|
43
|
1 <tool id="plant_tribes_gene_family_aligner" name="GeneFamilyAligner" version="@WRAPPER_VERSION@.3.0">
|
|
16
|
2 <description>aligns integrated orthologous gene family clusters</description>
|
|
0
|
3 <macros>
|
|
|
4 <import>macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements_gene_family_aligner" />
|
|
36
|
7 <command detect_errors="exit_code"><![CDATA[
|
|
|
8 #set input_format = $input_format_cond.input_format
|
|
|
9 #set alignment_method_cond = $input_format_cond.alignment_method_cond
|
|
|
10 #set alignment_method = $alignment_method_cond.alignment_method
|
|
43
|
11 GeneFamilyAligner
|
|
36
|
12 --alignment_method $alignment_method
|
|
|
13 #if str($alignment_method) == 'pasta':
|
|
|
14 --pasta_script_path '$__tool_directory__/run_pasta.py'
|
|
|
15 --pasta_iter_limit $alignment_method_cond.pasta_iter_limit
|
|
|
16 #end if
|
|
|
17 --num_threads \${GALAXY_SLOTS:-4}
|
|
|
18 #if str($input_format) == 'ptortho':
|
|
|
19 --orthogroup_faa '$input_format_cond.input_ptortho.extra_files_path'
|
|
|
20 #else:
|
|
|
21 ## str($input_format) == 'ptorthocs'
|
|
|
22 --orthogroup_faa '$input_format_cond.input_ptorthocs.extra_files_path'
|
|
|
23 #if str($input_format_cond.codon_alignments) == 'yes':
|
|
43
|
24 --codon_alignments
|
|
36
|
25 #end if
|
|
|
26 #end if
|
|
|
27 #set remove_gappy_sequences = $remove_gappy_sequences_cond.remove_gappy_sequences
|
|
|
28 #if str($remove_gappy_sequences) == 'yes':
|
|
|
29 #set trim_type_cond = $remove_gappy_sequences_cond.trim_type_cond
|
|
|
30 #set trim_type = $trim_type_cond.trim_type
|
|
|
31 #if str($trim_type) == 'gap_trimming' and str($trim_type_cond.gap_trimming):
|
|
|
32 --gap_trimming $trim_type_cond.gap_trimming
|
|
|
33 #else:
|
|
|
34 ## str($trim_type) == 'automated_trimming'
|
|
43
|
35 --automated_trimming
|
|
36
|
36 #end if
|
|
|
37 #set remove_sequences_with_gaps_cond = $remove_gappy_sequences_cond.remove_sequences_with_gaps_cond
|
|
|
38 #set remove_sequences_with_gaps = $remove_sequences_with_gaps_cond.remove_sequences_with_gaps
|
|
|
39 #if str($remove_sequences_with_gaps) == 'yes':
|
|
|
40 #if str($remove_sequences_with_gaps_cond.remove_sequences_with_gaps_of):
|
|
|
41 --remove_sequences $remove_sequences_with_gaps_cond.remove_sequences_with_gaps_of
|
|
|
42 #end if
|
|
|
43 #if str($remove_sequences_with_gaps_cond.iterative_realignment):
|
|
|
44 --iterative_realignment $remove_sequences_with_gaps_cond.iterative_realignment
|
|
|
45 #end if
|
|
|
46 #end if
|
|
38
|
47 #end if
|
|
36
|
48 ]]></command>
|
|
0
|
49 <inputs>
|
|
|
50 <conditional name="input_format_cond">
|
|
16
|
51 <param name="input_format" type="select" label="Classified orthogroup fasta files">
|
|
|
52 <option value="ptortho">Proteins orthogroup fasta files</option>
|
|
|
53 <option value="ptorthocs">Protein and coding sequences orthogroup fasta files</option>
|
|
0
|
54 </param>
|
|
|
55 <when value="ptortho">
|
|
16
|
56 <param name="input_ptortho" format="ptortho" type="data" label="Proteins orthogroup fasta files">
|
|
19
|
57 <validator type="empty_extra_files_path" />
|
|
14
|
58 </param>
|
|
0
|
59 <expand macro="cond_alignment_method" />
|
|
|
60 </when>
|
|
|
61 <when value="ptorthocs">
|
|
16
|
62 <param name="input_ptorthocs" format="ptorthocs" type="data" label="Protein and coding sequences orthogroup fasta files">
|
|
19
|
63 <validator type="empty_extra_files_path" />
|
|
14
|
64 </param>
|
|
0
|
65 <expand macro="cond_alignment_method" />
|
|
|
66 <expand macro="param_codon_alignments" />
|
|
|
67 </when>
|
|
|
68 </conditional>
|
|
12
|
69 <expand macro="cond_remove_gappy_sequences" />
|
|
0
|
70 </inputs>
|
|
|
71 <outputs>
|
|
43
|
72 <collection name="primary" type="list" label="${tool.name} (primary proteins orthogroup alignments) on ${on_string}">
|
|
45
|
73 <discover_datasets pattern="__name__" directory="geneFamilyAlignments_dir/orthogroups_aln" format="fasta" />
|
|
43
|
