annotate assembly_post_processor.xml @ 8:518b530c82de draft

Uploaded
author greg
date Thu, 06 Sep 2018 08:46:29 -0400
parents c197d5306cd6
children 9c72c91d291f
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
8
518b530c82de Uploaded
greg
parents: 6
diff changeset
1 <tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="@WRAPPER_VERSION@.3.0" profile="18.09">
0
fcc558568020 Uploaded
greg
parents:
diff changeset
2 <description>post-processes de novo transcriptome assembly</description>
fcc558568020 Uploaded
greg
parents:
diff changeset
3 <macros>
fcc558568020 Uploaded
greg
parents:
diff changeset
4 <import>macros.xml</import>
fcc558568020 Uploaded
greg
parents:
diff changeset
5 </macros>
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
6 <requirements>
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
7 <requirement type="package" version="1.0.3">plant_tribes_assembly_post_processor</requirement>
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
8 </requirements>
6
c197d5306cd6 Uploaded
greg
parents: 5
diff changeset
9 <code file="get_clustering_methods.py"/>
0
fcc558568020 Uploaded
greg
parents:
diff changeset
10 <command detect_errors="exit_code"><![CDATA[
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
11 #set output_dir = 'assemblyPostProcessing_dir'
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
12 AssemblyPostProcessor
0
fcc558568020 Uploaded
greg
parents:
diff changeset
13 --transcripts '$input'
fcc558568020 Uploaded
greg
parents:
diff changeset
14 --prediction_method $prediction_method_cond.prediction_method
fcc558568020 Uploaded
greg
parents:
diff changeset
15 #if str($prediction_method_cond.prediction_method) == 'estscan':
fcc558568020 Uploaded
greg
parents:
diff changeset
16 --score_matrices '$score_matrices'
fcc558568020 Uploaded
greg
parents:
diff changeset
17 #end if
fcc558568020 Uploaded
greg
parents:
diff changeset
18 #if str($options_type.options_type_selector) == 'advanced':
fcc558568020 Uploaded
greg
parents:
diff changeset
19 #set target_gene_family_assembly_cond = $options_type.target_gene_family_assembly_cond
fcc558568020 Uploaded
greg
parents:
diff changeset
20 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
fcc558568020 Uploaded
greg
parents:
diff changeset
21 --gene_family_search '$target_gene_family_assembly_cond.orthogroups'
fcc558568020 Uploaded
greg
parents:
diff changeset
22 --scaffold '$target_gene_family_assembly_cond.scaffold.fields.path'
fcc558568020 Uploaded
greg
parents:
diff changeset
23 --method '$target_gene_family_assembly_cond.method'
fcc558568020 Uploaded
greg
parents:
diff changeset
24 --gap_trimming $target_gene_family_assembly_cond.gap_trimming
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
25 #if str($target_gene_family_assembly_cond.min_coverage) != '0.0':
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
26 --min_coverage $target_gene_family_assembly_cond.min_coverage
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
27 #end if
0
fcc558568020 Uploaded
greg
parents:
diff changeset
28 #end if
fcc558568020 Uploaded
greg
parents:
diff changeset
29 #if str($options_type.strand_specific) == 'yes':
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
30 --strand_specific
0
fcc558568020 Uploaded
greg
parents:
diff changeset
31 #end if
fcc558568020 Uploaded
greg
parents:
diff changeset
32 #if str($options_type.dereplicate) == 'yes':
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
33 --dereplicate
0
fcc558568020 Uploaded
greg
parents:
diff changeset
34 #end if
fcc558568020 Uploaded
greg
parents:
diff changeset
35 --min_length $options_type.min_length
fcc558568020 Uploaded
greg
parents:
diff changeset
36 #end if
fcc558568020 Uploaded
greg
parents:
diff changeset
37 --num_threads \${GALAXY_SLOTS:-4}
5
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
38 &>assembly_post_processor_log.txt;
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
39 if [[ $? -ne 0 ]]; then
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
40 cp assembly_post_processor_log.txt '$output_cds';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
41 cp assembly_post_processor_log.txt '$output_pep';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
42 cp assembly_post_processor_log.txt '$output_cleaned_cds';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
43 cp assembly_post_processor_log.txt '$output_cleaned_pep';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
44 #if str($options_type.options_type_selector) == 'advanced':
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
45 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
46 cp assembly_post_processor_log.txt '$output_targeted_gene_families_stats';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
