Mercurial > repos > greg > plant_tribes_assembly_post_processor
annotate assembly_post_processor.xml @ 10:4d73965d99a2 draft
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/phylogenetics/plant_tribes/assembly_post_processor commit 71ba0e157346927bf42b788f552b95a71556b28a"
author | greg |
---|---|
date | Wed, 09 Jun 2021 20:26:55 +0000 |
parents | 9c72c91d291f |
children | 2c2ad8af0a4e |
rev | line source |
---|---|
9 | 1 <tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="@WRAPPER_VERSION@.4.0" profile="18.09"> |
0 | 2 <description>post-processes de novo transcriptome assembly</description> |
3 <macros> | |
4 <import>macros.xml</import> | |
5 </macros> | |
4 | 6 <requirements> |
9 | 7 <requirement type="package" version="1.0.4">plant_tribes_assembly_post_processor</requirement> |
4 | 8 </requirements> |
6 | 9 <code file="get_clustering_methods.py"/> |
0 | 10 <command detect_errors="exit_code"><![CDATA[ |
4 | 11 #set output_dir = 'assemblyPostProcessing_dir' |
12 AssemblyPostProcessor | |
0 | 13 --transcripts '$input' |
10
4d73965d99a2
"planemo upload for repository https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/phylogenetics/plant_tribes/assembly_post_processor commit 71ba0e157346927bf42b788f552b95a71556b28a"
greg
parents:
9
diff
changeset
|
14 --prediction_method 'transdecoder' |
0 | 15 #if str($options_type.options_type_selector) == 'advanced': |
16 #set target_gene_family_assembly_cond = $options_type.target_gene_family_assembly_cond | |
17 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes': | |
18 --gene_family_search '$target_gene_family_assembly_cond.orthogroups' | |
19 --scaffold '$target_gene_family_assembly_cond.scaffold.fields.path' | |
20 --method '$target_gene_family_assembly_cond.method' | |
21 --gap_trimming $target_gene_family_assembly_cond.gap_trimming | |
4 | 22 #if str($target_gene_family_assembly_cond.min_coverage) != '0.0': |
23 --min_coverage $target_gene_family_assembly_cond.min_coverage | |
24 #end if | |
0 | 25 #end if |
26 #if str($options_type.strand_specific) == 'yes': | |
4 | 27 --strand_specific |
0 | 28 #end if |
29 #if str($options_type.dereplicate) == 'yes': | |
4 | 30 --dereplicate |
0 | 31 #end if |
32 --min_length $options_type.min_length | |
33 #end if | |
34 --num_threads \${GALAXY_SLOTS:-4} | |
5 | 35 &>assembly_post_processor_log.txt; |
36 if [[ $? -ne 0 ]]; then | |
37 cp assembly_post_processor_log.txt '$output_cds'; | |
38 cp assembly_post_processor_log.txt '$output_pep'; | |
39 cp assembly_post_processor_log.txt '$output_cleaned_cds'; | |
40 cp assembly_post_processor_log.txt '$output_cleaned_pep'; | |
41 #if str($options_type.options_type_selector) == 'advanced': | |
42 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes': | |
43 cp assembly_post_processor_log.txt '$output_targeted_gene_families_stats'; | |
44 #end if | |
45 #if str($options_type.dereplicate) == 'yes': | |
46 cp assembly_post_processor_log.txt '$output_cleaned_nr_cds'; | |
47 cp assembly_post_processor_log.txt '$output_cleaned_nr_pep'; | |
48 #end if | |
4 | 49 #end if |
5 | 50 exit 1; |
51 else | |
52 mv $output_dir/transcripts.cds '$output_cds'; | |
53 mv $output_dir/transcripts.pep '$output_pep'; | |
54 mv $output_dir/transcripts.cleaned.cds '$output_cleaned_cds'; | |
55 mv $output_dir/transcripts.cleaned.pep '$output_cleaned_pep'; | |
56 #if str($options_type.options_type_selector) == 'advanced': | |
57 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes': | |
58 mv $output_dir/targeted_gene_family_assemblies.stats '$output_targeted_gene_families_stats'; | |
59 #end if | |
60 #if str($options_type.dereplicate) == 'yes': | |
61 mv $output_dir/transcripts.cleaned.nr.cds '$output_cleaned_nr_cds'; | |
62 mv $output_dir/transcripts.cleaned.nr.pep '$output_cleaned_nr_pep'; | |
63 #end if | |
4 | 64 #end if |
5 | 65 fi]]></command> |
0 | 66 <inputs> |
67 <param name="input" format="fasta" type="data" label="Transcriptome assembly fasta file"/> | |
68 <conditional name="options_type"> | |
