen Query sequence length | |
295 24 slen Subject sequence length | |
296 ====== ============= =========================================== | |
297 | |
298 The third option is BLAST XML output, which is designed to be parsed by | |
299 another program, and is understood by some Galaxy tools. | |
300 | |
301 You can also choose several plain text or HTML output formats which are designed to be read by a person (not by another program). | |
302 The HTML versions use basic webpage formatting and can include links to the hits on the NCBI website. | |
303 The pairwise output (the default on the NCBI BLAST website) shows each match as a pairwise alignment with the query. | |
304 The two query anchored outputs show a multiple sequence alignment between the query and all the matches, | |
305 and differ in how insertions are shown (marked as insertions or with gap characters added to the other sequences). | |
306 | |
307 ------- | |
308 | |
309 **References** | |
310 | |
311 Altschul et al. Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. 1997. Nucleic Acids Res. 25:3389-3402. | |
312 | |
313 </help> | |
314 </tool> |