47 #end if
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
48 #if str($options_type.dereplicate) == 'yes':
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
49 cp assembly_post_processor_log.txt '$output_cleaned_nr_cds';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
50 cp assembly_post_processor_log.txt '$output_cleaned_nr_pep';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
51 #end if
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
52 #end if
5
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
53 exit 1;
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
54 else
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
55 mv $output_dir/transcripts.cds '$output_cds';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
56 mv $output_dir/transcripts.pep '$output_pep';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
57 mv $output_dir/transcripts.cleaned.cds '$output_cleaned_cds';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
58 mv $output_dir/transcripts.cleaned.pep '$output_cleaned_pep';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
59 #if str($options_type.options_type_selector) == 'advanced':
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
60 #if str($target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
61 mv $output_dir/targeted_gene_family_assemblies.stats '$output_targeted_gene_families_stats';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
62 #end if
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
63 #if str($options_type.dereplicate) == 'yes':
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
64 mv $output_dir/transcripts.cleaned.nr.cds '$output_cleaned_nr_cds';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
65 mv $output_dir/transcripts.cleaned.nr.pep '$output_cleaned_nr_pep';
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
66 #end if
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
67 #end if
5
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
68 fi]]></command>
0
fcc558568020 Uploaded
greg
parents:
diff changeset
69 <inputs>
fcc558568020 Uploaded
greg
parents:
diff changeset
70 <param name="input" format="fasta" type="data" label="Transcriptome assembly fasta file"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
71 <conditional name="prediction_method_cond">
fcc558568020 Uploaded
greg
parents:
diff changeset
72 <param name="prediction_method" type="select" label="Coding regions prediction method">
fcc558568020 Uploaded
greg
parents:
diff changeset
73 <option value="transdecoder" selected="true">TransDecoder</option>
fcc558568020 Uploaded
greg
parents:
diff changeset
74 <option value="estscan">ESTScan</option>
fcc558568020 Uploaded
greg
parents:
diff changeset
75 </param>
fcc558568020 Uploaded
greg
parents:
diff changeset
76 <when value="transdecoder" />
fcc558568020 Uploaded
greg
parents:
diff changeset
77 <when value="estscan">
fcc558568020 Uploaded
greg
parents:
diff changeset
78 <param name="score_matrices" format="smat" type="data" label="Scores matrices"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
79 </when>
fcc558568020 Uploaded
greg
parents:
diff changeset
80 </conditional>
fcc558568020 Uploaded
greg
parents:
diff changeset
81 <conditional name="options_type">
fcc558568020 Uploaded
greg
parents:
diff changeset
82 <param name="options_type_selector" type="select" label="Options configuration">
fcc558568020 Uploaded
greg
parents:
diff changeset
83 <option value="basic" selected="true">Basic</option>
fcc558568020 Uploaded
greg
parents:
diff changeset
84 <option value="advanced">Advanced</option>
fcc558568020 Uploaded
greg
parents:
diff changeset
85 </param>
fcc558568020 Uploaded
greg
parents:
diff changeset
86 <when value="basic" />
fcc558568020 Uploaded
greg
parents:
diff changeset
87 <when value="advanced">
fcc558568020 Uploaded
greg
parents:
diff changeset
88 <conditional name="target_gene_family_assembly_cond">
fcc558568020 Uploaded
greg
parents:
diff changeset
89 <param name="target_gene_family_assembly" type="select" label="Perform targeted gene assembly?">
fcc558568020 Uploaded
greg
parents:
diff changeset
90 <option value="no" selected="true">No</option>
fcc558568020 Uploaded
greg
parents:
diff changeset
91 <option value="yes">Yes</option>
fcc558568020 Uploaded
greg
parents:
diff changeset
92 </param>
fcc558568020 Uploaded
greg
parents:
diff changeset
93 <when value="no" />
fcc558568020 Uploaded
greg
parents:
diff changeset
94 <when value="yes">
fcc558568020 Uploaded
greg
parents:
diff changeset
95 <param name="orthogroups" format="tabular" type="data" label="Targeted gene families"/>
6
c197d5306cd6 Uploaded
greg
parents: 5
diff changeset
96 <expand macro="param_scaffold"/>
