Mercurial > repos > iuc > icescreen

comparison icescreen.xml @ 5:6262a9977181 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/icescreen commit c45c31257dbfd6991c86cee56bb8961e4c5cbe47
author iuc
date Sun, 23 Feb 2025 16:52:24 +0000
parents 49bf81065a47
children
comparison
equal deleted inserted replaced
4:49bf81065a47 5:6262a9977181
1 <tool id="icescreen" name="ICEscreen" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.09"> 1 <tool id="icescreen" name="ICEscreen" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.09">
2 <description>detects and annotates ICEs (Integrative and Conjugative Elements) and IMEs (Integrative and Mobilizable Elements) in Firmicutes genomes.</description> 2 <description>annotates ICEs and IMEs in Bacillota genomes</description>
3
3 <macros> 4 <macros>
4 <token name="@TOOL_VERSION@">1.2.0</token> 5 <import>macros.xml</import>
5 <token name="@VERSION_SUFFIX@">0</token>
6 </macros> 6 </macros>
7 <requirements> 7 <expand macro="xrefs"/>
8 <requirement type="package" version="@TOOL_VERSION@">icescreen</requirement> 8 <expand macro="requirements"/>
9 <requirement type="package" version="3.0">zip</requirement> 9
10 </requirements>
11 <version_command><![CDATA[ 10 <version_command><![CDATA[
12 icescreen --version 11 icescreen --version
13 ]]> 12 ]]>
14 </version_command> 13 </version_command>
15 <command detect_errors="aggressive"><![CDATA[ 14 <command detect_errors="aggressive"><![CDATA[
16 #set $gbname = 'galaxy_genbank' 15 #set $gbname = 'galaxy_genbank'
17 mkdir -p ./tmp_icescreen/source_genbank 16 mkdir -p ./tmp_icescreen/source_genbank
17 && mkdir -p ./tmp_icescreen/icescreen_result
18 && ln -s '${genome}' ./tmp_icescreen/source_genbank/${gbname}.gb 18 && ln -s '${genome}' ./tmp_icescreen/source_genbank/${gbname}.gb
19 && icescreen 19 && icescreen
20 --galaxy 20 --galaxy
21 --gbdir ./tmp_icescreen/source_genbank 21 --gbdir ./tmp_icescreen/source_genbank
22 --outdir ./tmp_icescreen 22 --outdir ./tmp_icescreen/icescreen_result
23 --mode '${taxonomy.mode}' 23 --phylum '${taxonomy.phylum}'
24 --jobs "\${GALAXY_SLOTS:-4}" > ./tmp_icescreen/ICEscreen_log.txt 2>&1 24 --jobs "\${GALAXY_SLOTS:-4}" > ./tmp_icescreen/ICEscreen_log.txt 2>&1
25 25
26 && cat ./tmp_icescreen/ICEscreen_results/results/${gbname}/icescreen_detection_ME/${gbname}_detected_ME.summary > '${summary}' 26 && cat ./tmp_icescreen/icescreen_result/ICEscreen_results/${gbname}/detected_mobile_elements/${gbname}_detected_ME.summary > '${summary}'
27 && cat ./tmp_icescreen/ICEscreen_results/results/${gbname}/icescreen_detection_ME/${gbname}_detected_SP_withMEIds.tsv > '${detected_sp}' 27 && cat ./tmp_icescreen/icescreen_result/ICEscreen_results/${gbname}/detected_mobile_elements/${gbname}_detected_SP_withMEIds.tsv > '${detected_sp}'
28 && cat ./tmp_icescreen/ICEscreen_results/results/${gbname}/icescreen_detection_ME/${gbname}_detected_ME.tsv > '${detected_me}' 28 && cat ./tmp_icescreen/icescreen_result/ICEscreen_results/${gbname}/detected_mobile_elements/${gbname}_detected_ME.tsv > '${detected_me}'
29 29
30 #if "output_annotation_genbank" in $additional_output.optional_files:
31 && mv ./tmp_icescreen/ICEscreen_results/results/${gbname}/visualization_files/${gbname}_icescreen.gb '${gbout}'
32 #end if
33 #if "output_annotation_gff" in $additional_output.optional_files:
34 && mv ./tmp_icescreen/ICEscreen_results/results/${gbname}/visualization_files/${gbname}_icescreen.gff '${gffout}'
35 #end if
36 #if "output_annotation_embl" in $additional_output.optional_files:
37 && mv ./tmp_icescreen/ICEscreen_results/results/${gbname}/visualization_files/${gbname}_icescreen.embl '${emblout}'
38 #end if
39 #if "output_log" in $additional_output.optional_files:
40 && mv ./tmp_icescreen/ICEscreen_log.txt '${log}'
41 #end if
42 #if "output_zip_all_files" in $additional_output.optional_files:
43 && cd ./tmp_icescreen/ICEscreen_results/results/${gbname} && zip --quiet -r - -- . > '${outzip}'
44 #end if
45 ]]> 30 ]]>
46 </command> 31 </command>
47 <inputs> 32 <inputs>
48 <param name="genome" type="data" format="genbank" label="Input genomes to analyze in Genbank format" help="Multi-genbank files (i.e. gbff) are supported. Each record must include the ORIGIN nucleotide sequence at the end."/> 33 <param name="genome" type="data" format="genbank" label="Input genomes to analyze in Genbank format" help="Multi-genbank files (i.e. gbff) are supported. Each record must include the nucleotide sequence."/>
