comparison hifiasm.xml @ 4:3f7be05a1597 draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/hifiasm commit 8d76914ac4407512b1691a1ddd3d95dda6c80962"
author bgruening
date Wed, 22 Sep 2021 21:13:59 +0000
parents 9ef6920c3089
children 045c7c3d8e59
comparison
equal deleted inserted replaced
3:9ef6920c3089 4:3f7be05a1597
1 <tool id="hifiasm" name="Hifiasm" version="@VERSION@+galaxy0"> 1 <tool id="hifiasm" name="Hifiasm" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
2 <description>haplotype-resolved de novo assembler for PacBio Hifi reads</description> 2 <description>haplotype-resolved de novo assembler for PacBio Hifi reads</description>
3 <macros> 3 <macros>
4 <token name="@VERSION@">0.15.4</token> 4 <token name="@TOOL_VERSION@">0.16.1</token>
5 <token name="@VERSION_SUFFIX@">0</token>
5 <token name="@FORMATS@">fasta,fasta.gz,fastq,fastq.gz</token> 6 <token name="@FORMATS@">fasta,fasta.gz,fastq,fastq.gz</token>
6 <xml name="reads"> 7 <xml name="reads">
7 <param name="reads" type="data" format="@FORMATS@" multiple="true" label="Input reads" /> 8 <param name="reads" type="data" format="@FORMATS@" multiple="true" label="Input reads" />
8 </xml> 9 </xml>
9 </macros> 10 </macros>
10 <requirements> 11 <requirements>
11 <requirement type="package" version="@VERSION@">hifiasm</requirement> 12 <requirement type="package" version="@TOOL_VERSION@">hifiasm</requirement>
12 <requirement type="package" version="0.1">yak</requirement> 13 <requirement type="package" version="0.1">yak</requirement>
13 </requirements> 14 </requirements>
14 <version_command>hifiasm --version</version_command> 15 <version_command>hifiasm --version</version_command>
15 <command detect_errors="exit_code"> 16 <command detect_errors="exit_code">
16 17
51 -N $advanced_options.max_overlaps 52 -N $advanced_options.max_overlaps
52 -r $advanced_options.correction_rounds 53 -r $advanced_options.correction_rounds
53 #if $advanced_options.min_hist_cnt: 54 #if $advanced_options.min_hist_cnt:
54 --min-hist-cnt $advanced_options.min_hist_cnt 55 --min-hist-cnt $advanced_options.min_hist_cnt
55 #end if 56 #end if
57 --max-kocc $advanced_options.max_kocc
58 #if $advanced_options.hg_size
59 --hg-size $advanced_options.hg_size
60 #end if
61
56 #end if 62 #end if
57 #if str($assembly_options.assembly_selector) == 'set': 63 #if str($assembly_options.assembly_selector) == 'set':
58 -a $assembly_options.cleaning_rounds 64 -a $assembly_options.cleaning_rounds
59 -z $assembly_options.adapter_length 65 -z $assembly_options.adapter_length
60 -m $assembly_options.pop_contigs 66 -m $assembly_options.pop_contigs
62 -n $assembly_options.remove_tips 68 -n $assembly_options.remove_tips
63 -x $assembly_options.max_overlap 69 -x $assembly_options.max_overlap
64 -y $assembly_options.min_overlap 70 -y $assembly_options.min_overlap
65 $assembly_options.disable_post_join 71 $assembly_options.disable_post_join
66 $assembly_options.ignore_error_corrected 72 $assembly_options.ignore_error_corrected
73 #if $assembly_options.hom_cov
74 --hom-cov $assembly_options.hom_cov
75 #end if
67 #end if 76 #end if
68 #if str($mode.mode_selector) == 'trio': 77 #if str($mode.mode_selector) == 'trio':
69 -1 hap1.yak 78 -1 hap1.yak
70 -2 hap2.yak 79 -2 hap2.yak
71 -c $mode.max_kmers 80 -c $mode.max_kmers
73 #end if 82 #end if
74 #if str($purge_options.purge_selector) == 'set': 83 #if str($purge_options.purge_selector) == 'set':
75 -l $purge_options.purge_level 84 -l $purge_options.purge_level
76 -s $purge_options.similarity_threshold 85 -s $purge_options.similarity_threshold
77 -O $purge_options.minimum_overlap 86 -O $purge_options.minimum_overlap
78 #if $purge_options.purge_cov: 87 #if $purge_options.purge_max:
79 --purge-cov $purge_options.purge_cov 88 --purge-max $purge_options.purge_max
80 #end if 89 #end if
81 #if $purge_options.n_hap: 90 #if $purge_options.n_hap:
82 --n-hap $purge_options.n_hap 91 --n-hap $purge_options.n_hap
83 #end if 92 #end if
84 #end if 93 #end if
133 <option value="blank">Leave default</option> 142 <option value="blank">Leave default</option>