69 <param name="options_type_selector" type="select" label="Options configuration"> | |
70 <option value="basic" selected="true">Basic</option> | |
71 <option value="advanced">Advanced</option> | |
72 </param> | |
73 <when value="basic" /> | |
74 <when value="advanced"> | |
75 <conditional name="target_gene_family_assembly_cond"> | |
76 <param name="target_gene_family_assembly" type="select" label="Perform targeted gene assembly?"> | |
77 <option value="no" selected="true">No</option> | |
78 <option value="yes">Yes</option> | |
79 </param> | |
80 <when value="no" /> | |
81 <when value="yes"> | |
82 <param name="orthogroups" format="tabular" type="data" label="Targeted gene families"/> | |
6 | 83 <expand macro="param_scaffold"/> |
84 <expand macro="param_method"/> | |
0 | 85 <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/> |
4 | 86 <param name="min_coverage" type="float" value="0" min="0" max="1.0" label="Minimum alignment coverage"/> |
0 | 87 </when> |
88 </conditional> | |
89 <param name="strand_specific" type="select" label="Strand-specific assembly?"> | |
90 <option value="no" selected="true">No</option> | |
91 <option value="yes">Yes</option> | |
92 </param> | |
93 <param name="dereplicate" type="select" label="Remove duplicate sequences?"> | |
94 <option value="no" selected="true">No</option> | |
95 <option value="yes">Yes</option> | |
96 </param> | |
97 <param name="min_length" type="integer" value="200" label="Minimum sequence length"/> | |
98 </when> | |
99 </conditional> | |
100 </inputs> | |
101 <outputs> | |
4 | 102 <data name="output_targeted_gene_families_stats" format="tabular" label="Targeted gene families statistics: ${tool.name} on ${on_string}"> |
0 | 103 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter> |
104 </data> | |
4 | 105 <collection name="output_targeted_gene_families" type="list" label="Targeted gene families: ${tool.name} on ${on_string}"> |
106 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir/targeted_gene_family_assemblies" format="fasta" /> | |
107 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter> | |
108 </collection> | |
0 | 109 <data name="output_pep" format="fasta" label="transcripts.pep: ${tool.name} on ${on_string}"/> |
110 <data name="output_cleaned_pep" format="fasta" label="transcripts.cleaned.pep: ${tool.name} on ${on_string}"/> | |
111 <data name="output_cleaned_nr_pep" format="fasta" label="transcripts.cleaned.nr.pep: ${tool.name} on ${on_string}"> | |
112 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter> | |
113 </data> | |
114 <data name="output_cleaned_nr_cds" format="fasta" label="transcripts.cleaned.nr.cds: ${tool.name} on ${on_string}"> | |
115 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter> | |
116 </data> | |
117 <data name="output_cleaned_cds" format="fasta" label="transcripts.cleaned.cds: ${tool.name} on ${on_string}"/> | |
118 <data name="output_cds" format="fasta" label="transcripts.cds: ${tool.name} on ${on_string}"/> | |
119 </outputs> | |
120 <tests> | |
121 <test> | |
122 <param name="input" value="assembly.fasta" ftype="fasta"/> | |
123 <output name="output_cds" file="transcripts.cds" ftype="fasta"/> | |
124 <output name="output_cleaned_cds" file="transcripts.cleaned.cds" ftype="fasta"/> | |
125 <output name="output_cleaned_pep" file="transcripts.cleaned.pep" ftype="fasta"/> | |
126 <output name="output_pep" file="transcripts.pep" ftype="fasta"/> | |
127 </test> | |
128 <test> | |
129 <param name="input" value="assembly_tgf.fasta" ftype="fasta"/> | |
130 <param name="options_type_selector" value="advanced"/> | |
131 <param name="target_gene_family_assembly" value="yes"/> | |
132 <param name="orthogroups" value="target_orthos.ids"/> | |
133 <param name="method" value="orthomcl"/> | |
134 <param name="dereplicate" value="yes"/> | |
4 | 135 <output_collection name="output_targeted_gene_families" type="list"> |
136 </output_collection> | |