74 <filter>remove_gappy_sequences_cond['remove_gappy_sequences'] == 'no'</filter>
|
|
|
75 </collection>
|
|
|
76 <collection name="trimmed" type="list" label="${tool.name} (trimmed proteins orthogroup alignments) on ${on_string}">
|
|
45
|
77 <discover_datasets pattern="__name__" directory="geneFamilyAlignments_dir/orthogroups_aln" format="fasta" />
|
|
43
|
78 <filter>remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'no'</filter>
|
|
|
79 </collection>
|
|
|
80 <collection name="primary_trimmed" type="list" label="${tool.name} (primary proteins orthogroup alignments) on ${on_string}">
|
|
45
|
81 <discover_datasets pattern="__name__" directory="geneFamilyAlignments_dir/other_orthogroups_aln" format="fasta" />
|
|
43
|
82 <filter>remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'no'</filter>
|
|
|
83 </collection>
|
|
|
84 <collection name="filtered" type="list" label="${tool.name} (filtered proteins orthogroup alignments) on ${on_string}">
|
|
45
|
85 <discover_datasets pattern="__name__" directory="geneFamilyAlignments_dir/orthogroups_aln" format="fasta" />
|
|
43
|
86 <filter>remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'yes'</filter>
|
|
|
87 </collection>
|
|
|
88 <collection name="primary_filtered" type="list" label="${tool.name} (primary and trimmed proteins orthogroup alignments) on ${on_string}">
|
|
45
|
89 <discover_datasets pattern="__name__" directory="geneFamilyAlignments_dir/other_orthogroups_aln" format="fasta" />
|
|
43
|
90 <filter>remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'yes'</filter>
|
|
38
|
91 </collection>
|
|
0
|
92 </outputs>
|
|
|
93 <tests>
|
|
|
94 <test>
|
|
|
95 </test>
|
|
|
96 </tests>
|
|
|
97 <help>
|
|
|
98 This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and evolutionary
|
|
16
|
99 analyses of genome-scale gene families and transcriptomes. This tool estimates protein and codon multiple sequence alignments
|
|
|
100 of integrated orthologous gene family fasta files produced by the GeneFamilyIntegrator tool.
|
|
0
|
101
|
|
|
102 -----
|
|
|
103
|
|
|
104 **Required options**
|
|
|
105
|
|
28
|
106 * **Classified orthogroup fasta files** - orthogroup fasta files produced by the GeneFamilyClassifier tool selected from your history. Depending on how the GeneFamilyClassifier tool was executed, these could either be proteins or proteins and their corresponding coding sequences.
|
|
0
|
107
|
|
16
|
108 * **Multiple sequence alignment method** - method for estimating orthogroup multiple sequence alignments. PlantTribes estimates alignments using either MAFFT's L-INS-i algorithm or the divide and conquer approach implemented in the PASTA pipeline for large alignments.
|
|
0
|
109
|
|
20
|
110 - **PASTA iteration limit** - number of PASTA iterations. By default, PASTA performs 3 iterations.
|
|
0
|
111
|
|
23
|
112 * **Codon alignments** - select 'Yes' to create codon multiple sequence alignments. This option requires protein and their corresponding coding sequences to be provided as input data.
|
|
|
113
|
|
0
|
114 **Other options**
|
|
|
115
|
|
16
|
116 * **Alignment post-processing configuration** - select 'Yes' to enable multiple sequence alignment post-processing configuration options.
|
|
0
|
117
|
|
16
|
118 - **Trimming method** - multiple sequence alignment trimming method. PlantTribes trims alignments using two automated approaches implemented in trimAl. Gap score based trimming removes alignments sites that do not achieve a user specified gap score. For example, a setting of 0.1 removes sites that have gaps in 90% or more of the sequences in the multiple sequence alignment. The automated heuristic trimming approach determines the best automated trimAl method to trim a given alignment as described in the trimAl tutorial `trimAl`_.
|
|
0
|
119
|
|
22
|
120 - **Gap score** - the fraction of sequences with gap allowed in an alignment site. The score is restricted to the range 0.0 - 1.0. Zero value has no effect.
