Mercurial > repos > bgruening > hifiasm

comparison hifiasm.xml @ 0:bf0a4667e3ce draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/hifiasm commit a118fad06e94683813e214af107fedd5fd80500a"
author bgruening
date Tue, 02 Mar 2021 20:23:49 +0000
parents
children 6505bd37670d
comparison
equal deleted inserted replaced
-1:000000000000 0:bf0a4667e3ce
1 <tool id="hifiasm" name="Hifiasm" version="@VERSION@">
2 <description>de novo assembler</description>
3 <macros>
4 <token name="@VERSION@">0.14</token>
5 <token name="@FORMATS@">fasta,fasta.gz,fastq,fastq.gz</token>
6 <xml name="reads">
7 <param name="reads" type="data" format="@FORMATS@" label="Input reads" />
8 </xml>
9 </macros>
10 <requirements>
11 <requirement type="package" version="@VERSION@">hifiasm</requirement>
12 <requirement type="package" version="0.1">yak</requirement>
13 </requirements>
14 <version_command>hifiasm --version</version_command>
15 <command detect_errors="exit_code">
16 <![CDATA[
17 #if str($mode.mode_selector) == 'standard':
18 ln -s '$mode.reads' input.${mode.reads.extension} &&
19 #else:
20 ln -s '$mode.hap1_reads' hap1_reads.${mode.hap1_reads.extension} &&
21 ln -s '$mode.hap2_reads' hap2_reads.${mode.hap2_reads.extension} &&
22 yak count -k31 -b37 -t\${GALAXY_SLOTS:-1} -o hap1.yak hap1_reads.${mode.hap1_reads.extension} &&
23 yak count -k31 -b37 -t\${GALAXY_SLOTS:-1} -o hap2.yak hap2_reads.${mode.hap2_reads.extension} &&
24 #end if
25 hifiasm -i input.${mode.reads.extension} -t \${GALAXY_SLOTS:-1} -o output -f $filter_bits
26 #if str($advanced_options.advanced_selector) == 'set':
27 -z $advanced_options.adapter_length
28 -k $advanced_options.kmer_length
29 -w $advanced_options.window_size
30 -D $advanced_options.drop_kmers
31 -N $advanced_options.max_overlaps
32 -r $advanced_options.correction_rounds
33 #end if
34 #if str($assembly_options.assembly_selector) == 'set':
35 -a $assembly_options.cleaning_rounds
36 -m $assembly_options.pop_contigs
37 -p $assembly_options.pop_unitigs
38 -n $assembly_options.remove_tips
39 -x $assembly_options.max_overlap
40 -y $assembly_options.min_overlap
41 $assembly_options.disable_post_join
42 --pb-range $assembly_options.pb_range
43 #end if
44 #if str($mode.mode_selector) == 'trio':
45 -1 hap1.yak
46 -2 hap2.yak
47 -c $mode.max_kmers
48 -d $mode.min_kmers
49 #end if
50 #if str($purge_options.purge_selector) == 'set':
51 -l $purge_options.purge_level
52 -s $purge_options.similarity_threshold
53 -O $purge_options.minimum_overlap
54 #if $purge_options.purge_cov:
55 --purge-cov $purge_options.purge_cov
56 #end if
57 $purge_options.high_het
58 #end if
59 ]]>
60 </command>
61 <inputs>
62 <conditional name="mode">
63 <param name="mode_selector" type="select" label="Assembly mode">
64 <option value="standard">Standard</option>
65 <option value="trio">Trio mode</option>
66 </param>
67 <when value="standard">
68 <expand macro="reads" />
69 </when>
70 <when value="trio">
71 <expand macro="reads" />
72 <param name="hap1_reads" type="data" format="fastq,fastq.gz" label="Haplotype 1 reads" />
73 <param name="hap2_reads" type="data" format="fastq,fastq.gz" label="Haplotype 2 reads" />
74 <param name="max_kmers" argument="-c" type="integer" value="2" label="Lower bound of the binned k-mer's frequency" />
75 <param name="min_kmers" argument="-d" type="integer" value="5" label="Upper bound of the binned k-mer's frequency" />
76 </when>
77 </conditional>
78 <param name="filter_bits" argument="-f" type="integer" min="0" value="37" label="Bits for bloom filter" help="A value of 0 disables the bloom filter" />
79 <conditional name="advanced_options">
80 <param name="advanced_selector" type="select" label="Advanced options">
81 <option value="blank">Leave default</option>
82 <option value="set">Specify</option>
83 </param>
84 <when value="blank" />
85 <when value="set">
86 <param name="adapter_length" argument="-z" type="integer" min="0" value="0" label="Length of adapters to be removed" />
87 <param name="kmer_length" argument="-k" type="integer" min="0" max="64" value="51" label="K-mer length" />
88 <param name="window_size" argument="-w" type="integer" min="0" value="51" label="Minimizer window size" />
89 <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" />
90 <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" />
91 <param name="correction_rounds" argument="-r" type="integer" value="3" label="Correction rounds" />
92 </when>
93 </conditional>
94 <conditional name="assembly_options">
95 <param name="assembly_selector" type="select" label="Assembly options">
96 <option value="blank">Leave default</option>
97 <option value="set">Specify</option>
98 </param>
99 <when value="blank" />
100 <when value="set">
101 <param name="cleaning_rounds" argument="-a" type="integer" value="4" label="Cleaning rounds" />