c197d5306cd6 Uploaded
greg
parents: 5
diff changeset
97 <expand macro="param_method"/>
0
fcc558568020 Uploaded
greg
parents:
diff changeset
98 <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/>
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
99 <param name="min_coverage" type="float" value="0" min="0" max="1.0" label="Minimum alignment coverage"/>
0
fcc558568020 Uploaded
greg
parents:
diff changeset
100 </when>
fcc558568020 Uploaded
greg
parents:
diff changeset
101 </conditional>
fcc558568020 Uploaded
greg
parents:
diff changeset
102 <param name="strand_specific" type="select" label="Strand-specific assembly?">
fcc558568020 Uploaded
greg
parents:
diff changeset
103 <option value="no" selected="true">No</option>
fcc558568020 Uploaded
greg
parents:
diff changeset
104 <option value="yes">Yes</option>
fcc558568020 Uploaded
greg
parents:
diff changeset
105 </param>
fcc558568020 Uploaded
greg
parents:
diff changeset
106 <param name="dereplicate" type="select" label="Remove duplicate sequences?">
fcc558568020 Uploaded
greg
parents:
diff changeset
107 <option value="no" selected="true">No</option>
fcc558568020 Uploaded
greg
parents:
diff changeset
108 <option value="yes">Yes</option>
fcc558568020 Uploaded
greg
parents:
diff changeset
109 </param>
fcc558568020 Uploaded
greg
parents:
diff changeset
110 <param name="min_length" type="integer" value="200" label="Minimum sequence length"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
111 </when>
fcc558568020 Uploaded
greg
parents:
diff changeset
112 </conditional>
fcc558568020 Uploaded
greg
parents:
diff changeset
113 </inputs>
fcc558568020 Uploaded
greg
parents:
diff changeset
114 <outputs>
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
115 <data name="output_targeted_gene_families_stats" format="tabular" label="Targeted gene families statistics: ${tool.name} on ${on_string}">
0
fcc558568020 Uploaded
greg
parents:
diff changeset
116 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
fcc558568020 Uploaded
greg
parents:
diff changeset
117 </data>
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
118 <collection name="output_targeted_gene_families" type="list" label="Targeted gene families: ${tool.name} on ${on_string}">
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
119 <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir/targeted_gene_family_assemblies" format="fasta" />
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
120 <filter>options_type['options_type_selector'] == 'advanced' and options_type['target_gene_family_assembly_cond']['target_gene_family_assembly'] == 'yes'</filter>
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
121 </collection>
0
fcc558568020 Uploaded
greg
parents:
diff changeset
122 <data name="output_pep" format="fasta" label="transcripts.pep: ${tool.name} on ${on_string}"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
123 <data name="output_cleaned_pep" format="fasta" label="transcripts.cleaned.pep: ${tool.name} on ${on_string}"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
124 <data name="output_cleaned_nr_pep" format="fasta" label="transcripts.cleaned.nr.pep: ${tool.name} on ${on_string}">
fcc558568020 Uploaded
greg
parents:
diff changeset
125 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter>
fcc558568020 Uploaded
greg
parents:
diff changeset
126 </data>
fcc558568020 Uploaded
greg
parents:
diff changeset
127 <data name="output_cleaned_nr_cds" format="fasta" label="transcripts.cleaned.nr.cds: ${tool.name} on ${on_string}">
fcc558568020 Uploaded
greg
parents:
diff changeset
128 <filter>options_type['options_type_selector'] == 'advanced' and options_type['dereplicate'] == 'yes'</filter>
fcc558568020 Uploaded
greg
parents:
diff changeset
129 </data>
fcc558568020 Uploaded
greg
parents:
diff changeset
130 <data name="output_cleaned_cds" format="fasta" label="transcripts.cleaned.cds: ${tool.name} on ${on_string}"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
131 <data name="output_cds" format="fasta" label="transcripts.cds: ${tool.name} on ${on_string}"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
132 </outputs>
fcc558568020 Uploaded
greg
parents:
diff changeset
133 <tests>
fcc558568020 Uploaded
greg
parents:
diff changeset
134 <test>
fcc558568020 Uploaded
greg
parents:
diff changeset
135 <param name="input" value="assembly.fasta" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
136 <param name="prediction_method" value="transdecoder"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
137 <output name="output_cds" file="transcripts.cds" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
138 <output name="output_cleaned_cds" file="transcripts.cleaned.cds" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
