Mercurial > repos > mvdbeek > yaha

comparison yaha.xml @ 0:0c888a0686bb draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/yaha commit 15b31d03f0dbc59ec544d4ce5837ff03b6936c27-dirty
author mvdbeek
date Thu, 29 Dec 2016 14:51:49 -0500
parents
children 584220a3c520
comparison
equal deleted inserted replaced
-1:000000000000 0:0c888a0686bb
1 <tool id="yaha" name="yaha" version="0.1.83">
2 <description>fast and flexible long-read alignment with optimal breakpoint detection</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <requirements>
7 <requirement type="package" version="0.1.83">yaha</requirement>
8 <requirement type="package" version="0.6.5">sambamba</requirement>
9 </requirements>
10 <version_command><![CDATA[yaha 2>&1| head -n1]]></version_command>
11 <command detect_errors="aggressive"><![CDATA[
12 #if $reference_genome.reference_genome_source == "history" or "reference":
13 #if $reference_genome.reference_genome_source == "history":
14 ln -f -s "$reference_genome.history_item" genome.fa &&
15 #elif $reference_genome.reference_genome_source == "reference":
16 ln -f -s "$reference_genome.fasta_item" genome.fa &&
17 #end if
18 yaha -g genome.fa -H $reference_genome.maxHitsIndex -L $reference_genome.wordLenIndex -S $reference_genome.skipDistanceIndex &&
19 #set maxHitsIndex = "%s%s" % ("0" * (5 - len(str($reference_genome.maxHitsIndex))), $reference_genome.maxHitsIndex)
20 #set skipdist = $reference_genome.skipDistanceIndex if len(str($reference_genome.skipDistanceIndex)) > 1 else "0%s" % $reference_genome.skipDistanceIndex
21 #set wordLenIndex = $reference_genome.wordLenIndex if len(str($reference_genome.wordLenIndex)) > 1 else "0%s" % $reference_genome.wordLenIndex
22 #set index_path = "genome.X%s_%s_%sS" % ($wordLenIndex, $skipdist, $maxHitsIndex)
23 #else:
24 #pass ## augment with pre-built index if considered useful
25 #end if
26 yaha
27 -x '$index_path'
28 -q '$q'
29 $outformat stdout
30 -t \${GALAXY_SLOTS:-1}
31 -BW $BW
32 -G $G
33 -H $H
34 -M $M
35 -MD $MD
36 -P $P
37 -X $X
38 #if $ags.use_ags == "yes":
39 -AGS Y
40 -GEC $ags.GEC
41 -GOC $ags.GOC
42 -MS $ags.MS
43 -RC $ags.RC
44 #else:
45 -AGS N
46 #end if
47 #if $oqc.use_oqc == "yes":
48 -OQC Y
49 -BP $oqc.BP
50 -MGDP $oqc.MGDP
51 -MNO $oqc.MNO
52 #else:
53 -OQC N
54 #end if
55 #if $fbs.use_fbs == "yes":
56 -FBS Y
57 -PRL $fbs.PRL
58 -PSS $fbs.PSS
59 #else:
60 -FBS N
61 #end if
62 | sambamba view -S -f bam /dev/stdin | sambamba sort -o '$alignment' -l 6 -t \${GALAXY_SLOTS:-1} /dev/stdin
63 ]]></command>
64 <inputs>
65 <param type="data" argument="q" label="Fastq reads to align" format="fastqsanger" />
66 <conditional name="reference_genome">
67 <param help="Built-in references were created using default options" label="Source for the reference genome to align against" name="reference_genome_source" type="select">
68 <!-- Write a datamanager if prebuilt genomes are important
69 <option selected="True" value="indexed">Use a built-in index</option>
70 -->
71 <option value="history">Use a genome from history to build an index</option>
72 <option value="reference">Use a built-in genome to build an index</option>
73 </param>
74 <when value="indexed">
75 <param help="If your genome of interest is not listed, contact the Galaxy team" label="Select a reference genome" name="index" type="select">
76 <options from_data_table="yaha_indexes">
77 <filter column="2" type="sort_by" />
78 <validator message="No genomes are available for the selected input dataset" type="no_options" />
79 </options>
80 </param>
81 </when>
82 <when value="history">
83 <param format="fasta" label="Select the reference genome" name="history_item" type="data" />
84 <expand macro="index_parameter"/>
85 </when>
86 <when value="reference">
87 <param label="Select a reference genome" name="fasta_item" type="select">
88 <options from_data_table="fasta_indexes">
89 <filter column="2" type="sort_by"/>
90 </options>
91 </param>
92 <expand macro="index_parameter"/>
93 </when>
94 </conditional>
95 <param name="outformat" type="select" label="Produce alignment with softclipping?">
96 <option value="-osh">Produce alignment with hard clipping</option>
97 <option value="-oss">Produce alignment with soft clipping</option>
98 </param>
99 <param type="integer" argument="-BW" value="5" min="0" label="BandWidth" help="band size on each side of the diagonal of banded Smith Waterman" />
