Mercurial > repos > yating-l > ucsc_blat

comparison blat.xml @ 7:10f3a5b6f2ac draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 964ceec6b1c6371b10923c7d49446b1361fc5895-dirty
author yating-l
date Mon, 09 Jul 2018 13:07:54 -0400
parents 250a7f2b1331
children a9d863528f48
comparison
equal deleted inserted replaced
6:250a7f2b1331 7:10f3a5b6f2ac
1 <?xml version="1.0"?> 1 <?xml version="1.0"?>
2 <tool id="ucsc_blat" name="UCSC BLAT Alignment Tool" version="36"> 2 <tool id="ucsc_blat" name="UCSC BLAT Alignment Tool" version="1.1">
3 <description>BLAST-like sequence alignment tool</description> 3 <description>Standalone blat sequence search command line tool</description>
4 <requirements> 4 <requirements>
5 <requirement type="package" version="36">blat</requirement> 5 <requirement type="package" version="1.0">ucsc_tools_340_for_BLAT</requirement>
6 </requirements> 6 </requirements>
7 <command detect_errors="exit_code"><![CDATA[ 7 <command detect_errors="exit_code"><![CDATA[
8 #if str($reference_source.reference_source_selector) == "history": 8 #if str($reference_source.reference_source_selector) == "history":
9 ## blat depends on file extension 9 #set $reference_fasta_filename = "localref.fa"
10 #if $reference_source.database.is_of_type("fasta"):
11 #set $reference_fasta_filename = "localref.fa"
12 #elif $reference_source.database.is_of_type("twobit"):
13 #set $reference_fasta_filename = "localref.2bit"
14 #else
15 #set $reference_fasta_filename = "localref"
16 #end if
17
18 ln -s '${reference_source.database}' '${reference_fasta_filename}' && 10 ln -s '${reference_source.database}' '${reference_fasta_filename}' &&
19 #else: 11 #else:
20 #set $reference_fasta_filename = str($reference_source.database.fields.path) 12 #set $reference_fasta_filename = str($reference_source.database.fields.path)
21 #end if 13 #end if
22 14 blat
23 blat 15 #if $noHead == "yes"
24 16 -noHead
17 #end if
25 -q=$query_type 18 -q=$query_type
26 -t=$database_type 19 -t=$database_type
27
28 ${oneOff}
29
30 #if str($minScore)
31 -minScore=${minScore}
32 #end if
33
34 -maxGap=${maxGap}
35
36 #if str($repMatch)
37 -repMatch=${repMatch}
38 #end if
39
40 #if $mask_type.mask == "file.out": 20 #if $mask_type.mask == "file.out":
41 -mask='${mask_type.mask_file}' 21 -mask=$mask_type.mask_file
42 #else: 22 #else:
43 -mask=$mask_type.mask 23 -mask=$mask_type.mask
44 #end if 24 #end if
45
46 #if str($dots)
47 -dots=${dots}
48 #end if
49
50 ${trimT}
51 ${noTrimA}
52 ${trimHardA}
53 ${fastMap}
54 ${fine}
55
56 #if str($maxIntron)
57 -maxIntron=${maxIntron}
58 #end if
59
60 ${extendThroughN}
61
62 '$reference_fasta_filename' 25 '$reference_fasta_filename'
63 '${query}' 26 '${query}'
64 27 output
65 -out=${out} 28 && sort -k 10,10 -k 12,12n output > '${output_sorted}'
66
67 '${output}'
68 ]]></command> 29 ]]></command>
69 <inputs> 30 <inputs>
70 <conditional name="reference_source"> 31 <conditional name="reference_source">
71 <param name="reference_source_selector" type="select" label="Choose the source for the database"> 32 <param name="reference_source_selector" type="select" label="Choose the source for the database">
72 <option value="cached">Locally cached</option> 33 <option value="cached">Locally cached</option>
79 </options> 40 </options>
80 <validator type="no_options" message="A built-in database is not available" /> 41 <validator type="no_options" message="A built-in database is not available" />
81 </param> 42 </param>
82 </when> 43 </when>
83 <when value="history"> 44 <when value="history">
84 <param name="database" type="data" format="fasta, twobit" label="Using database file, either a .fa, .nib or .2bit file" /> 45 <param name="database" type="data" format="fasta,twobit" label="Using database file, either a .fa, .nib or .2bit file" />
85 </when> 46 </when>
86 </conditional> 47 </conditional>
87 <param type="data" name="query" format="fasta, twobit" label="Query data, either a .fa, .nib or .2bit file"/> 48 <param type="data" name="query" format="fasta,twobit" label="Query data, either a .fa, .nib or .2bit file"/>