137 <output name="output_targeted_gene_families_stats" file="output_targeted_gene_families_stats.tabular" ftype="tabular"/> | |
0 | 138 <output name="output_cds" file="transcripts_tgf.cds" ftype="fasta"/> |
139 <output name="output_cleaned_cds" file="transcripts.cleaned_tgf.cds" ftype="fasta"/> | |
140 <output name="output_cleaned_nr_cds" file="transcripts_tgf.cleaned.nr.cds" ftype="fasta"/> | |
141 <output name="output_cleaned_nr_pep" file="transcripts_tgf.cleaned.nr.pep" ftype="fasta"/> | |
142 <output name="output_cleaned_pep" file="transcripts.cleaned_tgf.pep" ftype="fasta"/> | |
143 <output name="output_pep" file="transcripts_tgf.pep" ftype="fasta"/> | |
144 </test> | |
145 </tests> | |
146 <help> | |
147 This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and | |
148 evolutionary analyses of genome-scale gene families and transcriptomes. This tool post-processes de novo | |
149 assembled transcripts into putative coding sequences and their corresponding amino acid translations and | |
150 optionally assigns transcripts to circumscribed gene families ("orthogroups")[2]. After transcripts have been | |
151 assigned to gene families, overlapping contigs can be identified and merged to reduce fragmentation in the | |
5 | 152 de novo assembly. |
0 | 153 |
154 ----- | |
155 | |
156 **Required options** | |
157 | |
158 * **Transcriptome assembly fasta file** - either de novo or reference-guided transcriptome assembly fasta file selected from your history. | |
159 * **Coding regions prediction method** - method for finding coding regions within transcripts. Available methods are TransDecoder[3] and ESTScan[4]. | |
160 | |
161 **Other options** | |
162 | |
163 * **Perform targeted gene assembly?** - selecting 'Yes' enables local assembly of one or more targeted gene families in a specific scaffold. Scaffolds are defined in PlantTribes as clusters of paralogous/orthologous sequences from a specified set of proteomes[5-7]. | |
164 | |
4 | 165 * **Targeted gene families** - select a history item containing a list of targeted orthogroup identifiers corresponding to the gene family classification from a specified scaffold. Gene family identifiers can be obtained from the function annotation table ("Orthogroup ID" field of .summary file) of scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool, and are also available in the PlantTribes "annotation" directory of the scaffold data download. |
0 | 166 * **Gene family scaffold** - one of the PlantTribes gene family scaffolds (installed into Galaxy by the PlantTribes Scaffolds Download Data Manager tool) whose orthogroup(s) are targeted for the localized assembly. |
167 * **Protein clustering method** - gene family scaffold protein clustering method. Each PlantTribes scaffold data has up to three sets of clusters - GFam[8] (clusters of consensus domain architecture), OrthoFinder[9] (broadly defined clusters) or OrthoMCL[10] (narrowly defined clusters). You can also install your own data scaffold created using a different clustering method as long as it conforms to the PlantTribes scaffold data format. | |
168 * **Trim alignments** - trim gene family multiple sequence alignments that include scaffold backbone genes and locally assembled transcripts to remove non-conserved regions (gappy sites)[11]. The trimmed alignments are used in assigning scores to locally assembled transcripts to determine how well they compare to the backbone gene models. The default setting of 0.1 removes sites that have gaps in 90% or more of the sequences in the multiple sequence alignment. This option is restricted to the range 0.0 - 1.0. | |
4 | 169 * **Minimum alignment coverage** - allowable sequence coverage in the orthogroup trimmed protein multiple sequence alignments. Selecting transcripts with coverage of at least the average of the backbone orthogroup gene models is recommended. Details are shown in the targeted gene family assembly statistics history item. |
0 | 170 |
171 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed. | |
