Mercurial > repos > nml > quasitools
comparison hydra.xml @ 9:18aad692772a draft default tip
planemo upload for repository https://github.com/phac-nml/quasitools commit 5a9e4c9a582828654893166caf20576f5e0c418e
author | nml |
---|---|
date | Mon, 20 Jun 2022 20:06:36 +0000 |
parents | 9def47f3c1e4 |
children |
comparison
equal
deleted
inserted
replaced
8:9def47f3c1e4 | 9:18aad692772a |
---|---|
1 <tool id="hydra" name="Hydra pipeline" version="0.5.1"> | 1 <tool id="hydra" name="Hydra pipeline" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"> |
2 <description>Identifies drug resistance within an NGS dataset</description> | 2 <description>Identifies drug resistance within an NGS dataset</description> |
3 <requirements> | 3 <macros> |
4 <requirement type="package" version="0.5.1">quasitools</requirement> | 4 <import>macros.xml</import> |
5 </requirements> | 5 </macros> |
6 <expand macro="requirements"/> | |
6 <command detect_errors="exit_code"><![CDATA[ | 7 <command detect_errors="exit_code"><![CDATA[ |
7 | 8 |
8 quasitools hydra | 9 quasitools hydra |
9 | 10 |
10 ## Preparing file input. | 11 ## Preparing file input. |
179 <data format="bam" label="HyDRA: alignment bam output" name="output_bam" from_work_dir="output/align.bam" /> | 180 <data format="bam" label="HyDRA: alignment bam output" name="output_bam" from_work_dir="output/align.bam" /> |
180 <data format="csv" label="HyDRA: coverage output" name="output_coverage" from_work_dir="output/coverage_file.csv" /> | 181 <data format="csv" label="HyDRA: coverage output" name="output_coverage" from_work_dir="output/coverage_file.csv" /> |
181 <data format="csv" label="HyDRA: drug resistance output" name="output_dr" from_work_dir="output/dr_report.csv" /> | 182 <data format="csv" label="HyDRA: drug resistance output" name="output_dr" from_work_dir="output/dr_report.csv" /> |
182 <data format="fastq" label="HyDRA: filtered reads output" name="output_filtered" from_work_dir="output/filtered.fastq" /> | 183 <data format="fastq" label="HyDRA: filtered reads output" name="output_filtered" from_work_dir="output/filtered.fastq" /> |
183 <data format="vcf" label="HyDRA: variants output" name="output_hydra" from_work_dir="output/hydra.vcf" /> | 184 <data format="vcf" label="HyDRA: variants output" name="output_hydra" from_work_dir="output/hydra.vcf" /> |
184 <data format="vcf" label="HyDRA: aa mutations output" name="output_aa_mt" from_work_dir="output/mutation_report.hmcf" /> | 185 <data format="txt" label="HyDRA: aa mutations output" name="output_aa_mt" from_work_dir="output/mutation_report.aavf" /> |
185 <data format="txt" label="HyDRA: stats output" name="output_stats" from_work_dir="output/stats.txt" /> | 186 <data format="txt" label="HyDRA: stats output" name="output_stats" from_work_dir="output/stats.txt" /> |
186 <data format="fasta" label="HyDRA: consensus output" name="output_consensus" from_work_dir="output/consensus.fasta" > | 187 <data format="fasta" label="HyDRA: consensus output" name="output_consensus" from_work_dir="output/consensus.fasta" > |
187 <filter>consensus['consensus_bool'] == "true_consensus"</filter> | 188 <filter>consensus['consensus_bool'] == "true_consensus"</filter> |
188 </data> | 189 </data> |
189 </outputs> | 190 </outputs> |
219 <has_text_matching expression="hxb2_pol\s958\s.\sc\sa\s100\sPASS\sDP=2503;AC=28;AF=0.0112" /> | 220 <has_text_matching expression="hxb2_pol\s958\s.\sc\sa\s100\sPASS\sDP=2503;AC=28;AF=0.0112" /> |
220 </assert_contents> | 221 </assert_contents> |
221 </output> | 222 </output> |
222 <output name="output_aa_mt"> | 223 <output name="output_aa_mt"> |
223 <assert_contents> | 224 <assert_contents> |
224 <has_text_matching expression="#CHROM\sGENE\sTYPE\sWILDTYPE\sPOS\sMUTANT\sFILTER\sMUTANT_FREQ\sCOVERAGE\sINFO"/> | 225 <has_text_matching expression="#CHROM\tGENE\tPOS\tREF\tALT\tFILTER\tALT_FREQ\tCOVERAGE\tINFO"/> |
225 <has_text_matching expression="hxb2_pol\sRT\smutation\sK\s101\sP\sPASS\s0.1423\s1574\sWC=aaa;MC=CCa;MCF=0.1423;CAT=NNRTI;SRVL=Yes" /> | 226 <has_text_matching expression="hxb2_pol\tRT\t101\tK\tP\tPASS\t0.1423\t1574\tRC=aaa;AC=CCa;ACF=0.1423;CAT=NNRTI;SRVL=Yes" /> |
226 <has_text_matching expression="hxb2_pol\sRT\smutation\sH\s221\sN\sPASS\s0.0113\s2475\sWC=cat;MC=Aat;MCF=0.0113;CAT=.;SRVL=." /> | 227 <has_text_matching expression="hxb2_pol\tRT\t101\tK\tT\tmf0.01\t0.0013\t1574\tRC=aaa;AC=aCa;ACF=0.0013;CAT=.;SRVL=." /> |
227 </assert_contents> | 228 </assert_contents> |
228 </output> | 229 </output> |
229 | 230 |
230 <output name="output_stats"> | 231 <output name="output_stats"> |
231 <assert_contents> | 232 <assert_contents> |
278 * align.bam | 279 * align.bam |
279 * coverage_file.csv | 280 * coverage_file.csv |
280 * dr_report.csv | 281 * dr_report.csv |