134 <option value="set">Specify</option> 143 <option value="set">Specify</option>
135 </param> 144 </param>
136 <when value="blank" /> 145 <when value="blank" />
137 <when value="set"> 146 <when value="set">
138 <param name="hifiasm_kmer_length" argument="-k" type="integer" min="0" max="64" value="51" label="HiFiasm k-mer length" /> 147 <param name="hifiasm_kmer_length" argument="-k" type="integer" min="0" max="64" value="51" label="Hifiasm k-mer length" />
139 <param name="window_size" argument="-w" type="integer" min="0" value="51" label="Minimizer window size" /> 148 <param name="window_size" argument="-w" type="integer" min="0" value="51" label="Minimizer window size" />
140 <param name="drop_kmers" argument="-D" type="float" value="5.0" label="Drop k-mers" help="K-mers that occur more than this value multiplied by the coverage will be discarded" /> 149 <param name="drop_kmers" argument="-D" type="float" value="5.0" label="Drop k-mers" help="K-mers that occur more than this value multiplied by the coverage will be discarded" />
141 <param name="max_overlaps" argument="-N" type="integer" value="100" label="Maximum overlaps to consider" help="The software selects the larger of this value and the k-mer count multiplied by coverage" /> 150 <param name="max_overlaps" argument="-N" type="integer" value="100" label="Maximum overlaps to consider" help="The software selects the larger of this value and the k-mer count multiplied by coverage" />
142 <param name="correction_rounds" argument="-r" type="integer" value="3" label="Correction rounds" /> 151 <param name="correction_rounds" argument="-r" type="integer" value="3" label="Correction rounds" />
143 <param argument="--min-hist-cnt" type="integer" min="0" value="" optional="true" label="Minimum count threshold" help="When analyzing the k-mer spectrum, ignore counts below this value" /> 152 <param argument="--min-hist-cnt" type="integer" min="0" value="" optional="true" label="Minimum count threshold" help="When analyzing the k-mer spectrum, ignore counts below this value" />
153 <param argument="--max-kocc" type="integer" min="0" value="20000" label="Maximum k-mer ocurrence" help="Employ k-mers occurring less than INT times to rescue repetitive overlaps" />
154 <param argument="--hg-size" type="text" value="" optional="true" label="Estimated haploid genome size" help="Estimated haploid genome size used for inferring read coverage. If not provided, this parameter will be infered by hifism. Common suffices are required, for example, 100m or 3g">
155 <sanitizer invalid_char="">
156 <valid initial="string.digits">
157 <add value="k" />
158 <add value="K" />
159 <add value="m" />
160 <add value="M" />
161 <add value="G" />
162 <add value="g" />
163 </valid>
164 </sanitizer>
165 <validator type="regex">[0-9kKmMGg]+</validator>
166 </param>
144 </when> 167 </when>
145 </conditional> 168 </conditional>
146 169
147 <conditional name="assembly_options"> 170 <conditional name="assembly_options">
148 <param name="assembly_selector" type="select" label="Assembly options"> 171 <param name="assembly_selector" type="select" label="Assembly options">
158 <param name="remove_tips" argument="-n" type="integer" value="3" label="Tip unitigs" help="Keep only tip unitigs with a number of reads greater than or equal to this value" /> 181 <param name="remove_tips" argument="-n" type="integer" value="3" label="Tip unitigs" help="Keep only tip unitigs with a number of reads greater than or equal to this value" />
159 <param name="max_overlap" argument="-x" type="float" min="0" max="1" value="0.8" label="Maximum overlap drop ratio" help="This option is used with -r. Given a node N in the assembly graph, let max(N) be the length of the largest overlap of N. Hifiasm iteratively drops overlaps of N if their length/max(N) are below a threshold controlled by -x. Hifiasm applies -r rounds of short overlap removal with an increasing threshold between -x and -y"/> 182 <param name="max_overlap" argument="-x" type="float" min="0" max="1" value="0.8" label="Maximum overlap drop ratio" help="This option is used with -r. Given a node N in the assembly graph, let max(N) be the length of the largest overlap of N. Hifiasm iteratively drops overlaps of N if their length/max(N) are below a threshold controlled by -x. Hifiasm applies -r rounds of short overlap removal with an increasing threshold between -x and -y"/>