172 * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12]. | |
173 * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp. | |
174 | |
175 </help> | |
176 <citations> | |
177 <expand macro="citation1" /> | |
178 <citation type="bibtex"> | |
179 @article{Honaas2016, | |
180 journal = {PloS one}, | |
181 author = {2. Honaas LA, Wafula EK, Wickett NJ, Der JP, Zhang Y, Edger PP, Altman NS, Pires JC, Leebens-Mack JH}, | |
182 title = {Selecting superior de novo transcriptome assemblies: lessons learned by leveraging the best plant genome}, | |
183 year = {2016}, | |
184 volume = {11}, | |
185 number = {1}, | |
186 pages = {e0146062},} | |
187 </citation> | |
188 <citation type="bibtex"> | |
189 @article{Haas2013, | |
190 journal = {Nature Protocols}, | |
191 author = {3. Haas BJ, Papanicolaou A, Yassour M, Grabherr M, Blood PD, Bowden J, Couger MB, Eccles D, Li B, Lieber M, MacManes MD}, | |
192 title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis}, | |
193 year = {2013}, | |
194 volume = {8}, | |
195 number = {8}, | |
196 pages = {1494-1512},} | |
197 </citation> | |
198 <citation type="bibtex"> | |
199 @article{Huang1999, | |
200 journal = {Genome Research}, | |
201 author = {5. Huang X, Madan A}, | |
202 title = {CAP3: A DNA sequence assembly program}, | |
203 year = {1999}, | |
204 volume = {9}, | |
205 number = {9}, | |
206 pages = {868-877}, | |
207 url = {http://seq.cs.iastate.edu/cap3.html},} | |
208 </citation> | |
209 <citation type="bibtex"> | |
210 @article{Eddy2009, | |
211 journal = {Genome Inform}, | |
212 author = {6. Eddy SR}, | |
213 title = {A new generation of homology search tools based on probabilistic inference}, | |
214 year = {2009}, | |
215 volume = {23}, | |
216 number = {1}, | |
217 pages = {205-211},} | |
218 </citation> | |
219 <citation type="bibtex"> | |
220 @article{Katoh2013, | |
221 journal = {Molecular biology and evolution}, | |
222 author = {7. Katoh K, Standley DM}, | |
223 title = {MAFFT multiple sequence alignment software version 7: improvements in performance and usability}, | |
224 year = {2013}, | |
225 volume = {30}, | |
226 number = {4}, | |
227 pages = {772-780},} | |
228 </citation> | |
229 <citation type="bibtex"> | |
230 @article{Sasidharan2012, | |
231 journal = {Nucleic Acids Research}, | |
232 author = {8. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A}, | |
233 title = {GFam: a platform for automatic annotation of gene families}, | |
234 year = {2012}, | |
235 pages = {gks631},} | |
236 </citation> | |
237 <citation type="bibtex"> | |
238 @article{Li2003, | |
239 journal = {Genome Research} | |
240 author = {9. Li L, Stoeckert CJ, Roos DS}, | |
241 title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes}, | |
242 year = {2003}, | |
243 volume = {13}, | |
244 number = {9}, | |
245 pages = {2178-2189},} | |
246 </citation> | |
247 <citation type="bibtex"> | |
248 @article{Emms2015, | |
249 journal = {Genome Biology} | |
250 author = {10. Emms DM, Kelly S}, | |
251 title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy}, | |
252 year = {2015}, | |
253 volume = {16}, | |
254 number = {1}, | |
255 pages = {157},} | |
256 </citation> | |
257 <citation type="bibtex"> | |
258 @article{Capella-Gutierrez2009, | |
259 journal = {Bioinformatics,}, | |
260 author = {11. Capella-Gutierrez S, Silla-MartÃnez JM, Gabaldón T}, | |
261 title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses}, | |
262 year = {2009}, | |
263 volume = {25}, | |
264 number = {15}, | |
265 pages = {1972-1973},} | |
266 </citation> | |
267 <citation type="bibtex"> | |
268 @article{Gremme2013, | |
269 journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics}, | |
270 author = {12. Gremme G, Steinbiss S, Kurtz S}, | |
271 title = {GenomeTools: a comprehensive software library for efficient processing of structured genome annotations}, | |
272 year = {2013}, | |
273 volume = {10}, | |
274 number = {3}, | |
275 pages = {645-656},} | |
276 </citation> | |
277 </citations> | |
278 </tool> |