100 <param type="integer" argument="-G" value="50" min="0" label="maxGap" help="maximum indel size allowed with a single alignment" />
101 <param type="integer" argument="-H" value="650" min="1" max="65525" label="maxHits" help="maximum times a seed is in the reference before it is ignored as too repetitive. To take advantage of k-mer sampling, use the same value of maxHits during index creation and alignment." />
102 <param type="integer" argument="-M" value="25" min="0" label="minMatch" help="minimum number of bases in seeds to start an alignment" />
103 <param type="integer" argument="-MD" value="50" min="0" label="MaxDesert" help="maximum number of contiguous bases without a seed before alignmment is split" />
104 <param type="float" argument="-P" value="0.9" min="0" label="minPercent-identity" help="minimum matching/alignment-length for a query to be included in output" />
105 <param type="integer" argument="-X" value="25" min="0" label="Xdropoff" help="maximum score dropoff before terminating alignment extensions" />
106 <conditional name="ags">
107 <param name="use_ags" type="select" label="Use Affine Gap Scoring?">
108 <option value="yes" selected="True">Yes</option>
109 <option value="no">No</option>
110 </param>
111 <when value="yes">
112 <param argument="-GEC" type="integer" value="2" min="0" label="GapExtensionCost" help="cost for extending a gap (indel)"/>
113 <param argument="-GOC" type="integer" value="5" min="0" label="GapOpenCost" help="cost for starting a new gap (indel)"/>
114 <param argument="-MS" type="integer" value="1" min="0" label="MatchScore" help="score added for each matching base"/>
115 <param argument="-RC" type="integer" value="3" min="0" label="ReplacementCost" help="score subtracted for each mismatched base"/>
116 </when>
117 <when value="no">
118 </when>
119 </conditional>
120 <conditional name="oqc">
121 <param name="use_oqc" type="select" label="Use Optimal Query Coverage Algorithm?" help="">
122 <option value="yes" selected="True">Yes (Find a set of alignments are found that optimally cover the query, using the remaining options)</option>
123 <option value="no">No (Output all alignments meeting above criteria)</option>
124 </param>
125 <when value="yes">
126 <param argument="-BP" type="integer" value="5" min="0" label="BreakpointPenalty" help="penalty for inserting a breakpoint in split-read alignment"/>
127 <param argument="-MGDP" type="integer" value="5" min="0" label="MaxGenomicDistancePenalty"/>
128 <param argument="-MNO" type="integer" value="25" min="0" label="MinNonOverlap" help="minimum number of unshared bases required in each split alignment"/>
129 </when>
130 <when value="no">
131 </when>
132 </conditional>
133 <conditional name="fbs">
134 <param name="use_fbs" type="select" label="Use Filter By Similarity Algorithm?" help="">
135 <option value="yes" selected="False">Yes (Output alignments similar to best alignment found using OQC.)</option>
136 <option value="no">No</option>
137 </param>
138 <when value="yes">
139 <param argument="-PRL" type="float" value="0.9" min="0" max="1" label="PercentReciprocalLength" help="minimum ratio of overlapping length between similar alignment"/>
140 <param argument="-PSS" type="float" value="0.9" min="0" max="1" label="PercentSimilarScore" help="minimum ratio of scores between similar alignments"/>
141 </when>
142 <when value="no">
143 </when>
144 </conditional>
145 </inputs>
146 <outputs>
147 <data name="alignment" format="bam" />
148 </outputs>
149 <tests>
150 <test>
151 <param name="q" value="input.fastq" ftype="fastqsanger"/>
152 <param name="reference_genome_source" value="history"/>
153 <param name="history_item" value="phiX.fa" ftype="fasta"/>
154 <output name="alignment" value="alignment.bam" ftype="bam"/>
155 </test>
156 </tests>
157 <help><![CDATA[
158 Summary
159 -------
160
161 *yaha* is an open source, flexible, sensitive and accurate DNA aligner
162 designed for single-end reads. It supports three major modes of
163 operation:
164
165 1. The default “Optimal Query Coverage” (**-OQC**) mode reports the best
166 set of alignments that cover the length of each query.
167 2. Using “Filter By Similarity” (**-FBS**), along with the best set of
168 alignments, *yaha* will also output alignments that are highly
169 similar to an alignment in the best set.
170 3. Finally, *yaha* can output all the alignments found for each query.
171
172 The **-OQC** and **-FBS** modes are specifically tuned to form split
173 read mappings that can be used to accurately identify structural
174 variation events (deletions, duplications, insertions or inversions)
175 between the subject query and the reference genome.
176
177 Usage
178 -----
179
180 **OPTIONS:** Default values enclosed in square brackets []
181
182 ::
183
184 Input/Output Options:
185 -g FILE input genome file to use during index creation (FASTA or nib2)
186 -q FILE input file of sequence reads to align (FASTA or FASTQ) [STDIN]
187 -osh FILE output file for alignment output in SAM format with hard clipping(default) [STDOUT]
188 -oss FILE output file for alignment output in SAM format with soft clipping [STDOUT]
189 -x FILE reference index file to use during alignment
190 NOTE: At most one of -osh or -oss should be specified.
191
192 Index Creation Options:
193 -H INT maxHits: During index creation, seeds occuring more than maxHits times will be sampled [65565]
194 -L INT seedLength: Length of seed to use. During alignment, seed length is taken from index file [15]
195 -S INT Skipdistance: Number of bases to skip ahead before forming next seed [1]
196
197 General Alignment Options:
198 -BW INT BandWidth: band size on each side of the diagonal of banded Smith Waterman [5]
199 -G INT maxGap: maximum indel size allowed with a single alignment [50]
200 -H INT maxHits: maximum times a seed is in the reference before it is ignored as too repetitive [650]
201 -M INT minMatch: minimum number of bases in seeds to start an alignment [25]
202 -MD INT MaxDesert: maximum number of contiguous bases without a seed before alignmment is split [50]
203 -P REAL minPercent-identity: minimum matching/alignment-length for a query to be included in output [0.9]
204 -X INT Xdropoff: maximum score dropoff before terminating alignment extensions [25]
205 -t INT numThreads: number of threads used to parallel process reads [1]
206
207 Affine Gap Scoring Options:
208 If -AGS is off, a simple edit distance calculation is done.
209 If on, the remaining options are used:
210 -AGS BOOL (Y|N) controls use of Affine Gap Scoring [Y].
211 -GEC INT GapExtensionCost: cost for extending a gap (indel) [2]
212 -GOC INT GapOpenCost: cost for starting a new gap (indel) [5]
213 -MS INT MatchScore: score added for each matching base [1]
214 -RC INT ReplacementCost: score subtracted for each mismatched base [3]
215
216 Optimal Query Coverage Options:
217 If -OQC if off, all alignments meeting above criteria are output.
218 If -OQC is on, a set of alignments are found that optimally cover the query, using the remaining options.
219 -OQC BOOL (Y|N) controls use of the Optimal Query Coverage Algorithm.
220 -BP INT BreakpointPenalty: penalty for inserting a breakpoint in split-read alignment [5]
221 -MGDP INT MaxGenomicDistancePenalty (5)]
222 -MNO INT MinNonOverlap: minimum number of unshared bases required in each split alignment [minMatch]
223 NOTE: The total cost of adding a breakpoint in a split-read mapping is:
224 BP*MIN(MGDP, Log10(genomic distance between reference loci))
225
226 Filter By Similarity Options:
227 If -FBS is on, the remaining options are used. An alignemnt must satisfy BOTH criteria to be "similar".
228 -FBS BOOL (Y|N) controls output of alignments similar to best alignment found using OQC.
229 -PRL REAL PercentReciprocalLength: minimum ratio of overlapping length between similar alignemnt [0.9]
230 -PSS REAL PercentSimilarScore: minimum ratio of scores between similar alignments [0.9]
231
232 See the `User Guide <https://www.dropbox.com/s/7j758vpbaskcq20/YAHA_User_Guide.0.1.83.pdf?dl=0>`__
233 for more details on all options and their usage.
234
235 | **Written by:** Greg Faust (gf4ea@virginia.edu)
236 | `Ira Hall Lab, University of
237 Virginia <http://faculty.virginia.edu/irahall/>`__
238
239 | **Please cite:**
240 | `Faust G.G. and Hall I.M., "*YAHA*: fast and flexible long-read
241 alignment with optimal breakpoint detection," *Bioinformatics* Oct.
242 2012; **28**\ (19):
243 2417-2424. <http://bioinformatics.oxfordjournals.org/content/28/19/2417>`__
244 ]]></help>
245 <citations>
246 <citation type="doi">10.1093/bioinformatics/bts456</citation>
247 </citations>
248 </tool>