Mercurial > repos > jdv > porechop

comparison porechop.xml @ 0:6b572c4f2ce1 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/jvolkening/galaxy-tools/tree/master/tools/porechop commit bf5788ad5a3293446a50a3246b44ba09174c9b71
author jdv
date Wed, 30 Aug 2017 02:45:08 -0400
parents
children 3cf98e7f21b7
comparison
equal deleted inserted replaced
-1:000000000000 0:6b572c4f2ce1
1 <tool id="porechop" name="Porechop" version="0.2.1">
2
3 <description>Demux and adapter removal of ONT reads</description>
4
5 <!-- ***************************************************************** -->
6
7 <!-- not yet working with Bioconda
8 <requirements>
9 <requirement type="package" version="0.2.1">porechop</requirement>
10 </requirements>
11 -->
12
13 <!-- ***************************************************************** -->
14
15 <version_command>porechop --version</version_command>
16
17 <!-- ***************************************************************** -->
18
19 <command detect_errors="aggressive">
20 <![CDATA[
21
22 #set filename = str($input.name)
23
24 mkdir out &&
25
26 porechop
27
28 --input ${input}
29
30 #if str($demux_section.demux_options.demux) == "yes":
31 --barcode_dir out
32 #else:
33 --output "out/$filename"
34 #end if
35
36 ##if $input.is_of_type('fastq')
37 --format fastq
38 ##else:
39 ##--format fasta
40 ##end if
41
42 --threads \${GALAXY_SLOTS:-1}
43
44 ##--Demultiplex Options--------------------------
45
46 #if str($demux_section.demux_options.demux) == "yes":
47
48 --barcode_threshold $demux_section.demux_options.barcode_threshold
49 --barcode_diff $demux_section.demux_options.barcode_diff
50 $demux_section.demux_options.require_two_barcodes
51
52 #end if
53
54 ##--Adapter Trim Options--------------------------
55
56 #if str($trim_section.trim_options.trim) == "yes":
57
58 --adapter_threshold $trim_section.trim_options.adapter_threshold
59 --check_reads $trim_section.trim_options.check_reads
60 --scoring_scheme $trim_section.trim_options.scoring_scheme
61
62 --end_size $trim_section.trim_options.end_size
63 --end_threshold $trim_section.trim_options.end_threshold
64 --min_trim_size $trim_section.trim_options.min_trim_size
65 --extra_end_trim $trim_section.trim_options.extra_end_trim
66
67 $trim_section.trim_options.discard_middle
68 --middle_threshold $trim_section.trim_options.middle_threshold
69 --extra_middle_trim_good_side $trim_section.trim_options.extra_middle_trim_good_side
70 --extra_middle_trim_bad_side $trim_section.trim_options.extra_middle_trim_bad_side
71 --min_split_read_size $trim_section.trim_options.min_split_read_size
72
73
74 #else:
75 --untrimmed
76
77 #end if
78
79 ]]>
80 </command>
81
82 <!-- ***************************************************************** -->
83
84 <inputs>
85
86 <param argument="--input" type="data" format="fastq,fasta" label="Input reads" />
87
88 <section name="demux_section" title="Demultiplexing Options" expanded="True">
89 <conditional name="demux_options">
90 <param name="demux" type="select" label="Perform demultiplexing" help="">
91 <option value="no" selected="true">no</option>
92 <option value="yes">yes</option>
93 </param>
94 <when value="no" />
95 <when value="yes">
96 <param argument="--barcode_threshold" size="5" type="float" value="75.0" min="0" max="100" label="Barcode threshold identity" />
97 <param argument="--barcode_diff" size="5" type="float" value="5.0" min="0" max="100" label="Barcode threshold difference" />
98 <param argument="--require_two_barcodes" type="boolean" truevalue="--require_two_barcodes" falsevalue="" checked="false" label="Require two barcodes" />
99 </when>
100 </conditional>
101 </section>
102
103 <section name="trim_section" title="Trimming Options" expanded="True">
104 <conditional name="trim_options">
105 <param name="trim" type="select" label="Perform adapter trimming" help="">
106 <option value="no" selected="true">no</option>
107 <option value="yes">yes</option>
108 </param>
109 <when value="no" />
110 <when value="yes">
111 <param argument="--adapter_threshold" size="4" type="float" value="90.0" min="0" max="100" label="Adapter set threshold identity" />
112 <param argument="--check_reads" size="7" type="integer" value="10000" label="Number of reads to check to determine adapter sets" />
