Mercurial > repos > iuc > polypolish

comparison polypolish.xml @ 1:bd2a15dbcea1 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/mesocentre-clermont-auvergne/galaxy-tools/tree/master/tools/polypolish commit afc3449a0b68d43fd1179543815dfe23b951e157
author iuc
date Fri, 20 Oct 2023 12:41:27 +0000
parents aaa868913641
children f355085dd2aa
comparison
equal deleted inserted replaced
0:aaa868913641 1:bd2a15dbcea1
12 ln -s '$input.fasta_file' input_data && 12 ln -s '$input.fasta_file' input_data &&
13 #*====================================== 13 #*======================================
14 For single SAM 14 For single SAM
15 ======================================*# 15 ======================================*#
16 #if $input.sam_data_type.sam_selector == 'single' 16 #if $input.sam_data_type.sam_selector == 'single'
17 #if $input.sam_data_type.single_sam.ext == 'unsorted.bam' 17 #if $input.sam_data_type.single_sam.is_of_type("unsorted.bam")
18 samtools view -h $input.sam_data_type.single_sam > input_sam && 18 samtools view -h $input.sam_data_type.single_sam > input_sam &&
19 #elif $input.sam_data_type.single_sam.ext == 'sam' 19 #elif $input.sam_data_type.single_sam.ext == 'sam'
20 ln -s $input.sam_data_type.single_sam input_sam && 20 ln -s $input.sam_data_type.single_sam input_sam &&
21 #else
22 echo "${input.sam_data_type.single_sam} not a sam/bam file"
21 #end if 23 #end if
22 polypolish input_data input_sam > '$polished_fasta' 24 polypolish input_data input_sam > '$polished_fasta'
23 #*====================================== 25 #*======================================
24 For paired SAM 26 For paired SAM
25 ======================================*# 27 ======================================*#
26 #elif $input.sam_data_type.sam_selector == 'paired' 28 #elif $input.sam_data_type.sam_selector == 'paired'
27 #if $input.sam_data_type.R1_sam.ext == 'unsorted.bam' 29 #if $input.sam_data_type.R1_sam.is_of_type("unsorted.bam")
28 samtools view -h $input.sam_data_type.R1_sam > sample_R1.sam && 30 samtools view -h $input.sam_data_type.R1_sam > sample_R1.sam &&
29 #elif $input.sam_data_type.R1_sam.ext == 'sam' 31 #elif $input.sam_data_type.R1_sam.ext == 'sam'
30 ln -s '$input.sam_data_type.R1_sam' sample_R1.sam && 32 ln -s '$input.sam_data_type.R1_sam' sample_R1.sam &&
33 #else
34 echo "${input.sam_data_type.single_sam} not a sam/bam file"
31 #end if 35 #end if
32 #if $input.sam_data_type.R2_sam.ext == 'unsorted.bam' 36 #if $input.sam_data_type.R2_sam.is_of_type("unsorted.bam")
33 samtools view -h $input.sam_data_type.R2_sam > sample_R2.sam && 37 samtools view -h $input.sam_data_type.R2_sam > sample_R2.sam &&
34 #elif $input.sam_data_type.R2_sam.ext == 'sam' 38 #elif $input.sam_data_type.R2_sam.ext == 'sam'
35 ln -s '$input.sam_data_type.R2_sam' sample_R2.sam && 39 ln -s '$input.sam_data_type.R2_sam' sample_R2.sam &&
40 #else
41 echo "${input.sam_data_type.single_sam} not a sam/bam file"
36 #end if 42 #end if
37 #if $input.sam_data_type.insert_filter.filter_select == 'filter' 43 #if $input.sam_data_type.insert_filter.filter_select == 'filter'
38 polypolish_insert_filter.py --low '$input.sam_data_type.insert_filter.low' 44 polypolish_insert_filter.py --low '$input.sam_data_type.insert_filter.low'
39 --high '$input.sam_data_type.insert_filter.high' 45 --high '$input.sam_data_type.insert_filter.high'
40 --in1 sample_R1.sam 46 --in1 sample_R1.sam
49 For multiple single-end SAM 55 For multiple single-end SAM
50 ======================================*# 56 ======================================*#
51 #elif $input.sam_data_type.sam_selector == 'multiple_single' 57 #elif $input.sam_data_type.sam_selector == 'multiple_single'
52 mkdir single_collection && 58 mkdir single_collection &&
53 #for $value, $single_sam in enumerate($input.sam_data_type.single_collection): 59 #for $value, $single_sam in enumerate($input.sam_data_type.single_collection):
