comparison windowmasker_ustat.xml @ 0:d90ae4a02efd draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/windowmasker/ commit d529dafd5a2d3a017de226cd59e42cf630348e06
author iuc
date Thu, 14 Dec 2023 16:04:27 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:d90ae4a02efd
1 <tool id="windowmasker_ustat" name="WindowMasker ustat" version="1.0" profile="22.01">
2 <description>Mask sequences using a WindowMasker unit counts table</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements" />
7 <command detect_errors="exit_code">
8 <![CDATA[
9 windowmasker -ustat '${mkcount_input}'
10 -infmt fasta
11 -in '${fasta_input}'
12 -outfmt '${output_format}'
13 ${parse_seqids}
14
15 #if str($use_dust.use_dust_selector) == "yes":
16 -dust true
17 -dust_level ${use_dust.dust_level}
18 #end if
19
20 #if $adv.set_t_high:
21 -set_t_high $adv.set_t_high
22 #end if
23 #if $adv.set_t_high:
24 -set_t_low $adv.set_t_high
25 #end if
26 #if $adv.t_extend
27 -t_extend $adv.t_extend
28 #end if
29 #if $adv.t_low
30 -t_low $adv.t_low
31 #end if
32 #if $adv.t_high
33 -t_high $adv.t_high
34 #end if
35 #if $adv.t_thres
36 -t_thres $adv.t_thres
37 #end if
38 #if $adv.window
39 -window $adv.window
40 #end if
41
42 ## Convert WindowMasker interval output to BED format
43 #if str($output_format) == "interval":
44 | perl '${__tool_directory__}/windowmasker_to_bed.pl' > '${mask_output}'
45 #else
46 -out '${mask_output}'
47 #end if
48 ]]>
49 </command>
50 <inputs>
51 <param argument="-in" name="fasta_input" type="data" format="fasta"
52 label="FASTA sequence file" />
53
54 <param name="mkcount_input" type="data" format="txt"
55 label="Unit counts produced by WindowMasker mkcount" />
56
57 <param argument="-parse_seqids" type="boolean" checked="false"
58 truevalue="-parse_seqids" falsevalue=""
59 label="Parse Seq-ids in FASTA input" />
60
61 <conditional name="use_dust">
62 <param argument="-dust" name="use_dust_selector" type="select" label="Use DUST to mask low complexity sequences?" >
63 <option value="yes">Yes</option>
64 <option value="no">No</option>
65 </param>
66 <when value="yes">
67 <param argument="-dust_level" type="integer" min="1" value="20" label="DUST level"
68 help="Score threshold for subwindows" />
69 </when>
70 <when value="no"></when>
71 </conditional>
72
73 <param name="output_format" type="select" label="Output format">
74 <option value="fasta">FASTA</option>
75 <option value="interval" selected="true">BED</option>
76 <option value="maskinfo_asn1_bin">maskinfo ASN.1 binary</option>
77 <option value="maskinfo_asn1_text">maskinfo ASN.1 text</option>
78 <option value="maskinfo_xml">maskinfo XML</option>
79 </param>
80
81 <section name="adv" title="Advanced options" expanded="false">
82
83 <param argument="-set_t_high" type="integer" label="set_t_high"
84 min="0" optional="true"
85 help="Score for units with unit count greater than T_high" />
86
87 <param argument="-set_t_low" type="integer" label="set_t_low"
88 min="0" optional="true"
89 help="Score for units with unit count less than T_low" />
90
91 <param argument="-t_extend" type="integer" label="t_extend"
92 min="0" optional="true"
93 help="Override the t_extend value in the unit counts file" />
94
95 <param argument="-t_low" type="integer" label="t_low"
96 min="0" optional="true"
97 help="Override the t_low value in the unit counts file" />
98
99 <param argument="-t_high" type="integer" label="t_high"
100 min="0" optional="true"
101 help="Override the t_high value in the unit counts file" />
102
103 <param argument="-t_thres" type="integer" label="Score threshold"
104 min="0" optional="true"
105 help="Override the score threshold value in the unit counts file" />
106
107 <param argument="-window" type="integer" label="Size of the sliding window"
108 min="0" optional="true"
109 help="The default is unit_size + 4" />
110 </section>
111 </inputs>
112 <outputs>
113 <data name="mask_output" format="bed">
114 <change_format>
115 <when input="output_format" value="fasta" format="fasta" />
116 <when input="output_format" value="maskinfo_asn1_bin" format="maskinfo-asn1-binary" />
117 <when input="output_format" value="maskinfo_asn1_text" format="maskinfo-asn1" />
118 <when input="output_format" value="maskinfo_xml" format="xml" />
119 </change_format>
120 </data>
121 </outputs>
122 <tests>
123 <test>
124 <!-- Test WindowMasker ustat with fasta output -->
125 <param name="fasta_input" value="contigs.fa" ftype="fasta" />
126 <param name="mkcount_input" value="chr4_part.oascii.counts" ftype="txt" />
127 <param name="output_format" value="fasta" />
128 <output name="mask_output" file="contigs.wm.fa" ftype="fasta" />
129 </test>
130 <test>
131 <!-- Test WindowMasker ustat with ASN.1 text output -->
132 <param name="fasta_input" value="contigs.fa" ftype="fasta" />
133 <param name="mkcount_input" value="chr4_part.oascii.counts" ftype="txt" />
134 <param name="output_format" value="maskinfo_asn1_text" />
135 <output name="mask_output" file="contigs.wm.asn1" ftype="maskinfo-asn1"/>
136 </test>
137 <test>
138 <!-- Test WindowMasker ustat with ASN.1 binary output -->
139 <param name="fasta_input" value="contigs.fa" ftype="fasta" />
140 <param name="mkcount_input" value="chr4_part.oascii.counts" ftype="txt" />
141 <param name="output_format" value="maskinfo_asn1_bin" />
142 <output name="mask_output" file="contigs.wm.asnb" ftype="maskinfo-asn1-binary"/>
143 </test>
144 <test>
145 <!-- Test WindowMasker ustat with XML output -->
146 <param name="fasta_input" value="contigs.fa" ftype="fasta" />
147 <param name="mkcount_input" value="chr4_part.oascii.counts" ftype="txt" />
148 <param name="output_format" value="maskinfo_xml" />
149 <output name="mask_output" file="contigs.wm.xml" ftype="xml"/>
150 </test>
151 <test>
152 <!-- Test WindowMasker ustat with advanced settings -->
153 <param name="fasta_input" value="contigs.fa" ftype="fasta" />
154 <param name="mkcount_input" value="chr4_part.oascii.counts" ftype="txt" />
155 <param name="set_t_high" value="10" />
156 <param name="set_t_low" value="9" />
157 <param name="t_extend" value="5" />
158 <param name="t_low" value="9" />
159 <param name="t_high" value="10" />
160 <param name="t_thres" value="20" />
161 <param name="window" value="50" />
162 <output name="mask_output" file="contigs.advanced_wm.bed" ftype="bed"/>
163 </test>
164 <test>
165 <!-- Test WindowMasker ustat without dust -->
166 <param name="fasta_input" value="contigs.fa" ftype="fasta" />
167 <param name="mkcount_input" value="chr4_part.oascii.counts" ftype="txt" />
168 <param name="use_dust_selector" value="no" />
169 <output name="mask_output" file="contigs.nodust_wm.bed" ftype="bed"/>
170 </test>
171 <test>
172 <!-- Test WindowMasker ustat with parse Seq-ids -->
173 <param name="fasta_input" value="contigs.fa" ftype="fasta" />
174 <param name="mkcount_input" value="chr4_part.oascii.counts" ftype="txt" />
175 <param name="parse_seqids" value="-parse_seqids" />
176 <output name="mask_output" file="contigs.seqid_wm.bed" ftype="bed"/>
177 </test>
178 </tests>
179 <help>
180 <![CDATA[
181 **What it does**
182
183 This tool runs `stage 2 <https://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/lxr/source/src/app/winmasker/>`_
184 of the WindowMasker analysis to identify repeats within the input sequences.
185
186 .. class:: infomark
187
188 **Output formats:**
189
190 * Use the **binary or text maskinfo ASN.1** output formats to generate the mask file for
191 the `NCBI BLAST+ makeblastdb tool <https://www.ncbi.nlm.nih.gov/books/NBK279681/#_cookbook_Create_BLAST_database_with_the_>`_
192 * Use the BED output format to generate a list of masked regions
193
194
195 .. class:: infomark
196
197 **Advanced options:**
198
199 * See the `WindowMasker README file <https://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/lxr/source/src/app/winmasker/README>`_
200 for additional details on the WindowMasker repeat masking options
201
202 ]]></help>
203 <expand macro="citations" />
204 </tool>