113 <param argument="--barcode_diff" size="4" type="float" value="5.0" min="0" max="100" label="Barcode threshold difference" />
114 <param argument="--scoring_scheme" type="text" value="3,-6,-5,-2" label="Scoring scheme" />
115 <param argument="--end_size" size="4" type="integer" value="150" label="Number of terminal bases to search" />
116 <param argument="--min_trim_size" size="4" type="integer" value="4" label="Minimum adapter match length" />
117 <param argument="--extra_end_trim" size="4" type="integer" value="2" label="Adjacent bases to trim " />
118 <param argument="--end_threshold" size="4" type="float" value="75.0" min="0" max="100" label="End adapter trim threshold identity" />
119
120 <param argument="--discard_middle" type="boolean" truevalue="--discard_middle" falsevalue="" checked="false" label="Discard reads with middle adapters" />
121 <param argument="--middle_threshold" size="4" type="float" value="85.0" min="0" max="100" label="Middle adapter trim threshold identity" />
122 <param argument="--extra_middle_trim_good_side" size="4" type="integer" value="10" label="Adjacent bases to trim on good side" />
123 <param argument="--extra_middle_trim_bad_side" size="4" type="integer" value="100" label="Adjacent bases to trim on bad side" />
124 <param argument="--min_split_read_size" size="4" type="integer" value="1000" label="Minimum length of split reads to keep" />
125 </when>
126 </conditional>
127 </section>
128
129 </inputs>
130
131 <!-- ***************************************************************** -->
132
133 <outputs>
134
135 <collection type="list" name="output">
136 <discover_datasets pattern="(?P&lt;name&gt;.*)" directory="out" format="fastq" />
137 </collection>
138
139 </outputs>
140
141 <!-- ***************************************************************** -->
142
143 <tests>
144 <test>
145 <param name="input" value="test_barcodes.fastq" ftype="fastq" />
146 <param name="demux" value="yes" />
147 <output_collection name="output" type="list">
148 <element name="BC01.fastq" file="bar1/BC01.fastq" compare="diff" decompress="true"/>
149 <element name="BC02.fastq" file="bar1/BC02.fastq" compare="diff" decompress="true"/>
150 <element name="BC03.fastq" file="bar1/BC03.fastq" compare="diff" decompress="true"/>
151 <element name="none.fastq" file="bar1/none.fastq" compare="diff" decompress="true"/>
152 </output_collection>
153 </test>
154 <test>
155 <param name="input" value="test_barcodes.fastq" ftype="fastq" />
156 <param name="demux" value="yes" />
157 <param name="require_two_barcodes" value="True" />
158 <output_collection name="output" type="list">
159 <element name="BC01.fastq" file="bar2/BC01.fastq" compare="diff" decompress="true"/>
160 <element name="BC02.fastq" file="bar2/BC02.fastq" compare="diff" decompress="true"/>
161 <element name="BC03.fastq" file="bar2/BC03.fastq" compare="diff" decompress="true"/>
162 <element name="none.fastq" file="bar2/none.fastq" compare="diff" decompress="true"/>
163 </output_collection>
164 </test>
165 <test>
166 <param name="input" value="test_barcodes.fastq" ftype="fastq" />
167 <param name="demux" value="yes" />
168 <param name="trim" value="yes" />
169 <output_collection name="output" type="list">
170 <element name="BC01.fastq" file="bar1_trim/BC01.fastq" compare="diff" decompress="true"/>
171 <element name="BC02.fastq" file="bar1_trim/BC02.fastq" compare="diff" decompress="true"/>
172 <element name="BC03.fastq" file="bar1_trim/BC03.fastq" compare="diff" decompress="true"/>
173 <element name="none.fastq" file="bar1_trim/none.fastq" compare="diff" decompress="true"/>
174 </output_collection>
175 </test>
176 </tests>
177
178 <!-- ***************************************************************** -->
179
180 <help>
181 <![CDATA[
182
183 **Description**
184
185 Porechop is a tool for finding and removing adapters from Oxford Nanopore
186 reads. Adapters on the ends of reads are trimmed off, and when a read has an
187 adapter in its middle, it is treated as chimeric and chopped into separate
188 reads. Porechop performs thorough alignments to effectively find adapters,
189 even at low sequence identity.