281 * filtered.fastq | 282 * filtered.fastq |
282 * hydra.vcf | 283 * hydra.vcf |
283 * mutation_report.hmcf | 284 * mutation_report.aavf |
284 * stats.txt | 285 * stats.txt |
285 | 286 |
286 The description of each of these directories/files are as follows: | 287 The description of each of these directories/files are as follows: |
287 | 288 |
288 * __run.conf__: The configuration used when this output was produced. | 289 * __run.conf__: The configuration used when this output was produced. |
290 * __align.bam__: The alignment file in bam format. | 291 * __align.bam__: The alignment file in bam format. |
291 * __coverage_file.csv__: A file with one entry per line with the AA position and the coverage at the position. | 292 * __coverage_file.csv__: A file with one entry per line with the AA position and the coverage at the position. |
292 * __dr_report.csv__: A report detailing the drug resistant mutations found, above the reporting threshold (default: 1%). | 293 * __dr_report.csv__: A report detailing the drug resistant mutations found, above the reporting threshold (default: 1%). |
293 * __filtered.fastq__: The reads remaining after the filtering stage. | 294 * __filtered.fastq__: The reads remaining after the filtering stage. |
294 * __hydra.vcf__: The variants found by the pipeline. | 295 * __hydra.vcf__: The variants found by the pipeline. |
295 * __mutation_report.hmcf__: The AA mutations found by the pipeline. | 296 * __mutation_report.aavf__: The AA mutations found by the pipeline. |
296 * __stats.txt__: A log file detailing size after filtering and major stages. | 297 * __stats.txt__: A log file detailing size after filtering and major stages. |
297 | 298 |
298 The __dr_report.csv__ file lists all found drug resistant mutations (mutations included in the mutation database) which have frequency greater than the reporting threshold. An example of this file is given below. | 299 The __dr_report.csv__ file lists all found drug resistant mutations (mutations included in the mutation database) which have frequency greater than the reporting threshold. An example of this file is given below. |
299 | 300 |
300 Example: __dr_report.csv__ | 301 Example: __dr_report.csv__ |
301 | 302 |
302 Gene,Category,Surveillance,Wildtype,Position,Mutation,Mutation Frequency,Coverage | 303 Gene,Category,Surveillance,Wildtype,Position,Mutation,Mutation Frequency,Coverage |
303 RT,NNRTI,Yes,K,103,N,9.03,155 | 304 RT,NNRTI,Yes,K,103,N,9.03,155 |
304 | 305 |
305 The __mutation_report.hmcf__ files is our custom VCF like file which details all of the AA mutations found by the pipeline. An example if this file is given below. | 306 The __mutation_report.aavf__ file is in AAVF format (https://github.com/winhiv/aavf-spec), an amino acid variant format inspired by the VCF format. The __mutation_report.aavf__ file details all of the AA mutations found by the pipeline. An example if this file is given below. |
306 | 307 |
307 Example: __mutation_report.hmcf__ | 308 Example: __mutation_report.aavf__ |
308 | 309 |
309 ##fileformat=HMCFv1 | 310 ##fileformat=AAVFv1.0 |
310 ##fileDate=20150008 | 311 ##fileDate=20220615 |
311 ##source=HyDRA | 312 ##source=quasitools:hydra |
312 ##reference=/home/ericenns/hydra/var/hxb2_pol.fas | 313 ##reference=hxb2_pol.fas |
313 ##INFO=<ID=MC,Number=.,Description="String"> | 314 ##INFO=<ID=RC,Number=1,Type=String,Description="Reference Codon"> |
314 ##INFO=<ID=MCF,Number=.,Description="String"> | 315 ##INFO=<ID=AC,Number=.,Type=String,Description="Alternate Codon"> |
315 ##INFO=<ID=WC,Number=.,Description="String"> | 316 ##INFO=<ID=ACF,Number=.,Type=Float,Description="Alternate Codon Frequency,for each Alternate Codon,in the same order aslisted."> |
316 ##FILTER=<ID=mf0.01,Description="Mutant freq below 0.01"> | 317 ##INFO=<ID=CAT,Number=.,Type=String,Description="Drug Resistance Category"> |
317 #GENE CATEGORY SURVEILLANCE TYPE WILDTYPE POS MUTANT FILTER MUTANT_FREQ COVERAGE INFO | 318 ##INFO=<ID=SRVL,Number=.,Type=String,Description="Drug Resistance Surveillance"> |
318 RT NNRTI Yes mutation K 103 N PASS 0.0903 155 WC=aaa;MC=aaC;MCF=0.0903 | 319 ##FILTER=<ID=af0.01,Description="Set if True; alt_freq<0.01"> |
320 #CHROM GENE POS REF ALT FILTER ALT_FREQ COVERAGE INFO | |
321 hxb2_pol RT 101 K P PASS 0.1423 1574 RC=aaa;AC=CCa;ACF=0.1423;CAT=NNRTI;SRVL=Yes | |
319 | 322 |
320 ]]></help> | 323 ]]></help> |
321 <citations> | 324 <expand macro="citations" /> |
322 <citation type="bibtex"> | |
323 @misc{GitHubquasitoolshydra, | |
324 title = {quasitools hydra}, | |
325 publisher = {phac-nml}, | |
326 journal = {GitHub repository}, | |
327 url = {https://github.com/phac-nml/quasitools}, | |
328 } | |
329 </citation> | |
330 </citations> | |
331 </tool> | 325 </tool> |