Mercurial > repos > iuc > sra_tools

comparison fastq_dump.xml @ 26:f7732611d0fc draft default tip

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/sra-tools commit 7632986831e24fcd189a57d824b9e6b1d5dc5c4c
author iuc
date Mon, 26 Aug 2024 14:59:07 +0000
parents 6669afa92957
children
comparison
equal deleted inserted replaced
25:0c5a5e670ac0 26:f7732611d0fc
10 <command detect_errors="exit_code"><![CDATA[ 10 <command detect_errors="exit_code"><![CDATA[
11 @COPY_CONFIGFILE@ 11 @COPY_CONFIGFILE@
12 @SET_ACCESSIONS@ 12 @SET_ACCESSIONS@
13 13
14 #if $input.input_select == "sra_file": 14 #if $input.input_select == "sra_file":
15 fastq-dump --log-level fatal --accession '${input.file.name}' 15 fastq-dump --log-level fatal --accession "\$acc"
16 #else: 16 #else:
17 ## Do not use prefetch if region is specified, to avoid downloading 17 ## Do not use prefetch if region is specified, to avoid downloading
18 ## the complete sra file. 18 ## the complete sra file.
19 #if ( str( $adv.region ) == "" ) and ( str( $adv.minID ) == "" ) and ( str( $adv.maxID ) == "" ): 19 #if ( str( $adv.region ) == "" ) and ( str( $adv.minID ) == "" ) and ( str( $adv.maxID ) == "" ):
20 prefetch -X 200000000 "\$acc" && 20 prefetch -X 200000000 "\$acc" &&
21 #end if 21 #end if
22 fastq-dump --accession "\$acc" 22 fastq-dump --accession "\$acc"
23 --split-files 23 #end if
24 #end if 24 --split-files
25 --defline-seq '@\$sn[_\$rn]/\$ri' 25 --defline-seq '$adv.defline_seq'
26 --defline-qual '+' 26 --defline-qual '+'
27 27
28 $adv.split 28 $adv.split
29 #if str( $adv.alignments ) == "aligned": 29 #if str( $adv.alignments ) == "aligned":
30 --aligned 30 --aligned
89 <option value="fastqsanger.gz">gzip compressed fastq</option> 89 <option value="fastqsanger.gz">gzip compressed fastq</option>
90 <option value="fastqsanger">Uncompressed fastq</option> 90 <option value="fastqsanger">Uncompressed fastq</option>
91 <option value="fastqsanger.bz2">bzip2 compressed fastq</option> 91 <option value="fastqsanger.bz2">bzip2 compressed fastq</option>
92 </param> 92 </param>
93 <section name="adv" title="Advanced Options" expanded="False"> 93 <section name="adv" title="Advanced Options" expanded="False">
94 <expand macro="defline" defline_param="--defline-seq" defline_default="@$ac.$sn[_$rn]/$ri"/>
94 <param name="minID" type="integer" label="Minimum spot ID" optional="true" help="Minimum spot id to be dumped." argument="--minSpotId"/> 95 <param name="minID" type="integer" label="Minimum spot ID" optional="true" help="Minimum spot id to be dumped." argument="--minSpotId"/>
95 <param name="maxID" type="integer" label="Maximum spot ID" optional="true" help="Maximum spot id to be dumped." argument="--maxSpotId"/> 96 <param name="maxID" type="integer" label="Maximum spot ID" optional="true" help="Maximum spot id to be dumped." argument="--maxSpotId"/>
96 <param name="minlen" type="integer" label="Minimum read length" optional="true" help="Filter by sequence length. Will dump only reads longer or equal to this value." argument="--minReadLen"/> 97 <param name="minlen" type="integer" label="Minimum read length" optional="true" help="Filter by sequence length. Will dump only reads longer or equal to this value." argument="--minReadLen"/>
97 <param name="split" type="boolean" checked="true" truevalue="--split-spot" falsevalue="" label="Split spot by read pairs" help="Split spots into individual reads." argument="--split-spot"/> 98 <param name="split" type="boolean" checked="true" truevalue="--split-spot" falsevalue="" label="Split spot by read pairs" help="Split spots into individual reads." argument="--split-spot"/>