190
191 Porechop also supports demultiplexing of Nanopore reads that were barcoded
192 with the Native Barcoding Kit, PCR Barcoding Kit or Rapid Barcoding Kit.
193
194 **Options**
195 ::
196
197 *** Barcode binning settings ***
198
199 -b BARCODE_DIR, --barcode_dir BARCODE_DIR
200 Reads will be binned based on their barcode and saved to separate
201 files in this directory (incompatible with --output)
202 --barcode_threshold BARCODE_THRESHOLD
203 A read must have at least this percent identity to a barcode to be
204 binned (default: 75.0)
205 --barcode_diff BARCODE_DIFF If the difference between a read's best barcode identity and its
206 second-best barcode identity is less than this value, it will not be
207 put in a barcode bin (to exclude cases which are too close to call)
208 (default: 5.0)
209 --require_two_barcodes Reads will only be put in barcode bins if they have a strong match for
210 the barcode on both their start and end (default: a read can be binned
211 with a match at its start or end)
212 --untrimmed Bin reads but do not trim the ends (appropriate if reads are to be
213 used with Nanopolish) (default: False)
214
215 *** Adapter search settings ***
216
217 --adapter_threshold ADAPTER_THRESHOLD
218 An adapter set has to have at least this percent identity to be
219 labelled as present and trimmed off (0 to 100) (default: 90.0)
220 --check_reads CHECK_READS This many reads will be aligned to all possible adapters to determine
221 which adapter sets are present (default: 10000)
222 --scoring_scheme SCORING_SCHEME Comma-delimited string of alignment scores: match,mismatch, gap open,
223 gap extend (default: 3,-6,-5,-2)
224
225 *** End adapter settings ***
226
227 --end_size END_SIZE The number of base pairs at each end of the read which will be
228 searched for adapter sequences (default: 150)
229 --min_trim_size MIN_TRIM_SIZE Adapter alignments smaller than this will be ignored (default: 4)
230 --extra_end_trim EXTRA_END_TRIM This many additional bases will be removed next to adapters found at
231 the ends of reads (default: 2)
232 --end_threshold END_THRESHOLD Adapters at the ends of reads must have at least this percent identity
233 to be removed (0 to 100) (default: 75.0)
234
235 *** Middle adapter settings ***
236
237 --discard_middle Reads with middle adapters will be discarded (default: reads with
238 middle adapters are split) (this option is on by default when
239 outputting reads into barcode bins)
240 --middle_threshold MIDDLE_THRESHOLD
241 Adapters in the middle of reads must have at least this percent
242 identity to be found (0 to 100) (default: 85.0)
243 --extra_middle_trim_good_side EXTRA_MIDDLE_TRIM_GOOD_SIDE
244 This many additional bases will be removed next to middle adapters on
245 their "good" side (default: 10)
246 --extra_middle_trim_bad_side EXTRA_MIDDLE_TRIM_BAD_SIDE
247 This many additional bases will be removed next to middle adapters on
248 their "bad" side (default: 100)
249 --min_split_read_size MIN_SPLIT_READ_SIZE
250 Post-split read pieces smaller than this many base pairs will not be
251 outputted (default: 1000)
252
253
254 ]]>
255 </help>
256
257 <!-- ***************************************************************** -->
258
259 <citations>
260 </citations>
261
262 </tool>