160 <param name="min_overlap" argument="-y" type="float" min="0" max="1" value="0.2" label="Minimum overlap drop ratio" help="This option is used with -r. Given a node N in the assembly graph, let max(N) be the length of the largest overlap of N. Hifiasm iteratively drops overlaps of N if their length/max(N) are over a threshold controlled by -y. Hifiasm applies -r rounds of short overlap removal with an increasing threshold between -x and -y"/> 183 <param name="min_overlap" argument="-y" type="float" min="0" max="1" value="0.2" label="Minimum overlap drop ratio" help="This option is used with -r. Given a node N in the assembly graph, let max(N) be the length of the largest overlap of N. Hifiasm iteratively drops overlaps of N if their length/max(N) are over a threshold controlled by -y. Hifiasm applies -r rounds of short overlap removal with an increasing threshold between -x and -y"/>
161 <param name="disable_post_join" argument="-u" type="boolean" truevalue="-u" falsevalue="" label="Skip post join contigs step" help="May improve N50" /> 184 <param name="disable_post_join" argument="-u" type="boolean" truevalue="-u" falsevalue="" label="Skip post join contigs step" help="May improve N50" />
162 <param name="ignore_error_corrected" argument="-i" type="boolean" truevalue="-i" falsevalue="" value="False" label="Ignore error corrected reads and overlaps" help="Ignore error corrected reads and overlaps saved in prefix.*.bin files. Apart from assembly graphs, hifiasm also outputs three binary files that save alloverlap information during assembly step. With these files, hifiasm can avoid the time-consuming all-to-all overlap calculation step, and do the assembly directly and quickly. This might be helpful when users want to get an optimized assembly by multiple rounds of experiments with different parameters." /> 185 <param name="ignore_error_corrected" argument="-i" type="boolean" truevalue="-i" falsevalue="" value="False" label="Ignore error corrected reads and overlaps" help="Ignore error corrected reads and overlaps saved in prefix.*.bin files. Apart from assembly graphs, hifiasm also outputs three binary files that save alloverlap information during assembly step. With these files, hifiasm can avoid the time-consuming all-to-all overlap calculation step, and do the assembly directly and quickly. This might be helpful when users want to get an optimized assembly by multiple rounds of experiments with different parameters." />
186 <param argument="--hom-cov" type="integer" optional="True" value="" label="Homozygous read coverage" />
163 </when> 187 </when>
164 </conditional> 188 </conditional>
165 189
166 <conditional name="purge_options"> 190 <conditional name="purge_options">
167 <param name="purge_selector" type="select" label="Options for purging duplicates"> 191 <param name="purge_selector" type="select" label="Options for purging duplicates">
176 <option value="2">Aggressive (2)</option> 200 <option value="2">Aggressive (2)</option>
177 <option value="3">Aggressive - high heterozygosity rate (3)</option> 201 <option value="3">Aggressive - high heterozygosity rate (3)</option>
178 </param> 202 </param>
179 <param name="similarity_threshold" argument="-s" type="float" min="0" max="1" value="0.75" label="Similarity threshold for duplicate haplotigs" /> 203 <param name="similarity_threshold" argument="-s" type="float" min="0" max="1" value="0.75" label="Similarity threshold for duplicate haplotigs" />
180 <param name="minimum_overlap" argument="-O" type="integer" value="1" label="Minimum overlapped reads for duplicate haplotigs" /> 204 <param name="minimum_overlap" argument="-O" type="integer" value="1" label="Minimum overlapped reads for duplicate haplotigs" />
