Mercurial > repos > cpt > cpt_progressivemauve
comparison cpt_progressivemauve/progressivemauve.xml @ 0:69795939c29b draft
Uploaded
author | cpt |
---|---|
date | Fri, 10 Jun 2022 08:41:20 +0000 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:69795939c29b |
---|---|
1 <?xml version="1.0"?> | |
2 <tool id="progressivemauve" name="progressiveMauve" version="19.1.0.0" profile="16.04"> | |
3 <description>constructs multiple genome alignments</description> | |
4 <macros> | |
5 <import>macros.xml</import> | |
6 <import>cpt-macros.xml</import> | |
7 </macros> | |
8 <requirements> | |
9 <requirement type="package">progressivemauve</requirement> | |
10 </requirements> | |
11 <command detect_errors="aggressive"><![CDATA[ | |
12 ## Symlink files in with correct extensions | |
13 #for $file in $sequences: | |
14 ln -s $file `basename $file`; | |
15 #end for | |
16 | |
17 progressiveMauve | |
18 ## Input Options | |
19 | |
20 #if $apply_backbone: | |
21 --apply-backbone=$apply_backbone | |
22 #end if | |
23 --island-gap-size=$island_gap_size | |
24 $mums | |
25 | |
26 #if $seed_weight: | |
27 --seed-weight=$seed_weight | |
28 #end if | |
29 | |
30 #if $max_gapped_aligner_length: | |
31 --max-gapped-aligner-length=$max_gapped_aligner_length | |
32 #end if | |
33 | |
34 #if $match_input: | |
35 --match-input=$match_input | |
36 #end if | |
37 | |
38 $collinear | |
39 --scoring-scheme=$scoring_scheme | |
40 $no_weight_scaling | |
41 | |
42 --max-breakpoint-distance-scale=$max_breakpoint_distance_scale | |
43 --conservation-distance-scale=$conservation_distance_scale | |
44 $skip_refinement | |
45 $skip_gapped_alignment | |
46 | |
47 #if $bp_dist_estimate_min_score: | |
48 --bp-dist-estimate-min-score=$bp_dist_estimate_min_score | |
49 #end if | |
50 | |
51 #if $gap_open: | |
52 --gap-open=$gap_open | |
53 #end if | |
54 | |
55 #if $gap_extend: | |
56 --gap-extend=$gap_extend | |
57 #end if | |
58 | |
59 #if $weight: | |
60 --weight=$weight | |
61 #end if | |
62 | |
63 #if $min_scaled_penalty: | |
64 --min-scaled-penalty=$min_scaled_penalty | |
65 #end if | |
66 | |
67 --hmm-p-go-homologous=$hmm_p_go_homologous | |
68 --hmm-p-go-unrelated=$hmm_p_go_unrelated | |
69 --hmm-identity=$hmm_identity | |
70 | |
71 $seed_family | |
72 $solid_seeds | |
73 $coding_seeds | |
74 $no_recursion | |
75 $disable_backbone | |
76 | |
77 ## Outputs | |
78 --output=$output | |
79 #if $output_guide_tree: | |
80 --output-guide-tree=$output_guide_tree_file | |
81 #end if | |
82 | |
83 #if $output_backbone: | |
84 --backbone-output=$output_backbone_file | |
85 #end if | |
86 | |
87 ## Sequences | |
88 #for file in $sequences: | |
89 `basename "${file}"` | |
90 #end for | |
91 | |
92 ]]></command> | |
93 <inputs> | |
94 <param type="data" format="fasta" name="sequences" multiple="True" | |
95 label="Select sequences to align" help="in fasta format" /> | |
96 <param type="data" format="xmfa" label="Apply Backbone" name="apply_backbone" optional="True" | |
97 help="Read an existing sequence alignment in XMFA format and apply backbone statistics to it (--apply-backbone)" /> | |
98 | |
99 <param type="integer" label="Island gap size" value="20" name="island_gap_size" | |
100 help="Alignment gaps above this size in nucleotides are considered to be islands (--island-gap-size)"/> | |
101 | |
102 <param type="boolean" truevalue="--disable-backbone" falsevalue="" name="disable_backbone" | |
103 label="Disable backbone" help="Disable backbone detection (--disable-backbone)" /> | |
104 | |
105 <param type="boolean" truevalue="True" falsevalue="" name="output_guide_tree" | |
106 label="Output Guide Tree" help="Write out the guide tree used for alignment to a file (--output-guide-tree)" /> | |
107 | |
108 <param type="boolean" truevalue="True" falsevalue="" name="output_backbone" | |