139 <output name="output_cleaned_pep" file="transcripts.cleaned.pep" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
140 <output name="output_pep" file="transcripts.pep" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
141 </test>
fcc558568020 Uploaded
greg
parents:
diff changeset
142 <test>
fcc558568020 Uploaded
greg
parents:
diff changeset
143 <param name="input" value="assembly.fasta" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
144 <param name="prediction_method" value="estscan"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
145 <param name="score_matrices" value="arabidopsis_thaliana.smat" ftype="smat"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
146 <param name="options_type_selector" value="advanced"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
147 <param name="dereplicate" value="yes"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
148 <output name="output_cds" file="transcripts2.cds" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
149 <output name="output_cleaned_cds" file="transcripts.cleaned.nr.cds" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
150 <output name="output_cleaned_nr_cds" file="transcripts.cleaned.nr.cds" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
151 <output name="output_cleaned_nr_pep" file="transcripts.cleaned.nr.pep" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
152 <output name="output_cleaned_pep" file="transcripts.cleaned.nr.pep" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
153 <output name="output_pep" file="transcripts2.pep" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
154 </test>
fcc558568020 Uploaded
greg
parents:
diff changeset
155 <test>
fcc558568020 Uploaded
greg
parents:
diff changeset
156 <param name="input" value="assembly_tgf.fasta" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
157 <param name="prediction_method" value="transdecoder"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
158 <param name="options_type_selector" value="advanced"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
159 <param name="target_gene_family_assembly" value="yes"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
160 <param name="orthogroups" value="target_orthos.ids"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
161 <param name="scaffold" value="22Gv1.1"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
162 <param name="method" value="orthomcl"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
163 <param name="dereplicate" value="yes"/>
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
164 <output_collection name="output_targeted_gene_families" type="list">
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
165 </output_collection>
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
166 <output name="output_targeted_gene_families_stats" file="output_targeted_gene_families_stats.tabular" ftype="tabular"/>
0
fcc558568020 Uploaded
greg
parents:
diff changeset
167 <output name="output_cds" file="transcripts_tgf.cds" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
168 <output name="output_cleaned_cds" file="transcripts.cleaned_tgf.cds" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
169 <output name="output_cleaned_nr_cds" file="transcripts_tgf.cleaned.nr.cds" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
170 <output name="output_cleaned_nr_pep" file="transcripts_tgf.cleaned.nr.pep" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
171 <output name="output_cleaned_pep" file="transcripts.cleaned_tgf.pep" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
172 <output name="output_pep" file="transcripts_tgf.pep" ftype="fasta"/>
fcc558568020 Uploaded
greg
parents:
diff changeset
173 </test>
fcc558568020 Uploaded
greg
parents:
diff changeset
174 </tests>
fcc558568020 Uploaded
greg
parents:
diff changeset
175 <help>
fcc558568020 Uploaded
greg
parents:
diff changeset
176 This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and
fcc558568020 Uploaded
greg
parents:
diff changeset
177 evolutionary analyses of genome-scale gene families and transcriptomes. This tool post-processes de novo
fcc558568020 Uploaded
greg
parents:
diff changeset
178 assembled transcripts into putative coding sequences and their corresponding amino acid translations and
fcc558568020 Uploaded
greg
parents:
diff changeset
179 optionally assigns transcripts to circumscribed gene families ("orthogroups")[2]. After transcripts have been
fcc558568020 Uploaded
greg
parents:
diff changeset
180 assigned to gene families, overlapping contigs can be identified and merged to reduce fragmentation in the
5
2732db7dd0ef Uploaded
greg
parents: 4
diff changeset
181 de novo assembly.