181 <param argument="--purge-cov" type="integer" optional="true" label="Coverage upper bound" help="If not set, this will be determined automatically" /> 205 <param argument="--purge-max" type="integer" optional="true" label="Coverage upper bound" help="If not set, this will be determined automatically" />
182 <param argument="--n-hap" type="integer" min="0" value="" optional="True" label="Assumtion of haplotype number" help="A haplotype is defined as the combination of alleles for different polymorphisms that occur on the same chromosome." /> 206 <param argument="--n-hap" type="integer" min="0" value="" optional="true" label="Assumtion of haplotype number" help="A haplotype is defined as the combination of alleles for different polymorphisms that occur on the same chromosome." />
183 </when> 207 </when>
184 </conditional> 208 </conditional>
185 209
186 <conditional name="hic_partition"> 210 <conditional name="hic_partition">
187 <param name="hic_partition_selector" type="select" label="Options for Hi-C-partition"> 211 <param name="hic_partition_selector" type="select" label="Options for Hi-C-partition">
384 <assert_contents> 408 <assert_contents>
385 <has_size value="0"/> 409 <has_size value="0"/>
386 </assert_contents> 410 </assert_contents>
387 </output> 411 </output>
388 </test> 412 </test>
413 <!-- Test max_kooc option -->
414 <test>
415 <param name="reads" value="hifiasm-in1.fa.gz" ftype="fasta.gz" />
416 <param name="filter_bits" value="0" />
417 <param name="mode_selector" value="standard" />
418 <conditional name="advanced_options">
419 <param name="advanced_selector" value="set"/>
420 <param name="max_kooc" value="21000"/>
421 </conditional>
422 <output name="raw_unitigs" file="hifiasm-out6-raw.gfa" ftype="gfa1" />
423 <output name="processed_unitigs" file="hifiasm-out6-processed.gfa" ftype="gfa1" />
424 <output name="primary_contig_graph" file="hifiasm-out6-primary.gfa" ftype="gfa1" />
425 <output name="alternate_contig_graph" ftype="gfa1">
426 <assert_contents>
427 <has_size value="0"/>
428 </assert_contents>
429 </output>
430 </test>
431 <!-- Test hg-size option -->
432 <test>
433 <param name="reads" value="hifiasm-in1.fa.gz" ftype="fasta.gz" />
434 <param name="filter_bits" value="0" />
435 <param name="mode_selector" value="standard" />
436 <conditional name="advanced_options">
437 <param name="advanced_selector" value="set"/>
438 <param name="hg_size" value="1k"/>
439 </conditional>
440 <output name="raw_unitigs" file="hifiasm-out7-raw.gfa" ftype="gfa1" />
441 <output name="processed_unitigs" file="hifiasm-out7-processed.gfa" ftype="gfa1" />
442 <output name="primary_contig_graph" file="hifiasm-out7-primary.gfa" ftype="gfa1" />
443 <output name="alternate_contig_graph" ftype="gfa1">
444 <assert_contents>
445 <has_size value="0"/>
446 </assert_contents>
447 </output>
448 </test>
449 <!-- Test ignore-error-corrected option -->
450 <test>
451 <param name="reads" value="hifiasm-in1.fa.gz" ftype="fasta.gz" />
452 <param name="filter_bits" value="0" />
453 <param name="mode_selector" value="standard" />
454 <conditional name="assembly_options">
455 <param name="assembly_selector" value="set"/>
456 <param name="hom-cov" value="1000"/>
457 </conditional>
458 <output name="raw_unitigs" file="hifiasm-out8-raw.gfa" ftype="gfa1" />
459 <output name="processed_unitigs" file="hifiasm-out8-processed.gfa" ftype="gfa1" />
460 <output name="primary_contig_graph" file="hifiasm-out8-primary.gfa" ftype="gfa1" />
461 <output name="alternate_contig_graph" ftype="gfa1">
462 <assert_contents>
463 <has_size value="0"/>
464 </assert_contents>
465 </output>
466 </test>
389 </tests> 467 </tests>
390 <help><![CDATA[ 468 <help><![CDATA[
391 *********************************** 469 ***********************************
392 HiFiASM - a fast de novo assembler 470 HiFiASM - a fast de novo assembler
393 *********************************** 471 ***********************************