109 label="Output Backbone" help="Write out the backbone to a file (--backbone-output)" /> | |
110 | |
111 <param type="boolean" truevalue="--mums" falsevalue="" label="MUMs" name="mums" | |
112 help="Find MUMs only, do not attempt to determine locally collinear blocks (LCBs) (--mums)" /> | |
113 | |
114 <param type="integer" label="Seed weight" name="seed_weight" value="0" optional="True" | |
115 help="Use the specified seed weight for calculating initial anchors (--seed-weight)" /> | |
116 | |
117 <param type="data" format="tabular" label="Match Input" name="match_input" optional="True" | |
118 help="Use specified match file instead of searching for matches (--match-input)" /> | |
119 | |
120 <!--<param type="file" label="input-id-matrix" help="An identity matrix describing similarity among all pairs of input sequences/alignments (- -input-id-matrix)" />--> | |
121 <param type="integer" label="Max gapped aligner length" value="0" optional="True" name="max_gapped_aligner_length" | |
122 help="Maximum number of base pairs to attempt aligning with the gapped aligner (--max-gapped-aligner-length)" /> | |
123 | |
124 <param type="data" format="nhx" label="input-guide-tree" optional="True" name="input_guide_tree" | |
125 help="A phylogenetic guide tree in Newick format that describes the order in which sequences will be aligned (--input-guide-tree)" /> | |
126 | |
127 <param type="boolean" truevalue="--collinear" falsevalue="" label="Collinear inputs" name="collinear" | |
128 help="Assume that input sequences are collinear--they have no rearrangements (--collinear)" /> | |
129 | |
130 <param type="select" label="Scoring scheme" name="scoring_scheme" help="Selects the anchoring score function. (--scoring-scheme)" > | |
131 <option value="sp" selected="True">Extant sum-of-pairs (sp)</option> | |
132 <option value="ancestral_sp">Sum-of-pairs + Ancestral (ancestral_sp)</option> | |
133 <option value="ancestral">Ancestral (ancestral)</option> | |
134 </param> | |
135 | |
136 <param type="boolean" truevalue="--no-weight-scaling" falsevalue="" label="No weight scaling" name="no_weight_scaling" | |
137 help="Don't scale LCB weights by conservation distance and breakpoint distance (--no-weight-scaling)" /> | |
138 | |
139 <param type="float" min="0" max="1" label="max-breakpoint-distance-scale" value="0.5" name="max_breakpoint_distance_scale" | |
140 help="Set the maximum weight scaling by breakpoint distance. (--max-breakpoint-distance-scale)" /> | |
141 | |
142 <param type="float" min="0" max="1" label="conservation-distance-scale" value="0.5" name="conservation_distance_scale" | |
143 help="Scale conservation distances by this amount. (--conservation-distance-scale)" /> | |
144 | |
145 <param type="boolean" truevalue="--skip-refinement" falsevalue="" label="Skip refinement" name="skip_refinement" | |
146 help="Do not perform iterative refinement (--skip-refinement)" /> | |
147 <param type="boolean" truevalue="--skip-gapped-alignment" falsevalue="" label="Skip gapped alignment" name="skip_gapped_alignment" | |
148 help="Do not perform gapped alignment (--skip-gapped-alignment)" /> | |
149 <param type="integer" label="BP dist estimate min score" name="bp_dist_estimate_min_score" value="0" optional="True" | |
150 help="Minimum LCB score for estimating pairwise breakpoint distance (--bp-dist-estimate-min-score)" /> | |
151 | |
152 <param type="integer" label="Gap open" name="gap_open" value="0" optional="True" | |
153 help="Gap open penalty (--gap-open)" /> | |
154 | |
155 <param type="select" label="Repeat penalty" name="repeat_penalty" | |
156 help="Sets whether the repeat scores go negative or go to zero for highly repetitive sequences. (--repeat-penalty)"> | |
157 <option value="negative" selected="True">Negative</option> | |
158 <option value="zero">Zero</option> | |
159 </param> | |
160 | |
161 <param type="integer" label="Gap extend" name="gap_extend" value="0" optional="True" | |
162 help="Gap extend penalty (--gap-extend)" /> | |
163 | |
164 <!--<param type="data" label="Substitution matrix" --> | |
165 <!--help="Nucleotide substitution matrix in NCBI format (- -substitution-matrix)" />--> | |
166 | |
167 <param type="integer" label="Weight" name="weight" value="0" optional="True" | |
168 help="Minimum pairwise LCB score (--weight)" /> | |
169 <param type="integer" label="Min scaled penalty" name="min_scaled_penalty" value="0" optional="True" | |
170 help="Minimum breakpoint penalty after scaling the penalty by expected divergence (--min-scaled-penalty)" /> | |
171 | |
172 <param type="float" label="HMM p go homologous" name="hmm_p_go_homologous" min="0" max="1" value="0.00001" | |
173 help="Probability of transitioning from the unrelated to the homologous state (--hmm-p-go-homologous)" /> | |
174 <param type="float" label="HMM p go unrelated" name="hmm_p_go_unrelated" min="0" max="1" value="0.000000001" | |
175 help="Probability of transitioning from the homologous to the unrelated state (--hmm-p-go-unrelated)" /> | |
176 <param type="float" label="HMM identity" name="hmm_identity" min="0" max="1" value="0.7" | |
177 help="Expected level of sequence identity among pairs of sequences(--hmm-identity)" /> | |
178 | |
179 <param type="boolean" truevalue="--seed-family" falsevalue="" label="Seed family" name="seed_family" | |
180 help="Use a family of spaced seeds to improve sensitivity (--seed-family)" /> | |
181 <param type="boolean" truevalue="--solid-seeds" falsevalue="" label="Solid seeds" name="solid_seeds" | |
182 help="Use solid seeds. Do not permit substitutions in anchor matches. (--solid-seeds)" /> | |
183 <param type="boolean" truevalue="--coding-seeds" falsevalue="" label="Coding seeds" name="coding_seeds" | |
184 help="Use coding pattern seeds. Useful to generate matches coding regions with 3rd codon position degeneracy. (--coding-seeds)" /> | |
185 <param type="boolean" truevalue="--no-recursion" falsevalue="" label="No recursion" name="no_recursion" | |
186 help="Disable recursive anchor search (--no-recursion)" /> | |
187 </inputs> | |
188 <outputs> | |
189 <data format="xmfa" name="output" label="${tool.name} alignment of ${on_string}"> | |
190 <change_format> | |
191 <when input="mums" value="--mums" format="tabular" /> | |
192 </change_format> | |
193 </data> | |
194 <data format="nhx" name="output_guide_tree_file" label="${tool.name} alignment of ${on_string}: Guide tree"> | |
195 <filter>output_guide_tree</filter> | |
196 </data> | |
197 <data format="tabular" name="output_backbone_file" label="${tool.name} alignment of ${on_string}: Backbone"> | |
198 <filter>output_backbone</filter> | |
199 </data> | |
200 </outputs> | |
201 <tests> | |
202 <test> | |
203 <param name="sequences" value="phagey.fa,karma.fa" /> | |
204 <output name="output" file="1.xmfa" lines_diff="20"/> | |
205 </test> | |
206 <test> | |
207 <param name="sequences" value="merged.fa" /> | |
208 <output name="output" file="2.xmfa" lines_diff="20"/> | |
209 </test> | |
210 <test> | |
211 <param name="sequences" value="merged.fa" /> | |
212 <param name="output_guide_tree" value="True" /> | |
213 <output name="output" file="3.xmfa" lines_diff="20"/> | |
214 <output name="output_guide_tree_file" file="3.nhx" /> | |
215 </test> | |
216 <test> | |
217 <param name="sequences" value="merged.fa" /> | |
218 <param name="mums" value="True" /> | |
219 <output name="output" file="4.mums" compare="sim_size" delta="1000"/> | |
220 </test> | |
221 <test> | |
222 <param name="sequences" value="merged.fa" /> | |
223 <param name="match_input" value="4.mums" /> | |
224 <output name="output" file="5.xmfa" lines_diff="24"/> | |
225 </test> | |
226 </tests> | |
227 <help><![CDATA[ | |
228 What it does | |
229 ============ | |
230 | |
231 Mauve is a system for efficiently constructing multiple genome alignments in | |
232 the presence of large-scale evolutionary events such as rearrangement and | |
233 inversion. Multiple genome alignment provides a basis for research into | |
234 comparative genomics and the study of evolutionary dynamics. Aligning whole | |
235 genomes is a fundamentally different problem than aligning short sequences. | |
236 | |
237 Mauve has been developed with the idea that a multiple genome aligner should | |
238 require only modest computational resources. It employs algorithmic techniques | |
239 that scale well in the amount of sequence being aligned. For example, a pair of | |
240 Y. pestis genomes can be aligned in under a minute, while a group of 9 | |
241 divergent Enterobacterial genomes can be aligned in a few hours. | |
242 | |
243 | |
244 Example Usage | |
245 ============= | |
246 | |
247 +-----------------------------------+-------------+ | |
248 | Usage | Notes | | |
249 +===================================+=============+ | |
250 | Align genomes |Simply | | |
251 | |select as | | |
252 | |many fasta | | |
253 | |files with | | |
254 | |one or more | | |
255 | |sequences as | | |
256 | |necessary | | |
257 +-----------------------------------+-------------+ | |
258 | Align genomes but also save |Use the | | |
259 | the guide tree and produce a |**Output | | |
260 | backbone file |Guide Tree** | | |
261 | |and **Output | | |
262 | |Backbone** | | |
263 | |options | | |
264 +-----------------------------------+-------------+ | |
265 | Align genomes, but do not |Use the | | |
266 | detect forced alignment of |**Disable | | |
267 | unrelated sequences |backbone** | | |
268 | |option | | |
269 +-----------------------------------+-------------+ | |
270 | Detect forced alignment of |Use the | | |
271 | unrelated sequence in the |**Apply | | |
272 | alignment produced |Backbone** | | |
273 | in previous example, use |option and | | |
274 | custom Homology HMM transition |specify the | | |
275 | parameters. |XMFA file | | |
276 | |produced | | |
277 | |in the | | |
278 | |previous | | |
279 | |example | | |
280 +-----------------------------------+-------------+ | |
281 | Compute ungapped |Use the | | |
282 | local-multiple alignments among |**MUMs** | | |
283 | the input sequences |option | | |
284 +-----------------------------------+-------------+ | |
285 | Compute an alignment of the |Set the | | |
286 | same genomes, using previously |**Match | | |
287 | computed local-multiple |Input** to | | |
288 | alignments |the tabular | | |
289 | |MUMs file | | |
290 | |produced in | | |
291 | |the previous | | |
292 | |example | | |
293 +-----------------------------------+-------------+ | |
294 | Set a minimum scaled |Use the | | |
295 | breakpoint penalty to cope with |**Min Scaled | | |
296 | the case where most genomes |Penalty** and| | |
297 | are aligned correctly, but manual |set to a | | |
298 | inspection reveals that |value like | | |
299 | a divergent genome has too |5000 | | |
300 | many predicted rearrangements. | | | |
301 +-----------------------------------+-------------+ | |
302 | Globally align a set of |Use the | | |
303 | collinear virus |**Colinear**,| | |
304 | genomes, using seed families |**Seed | | |
305 | to improve anchoring sensitivity |Family** | | |
306 | in regions below 70% sequence |options | | |
307 | identity. | | | |
308 +-----------------------------------+-------------+ | |
309 | |
310 ]]></help> | |
311 <citations> | |
312 <expand macro="citation/progressive_mauve" /> | |
313 <expand macro="citation/mijalisrasche" /> | |
314 </citations> | |
315 </tool> |