Mercurial > repos > ufz > dfast

comparison dfast.xml @ 0:9a9603da37ea draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/Helmholtz-UFZ/ufz-galaxy-tools/blob/main/tools/dfast/ commit ceec7eb1afdcdebbbc145e7fe9fa5a38dafcd9b0
author ufz
date Wed, 16 Apr 2025 10:58:18 +0000
parents
children 81034b7caa01
comparison
equal deleted inserted replaced
-1:000000000000 0:9a9603da37ea
1 <tool id="dfast" name="DFAST" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="24.0" license="MIT">
2 <description>DDBJ Fast Annotation and Submission Tool</description>
3 <macros>
4 <token name="@TOOL_VERSION@">1.3.6</token>
5 <token name="@VERSION_SUFFIX@">0</token>
6 </macros>
7 <xrefs>
8 <xref type="bio.tools">dfast</xref>
9 </xrefs>
10 <requirements>
11 <requirement type="package" version="@TOOL_VERSION@">dfast</requirement>
12 </requirements>
13 <version_command>dfast --version | cut -d" " -f3</version_command>
14 <command detect_errors="exit_code"><![CDATA[
15 dfast
16 --genome '$genome_x'
17 --dbroot '$dbroot.fields.path'
18 #if $organism != ''
19 --organism '$organism'
20 #end if
21 #if $strain != ''
22 --strain '$strain'
23 #end if
24
25 ## Genome settings
26 $genome.complete_cond.complete
27 #if $genome.complete_cond.complete
28 $genome.complete_cond.fix_origin
29 #if $genome.complete_cond.fix_origin
30 --offset $genome.complete_cond.offset
31 #end if
32 #end if
33 $genome.use_original_name
34 $genome.sort_sequence
35 --minimum_length $genome.minimum_length
36
37 ##Locus_tag settings
38 --locus_tag_prefix $locus_tag.locus_tag_prefix
39 --step $locus_tag.step
40 $locus_tag.use_separate_tags
41
42 ##Workflow option
43 ## --threshold $workflow.threshold_pident,$workflow.threshold_q_cov,$workflow.threshold_s_cov,$workflow.threshold_evalue
44 --aligner $workflow.aligner
45 $workflow.cds_method_cond.cds_method
46 #if $workflow.cds_method_cond.cds_method == "use_genemarks2"
47 $workflow.cds_method_cond.use_genemarks2
48 #end if
49 $workflow.use_trnascan
50 $workflow.use_rnammer
51 --gcode $workflow.gcode
52 $workflow.amr
53 #if $workflow.gff
54 --gff '$workflow.gff'
55 #end if
56 $use_locustag_as_gene_id
57 --cpu "\${GALAXY_SLOTS:-1}"
58 ]]></command>
59 <inputs>
60 <param argument="--genome_x" type="data" format="fasta,fasta.gz" label="Genome"/>
61 <param argument="--dbroot" type="select" label="DFAST reference database" >
62 <options from_data_table="dfast">
63 <validator type="no_options" message="Ne reference data available. Contact you Galaxy admin"/>
64 </options>
65 </param>
66 <param argument="--organism" type="text" value="" label="Organism name">
67 <validator type="regex">[0-9a-zA-Z_ \-]*</validator>
68 </param>
69 <param argument="--strain" type="text" value="" label="Strain name">
70 <validator type="regex">[0-9a-zA-Z_ \-]*</validator>
71 </param>
72 <section name="genome" title="Genome settings">
73 <conditional name="complete_cond">
74 <param argument="--complete" type="boolean" truevalue="--complete t" falsevalue="--complete f" checked="false" label="Treat the query as a complete genome" help="Not required unless you need INSDC submission files"/>
75 <when value="--complete t">
76 <param argument="--fix_origin" type="boolean" truevalue="--fix_origin" falsevalue="" checked="false" label="Rotate/flip the chromosome so that the dnaA gene comes first" />
77 <param argument="--offset" type="integer" min="0" value="0" label="Offset from the start codon of the dnaA gene"/>
78 </when>
79 <when value="--complete f"/>
80 </conditional>
81 <param argument="--use_original_name" type="boolean" truevalue="--use_original_name t" falsevalue="--use_original_name f" checked="false" label="Use original sequence names" help="in a query FASTA file" />
82 <param argument="--sort_sequence" type="boolean" truevalue="--sort_sequence t" falsevalue="--sort_sequence f" checked="true" label="ort sequences by length" />
83 <param argument="--minimum_length" type="integer" min="1" value="200" label="Minimum sequence length"/>
84 </section>
85 <section name="locus_tag" title="Locus_tag settings">
86 <param argument="--locus_tag_prefix" type="text" value="LOCUS" label="Locus tag prefix">
87 <validator type="regex">[0-9a-zA-Z_]+</validator>
88 <validator type="empty_field"></validator>
89 </param>
90 <param argument="--step" type="integer" min="1" value="10" label="Increment step of locus tag"/>
91 <param argument="--use_separate_tags" type="boolean" truevalue="--use_separate_tags t" falsevalue="--use_separate_tags f" checked="true" label="Use separate tags according to feature types" />
92 </section>
93
94 <section name="workflow" title="Workflow options">
95 <!-- Disabled for now since it overwrites the thresholds for all steps, which all have different defaults
96 for more configurability we could use https://github.com/nigyta/dfast_core/blob/9d3b6d8255344e7b7174bd71fed8be26534990a5/dfc/default_config.py#L216
97 <param name="threshold_pident" type="integer" min="0" max="100" value="0" label="Percent identity threshold"/>
98 <param name="threshold_q_cov" type="integer" min="0" max="100" value="70" label="Query coverage threshold"/>
99 <param name="threshold_s_cov" type="integer" min="0" max="100" value="70" label="Subject coverage threshold"/>
100 <param name="threshold_evalue" type="text" value="1e-5" label="Evalue threshold">
101 <validator type="regex">1e-[0-9]+</validator>
102 </param> -->
103 <!-- \-\-references -->
104 <param argument="--aligner" type="select" label="Aligner">
105 <option value="ghostx">ghostx</option>
106 <option value="blastp">blastp</option>
107 <option value="diamond">diamond</option>
108 </param>
109 <conditional name="cds_method_cond">
110 <param name="cds_method" type="select" label="CDS prediction method">
111 <option value="">MGA</option>
112 <option value="--use_prodigal">Prodigal</option>
113 <option value="--use_genemarks2">GeneMarkS2 (--use_genemarks2</option>
114 </param>
115 <when value=""></when>
116 <when value="--use_prodigal"></when>
117 <when value="--use_genemarks2">
118 <param argument="--use_genemarks2" type="select" label="" help="TODO">
119 <option value="auto">auto</option>
120 <option value="bact">bact</option>
121 <option value="arch">arch</option>
122 </param>
123 </when>
124 </conditional>
125 <param argument="--use_trnascan" type="select" label="tRNA prediction method">
126 <option value="">Aragorn</option>
127 <option value="--use_trnascan bact">tRNAScan bacteria</option>
128 <option value="--use_trnascan arch">tRNAScan archaea</option>
129 </param>
130 <param argument="--use_rnammer" type="select" label="rRNA prediction method">
131 <option value="">Barrnap</option>
132 <option value="--use_rnammer bact">RNAmmer bacteria</option>
133 <option value="--use_rnammer arch">RNAmmer archaea</option>
134 </param>
135 <param argument="--gcode" type="select" label="Genetic code">
136 <option value="4">The Mold, Protozoan, and Coelenterate Mitochondrial Code and the Mycoplasma/Spiroplasma</option>
137 <option value="11" selected="true">The Bacterial, Archaeal and Plant Plastid Code</option>
138 </param>
139 <param name="disable_functional" type="select" optional="true" label="Disable functional annotation steps">
140 <option value="--no_hmm">Disable HMMscan</option>
141 <option value="--no_cdd">Disable CDDsearch</option>
142 <option value="--no_cds">Disable CDS prediction</option>
143 <option value="--no_rrna">Disable rRNA prediction</option>
144 <option value="--no_trna">Disable tRNA prediction</option>
145 <option value="--no_crispr">Disable CRISPR prediction</option>
146 </param>
147 <param argument="--amr" type="boolean" truevalue="--amr" falsevalue="" checked="false" label="Enable AMR/VFG annotation" help="for plasmid-derived contigs" />
148 <param argument="--gff" type="data" optional="true" format="gff3" label="Structural annotation" help="Ignores --use_original_name, --sort_sequence, --fix_origin"/>
149 </section>
150 <param argument="--use_locustag_as_gene_id" type="boolean" truevalue="--use_locustag_as_gene_id" falsevalue="" checked="false" label="Use locustag as gene ID for FASTA and GFF" help="Useful when providing DFAST results to other tools such as Roary" />
151 <param name="outputs" type="select" multiple="true" label="Outputs">
152 <option value="statistics" selected="true">Statistics</option>
153 <option value="cds">Coding sequences (nucleotide)</option>
154 <option value="protein">Proteins (aminoacid)</option>
155 <option value="embl">Annotation (embl)</option>
156 <option value="gbk">Annotation (gbk)</option>
157 <option value="gff" selected="true">Annotation (gff)</option>
158 <option value="pseudogene">Pseudogene summary</option>
159 <option value="rna">RNAs</option>
160 <option value="ddbj_annotation"> DDBJ annotation file</option>
161 <option value="ddbj_sequence">DDBJ sequence file</option>
162 </param>
163 </inputs>
164 <outputs>
165 <data name="statistics" format="tabular" from_work_dir="OUT/statistics.txt" label="${tool.name} on ${on_string}: Statistics">
166 <filter>outputs and "statistics" in outputs</filter>
167 </data>
168 <data name="cds" format="fasta" from_work_dir="OUT/cds.fna" label="${tool.name} on ${on_string}: Coding sequences">
169 <filter>outputs and "cds" in outputs</filter>
170 </data>
171 <data name="embl" format="embl" from_work_dir="OUT/genome.embl" label="${tool.name} on ${on_string}: annotation (embl)">
172 <filter>outputs and "embl" in outputs</filter>
173 </data>
174 <data name="gbk" format="genbank" from_work_dir="OUT/genome.gbk" label="${tool.name} on ${on_string}: annotation (gbk)">
175 <filter>outputs and "gbk" in outputs</filter>
176 </data>
177 <data name="gff" format="gff3" from_work_dir="OUT/genome.gff" label="${tool.name} on ${on_string}: annotation (gff)">
178 <filter>outputs and "gff" in outputs</filter>
179 </data>
180 <data name="protein" format="fasta" from_work_dir="OUT/protein.faa" label="${tool.name} on ${on_string}: Protein sequences">
181 <filter>outputs and "protein" in outputs</filter>
182 </data>
183 <data name="pseudogene" format="tabular" from_work_dir="OUT/pseudogene_summary.tsv" label="${tool.name} on ${on_string}: Pseudogene summary">
184 <filter>outputs and "pseudogene" in outputs</filter>
185 </data>
186 <data name="rna" format="fasta" from_work_dir="OUT/rna.fna" label="${tool.name} on ${on_string}: RNAs">
187 <filter>outputs and "rna" in outputs</filter>
188 </data>
189
190 <data name="ddbj_annotation" format="txt" from_work_dir="OUT/ddbj/mss.ann" label="${tool.name} on ${on_string}: DDBJ annotation file">
191 <filter>outputs and "ddbj_annotation" in outputs</filter>
192 </data>
193 <data name="ddbj_sequence" format="txt" from_work_dir="OUT/ddbj/mss.fasta" label="${tool.name} on ${on_string}: DDBJ sequence file">
194 <filter>outputs and "ddbj_sequence" in outputs</filter>
195 </data>
196 </outputs>
197 <tests>
198 <test expect_num_outputs="2">
199 <param name="genome_x" value="test.genome.fna" ftype="fasta"/>
200 <param name="outputs" value="statistics,pseudogene"/>
201 <output name="statistics">
202 <assert_contents>
203 <has_n_lines n="12"/>
204 <has_n_columns n="2"/>
205 </assert_contents>
206 </output>
207 <output name="pseudogene">
208 <assert_contents>
209 <has_n_lines n="7"/>
210 <has_n_columns n="11"/>
211 </assert_contents>
212 </output>
213 </test>
214 <test expect_num_outputs="4">
215 <param name="genome_x" value="test.genome.fna" ftype="fasta"/>
216 <param name="outputs" value="cds,protein,gff,rna"/>
217 <output name="cds">
218 <assert_contents>
219 <has_n_lines min="1"/>
220 </assert_contents>
221 </output>
222 <output name="protein">
223 <assert_contents>
224 <has_n_lines min="1"/>
225 </assert_contents>
226 </output>
227 <output name="gff">
228 <assert_contents>
229 <has_n_lines min="1"/>
230 </assert_contents>
231 </output>
232 <output name="rna">
233 <assert_contents>
234 <has_n_lines min="1"/>
235 </assert_contents>
236 </output>
237 </test>
238 </tests>
239 <help><![CDATA[
240 DFAST is a flexible and customizable pipeline for prokaryotic genome annotation as well as data submission to the INSDC.
241 ]]></help>
242 <citations>
243 <citation type="doi">10.1093/bioinformatics/btx713</citation>
244 </citations>
245 </tool>