54 #if $single_sam.ext == 'unsorted.bam' 60 #if $single_sam.is_of_type("unsorted.bam")
55 samtools view -h $single_sam > 'single_collection/$(single_sam.element_identifier).sam' && 61 samtools view -h $single_sam > 'single_collection/$(single_sam.element_identifier).sam' &&
56 #elif $single_sam.ext == 'sam' 62 #elif $single_sam.ext == 'sam'
57 ln -s $single_sam 'single_collection/$(single_sam.element_identifier).$(single_sam.ext)' && 63 ln -s $single_sam 'single_collection/$(single_sam.element_identifier).$(single_sam.ext)' &&
64 #else
65 echo "${single_sam} is not a sam/bam file"
58 #end if 66 #end if
59 #end for 67 #end for
60 polypolish input_data single_collection/*.sam > '$polished_fasta' 68 polypolish input_data single_collection/*.sam > '$polished_fasta'
61 #*====================================== 69 #*======================================
62 For multiple paired-end SAM 70 For multiple paired-end SAM
63 ======================================*# 71 ======================================*#
64 #elif $input.sam_data_type.sam_selector == "multiple_paired" 72 #elif $input.sam_data_type.sam_selector == "multiple_paired"
65 mkdir paired_collection && 73 mkdir paired_collection &&
66 #for $value, $paired_sam in enumerate($input.sam_data_type.paired_collection): 74 #for $value, $paired_sam in enumerate($input.sam_data_type.paired_collection):
67 #if $paired_sam.forward.ext == 'unsorted.bam' 75 #if $paired_sam.forward.is_of_type("unsorted.bam")
68 samtools view -h $paired_sam.forward > 'paired_collection/forward_input$(value)$(paired_sam.forward.element_identifier).sam' && 76 samtools view -h $paired_sam.forward > 'paired_collection/forward_input$(value)$(paired_sam.forward.element_identifier).sam' &&
69 #else 77 #else
70 ln -s '$paired_sam.forward' 'paired_collection/forward_input$(value)$(paired_sam.forward.element_identifier).sam' && 78 ln -s '$paired_sam.forward' 'paired_collection/forward_input$(value)$(paired_sam.forward.element_identifier).sam' &&
71 #end if 79 #end if
72 #if $paired_sam.reverse.ext == 'unsorted.bam' 80 #if $paired_sam.reverse.is_of_type("unsorted.bam")
73 samtools view -h $paired_sam.reverse > 'paired_collection/reverse_input$(value)$(paired_sam.reverse.element_identifier).sam' && 81 samtools view -h $paired_sam.reverse > 'paired_collection/reverse_input$(value)$(paired_sam.reverse.element_identifier).sam' &&
74 #else 82 #else
75 ln -s '$paired_sam.reverse' 'paired_collection/reverse_input$(value)$(paired_sam.reverse.element_identifier).sam' && 83 ln -s '$paired_sam.reverse' 'paired_collection/reverse_input$(value)$(paired_sam.reverse.element_identifier).sam' &&
76 #end if 84 #end if
77 #if $input.sam_data_type.insert_filter.filter_select == 'filter' 85 #if $input.sam_data_type.insert_filter.filter_select == 'filter'
133 <expand macro="filter_option"/> 141 <expand macro="filter_option"/>
134 </when> 142 </when>
135 </conditional> 143 </conditional>
136 </section> 144 </section>
137 <section name="options" title="Options" expanded="False"> 145 <section name="options" title="Options" expanded="False">
138 <param name="min_depth" argument="--min_depth" type="integer" min="0" value="5" label="Minimal depth" 146 <param argument="--min_depth" type="integer" min="0" value="5" label="Minimal depth"
139 help="A base must occur at least this many times in the pileup to be considered valid [default: 5]"/> 147 help="A base must occur at least this many times in the pileup to be considered valid [default: 5]"/>
140 <param name="fraction_invalid" argument="--fraction_invalid" type="float" min="0" value="0.2" max="1" label="Minimal invalid fraction" 148 <param argument="--fraction_invalid" type="float" min="0" value="0.2" max="1" label="Minimal invalid fraction"