102 <param name="pop_contigs" argument="-m" type="integer" value="10000000" label="Minimum contig bubble size" help="Pop contig graph bubbles smaller than this value" />
103 <param name="pop_unitigs" argument="-p" type="integer" value="100000" label="Minimum unitig bubble size" help="Pop unitig graph bubbles smaller than this value" />
104 <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" />
105 <param name="max_overlap" argument="-x" type="float" min="0" max="1" value="0.8" label="Maximum overlap drop ratio" />
106 <param name="min_overlap" argument="-y" type="float" min="0" max="1" value="0.2" label="Minimum overlap drop ratio" />
107 <param name="disable_post_join" argument="-u" type="boolean" truevalue="-u" falsevalue="" label="Skip post join contigs step" help="May improve N50" />
108 <param argument="--pb-range" type="integer" min="0" max="100" value="0" label="Inconsistent contigs" help="If this option is set to a value greater than zero the tool generates an additional BED dataset containing regions that are &gt;= x% inconsistent." />
109 </when>
110 </conditional>
111 <conditional name="purge_options">
112 <param name="purge_selector" type="select" label="Options for purging duplicates">
113 <option value="blank">Leave default</option>
114 <option value="set">Specify</option>
115 </param>
116 <when value="blank" />
117 <when value="set">
118 <param name="purge_level" argument="-l" type="select" label="Purge level">
119 <option value="0" selected="true">None</option>
120 <option value="1">Light</option>
121 <option value="2">Aggressive</option>
122 </param>
123 <param name="similarity_threshold" argument="-s" type="float" min="0" max="1" value="0.75" label="Similarity threshold for duplicate haplotigs" />
124 <param name="minimum_overlap" argument="-O" type="integer" value="1" label="Minimum overlapped reads for duplicate haplotigs" />
125 <param argument="--purge-cov" type="integer" optional="true" label="Coverage upper bound" help="If not set, this will be determined automatically" />
126 <param argument="--high-het" type="boolean" truevalue="--high-het" falsevalue="" label="Experimental high-heterozygosity mode" help="NB: May be unstable" />
127 </when>
128 </conditional>
129 </inputs>
130 <outputs>
131 <data name="raw_unitigs" format="gfa1" from_work_dir="output.r_utg.gfa" label="${tool.name} on ${on_string} Haplotype-resolved raw unitig graph">
132 <filter>mode['mode_selector'] == 'standard'</filter>
133 </data>
134 <data name="raw_unitigs" format="gfa1" from_work_dir="output.dip.r_utg.gfa" label="${tool.name} on ${on_string} Haplotype-resolved raw unitig graph">
135 <filter>mode['mode_selector'] == 'trio'</filter>
136 </data>
137 <data name="processed_unitigs" format="gfa1" from_work_dir="output.p_utg.gfa" label="${tool.name} on ${on_string} Processed unitig graph">
138 <filter>mode['mode_selector'] == 'standard'</filter>
139 </data>
140 <data name="primary_contig_graph" format="gfa1" from_work_dir="output.p_ctg.gfa" label="${tool.name} on ${on_string} Primary assembly contig graph">
141 <filter>mode['mode_selector'] == 'standard'</filter>
142 </data>
143 <data name="alternate_contig_graph" format="gfa1" from_work_dir="output.a_ctg.gfa" label="${tool.name} on ${on_string} Alternate assembly contig graph">
144 <filter>mode['mode_selector'] == 'standard'</filter>
145 </data>
146 <data name="hap1_contigs" format="gfa1" from_work_dir="output.hap1.p_ctg.gfa" label="${tool.name} ${mode.hap1_reads.name} contig graph">
147 <filter>mode['mode_selector'] == 'trio'</filter>
148 </data>
149 <data name="hap2_contigs" format="gfa1" from_work_dir="output.hap2.p_ctg.gfa" label="${tool.name} ${mode.hap2_reads.name} contig graph">
150 <filter>mode['mode_selector'] == 'trio'</filter>
151 </data>
152 </outputs>
153 <tests>
154 <test>
155 <param name="reads" value="hifiasm-in1.fa.gz" ftype="fasta.gz" />
156 <param name="filter_bits" value="0" />
157 <param name="mode_selector" value="standard" />
158 <output name="raw_unitigs" file="hifiasm-out1-raw.gfa" ftype="gfa1" />
159 <output name="processed_unitigs" file="hifiasm-out1-processed.gfa" ftype="gfa1" />
160 <output name="primary_contig_graph" file="hifiasm-out1-primary.gfa" ftype="gfa1" />
161 <output name="alternate_contig_graph" file="hifiasm-out1-alternate.gfa" ftype="gfa1" />
162 </test>
163 </tests>
164 <help><![CDATA[
165 ***********************************
166 HiFiASM - a fast de novo assembler
167 ***********************************
168
169 Hifiasm is a fast haplotype-resolved de novo assembler for PacBio Hifi reads. It can assemble a human genome in several hours and works with the California redwood genome, one of the most complex genomes sequenced so far. Hifiasm can produce primary/alternate assemblies of quality competitive with the best assemblers. It also introduces a new graph binning algorithm and achieves the best haplotype-resolved assembly given trio data.