|
|
16
|
121
|
|
|
122 - **Remove sequences** - select 'Yes' to remove sequences in multiple sequence alignments that do not achieve a user specified alignment coverage score. For example, a setting of 0.7 removes sequences with more than 30% gaps in the alignment. This option requires one of the trimming methods to be set.
|
|
|
123
|
|
22
|
124 - **Coverage score** - minimum fraction of sites without gaps for a sequence in a multiple sequence alignment. The score is restricted to the range 0.0 - 1.0. Zero value has no effect.
|
|
16
|
125
|
|
22
|
126 - **Realignment iteration limit** - number of iterations to perform trimming, removal of sequences, and realignment of orthogroup sequences. Zero value has no effect.
|
|
0
|
127
|
|
38
|
128 * **Output additional dataset collection of files** - selecting 'Yes' will produce an additional output dataset collection whose elements are copies of the directories of files (these elements can be viewed with visualization tools).
|
|
|
129
|
|
18
|
130 .. _trimAl: http://trimal.cgenomics.org
|
|
|
131
|
|
0
|
132 </help>
|
|
|
133 <citations>
|
|
|
134 <expand macro="citation1" />
|
|
16
|
135 <citation type="bibtex">
|
|
|
136 @article{Wall2008,
|
|
|
137 journal = {Nucleic Acids Research},
|
|
|
138 author = {2. Wall PK, Leebens-Mack J, Muller KF, Field D, Altman NS},
|
|
|
139 title = {PlantTribes: a gene and gene family resource for comparative genomics in plants},
|
|
|
140 year = {2008},
|
|
|
141 volume = {36},
|
|
|
142 number = {suppl 1},
|
|
|
143 pages = {D970-D976},}
|
|
|
144 </citation>
|
|
|
145 <citation type="bibtex">
|
|
|
146 @article{Katoh2013,
|
|
|
147 journal = {Molecular biology and evolution},
|
|
|
148 author = {3. Katoh K, Standley DM},
|
|
|
149 title = {MAFFT multiple sequence alignment software version 7: improvements in performance and usability},
|
|
|
150 year = {2013},
|
|
|
151 volume = {30},
|
|
|
152 number = {4},
|
|
|
153 pages = {772-780},}
|
|
|
154 </citation>
|
|
|
155 <citation type="bibtex">
|
|
|
156 @article{Mirarab2014,
|
|
|
157 journal = {Research in Computational Molecular Biology (RECOMB)},
|
|
|
158 author = {4. Mirarab S, Nguyen N, Warnow T},
|
|
|
159 title = {PASTA: Ultra-Large Multiple Sequence Alignment. In R. Sharan (Ed.)},
|
|
|
160 year = {2014},
|
|
|
161 pages = {177–191},
|
|
|
162 url = {https://github.com/smirarab/pasta},}
|
|
|
163 </citation>
|
|
|
164 <citation type="bibtex">
|
|
|
165 @article{Capella-Gutierrez2009,
|
|
|
166 journal = {Bioinformatics,},
|
|
|
167 author = {5. Capella-Gutierrez S, Silla-Martínez JM, Gabaldón T},
|
|
|
168 title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses},
|
|
|
169 year = {2009},
|
|
|
170 volume = {25},
|
|
|
171 number = {15},
|
|
|
172 pages = {1972-1973},}
|
|
|
173 </citation>
|
|
40
|
174 <citation type="bibtex">
|
|
|
175 @article{Yachdav2016,
|
|
|
176 journal = {Bioinformatics,},
|
|
|
177 author = {6. Yachdav G, Wilzbach S, Rauscher B, Sheridan R, Sillitoe I, Procter J, Lewis SE, Rost B, Goldberg T},
|
|
|
178 title = {MSAViewer: interactive JavaScript visualization of multiple sequence alignments},
|
|
|
179 year = {2016},
|
|
|
180 volume = {32},
|
|
|
181 number = {22},
|
|
|
182 pages = {3501-3503},}
|
|
|
183 </citation>
|
|
|
184 <citation type="bibtex">
|
|
|
185 @article{Clamp2004,
|
|
|
186 journal = {Bioinformatics,},
|
|
|
187 author = {7. Clamp M, Cuff J, Searle SM, Barton GJ},
|
|
|
188 title = {The jalview java alignment editor},
|
|
|
189 year = {2004},
|
|
|
190 volume = {20},
|
|
|
191 number = {3},
|
|
|
192 pages = {426-427},}
|
|
|
193 </citation>
|
|
0
|
194 </citations>
|
|
|
195 </tool>
|