0
fcc558568020 Uploaded
greg
parents:
diff changeset
182
fcc558568020 Uploaded
greg
parents:
diff changeset
183 -----
fcc558568020 Uploaded
greg
parents:
diff changeset
184
fcc558568020 Uploaded
greg
parents:
diff changeset
185 **Required options**
fcc558568020 Uploaded
greg
parents:
diff changeset
186
fcc558568020 Uploaded
greg
parents:
diff changeset
187 * **Transcriptome assembly fasta file** - either de novo or reference-guided transcriptome assembly fasta file selected from your history.
fcc558568020 Uploaded
greg
parents:
diff changeset
188 * **Coding regions prediction method** - method for finding coding regions within transcripts. Available methods are TransDecoder[3] and ESTScan[4].
fcc558568020 Uploaded
greg
parents:
diff changeset
189 * **Scores matrices** - scores matrices, based on a related species, are required when ESTScan is used to find coding regions. Details of how to create species-specific scores matrices can be found on the ESTScan website (http://estscan.sourceforge.net). Matrices of some organisms are also available to download.
fcc558568020 Uploaded
greg
parents:
diff changeset
190
fcc558568020 Uploaded
greg
parents:
diff changeset
191 **Other options**
fcc558568020 Uploaded
greg
parents:
diff changeset
192
fcc558568020 Uploaded
greg
parents:
diff changeset
193 * **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].
fcc558568020 Uploaded
greg
parents:
diff changeset
194
4
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
195 * **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
fcc558568020 Uploaded
greg
parents:
diff changeset
196 * **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.
fcc558568020 Uploaded
greg
parents:
diff changeset
197 * **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.
fcc558568020 Uploaded
greg
parents:
diff changeset
198 * **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
b0d9dc3c8535 Uploaded
greg
parents: 3
diff changeset
199 * **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
fcc558568020 Uploaded
greg
parents:
diff changeset
200
fcc558568020 Uploaded
greg
parents:
diff changeset
201 * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific. If 'Yes" is selected, transcripts from the minority strand (antisense) are removed.
fcc558568020 Uploaded
greg
parents:
diff changeset
202 * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12].
fcc558568020 Uploaded
greg
parents:
diff changeset
203 * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp.
fcc558568020 Uploaded
greg
parents:
diff changeset
204
fcc558568020 Uploaded
greg
parents:
diff changeset
205 </help>
fcc558568020 Uploaded
greg
parents:
diff changeset
206 <citations>
fcc558568020 Uploaded
greg
parents:
diff changeset
207 <expand macro="citation1" />
fcc558568020 Uploaded
greg
parents:
diff changeset
208 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
209 @article{Honaas2016,
fcc558568020 Uploaded
greg
parents:
diff changeset
210 journal = {PloS one},
fcc558568020 Uploaded
greg
parents:
diff changeset
211 author = {2. Honaas LA, Wafula EK, Wickett NJ, Der JP, Zhang Y, Edger PP, Altman NS, Pires JC, Leebens-Mack JH},
fcc558568020 Uploaded
greg
parents:
diff changeset
212 title = {Selecting superior de novo transcriptome assemblies: lessons learned by leveraging the best plant genome},
fcc558568020 Uploaded
greg
parents:
diff changeset
213 year = {2016},
fcc558568020 Uploaded
greg
parents:
diff changeset
214 volume = {11},
fcc558568020 Uploaded
greg
parents:
diff changeset
215 number = {1},
fcc558568020 Uploaded
greg
parents:
diff changeset
216 pages = {e0146062},}
fcc558568020 Uploaded
greg
parents:
diff changeset
217 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
218 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
219 @article{Haas2013,
fcc558568020 Uploaded
greg
parents:
diff changeset
220 journal = {Nature Protocols},
fcc558568020 Uploaded
greg
parents:
diff changeset