49 <section name="taxonomy" title="Taxonomy of the genomes to analyse" expanded="False"> 34 <section name="taxonomy" title="Phylum of the genomes to analyse" expanded="True">
50 <param name="mode" type="select" label="Firmicutes is the defaut parameter" help="Streptomyces is EXPERIMENTAL and is NOT recommended."> 35 <param name="phylum" type="select" label="Bacillota is the defaut parameter">
51 <option value="firmicutes" selected="true">Firmicutes</option> 36 <option value="bacillota" selected="true">Bacillota</option>
52 <option value="streptomyces">Streptomyces</option>
53 </param> 37 </param>
54 </section> 38 </section>
55 <section name="additional_output" title="Additional output files" expanded="False"> 39 <section name="additional_output" title="Additional output files" expanded="False">
56 <param name="optional_files" type="select" label="Make the following optional files available in the Galaxy history" multiple="true" optional="true" display="checkboxes" > 40 <param name="optional_files" type="select" label="Make the following optional files available in the Galaxy history" multiple="true" optional="true" display="checkboxes" >
57 <option value="output_annotation_genbank">Genome annotation in genbank format</option> 41 <option value="output_annotation_genbank" selected="false">Annotation in genbank format (full)</option>
58 <option value="output_annotation_gff">Genome annotation in gff format</option> 42 <option value="output_annotation_gff" selected="false">Annotation in gff format (ICEs and IMEs only)</option>
59 <option value="output_annotation_embl">Genome annotation in embl format</option> 43 <option value="output_annotation_embl" selected="false">Annotation in embl format (ICEs and IMEs only)</option>
60 <option value="output_zip_all_files">Zip of all final and intermediate results</option> 44 <option value="output_tar_gz_intermediate_files" selected="false">Archive of intermediate files</option>
61 <option value="output_log">ICEscreen log</option> 45 <option value="output_log" selected="false">Log file</option>
46 <option value="output_param_conf" selected="false">Param conf file</option>
62 </param> 47 </param>
63 </section> 48 </section>
64 </inputs> 49 </inputs>
65 <outputs> 50 <outputs>
66 <data format="tabular" name="detected_sp" label="${tool.name} on ${on_string}: Signature Proteins table" /> 51 <data format="tabular" name="detected_sp" label="${tool.name} on ${on_string}: Signature Proteins table" />
67 <data format="tabular" name="detected_me" label="${tool.name} on ${on_string}: ICEs/IMEs table" /> 52 <data format="tabular" name="detected_me" label="${tool.name} on ${on_string}: ICEs/IMEs table" />
68 <data format="txt" name="summary" label="${tool.name} on ${on_string}: results summary" /> 53 <data format="txt" name="summary" label="${tool.name} on ${on_string}: results summary" />
69 <data format="genbank" name="gbout" label="${tool.name} on ${on_string}: annotated genbank" > 54 <data format="genbank.gz" name="gbout" from_work_dir="./tmp_icescreen/icescreen_result/ICEscreen_results/galaxy_genbank/detected_mobile_elements/standard_genome_annotation_formats/galaxy_genbank_icescreen.gb.gz" label="${tool.name} on ${on_string}: genbank annotation (full)" >
70 <filter>additional_output['optional_files'] and "output_annotation_genbank" in additional_output['optional_files']</filter> 55 <filter>additional_output['optional_files'] and "output_annotation_genbank" in additional_output['optional_files']</filter>
71 </data> 56 </data>
72 <data format="gff3" name="gffout" label="${tool.name} on ${on_string}: annotated GFF3" > 57 <data format="gff3.gz" name="gffout" from_work_dir="./tmp_icescreen/icescreen_result/ICEscreen_results/galaxy_genbank/detected_mobile_elements/standard_genome_annotation_formats/galaxy_genbank_icescreen.gff.gz" label="${tool.name} on ${on_string}: GFF3 annotation (ICEs and IMEs only)" >
73 <filter>additional_output['optional_files'] and "output_annotation_gff" in additional_output['optional_files']</filter> 58 <filter>additional_output['optional_files'] and "output_annotation_gff" in additional_output['optional_files']</filter>
74 </data> 59 </data>