170
171 #### Assembly mode
172 - *Standard*
173 - *Trio* When parental short reads are available, hifiasm can generate a pair of haplotype-resolved assemblies with trio binning.
174
175 #### Trio Options
176 - *Haplotype 1 reads* : list of hap1/paternal read names
177 - *Haplotype 2 reads* : list of hap2/maternal read names
178 - *Lower bound of the binned k-mer's frequency*
179 - *Upper bound of the binned k-mer's frequency*
180
181 *Bits for bloom filter* (-f) - A value of 0 disables the bloom filter for small genomes. For genomes much larger than human, applying -f 38 or even - f39 is preferred to save memory on k-mer counting.
182
183 #### Advanced options
184 - *Length of adapters to be removed* Old HiFi reads may contain short adapter sequences at the ends of reads. You can specify 20 to trim both ends of reads by 20bp.
185 - *K-mer length* (must be <64)
186 - *Minimizer window size*
187 - *Drop K-mers* K-mers that occur more than this value multiplied by the coverage will be discarded
188 - *Maximum overlaps to consider* consider up to max(-D*coverage,-N) overlaps for each oriented read
189 - *Correction rounds* round of correction
190
191 #### Assembly options
192 - *Cleaning rounds* round of assembly cleaning
193 - *Minimum contig bubble* size Pop contig graph bubbles smaller than this value
194 - *Minimum unitig bubble* size Pop unitig graph bubbles smaller than this value
195 - *Tip unitigs* Keep only tip unitigs with a number of reads greater than or equal to this value
196 - *Maximum overlap drop ratio*
197 - *Minimum overlap drop ratio*
198 - *Skip post join contigs step* disable post join contigs step which may improve N50
199 - *Inconsistent contigs* If this option is set to a value greater than zero the tool generates an additional BED dataset containing regions that are &gt;= x% inconsistent.
200
201 #### Options for purging duplicates
202 - *Purge level* 0: no purging; 1: light; 2: aggressive [0 for trio; 2 for unzip]
203 - *Similarity threshold for duplicate haplotigs*
204 - *Minimum overlapped reads for duplicate haplotigs*
205 - *Coverage upper bound* If not set, this will be determined automatically
206 - *Experimental high-heterozygosity mode* enable this mode for high heterozygosity sample NB: May be unstable
207
208
209 ### Outputs
210
211 Non Trio assembly
212 - Haplotype-resolved raw unitig graph in GFA format. This graph keeps all haplotype information, including somatic mutations and recurrent sequencing errors.
213 - Haplotype-resolved processed unitig graph without small bubbles : Small bubbles might be caused by somatic mutations or noise in data, which are not the real haplotype information.
214 - Primary assembly contig graph : This graph collapses different haplotypes.
215 - Alternate assembly contig graph : This graph consists of all assemblies that are discarded in primary contig graph.
216
217
218 Trio assembly
219 - Haplotype-resolved raw unitig graph in GFA format . This graph keeps all haplotype information.
220 - Phased paternal/haplotype1 contig graph. This graph keeps the phased paternal/haplotype1 assembly.
221 - Phased maternal/haplotype2 contig graph. This graph keeps the phased maternal/haplotype2 assembly.
222
223
224
225 ]]></help>
226 <citations>
227 <citation type="doi">10.1038/s41592-020-01056-5</citation>
228 </citations>
229 </tool>