221 author = {3. Haas BJ, Papanicolaou A, Yassour M, Grabherr M, Blood PD, Bowden J, Couger MB, Eccles D, Li B, Lieber M, MacManes MD},
fcc558568020 Uploaded
greg
parents:
diff changeset
222 title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis},
fcc558568020 Uploaded
greg
parents:
diff changeset
223 year = {2013},
fcc558568020 Uploaded
greg
parents:
diff changeset
224 volume = {8},
fcc558568020 Uploaded
greg
parents:
diff changeset
225 number = {8},
fcc558568020 Uploaded
greg
parents:
diff changeset
226 pages = {1494-1512},}
fcc558568020 Uploaded
greg
parents:
diff changeset
227 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
228 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
229 @article{Iseli1999,
fcc558568020 Uploaded
greg
parents:
diff changeset
230 journal = {ISMB},
fcc558568020 Uploaded
greg
parents:
diff changeset
231 author = {4. Iseli C, Jongeneel CV, Bucher P},
fcc558568020 Uploaded
greg
parents:
diff changeset
232 title = {ESTScan: a program for detecting, evaluating, and reconstructing potential coding regions in EST sequences},
fcc558568020 Uploaded
greg
parents:
diff changeset
233 year = {1999},
fcc558568020 Uploaded
greg
parents:
diff changeset
234 volume = {99},
fcc558568020 Uploaded
greg
parents:
diff changeset
235 pages = {138-148},
fcc558568020 Uploaded
greg
parents:
diff changeset
236 url = {http://estscan.sourceforge.net},}
fcc558568020 Uploaded
greg
parents:
diff changeset
237 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
238 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
239 @article{Huang1999,
fcc558568020 Uploaded
greg
parents:
diff changeset
240 journal = {Genome Research},
fcc558568020 Uploaded
greg
parents:
diff changeset
241 author = {5. Huang X, Madan A},
fcc558568020 Uploaded
greg
parents:
diff changeset
242 title = {CAP3: A DNA sequence assembly program},
fcc558568020 Uploaded
greg
parents:
diff changeset
243 year = {1999},
fcc558568020 Uploaded
greg
parents:
diff changeset
244 volume = {9},
fcc558568020 Uploaded
greg
parents:
diff changeset
245 number = {9},
fcc558568020 Uploaded
greg
parents:
diff changeset
246 pages = {868-877},
fcc558568020 Uploaded
greg
parents:
diff changeset
247 url = {http://seq.cs.iastate.edu/cap3.html},}
fcc558568020 Uploaded
greg
parents:
diff changeset
248 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
249 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
250 @article{Eddy2009,
fcc558568020 Uploaded
greg
parents:
diff changeset
251 journal = {Genome Inform},
fcc558568020 Uploaded
greg
parents:
diff changeset
252 author = {6. Eddy SR},
fcc558568020 Uploaded
greg
parents:
diff changeset
253 title = {A new generation of homology search tools based on probabilistic inference},
fcc558568020 Uploaded
greg
parents:
diff changeset
254 year = {2009},
fcc558568020 Uploaded
greg
parents:
diff changeset
255 volume = {23},
fcc558568020 Uploaded
greg
parents:
diff changeset
256 number = {1},
fcc558568020 Uploaded
greg
parents:
diff changeset
257 pages = {205-211},}
fcc558568020 Uploaded
greg
parents:
diff changeset
258 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
259 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
260 @article{Katoh2013,
fcc558568020 Uploaded
greg
parents:
diff changeset
261 journal = {Molecular biology and evolution},
fcc558568020 Uploaded
greg
parents:
diff changeset
262 author = {7. Katoh K, Standley DM},
fcc558568020 Uploaded
greg
parents:
diff changeset
263 title = {MAFFT multiple sequence alignment software version 7: improvements in performance and usability},
fcc558568020 Uploaded
greg
parents:
diff changeset
264 year = {2013},
fcc558568020 Uploaded
greg
parents:
diff changeset
265 volume = {30},
fcc558568020 Uploaded
greg
parents:
diff changeset
266 number = {4},
fcc558568020 Uploaded
greg
parents:
diff changeset
267 pages = {772-780},}
fcc558568020 Uploaded
greg
parents:
diff changeset
268 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
269 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