98 <expand macro="alignments"/> 99 <expand macro="alignments"/>
223 <element name="forward" file="SRR11953971_1.fastq.gz" ftype="fastqsanger.gz" decompress="True"/> 224 <element name="forward" file="SRR11953971_1.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
224 <element name="reverse" file="SRR11953971_2.fastq.gz" ftype="fastqsanger.gz" decompress="True"/> 225 <element name="reverse" file="SRR11953971_2.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
225 </element> 226 </element>
226 </output_collection> 227 </output_collection>
227 </test> 228 </test>
229 <test expect_num_outputs="2">
230 <param name="input_select" value="accession_number"/>
231 <param name="outputformat" value="fastqsanger.gz"/>
232 <param name="accession" value="ERR086330, SRR11953971"/>
233 <section name="adv">
234 <param name="defline_seq" value="@$ac.$si/$ri $sn length=$rl"/>
235 </section>
236 <output_collection name="list_paired" type="list:paired" count="2">
237 <element name="ERR086330">
238 <element name="forward" ftype="fastqsanger.gz" decompress="True">
239 <assert_contents>
240 <!-- decompressed content assertions only work from 23.1
241 therefore we test for size being at least one byte
242 larger than the results of the previous test which
243 uses the shorter default deflines
244 TODO replace has_size by has_line-->
245 <has_size min="147"/>
246 <!-- <has_line line="@ERR086330.1/1 1 length=76"/> -->
247 </assert_contents>
248 </element>
249 <element name="reverse" ftype="fastqsanger.gz" decompress="True">
250 <assert_contents>
251 <has_size min="141"/>
252 <!-- <has_line line="@ERR086330.1/2 1 length=76"/> -->
253 </assert_contents>
254 </element>
255 </element>
256 <element name="SRR11953971">
257 <element name="forward" ftype="fastqsanger.gz" decompress="True">
258 <assert_contents>
259 <has_size min="56206"/>
260 <!-- <has_line line="@SRR11953971.1/1 1 length=101"/> -->
261 </assert_contents>
262 </element>
263 <element name="reverse" ftype="fastqsanger.gz" decompress="True">
264 <assert_contents>
265 <has_size min="59843"/>
266 <!-- <has_line line="@SRR11953971.1/2 1 length=101"/> -->
267 </assert_contents>
268 </element>
269 </element>
270 </output_collection>
271 </test>
272 <test expect_num_outputs="2">
273 <param name="input_select" value="sra_file"/>
274 <param name="sra_file" value="SRR522874.sra"/>
275 <param name="split" value="True"/>
276 <param name="skip_technical" value="True"/>
277 <section name="adv">
278 <param name="defline_seq" value="@$sn/$ri"/>
279 </section>
280 <output_collection name="list_paired" type="list:paired" count="1">
281 <element name="SRR522874.sra">
282 <element name="forward" file="SRR522874.sra_2_1.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
283 <element name="reverse" file="SRR522874.sra_4_1.fastq.gz" ftype="fastqsanger.gz" decompress="True"/>
284 </element>
285 </output_collection>
286 </test>
228 </tests> 287 </tests>
229 <help><![CDATA[ 288 <help><![CDATA[
230 **What it does?** 289 **What it does?**
231 290
232 This tool extracts data (in fastq_ format) from the Short Read Archive (SRA) at the National Center for Biotechnology Information (NCBI). It is based on the fasterq-dump_ utility of the SRA Toolkit. The following applies: 291 This tool extracts data (in fastq_ format) from the Short Read Archive (SRA) at the National Center for Biotechnology Information (NCBI). It is based on the fasterq-dump_ utility of the SRA Toolkit. The following applies: