|
6
|
1 <tool id="plant_tribes_gene_family_aligner" name="GeneFamilyAligner" version="@WRAPPER_VERSION@.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" />
|
|
|
7 <expand macro="stdio" />
|
|
|
8 <command>
|
|
|
9 <![CDATA[
|
|
|
10 #set input_format = $input_format_cond.input_format
|
|
|
11 #set alignment_method_cond = $input_format_cond.alignment_method_cond
|
|
|
12 #set alignment_method = $alignment_method_cond.alignment_method
|
|
12
|
13 #if str($input_format_cond.input_format) == 'ptortho':
|
|
13
|
14 #set output_codon_alignments = False
|
|
12
|
15 #else if str($input_format_cond.input_format) == 'ptorthocs' and str($input_format_cond.codon_alignments ) == 'no':
|
|
13
|
16 #set output_codon_alignments = False
|
|
12
|
17 #else:
|
|
13
|
18 #set output_codon_alignments = True
|
|
12
|
19 #end if
|
|
0
|
20
|
|
|
21 python $__tool_directory__/gene_family_aligner.py
|
|
|
22 --alignment_method $alignment_method
|
|
|
23 #if str($alignment_method) == 'pasta':
|
|
|
24 --pasta_script_path '$__tool_directory__/run_pasta.py'
|
|
|
25 --pasta_iter_limit $alignment_method_cond.pasta_iter_limit
|
|
|
26 #end if
|
|
|
27 --num_threads \${GALAXY_SLOTS:-4}
|
|
|
28 #if str($input_format) == 'ptortho':
|
|
|
29 --orthogroup_faa '$input_format_cond.input_ptortho.extra_files_path'
|
|
|
30 #else:
|
|
|
31 ## str($input_format) == 'ptorthocs'
|
|
|
32 --orthogroup_faa '$input_format_cond.input_ptorthocs.extra_files_path'
|
|
|
33 #if str($input_format_cond.codon_alignments) == 'yes':
|
|
|
34 --codon_alignments 'true'
|
|
|
35 #end if
|
|
|
36 #end if
|
|
12
|
37 #set remove_gappy_sequences = $remove_gappy_sequences_cond.remove_gappy_sequences
|
|
|
38 #if str($remove_gappy_sequences) == 'yes':
|
|
|
39 #set trim_type_cond = $remove_gappy_sequences_cond.trim_type_cond
|
|
|
40 #set trim_type = $trim_type_cond.trim_type
|
|
14
|
41 #if str($trim_type) == 'gap_trimming' and str($trim_type_cond.gap_trimming):
|
|
12
|
42 --gap_trimming $trim_type_cond.gap_trimming
|
|
|
43 #else:
|
|
|
44 ## str($trim_type) == 'automated_trimming'
|
|
|
45 --automated_trimming 'true'
|
|
|
46 #end if
|
|
|
47 #set remove_sequences_with_gaps_cond = $remove_gappy_sequences_cond.remove_sequences_with_gaps_cond
|
|
|
48 #set remove_sequences_with_gaps = $remove_sequences_with_gaps_cond.remove_sequences_with_gaps
|
|
|
49 #if str($remove_sequences_with_gaps) == 'yes':
|
|
14
|
50 #if str($remove_sequences_with_gaps_cond.remove_sequences_with_gaps_of):
|
|
|
51 --remove_sequences $remove_sequences_with_gaps_cond.remove_sequences_with_gaps_of
|
|
|
52 #end if
|
|
|
53 #if str($remove_sequences_with_gaps_cond.iterative_realignment):
|
|
|
54 --iterative_realignment $remove_sequences_with_gaps_cond.iterative_realignment
|
|
|
55 #end if
|
|
12
|
56 #if $output_codon_alignments:
|
|
|
57 --output '$output_aln_filtered_ca'
|
|
|
58 --output_dir '$output_aln_filtered_ca.files_path'
|
|
0
|
59 #else:
|
|
12
|
60 --output '$output_aln_filtered'
|
|
|
61 --output_dir '$output_aln_filtered.files_path'
|
|
0
|
62 #end if
|
|
8
|
63 #else:
|
|
12
|
64 #if $output_codon_alignments:
|
|
|
65 --output '$output_aln_trimmed_ca'
|
|
|
66 --output_dir '$output_aln_trimmed_ca.files_path'
|
|
10
|
67 #else:
|
|
12
|
68 --output '$output_aln_trimmed'
|
|
|
69 --output_dir '$output_aln_trimmed.files_path'
|
|
10
|
70 #end if
|
|
|
71 #end if
|
|
12
|
72 #else:
|
|
|
73 #if $output_codon_alignments:
|
|
|
74 --output '$output_aln_ca'
|
|
|
75 --output_dir '$output_aln_ca.files_path'
|
|
|
76 #else:
|
|
8
|
77 --output '$output_aln'
|
|
|
78 --output_dir '$output_aln.files_path'
|
|
0
|
79 #end if
|
|
|
80 #end if
|
|
|
81 ]]>
|
|
|
82 </command>
|
|
|
83 <inputs>
|
|
|
84 <conditional name="input_format_cond">
|
|
16
|
85 <param name="input_format" type="select" label="Classified orthogroup fasta files">
|
|
|
86 <option value="ptortho">Proteins orthogroup fasta files</option>
|
|
|
87 <option value="ptorthocs">Protein and coding sequences orthogroup fasta files</option>
|
|
0
|
88 </param>
|
|
|
89 <when value="ptortho">
|
|
16
|
90 <param name="input_ptortho" format="ptortho" type="data" label="Proteins orthogroup fasta files">
|
|
19
|
91 <validator type="empty_extra_files_path" />
|
|
14
|
92 </param>
|
|
0
|
93 <expand macro="cond_alignment_method" />
|
|
|
94 </when>
|
|
|
95 <when value="ptorthocs">
|
|
16
|
96 <param name="input_ptorthocs" format="ptorthocs" type="data" label="Protein and coding sequences orthogroup fasta files">
|
|
19
|
97 <validator type="empty_extra_files_path" />
|
|
14
|
98 </param>
|
|
0
|
99 <expand macro="cond_alignment_method" />
|
|
|
100 <expand macro="param_codon_alignments" />
|
|
|
101 </when>
|
|
|
102 </conditional>
|
|
12
|
103 <expand macro="cond_remove_gappy_sequences" />
|
|
0
|
104 </inputs>
|
|
|
105 <outputs>
|
|
8
|
106 <data name="output_aln" format="ptalign" label="Aligned gene family sequences on ${on_string}">
|
|
12
|
107 <filter>(input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'no')) and remove_gappy_sequences_cond['remove_gappy_sequences'] == 'no'</filter>
|
|
10
|
108 </data>
|
|
|
109 <data name="output_aln_ca" format="ptalignca" label="Aligned gene family sequences with codon alignments on ${on_string}">
|
|
12
|
110 <filter>(input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'yes')) and remove_gappy_sequences_cond['remove_gappy_sequences'] == 'no'</filter>
|
|
8
|
111 </data>
|
|
|
112 <data name="output_aln_filtered" format="ptalignfiltered" label="Filtered aligned gene family sequences on ${on_string}">
|
|
12
|
113 <filter>(input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'no')) and (remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'yes')</filter>
|
|
10
|
114 </data>
|
|
|
115 <data name="output_aln_filtered_ca" format="ptalignfilteredca" label="Filtered aligned gene family sequences with codon alignments on ${on_string}">
|
|
12
|
116 <filter>(input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'yes')) and (remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'yes')</filter>
|
|
8
|
117 </data>
|
|
|
118 <data name="output_aln_trimmed" format="ptaligntrimmed" label="Trimmed aligned gene family sequences on ${on_string}">
|
|
12
|
119 <filter>(input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'no')) and (remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'no')</filter>
|
|
10
|
120 </data>
|
|
|
121 <data name="output_aln_trimmed_ca" format="ptaligntrimmedca" label="Trimmed aligned gene family sequences with codon alignments on ${on_string}">
|
|
12
|
122 <filter>(input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'yes')) and (remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'no')</filter>
|
|
8
|
123 </data>
|
|
0
|
124 </outputs>
|
|
|
125 <tests>
|
|
18
|
126 <!-- Test framework does not currently support inputs whose associated extra_files_path contains files to be analyzed.
|
|
0
|
127 <test>
|
|
|
128 </test>
|
|
|
129 -->
|
|
|
130 </tests>
|
|
|
131 <help>
|
|
|
132 This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and evolutionary
|
|
16
|
133 analyses of genome-scale gene families and transcriptomes. This tool estimates protein and codon multiple sequence alignments
|
|
|
134 of integrated orthologous gene family fasta files produced by the GeneFamilyIntegrator tool.
|
|
0
|
135
|
|
|
136 -----
|
|
|
137
|
|
|
138 **Required options**
|
|
|
139
|
|
16
|
140 * **Classified orthogroup fasta files** - orthogroup fasta files produced by the GeneFamilyClassifier tool selected from your history. Depending on how the GeneFamilyClassifier tool was exectured, these could either be proteins or proteins and their corresponding coding sequences.
|
|
0
|
141
|
|
16
|
142 - **Proteins orthogroup fasta files** - proteins fasta files.
|
|
|
143 - **Protein and coding sequences orthogroup fasta files** - proteins and their corresponding coding sequences fasta files.
|
|
0
|
144
|
|
|
145 - **Construct orthogroup multiple codon alignments** - construct orthogroup multiple codon alignments.
|
|
|
146
|
|
16
|
147 * **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
|
148
|
|
16
|
149 - **MAFFT** - MAFFT algorithm.
|
|
|
150 - **PASTA** - PASTA algorithm.
|
|
0
|
151
|
|
16
|
152 - **PASTA iteration limit** - number of PASTA iterations. By default, PASTA performs 3 iterations.
|
|
0
|
153
|
|
|
154 **Other options**
|
|
|
155
|
|
16
|
156 * **Alignment post-processing configuration** - select 'Yes' to enable multiple sequence alignment post-processing configuration options.
|
|
0
|
157
|
|
16
|
158 - **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
|
159 - **Nucleotide based**
|
|
|
160
|
|
16
|
161 - **Gap score** - 1.0 - (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.
|
|
|
162
|
|
|
163 - **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.
|
|
|
164
|
|
|
165 - **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.
|
|
|
166
|
|
|
167 - **Realignment iteration limit** - number of iterations to perform trimming, removal of sequences, and realignment of orthogroup sequences. Zero value has no effect.
|
|
0
|
168
|
|
18
|
169 .. _trimAl: http://trimal.cgenomics.org
|
|
|
170
|
|
0
|
171 </help>
|
|
|
172 <citations>
|
|
|
173 <expand macro="citation1" />
|
|
16
|
174 <citation type="bibtex">
|
|
|
175 @article{Wall2008,
|
|
|
176 journal = {Nucleic Acids Research},
|
|
|
177 author = {2. Wall PK, Leebens-Mack J, Muller KF, Field D, Altman NS},
|
|
|
178 title = {PlantTribes: a gene and gene family resource for comparative genomics in plants},
|
|
|
179 year = {2008},
|
|
|
180 volume = {36},
|
|
|
181 number = {suppl 1},
|
|
|
182 pages = {D970-D976},}
|
|
|
183 </citation>
|
|
|
184 <citation type="bibtex">
|
|
|
185 @article{Katoh2013,
|
|
|
186 journal = {Molecular biology and evolution},
|
|
|
187 author = {3. Katoh K, Standley DM},
|
|
|
188 title = {MAFFT multiple sequence alignment software version 7: improvements in performance and usability},
|
|
|
189 year = {2013},
|
|
|
190 volume = {30},
|
|
|
191 number = {4},
|
|
|
192 pages = {772-780},}
|
|
|
193 </citation>
|
|
|
194 <citation type="bibtex">
|
|
|
195 @article{Mirarab2014,
|
|
|
196 journal = {Research in Computational Molecular Biology (RECOMB)},
|
|
|
197 author = {4. Mirarab S, Nguyen N, Warnow T},
|
|
|
198 title = {PASTA: Ultra-Large Multiple Sequence Alignment. In R. Sharan (Ed.)},
|
|
|
199 year = {2014},
|
|
|
200 pages = {177–191},
|
|
|
201 url = {https://github.com/smirarab/pasta},}
|
|
|
202 </citation>
|
|
|
203 <citation type="bibtex">
|
|
|
204 @article{Capella-Gutierrez2009,
|
|
|
205 journal = {Bioinformatics,},
|
|
|
206 author = {5. Capella-Gutierrez S, Silla-Martínez JM, Gabaldón T},
|
|
|
207 title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses},
|
|
|
208 year = {2009},
|
|
|
209 volume = {25},
|
|
|
210 number = {15},
|
|
|
211 pages = {1972-1973},}
|
|
|
212 </citation>
|
|
0
|
213 </citations>
|
|
|
214 </tool>
|