75 <data format="embl" name="emblout" label="${tool.name} on ${on_string}: annotated EMBL" > 60 <data format="embl.gz" name="emblout" from_work_dir="./tmp_icescreen/icescreen_result/ICEscreen_results/galaxy_genbank/detected_mobile_elements/standard_genome_annotation_formats/galaxy_genbank_icescreen.embl.gz" label="${tool.name} on ${on_string}: EMBL annotation (ICEs and IMEs only)" >
76 <filter>additional_output['optional_files'] and "output_annotation_embl" in additional_output['optional_files']</filter> 61 <filter>additional_output['optional_files'] and "output_annotation_embl" in additional_output['optional_files']</filter>
77 </data> 62 </data>
78 <data format="zip" name="outzip" label="${tool.name} on ${on_string}: all results zipped"> 63 <data format="tar.gz" name="intermediate_tar_gz" from_work_dir="./tmp_icescreen/icescreen_result/ICEscreen_results/galaxy_genbank/tmp_intermediate_files.tar.gz" label="${tool.name} on ${on_string}: intermediate files archive">
79 <filter>additional_output['optional_files'] and "output_zip_all_files" in additional_output['optional_files']</filter> 64 <filter>additional_output['optional_files'] and "output_tar_gz_intermediate_files" in additional_output['optional_files']</filter>
80 </data> 65 </data>
81 <data format="txt" name="log" label="${tool.name} on ${on_string}: log file" > 66 <data format="txt" name="log" from_work_dir="./tmp_icescreen/ICEscreen_log.txt" label="${tool.name} on ${on_string}: log file" >
82 <filter>additional_output['optional_files'] and "output_log" in additional_output['optional_files']</filter> 67 <filter>additional_output['optional_files'] and "output_log" in additional_output['optional_files']</filter>
68 </data>
69 <data format="gz" name="param_conf" from_work_dir="./tmp_icescreen/icescreen_result/ICEscreen_results/galaxy_genbank/param.conf.gz" label="${tool.name} on ${on_string}: param conf file" >
70 <filter>additional_output['optional_files'] and "output_param_conf" in additional_output['optional_files']</filter>
83 </data> 71 </data>
84 </outputs> 72 </outputs>
85 <tests> 73 <tests>
86 <test expect_num_outputs="3"> 74 <test expect_num_outputs="3">
87 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" /> 75 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" />
98 </output> 86 </output>
99 </test> 87 </test>
100 <test expect_num_outputs="4"> 88 <test expect_num_outputs="4">
101 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" /> 89 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" />
102 <param name="optional_files" value="output_annotation_genbank" /> 90 <param name="optional_files" value="output_annotation_genbank" />
103 <output name="gbout" file="NC_004668_137848_164286_icescreen.gb" ftype="genbank" /> 91 <output name="gbout" ftype="genbank.gz">
92 <assert_contents>
93 <has_size value="19794" delta="100"/>
94 </assert_contents>
95 </output>
104 </test> 96 </test>
105 <test expect_num_outputs="4"> 97 <test expect_num_outputs="4">
106 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" /> 98 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" />
107 <param name="optional_files" value="output_annotation_gff" /> 99 <param name="optional_files" value="output_annotation_gff" />
108 <output name="gffout" file="NC_004668_137848_164286_icescreen.gff" ftype="gff3" /> 100 <output name="gffout" ftype="gff3.gz">
101 <assert_contents>
102 <has_size value="794" delta="100"/>
103 </assert_contents>
104 </output>
109 </test> 105 </test>
110 <test expect_num_outputs="4"> 106 <test expect_num_outputs="4">
111 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" /> 107 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" />
112 <param name="optional_files" value="output_annotation_embl" /> 108 <param name="optional_files" value="output_annotation_embl" />
113 <output name="emblout" file="NC_004668_137848_164286_icescreen.embl" ftype="embl" /> 109 <output name="emblout" ftype="embl.gz">
114 </test> 110 <assert_contents>
115 <test expect_num_outputs="4"> 111 <has_size value="1002" delta="100"/>
116 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" /> 112 </assert_contents>
117 <param name="optional_files" value="output_zip_all_files" /> 113 </output>
118 <output name="outzip" > 114 </test>
119 <assert_contents> 115 <test expect_num_outputs="4">