141 help="A base must make up less than this fraction of the read depth to be considered invalid [default: 0.2]"/> 149 help="A base must make up less than this fraction of the read depth to be considered invalid [default: 0.2]"/>
142 <param name="max_errors" argument="--max_errors" type="integer" min="0" value="10" label="Number of mismatch/indels to ignore alignments" 150 <param argument="--max_errors" type="integer" min="0" value="10" label="Number of mismatch/indels to ignore alignments"
143 help="Ignore alignments with more than this many mismatches and indels [default: 10]"/> 151 help="Ignore alignments with more than this many mismatches and indels [default: 10]"/>
144 <param name="fraction_valid" argument="--fraction_valid" type="float" min="0" value="0.5" max="1" label="Minimal valid fraction" 152 <param argument="--fraction_valid" type="float" min="0" value="0.5" max="1" label="Minimal valid fraction"
145 help="A base must make up at least this fraction of the read depth to be considered valid [default: 0.5"/> 153 help="A base must make up at least this fraction of the read depth to be considered valid [default: 0.5"/>
146 <param name="keep_logfile" type="boolean" truevalue="true" falsevalue="false" label="Keep log file"/> 154 <param name="keep_logfile" type="boolean" truevalue="true" falsevalue="false" label="Keep log file"/>
147 <param name="debug" argument="--debug" type="boolean" truevalue="true" falsevalue="false" label="Keep per base information file"/> 155 <param argument="--debug" type="boolean" truevalue="true" falsevalue="false" label="Keep per base information file"/>
148 </section> 156 </section>
149 </inputs> 157 </inputs>
150 <outputs> 158 <outputs>
151 <data name="polished_fasta" format="fasta" label="${tool.name} on ${on_string}: polished fasta"/> 159 <data name="polished_fasta" format="fasta" label="${tool.name} on ${on_string}: polished fasta"/>
152 <data name="debug_file" format="tabular" label="${tool.name} on ${on_string}: Per base informations"> 160 <data name="debug_file" format="tabular" label="${tool.name} on ${on_string}: Per base informations">
341 <param name="fasta_file" value="contigs.fa"/> 349 <param name="fasta_file" value="contigs.fa"/>
342 <conditional name="sam_data_type"> 350 <conditional name="sam_data_type">
343 <param name="sam_selector" value="multiple_single"/> 351 <param name="sam_selector" value="multiple_single"/>
344 <param name="single_collection"> 352 <param name="single_collection">
345 <collection type="list"> 353 <collection type="list">
346 <element name="R1_sam" value="aligned_test_file/alignement_R1.bam" ftype="unsorted.bam"/> 354 <element name="R1_sam" value="aligned_test_file/alignement_R1.sam" ftype="sam"/>
347 <element name="R1_bis_sam" value="aligned_test_file/alignement_R1_bis.bam" ftype="unsorted.bam"/> 355 <element name="R1_bis_sam" value="aligned_test_file/alignement_R1_bis.sam" ftype="sam"/>
348 <element name="R1_ter_sam" value="aligned_test_file/alignement_R1_ter.bam" ftype="unsorted.bam"/> 356 <element name="R1_ter_sam" value="aligned_test_file/alignement_R1_ter.sam" ftype="sam"/>
349 </collection> 357 </collection>
350 </param> 358 </param>
351 </conditional> 359 </conditional>
352 </section> 360 </section>
353 <section name="options"> 361 <section name="options">
390 <param name="debug" value="false"/> 398 <param name="debug" value="false"/>
391 <param name="keep_logfile" value="false"/> 399 <param name="keep_logfile" value="false"/>
392 </section> 400 </section>
393 <output name="polished_fasta" value="polished.fasta"/> 401 <output name="polished_fasta" value="polished.fasta"/>
394 </test> 402 </test>
403 <!-- Test_12 Test with bam files -->
404 <test expect_num_outputs="1">
405 <section name="input">
406 <param name="fasta_file" value="contigs.fa"/>
407 <conditional name="sam_data_type">
408 <param name="sam_selector" value="single"/>
409 <param name="single_sam" value="aligned_test_file/alignement_R1.bam"/>
410 </conditional>
411 </section>
412 <output name="polished_fasta" value="polished.fasta"/>
413 </test>
414 <!-- Test_13 paired bam -->
415 <test expect_num_outputs="2">
416 <section name="input">
417 <param name="fasta_file" value="contigs.fa"/>
418 <conditional name="sam_data_type">
419 <param name="sam_selector" value="paired"/>
420 <param name="R1_sam" value="aligned_test_file/alignement_R1.bam"/>
421 <param name="R2_sam" value="aligned_test_file/alignement_R2.bam"/>
422 </conditional>
423 </section>
424 <section name="options">
425 <param name="debug" value="true"/>
426 <param name="keep_logfile" value="false"/>
427 </section>
428 <output name="polished_fasta" value="polished.fasta"/>
429 <output name="debug_file" value="debug_file_test_2.tsv"/>
430 </test>
395 </tests> 431 </tests>
396 <help><![CDATA[ 432 <help><![CDATA[
397 **What it does** 433 **What it does**
398 Polypolish is a tool for polishing genome assemblies with short reads. 434 Polypolish is a tool for polishing genome assemblies with short reads.
399 Polypolish uses SAM/BAM files where each read has been aligned to all possible locations (not just a single best location). 435 Polypolish uses SAM/BAM files where each read has been aligned to all possible locations (not just a single best location).
400 This allows it to repair errors in repeat regions that other alignment-based polishers cannot fix. 436 This allows it to repair errors in repeat regions that other alignment-based polishers cannot fix.
401 437
402 **Polypolish pipeline steps** 438 **Polypolish pipeline steps**
403 1. [Optional] Filter aligned reads 439 1. [Optional] Filter aligned reads
404 - Exclude some alignments based on their insert size 440 Exclude some alignments based on their insert size
405 - This should reduce the number of excessive alignments, particularly near the edges of repeat sequences, improving Polypolish's ability to fix errors in those regions. 441 This should reduce the number of excessive alignments,
442 particularly near the edges of repeat sequences, improving Polypolish's ability to fix errors in those regions.
406 2. Clean assembly with filtered reads 443 2. Clean assembly with filtered reads
444
407 445
408 **Inputs** 446 **Inputs**
409 Polypolish need SAM/BAM input format obtain from aligner with option to keep all possible location 447 Polypolish need SAM/BAM input format obtain from aligner with option to keep all possible location
410 Polypolish take on or more assembly as input fasta. 448 Polypolish take on or more assembly as input fasta.
411 It need also raw data reads in single or paired-end SAM/BAM format. 449 It need also raw data reads in single or paired-end SAM/BAM format.
412 You can use multiple aligned data to polish the same assembly. 450 You can use multiple aligned data to polish the same assembly.
413 **WARNING It can only work if multiple location information is available in sam/bam files** 451 **WARNING It can only work if multiple location information is available in sam/bam files**
414 For example using bwa mem to align raw data before use, you need : 452 For example using bwa mem to align raw data before use, you need :
415 1. To align each read data independantly (also for paired data) 453 1. To align each read data independantly (also for paired data)
416 2. Set the option "Output all alignments for single-ends or unpaired paired-ends" in Select analysis mode>Set input/output options 454 2. Set the option "Output all alignments for single-ends or unpaired paired-ends" in Select analysis mode>Set input/output options
417 - This allow multiple ailgnemnt output need to use polypolish 455 This allow multiple ailgnemnt output need to use polypolish
418
419
420 ]]></help> 456 ]]></help>
421 <expand macro="citations"/> 457 <expand macro="citations"/>
422 </tool> 458 </tool>