comparison contains.xml @ 1:2c1cb37a3ffe draft

planemo upload for repository https://github.com/phac-nml/refseq_masher commit e83730c5df84a960af58ff09db7eb09d11df2398
author nml
date Wed, 08 May 2019 09:15:56 -0400
parents 26df66c32861
children 1ec42f033bb4
comparison
equal deleted inserted replaced
0:26df66c32861 1:2c1cb37a3ffe
1 <tool id="refseq_masher_contains" name="RefSeq Masher Contains" version="0.1.1"> 1 <tool id="refseq_masher_contains" name="RefSeq Masher Contains" version="0.1.2">
2 <description> 2 <description>
3 Find NCBI RefSeq Genomes contained in your sequences 3 Find NCBI RefSeq Genomes contained in your sequences
4 </description> 4 </description>
5 <requirements> 5 <requirements>
6 <requirement type="package" version="0.1.1">refseq_masher</requirement> 6 <requirement type="package" version="0.1.1">refseq_masher</requirement>
7 </requirements> 7 </requirements>
8 <command detect_errors="exit_code"> 8 <command detect_errors="exit_code">
9 <![CDATA[ 9 <![CDATA[
10 10
11 #import re 11 #import re
12 #import os
12 13
13 #if $input.type == 'fasta' 14 #if $input.type == 'fasta'
14 #set $input_files = '"{}"'.format($input.fasta.name) 15 #set $input_files = '"{}.fasta"'.format(os.path.splitext($input.fasta.name)[0])
15 ln -s "$input.fasta" $input_files && 16 ln -s "$input.fasta" $input_files &&
16 #elif $input.type == 'paired' 17 #elif $input.type == 'paired'
17 #set $_forward_ext = '.fastq.gz' if $re.match(r'.*\.gz$', $input.forward.name) else '.fastq' 18 #set $_forward_ext = '.fastq.gz' if $re.match(r'.*\.gz$', $input.forward.name) else '.fastq'
18 #set $_forward = '"{}_1{}"'.format($re.sub(r'_[12]\..+$', '', $input.forward.name), $_forward_ext) 19 #set $_forward = '"{}_1{}"'.format($re.sub(r'_[12]\..+$', '', $input.forward.name), $_forward_ext)
19 #set $_reverse_ext = '.fastq.gz' if $re.match(r'.*\.gz$', $input.reverse.name) else '.fastq' 20 #set $_reverse_ext = '.fastq.gz' if $re.match(r'.*\.gz$', $input.reverse.name) else '.fastq'
169 =========================== 170 ===========================
170 171
171 Find what NCBI RefSeq genomes are contained within your sequence data using Mash_ with a Mash sketch database of 54,925 NCBI RefSeq Genomes. 172 Find what NCBI RefSeq genomes are contained within your sequence data using Mash_ with a Mash sketch database of 54,925 NCBI RefSeq Genomes.
172 173
173 174
174 Source code available on Github at https://github.com/phac-nml/refseq_masher 175 Source code available on Github at github.com/phac-nml/refseq_masher
175 176
176 177
177 `contains` - find what NCBI RefSeq Genomes are contained in your input sequences 178 `contains` - find what NCBI RefSeq Genomes are contained in your input sequences
178 -------------------------------------------------------------------------------- 179 --------------------------------------------------------------------------------
179 180
215 Design, Setting and Patients Forty-five samples were selected from a set of fecal specimens obtained from patients with diarrhea during the 2011 outbreak of STEC O104:H4 in Germany. Samples were chosen to represent STEC-positive patients with a range of clinical conditions and colony counts together with a small number of patients with other infections (Campylobacter jejnuni, Clostridium difficile and Salmonella enterica). Samples were subjected to high-throughput sequencing on the Illumina MiSeq and HiSeq 2500, followed by bioinformatics analysis. 216 Design, Setting and Patients Forty-five samples were selected from a set of fecal specimens obtained from patients with diarrhea during the 2011 outbreak of STEC O104:H4 in Germany. Samples were chosen to represent STEC-positive patients with a range of clinical conditions and colony counts together with a small number of patients with other infections (Campylobacter jejnuni, Clostridium difficile and Salmonella enterica). Samples were subjected to high-throughput sequencing on the Illumina MiSeq and HiSeq 2500, followed by bioinformatics analysis.
216 217
217 218
218 We're going to download the FASTQ files for ERR260489_:: 219 We're going to download the FASTQ files for ERR260489_::
219 220
220 wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR260/ERR260489/ERR260489_1.fastq.gz 221 wget ftp.sra.ebi.ac.uk/vol1/fastq/ERR260/ERR260489/ERR260489_1.fastq.gz
221 wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR260/ERR260489/ERR260489_2.fastq.gz 222 wget ftp.sra.ebi.ac.uk/vol1/fastq/ERR260/ERR260489/ERR260489_2.fastq.gz
222 223
223 224
224 We're going to run `refseq_masher` against these FASTQ files:: 225 We're going to run `refseq_masher` against these FASTQ files::
225 226
226 refseq_masher -vv contains --top-n-results 50 -p 12 -o containment-ERR260489.tab ERR260489_1.fastq.gz ERR260489_2.fastq.gz 227 refseq_masher -vv contains --top-n-results 50 -p 12 -o containment-ERR260489.tab ERR260489_1.fastq.gz ERR260489_2.fastq.gz
293 294
294 Licensed under the Apache License, Version 2.0 (the "License"); you may not use 295 Licensed under the Apache License, Version 2.0 (the "License"); you may not use
295 this work except in compliance with the License. You may obtain a copy of the 296 this work except in compliance with the License. You may obtain a copy of the
296 License at: 297 License at:
297 298
298 http://www.apache.org/licenses/LICENSE-2.0 299 www.apache.org/licenses/LICENSE-2.0
299 300
300 Unless required by applicable law or agreed to in writing, software distributed 301 Unless required by applicable law or agreed to in writing, software distributed
301 under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR 302 under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
302 CONDITIONS OF ANY KIND, either express or implied. See the License for the 303 CONDITIONS OF ANY KIND, either express or implied. See the License for the
303 specific language governing permissions and limitations under the License. 304 specific language governing permissions and limitations under the License.
307 308
308 **Gary van Domselaar**: gary.vandomselaar@phac-aspc.gc.ca 309 **Gary van Domselaar**: gary.vandomselaar@phac-aspc.gc.ca
309 310
310 311
311 312
312 .. _Mash: https://genomebiology.biomedcentral.com/articles/10.1186/s13059-016-0997-x 313 .. _Mash: genomebiology.biomedcentral.com/articles/10.1186/s13059-016-0997-x
313 .. _SAMEA1877340: https://www.ebi.ac.uk/ena/data/view/SAMEA1877340 314 .. _SAMEA1877340: www.ebi.ac.uk/ena/data/view/SAMEA1877340
314 .. _PRJEB1775: https://www.ebi.ac.uk/ena/data/view/PRJEB1775 315 .. _PRJEB1775: www.ebi.ac.uk/ena/data/view/PRJEB1775
315 .. _ERR260489: https://www.ebi.ac.uk/ena/data/view/ERR260489&display=html 316 .. _ERR260489: www.ebi.ac.uk/ena/data/view/ERR260489&display=html
316 317
317 ]]> 318 ]]>
318 </help> 319 </help>
319 <citations> 320 <citations>
320 <!-- Citation for Mash paper --> 321 <!-- Citation for Mash paper -->