120 <has_archive_member path=".*/*_detected_SP_withMEIds.tsv"><has_text text="ICE_IME_id" /></has_archive_member> 116 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" />
117 <param name="optional_files" value="output_tar_gz_intermediate_files" />
118 <output name="intermediate_tar_gz" >
119 <assert_contents>
120 <has_archive_member path=".*/*_detected_SP.tsv"><has_text text="Is_hit_blast" /></has_archive_member>
121 </assert_contents> 121 </assert_contents>
122 </output> 122 </output>
123 </test> 123 </test>
124 <test expect_num_outputs="4"> 124 <test expect_num_outputs="4">
125 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" /> 125 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" />
126 <param name="optional_files" value="output_log" /> 126 <param name="optional_files" value="output_log" />
127 <output name="log" > 127 <output name="log" >
128 <assert_contents> 128 <assert_contents>
129 <has_text text="firmicutes" /> 129 <has_text text="bacillota" />
130 <has_text text="Building DAG of jobs" /> 130 <has_text text="Building DAG of jobs" />
131 <has_text text="Complete log" /> 131 <has_text text="Complete log" />
132 <not_has_text text="Error" /> 132 <not_has_text text="Error" />
133 </assert_contents> 133 </assert_contents>
134 </output> 134 </output>
135 </test> 135 </test>
136 <test expect_num_outputs="4"> 136 <test expect_num_outputs="4">
137 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" /> 137 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" />
138 <param name="mode" value="streptomyces" /> 138 <param name="phylum" value="bacillota" />
139 <param name="optional_files" value="output_log" /> 139 <param name="optional_files" value="output_log" />
140 <output name="log" > 140 <output name="log" >
141 <assert_contents> 141 <assert_contents>
142 <has_text text="streptomyces" /> 142 <has_text text="bacillota" />
143 <not_has_text text="Error" /> 143 <not_has_text text="Error" />
144 </assert_contents> 144 </assert_contents>
145 </output> 145 </output>
146 </test> 146 </test>
147 <test expect_num_outputs="5"> 147 <test expect_num_outputs="6">
148 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" /> 148 <param name="genome" value="genbank/NC_004668_137848_164286.gb" ftype="genbank" />
149 <param name="mode" value="firmicutes" /> 149 <param name="phylum" value="bacillota" />
150 <param name="optional_files" value="output_zip_all_files,output_log" /> 150 <param name="optional_files" value="output_tar_gz_intermediate_files,output_log,output_param_conf" />
151 <output name="log" > 151 <output name="log" >
152 <assert_contents> 152 <assert_contents>
153 <has_text text="firmicutes" /> 153 <has_text text="bacillota" />
154 <not_has_text text="Error" /> 154 <not_has_text text="Error" />
155 </assert_contents> 155 </assert_contents>
156 </output> 156 </output>
157 </test> 157 </test>
158 <test expect_num_outputs="3"> 158 <test expect_num_outputs="3">
169 </test> 169 </test>
170 </tests> 170 </tests>
171 <help><![CDATA[ 171 <help><![CDATA[
172 .. class:: warningmark 172 .. class:: warningmark
173 173
174 ICEscreen requires input files in genbank format. Multigenbank files (i.e. gbff files featuring multiple genome records back to back) are supported. Each Genbank record must include the ORIGIN nucleotide sequence. 174 ICEscreen requires input files in genbank format. Multigenbank files (i.e. gbff files featuring multiple genome records back to back) are supported. Each Genbank record must include the nucleotide sequence.
175 175
176 ----- 176 -----
177 177
178 **What it does** 178 **What it does**
179 179
180 ICEscreen is a bioinformatic pipeline for the detection and annotation of ICEs (Integrative and Conjugative Elements) and IMEs (Integrative and Mobilizable Elements) in Firmicutes genomes. The full documentation is available at https://icescreen.migale.inrae.fr. The forge of the project is accessible at https://forgemia.inra.fr/ices_imes_analysis/icescreen. 180 ICEscreen is a bioinformatic pipeline for the detection and annotation of ICEs (Integrative and Conjugative Elements) and IMEs (Integrative and Mobilizable Elements) in Bacillota genomes. The full documentation is available at https://icescreen.migale.inrae.fr. The forge of the project is accessible at https://forgemia.inra.fr/ices_imes_analysis/icescreen.