88 <param type="select" name="database_type" format="text" multiple="false" label="database type" help="Choose your database type, the default is dnax" argument="-t"> 49 <param type="select" name="database_type" format="text" multiple="false" label="database type" help="Choose your database type, the default is dnax" argument="-t">
89 <option value="dna">dna - DNA sequence</option> 50 <option value="dna">dna - DNA sequence</option>
90 <option value="prot">prot - protein sequence</option> 51 <option value="prot">prot - protein sequence</option>
91 <option value="dnax" selected="true">dnax - DNA sequence translated in six frames to protein</option> 52 <option value="dnax" selected="true">dnax - DNA sequence translated in six frames to protein</option>
92 </param> 53 </param>
95 <option value="rna">rna - RNA sequence</option> 56 <option value="rna">rna - RNA sequence</option>
96 <option value="prot">prot - protein sequence</option> 57 <option value="prot">prot - protein sequence</option>
97 <option value="dnax">dnax - DNA sequence translated in six frames to protein</option> 58 <option value="dnax">dnax - DNA sequence translated in six frames to protein</option>
98 <option value="rnax" selected="true">rnax - DNA sequence translated in three frames to protein</option> 59 <option value="rnax" selected="true">rnax - DNA sequence translated in three frames to protein</option>
99 </param> 60 </param>
100 <param argument="-oneOff" type="boolean" truevalue="-oneOff=1" falsevalue="" label="If set, this allows one mismatch in tile and still triggers an alignments" /> 61 <param type="select" name="noHead" format="text" label="Suppresses .psl header (so it's just a tab-separated file)." >
101 <param argument="-minScore" type="integer" value="30" label="Minimum score" help="It is the matches minus the mismatches minus some sort of gap penalty" /> 62 <option value="yes" selected="true">Yes, suppresses .psl header</option>
102 <param argument="-maxGap" type="integer" value="2" min="0" max="3" label="Maximum gap between tiles in a clump" help="Usually set from 0 to 3. Only relevant for minMatch > 1" /> 63 <option value="no">No, do not suppresses .psl header</option>
103 <param argument="-repMatch" type="integer" value="" optional="true" label="Number of repetitions of a tile allowed before it is marked as overused" help="Typically this is 256 for tileSize 12, 1024 for tileSize 11, 4096 for tileSize 10. Also affected by stepSize. When stepSize is halved repMatch is doubled to compensate" /> 64 </param>
104 <conditional name="mask_type"> 65 <conditional name="mask_type">
105 <param name="mask" type="select" label="Mask out repeats" help="Alignments won't be started in masked region 66 <param name="mask" type="select" label="Mask out repeats" help="Alignments won't be started in masked region
106 but may extend through it in nucleotide searches. Masked areas 67 but may extend through it in nucleotide searches. Masked areas
107 are ignored entirely in protein or translated searches. Default is lower" argument="-mask"> 68 are ignored entirely in protein or translated searches. Default is lower" argument="-mask">
108 <option value="lower" selected="true">lower - mask out lower-cased sequence</option> 69 <option value="lower" selected="true">lower - mask out lower-cased sequence</option>
113 <when value="lower" /> 74 <when value="lower" />
114 <when value="upper" /> 75 <when value="upper" />
115 <when value="out" /> 76 <when value="out" />
116 <when value="file.out"> 77 <when value="file.out">
117 <param name="mask_file" type="data" format="txt" label="RepeatMasker file.out" /> 78 <param name="mask_file" type="data" format="txt" label="RepeatMasker file.out" />
118 </when> 79 </when>
119 </conditional> 80 </conditional>
120 <param argument="-dots" type="integer" value="" optional="true" label="Output a dot every N sequences in log" help="Dots show program's progress" />
121 <param argument="-trimT" type="boolean" truevalue="-trimT" falsevalue="" label="Trim leading poly-T" />
122 <param argument="-noTrimA" type="boolean" truevalue="-noTrimA" falsevalue="" label="Don't trim trailing poly-A" />
123 <param argument="-trimHardA" type="boolean" truevalue="-trimHardA" falsevalue="" label="Remove poly-A tail from qSize and alignments in .psl output" />
124 <param argument="-fastMap" type="boolean" truevalue="-fastMap" falsevalue="" label="Run for fast DNA/DNA remapping" help="It does not allow introns and require high %ID. Query sizes must not exceed 5000" />
125 <param argument="-fine" type="boolean" truevalue="-fine" falsevalue="" label="Refine search for small initial and terminal exons" help="For high-quality mRNAs. Not recommended for ESTs" />
126 <param argument="-maxIntron" type="integer" value="750000" optional="true" label="Maximum intron size" />
127 <param argument="-extendThroughN" type="boolean" truevalue="-extendThroughN" falsevalue="" label="Allow extension of alignment through large blocks of N's" />
128 <param name="out" type="select" label="Select output file format (-out)">
129 <option value="psl">Tab-separated format, no sequence (psl)</option>
130 <option value="psl -noHead">Tab-separated format, no sequence, no header (psl -noHead)</option>
131 <option value="axt">Blastz-associated axt format (axt)</option>
132 <option value="maf">Multiz-associated maf format (maf)</option>
133 <option value="sim4">Similar to sim4 format (sim4)</option>
134 <option value="wublast">Similar to WU-BLAST format (wublast)</option>
135 <option value="blast">Similar to NCBI BLAST format (blast)</option>
136 <option value="blast8">NCBI BLAST tabular format (blast8)</option>
137 <option value="blast9">NCBI BLAST tabular format with comments (blast9)</option>
138 </param>
139 </inputs> 81 </inputs>
140 <outputs> 82 <outputs>
141 <data name="output" format="tabular" label="${tool.name} on ${on_string}"> 83 <data format="psl" name="output_sorted" label="${tool.name} on ${on_string}"></data>
142 <change_format>
143 <when input="out" value="psl" format="psl" />
144 <when input="out" value="axt" format="axt" />
145 <when input="out" value="maf" format="maf" />
146 <when input="out" value="sim4" format="txt" />
147 <when input="out" value="wublast" format="txt" />
148 <when input="out" value="blast" format="txt" />
149 </change_format>
150 </data>
151 </outputs> 84 </outputs>
152 <tests> 85 <tests>
153 <!-- test on query of GenBank RefSeq records for Gallus gallus and database of Amazona vittata --> 86 <!-- test on query of GenBank RefSeq records for Gallus gallus and database of Amazona vittata -->
154 <test> 87 <test>
155 <param name="reference_source_selector" value="history" /> 88 <param name="reference_source_selector" value="history" />
156 <param name="database" value="amaVit1_Gallus/amaVit1.fa" /> 89 <param name="database" value="amaVit1_Gallus/amaVit1.fa" />
157 <param name="query" value="amaVit1_Gallus/Gallus_gallus_RefSeq.fa" /> 90 <param name="query" value="amaVit1_Gallus/Gallus_gallus_RefSeq.fa" />
158 <param name="database_type" value="dnax" /> 91 <param name="database_type" value="dnax" />
159 <param name="query_type" value="rnax" /> 92 <param name="query_type" value="rnax" />
93 <param name="noHead" value="yes" />
160 <param name="mask" value="lower" /> 94 <param name="mask" value="lower" />
161 <param name="out" value="psl -noHead" /> 95 <output name="output_sorted" value="amaVit1_Gallus/amaVit1_Gallus_gallus.psl" />
162 <output name="output" value="amaVit1_Gallus/amaVit1_Gallus_gallus_sorted.psl" sort="True"/>
163 </test> 96 </test>
164 <!-- test on query of partial mRNA of Drosophila melanogaster and the database of Drosophila biamipes dot chromosome --> 97 <!-- test on query of partial mRNA of Drosophila melanogaster and the database of Drosophila biamipes dot chromosome -->
165 <test> 98 <test>
166 <param name="reference_source_selector" value="history" /> 99 <param name="reference_source_selector" value="history" />
167 <param name="database" value="dbia3/dbia3.fa" /> 100 <param name="database" value="dbia3/dbia3.fa" />
168 <param name="query" value="dbia3/dmel-transcript.fa" /> 101 <param name="query" value="dbia3/dmel-transcript.fa" />
169 <param name="database_type" value="dnax" /> 102 <param name="database_type" value="dnax" />
170 <param name="query_type" value="rnax" /> 103 <param name="query_type" value="rnax" />
104 <param name="noHead" value="yes" />
171 <param name="mask" value="lower" /> 105 <param name="mask" value="lower" />
172 <param name="out" value="psl -noHead" /> 106 <output name="output_sorted" value="dbia3/dbia3.sorted.psl" />
173 <param name="maxIntron" value="" />
174 <output name="output" value="dbia3/dbia3.sorted.psl" sort="True"/>
175 </test> 107 </test>
176 <!-- test on the database masked by repeat masker --> 108 <!-- test on the database masked by repeat masker -->
177 <test> 109 <test>
178 <param name="reference_source_selector" value="history" /> 110 <param name="reference_source_selector" value="history" />
179 <param name="database" value="dbia3/dbia3_masked.2bit" /> 111 <param name="database" value="dbia3/dbia3_masked.2bit" />
180 <param name="query" value="dbia3/dmel-transcript.fa" /> 112 <param name="query" value="dbia3/dmel-transcript.fa" />
181 <param name="database_type" value="dnax" /> 113 <param name="database_type" value="dnax" />
182 <param name="query_type" value="rnax" /> 114 <param name="query_type" value="rnax" />
183 <param name="oneOff" value="false" /> 115 <param name="noHead" value="yes" />
184 <param name="minScore" value="30" />
185 <param name="maxGap" value="2" />
186 <param name="trimT" value="false" />
187 <param name="noTrimA" value="false" />
188 <param name="fine" value="false" />
189 <param name="maxIntron" value="750000" />
190 <param name="extendThroughN" value="false" />
191 <param name="mask" value="file.out" /> 116 <param name="mask" value="file.out" />
192 <param name="mask_file" value="dbia3/dbia3_RM.out" /> 117 <param name="mask_file" value="dbia3/dbia3_RM.out" />
193 <param name="out" value="psl -noHead" /> 118 <output name="output_sorted" value="dbia3/dbia3_masked.sorted.psl" />
194 <output name="output" value="dbia3/dbia3_masked.sorted.psl"/>
195 </test> 119 </test>
196 120
197 </tests> 121 </tests>
198 <help> 122 <help>
199 <![CDATA[ 123 <![CDATA[
200 BLAT 124 BLAT
201 ==== 125 ====
202 BLAT is a bioinformatics software a tool which performs rapid mRNA/DNA and cross-species protein alignments. 126 BLAT is a bioinformatics software a tool which performs rapid mRNA/DNA and cross-species protein alignments.
203 127
204 blat (version: v36)- Standalone blat sequence search command line tool. 128 blat (version: v340)- Standalone blat sequence search command line tool.
205 ------------------------------------------------------------------------- 129 -------------------------------------------------------------------------
206 130
207 usage: 131 usage:
208 ++++++ 132 ++++++
209 133
213 database and query are each either a .fa, .nib or .2bit file, 137 database and query are each either a .fa, .nib or .2bit file,
214 or a list of these files with one file name per line. 138 or a list of these files with one file name per line.
215 -ooc=11.ooc tells the program to load over-occurring 11-mers from 139 -ooc=11.ooc tells the program to load over-occurring 11-mers from
216 an external file. This will increase the speed 140 an external file. This will increase the speed
217 by a factor of 40 in many cases, but is not required. 141 by a factor of 40 in many cases, but is not required.
218 output.psl is the name of the output file. 142 output.psl is the name of the output file.
219 143
220 documentation: 144 documentation:
221 ++++++++++++++ 145 ++++++++++++++
222 146
223 See Blat documentation (http://genome.ucsc.edu/goldenPath/help/blatSpec.html) 147 See Blat documentation (http://genome.ucsc.edu/goldenPath/help/blatSpec.html)
224 148
225 Source code: 149 Source code:
226 ++++++++++++ 150 ++++++++++++
227 151
228 http://hgdownload.cse.ucsc.edu/admin/exe/ 152 http://hgdownload.cse.ucsc.edu/admin/exe/
229 153
230 ]]></help> 154 ]]></help>
231 <citations> 155 <citations>
232 <citation type="doi">10.1101/gr.229202</citation> 156 <citation type="doi">10.1101/gr.229202</citation>
233 </citations> 157 </citations>
234 </tool> 158 </tool>
159
160
161
162
163