270 @article{Sasidharan2012,
fcc558568020 Uploaded
greg
parents:
diff changeset
271 journal = {Nucleic Acids Research},
fcc558568020 Uploaded
greg
parents:
diff changeset
272 author = {8. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A},
fcc558568020 Uploaded
greg
parents:
diff changeset
273 title = {GFam: a platform for automatic annotation of gene families},
fcc558568020 Uploaded
greg
parents:
diff changeset
274 year = {2012},
fcc558568020 Uploaded
greg
parents:
diff changeset
275 pages = {gks631},}
fcc558568020 Uploaded
greg
parents:
diff changeset
276 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
277 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
278 @article{Li2003,
fcc558568020 Uploaded
greg
parents:
diff changeset
279 journal = {Genome Research}
fcc558568020 Uploaded
greg
parents:
diff changeset
280 author = {9. Li L, Stoeckert CJ, Roos DS},
fcc558568020 Uploaded
greg
parents:
diff changeset
281 title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes},
fcc558568020 Uploaded
greg
parents:
diff changeset
282 year = {2003},
fcc558568020 Uploaded
greg
parents:
diff changeset
283 volume = {13},
fcc558568020 Uploaded
greg
parents:
diff changeset
284 number = {9},
fcc558568020 Uploaded
greg
parents:
diff changeset
285 pages = {2178-2189},}
fcc558568020 Uploaded
greg
parents:
diff changeset
286 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
287 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
288 @article{Emms2015,
fcc558568020 Uploaded
greg
parents:
diff changeset
289 journal = {Genome Biology}
fcc558568020 Uploaded
greg
parents:
diff changeset
290 author = {10. Emms DM, Kelly S},
fcc558568020 Uploaded
greg
parents:
diff changeset
291 title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy},
fcc558568020 Uploaded
greg
parents:
diff changeset
292 year = {2015},
fcc558568020 Uploaded
greg
parents:
diff changeset
293 volume = {16},
fcc558568020 Uploaded
greg
parents:
diff changeset
294 number = {1},
fcc558568020 Uploaded
greg
parents:
diff changeset
295 pages = {157},}
fcc558568020 Uploaded
greg
parents:
diff changeset
296 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
297 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
298 @article{Capella-Gutierrez2009,
fcc558568020 Uploaded
greg
parents:
diff changeset
299 journal = {Bioinformatics,},
fcc558568020 Uploaded
greg
parents:
diff changeset
300 author = {11. Capella-Gutierrez S, Silla-Martínez JM, Gabaldón T},
fcc558568020 Uploaded
greg
parents:
diff changeset
301 title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses},
fcc558568020 Uploaded
greg
parents:
diff changeset
302 year = {2009},
fcc558568020 Uploaded
greg
parents:
diff changeset
303 volume = {25},
fcc558568020 Uploaded
greg
parents:
diff changeset
304 number = {15},
fcc558568020 Uploaded
greg
parents:
diff changeset
305 pages = {1972-1973},}
fcc558568020 Uploaded
greg
parents:
diff changeset
306 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
307 <citation type="bibtex">
fcc558568020 Uploaded
greg
parents:
diff changeset
308 @article{Gremme2013,
fcc558568020 Uploaded
greg
parents:
diff changeset
309 journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics},
fcc558568020 Uploaded
greg
parents:
diff changeset
310 author = {12. Gremme G, Steinbiss S, Kurtz S},
fcc558568020 Uploaded
greg
parents:
diff changeset
311 title = {GenomeTools: a comprehensive software library for efficient processing of structured genome annotations},
fcc558568020 Uploaded
greg
parents:
diff changeset
312 year = {2013},
fcc558568020 Uploaded
greg
parents:
diff changeset
313 volume = {10},
fcc558568020 Uploaded
greg
parents:
diff changeset
314 number = {3},
fcc558568020 Uploaded
greg
parents:
diff changeset
315 pages = {645-656},}
fcc558568020 Uploaded
greg
parents:
diff changeset
316 </citation>
fcc558568020 Uploaded
greg
parents:
diff changeset
317 </citations>
fcc558568020 Uploaded
greg
parents:
diff changeset
318 </tool>