181 181
182 **Main features of ICEscreen** 182 **Main features of ICEscreen**
183 183
184 - Detection of signature proteins (SPs) of ICEs/IMEs by using blastP on a curated resource. BlastP allows for an accurate assignment of hits to a given ICE/IME superfamily or family. The curated resource was derived from an analysis of over 120 ICEs and IMEs in Streptococcus genomes by the DINAMIC lab. 184 - Detection of signature proteins (SPs) of ICEs/IMEs by using blastP on a curated resource. BlastP allows for an accurate assignment of hits to a given ICE/IME superfamily or family. The curated resource was derived from an analysis of over 120 ICEs and IMEs in Streptococcus genomes by the DINAMIC lab.
185 - Detection of distant homologs of SPs by using HMM profiles of ICEs/IMEs protein families. The HMM profiles have been either imported from trusted resources or created and curated when needed. 185 - Detection of distant homologs of SPs by using HMM profiles of ICEs/IMEs protein families. The HMM profiles have been either imported from trusted resources or created and curated when needed.
188 188
189 **Output files** 189 **Output files**
190 190
191 There are 3 main output results files generated by ICEscreen: 191 There are 3 main output results files generated by ICEscreen:
192 192
193 - Detected Signature Proteins table (`*_detected_SP_withMEIds.csv`): list of the signature proteins detected by the tool and their possible assignment to an ICE or IME element. It is a comma separated table of 48 columns with a one line header. Each line represents a signature protein detected by ICEscreen. 193 - Detected Signature Proteins table (`*_detected_SP_withMEIds.csv`): list of the signature proteins detected by the tool and their possible assignment to an ICE or IME element. Each line represents a signature protein detected by ICEscreen.
194 - Detected ICEs/IMEs table (`*_detected_ME.tsv`): list of the ICEs and IMEs elements detected by the tool, including information about the signature proteins they contain. It is a tab separated table of 21 columns, the header is at line #3. Information in this file is similar to the output file _withICEIMEIds.csv (option -m) but centered around a list of ICE / IME structures instead of a list of SPs. 194 - Detected ICEs/IMEs table (`*_detected_ME.tsv`): list of the ICEs and IMEs elements detected by the tool, including information about the signature proteins they contain. Information in this file is complementary to the _withICEIMEIds.csv file above with each line representing an ICE / IME structures instead of a signature protein.
195 - Results summary (`*_detected_ME.summary`): this file summarizes the main parameters and statistics regarding the ICE / IME structures and the SPs. 195 - Results summary (`*_detected_ME.summary`): this file summarizes the main parameters and statistics regarding the ICE / IME structures and the SPs.
196 196
197 Other optional and additional output files generated by ICEscreen: 197 Other optional and additional output files generated by ICEscreen:
198 198
199 - Annotated Genbank, EMBL, and GFF3 files: tose files contains the annotations of the original Genbank file in addition to annotations added by ICEscreen such as ICEscreen signature proteins and mobile elements. 199 - Genbank annotation file (full): annotations of the original Genbank file as well as annotations of ICEscreen on ICEs, IMEs, and the detected signature proteins.
200 - All results zipped file: You can download this file locally and unzip it to have the complete output folder generated by the tool, including intermediate processing files. See https://icescreen.migale.inrae.fr for details. 200 - EMBL and GFF3 annotation files (ICEs and IMEs only): annotations of ICEscreen on ICEs, IMEs, and the detected signature proteins.
201 - Log file (`*_detected_ME.log`): this file contains the detailed internal details used by ICEscreen to generate the results and logs of each step of the ICEscreen tool pipeline. 201 - Intermediate files (tar.gz): You can download this file locally and uncompress it to have the intermediate files generated by the tool. See https://icescreen.migale.inrae.fr for details.
202 - Log file (`*_detected_ME.log`): this file contains the log of each step of the ICEscreen pipeline.
203 - Param conf file (`param.conf.gz`): this file contains the configuration parameters related to the ICEscreen run.
202 204
203 ]]> 205 ]]>
204 206
205 </help> 207 </help>
206 <citations> 208
207 <citation type="bibtex">@UNPUBLISHED{Kim07aninterior-point, 209 <expand macro="citation"/>
208 author = {Julie Lao and Thomas Lacroix and Gérard Guédon and Charles Coluzzi and Nathalie Leblond-Bourget and Hélène Chiapello}, 210
209 title = {"See our latest publication at https://icescreen.migale.inrae.fr."}
210 }
211 </citation>
212 </citations>
213 </tool> 211 </tool>