comparison glob_report.xml.orig @ 17:f93c868203cc draft default tip

planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/GraphClust/CollectResults commit 4406735e44aba20859c252be39f4e99df28c7a92
author rnateam
date Sat, 27 Oct 2018 13:23:06 -0400
parents
children
comparison
equal deleted inserted replaced
16:79df97a1bc0f 17:f93c868203cc
1 <<<<<<< HEAD
2 <tool id="glob_report" name="cluster_collection_report" version="0.4" >
3 =======
4 <tool id="glob_report" name="cluster_collection_report" version="0.3" >
5 >>>>>>> edc317491e1fdf1233bd9b45376dc05abf6eabd5
6 <requirements>
7 <requirement type="package" version="0.5.2">graphclust-wrappers</requirement>
8 <requirement type="package" version='0.5'>perl-array-utils</requirement>
9 <requirement type="package" version='0.18.1'>scikit-learn</requirement>
10 <requirement type="package" version='1.8.10'>locarna</requirement>
11 <requirement type="package" version='2.1'>rnaz</requirement>
12 <requirement type="package" version="1.1.2">infernal</requirement>
13 <requirement type="package" version='2.2.10'>viennarna</requirement>
14 <requirement type="package" version='1.3.26'>graphicsmagick</requirement>
15 <requirement type="package" version='0.6.1'>rscape</requirement>
16 <requirement type="package" version='6.0'>unzip</requirement>
17
18 </requirements>
19 <stdio>
20 <exit_code range="1:" />
21 </stdio>
22 <command>
23 <![CDATA[
24 unzip $FASTA &> /dev/null &&
25
26 mkdir ./CMSEARCH &&
27 mkdir ./MODEL &&
28
29 #set $inputFiles = ""
30
31 #for $cms_res in $cmsearch_results:
32 ###set $inputFiles += str($cms_res.element_identifier)+','
33 ln -f -s '$cms_res' ./CMSEARCH/$cms_res.element_identifier &&
34 #end for
35 #set $inputFiles = $inputFiles[:-1]
36
37 #set $inputFilesTrees = ""
38
39 #for $mods in $model_tree_files:
40 ###set $inputFilesTrees += str($mods.element_identifier)+','
41 ln -f -s '$mods' ./MODEL/$mods.element_identifier &&
42 #end for
43 #set $inputFilesTrees = $inputFilesTrees[:-1]
44
45
46 'glob_res.pl'
47 ##'$inputFiles'
48 $merge_cluster_ol
49 $merge_overlap
50 $min_cluster_size
51 $cm_min_bitscore
52 $cm_max_eval
53 $cm_bitscore_sig
54 $partition_type ''
55 $cut_type
56 ##'$inputFilesTrees'
57 $results_top_num
58 #if $iteration_num.iteration_num_selector:
59 $iteration_num.CI
60 $final_partition_soft
61 $final_partition_used_cmsearch
62 '$combined_cm'
63
64 #end if
65
66 #if str($advanced_opts.advanced_opts_selector) == "show":
67 #if str($advanced_opts.param_type.param_type_selector) == "gclust":
68 $advanced_opts.param_type.p
69 $advanced_opts.param_type.max_diff_am
70 $advanced_opts.param_type.max_diff
71 $advanced_opts.param_type.tau
72 $advanced_opts.param_type.struct_weight
73 $advanced_opts.param_type.indel_opening
74 $advanced_opts.param_type.indel
75 $advanced_opts.param_type.alifold_consensus_dp
76 #end if
77 #end if
78
79 &&
80 <<<<<<< HEAD
81 python '$__tool_directory__/evaluation.py' FASTA/ RESULTS/
82 =======
83 python '$__tool_directory__/evaluation.py'
84 >>>>>>> edc317491e1fdf1233bd9b45376dc05abf6eabd5
85
86 #if $cdhit:
87 &&
88 python '$__tool_directory__/addCdhitseqs.py' '$cdhit'
89 #end if
90 ]]>
91 </command>
92 <inputs>
93 <param type="data" name="FASTA" format="zip" />
94 <param type="data" name="cmsearch_results" format="tabular" multiple="True"/>
95 <param type="data" name="model_tree_files" format="txt" multiple="True"/>
96 <param name="partition_type" type="boolean" checked="True" truevalue="0" falsevalue="1" label="Hard partition"/>
97 <param name="cut_type" type="boolean" checked="True" truevalue="0" falsevalue="1" label="Use CM score for cutoff" help="otherwise use E-value"/>
98 <param type="data" name="cdhit" format="txt" optional="true"/>
99 <conditional name="iteration_num">
100 <param name="iteration_num_selector" type="boolean" checked="no" label="Multiple iterations" help="for single iteration- NO, for multiple-YES"/>
101 <when value="true">
102 <param name="CI" type="integer" value="2" size="5" label="Number of current iteration "/>
103 <param type="data" name="final_partition_soft" format="txt" />
104 <param type="data" name="final_partition_used_cmsearch" format="txt" />
105 <param type="data" name="combined_cm" format="txt" />
106 </when>
107 <when value="false" ></when>
108 </conditional>
109 <param name="merge_cluster_ol" type="float" value="0.66" size="5" label="merge_cluster_ol" help=""/>
110 <param name="merge_overlap" type="float" value="0.51" size="5" label="merge_overlap" help=""/>
111 <param name="min_cluster_size" type="integer" value="3" size="5" label="min_cluster_size" help=""/>
112 <param name="cm_min_bitscore" type="integer" value="20" size="5" label="cm_min_bitscore" help=""/>
113 <param name="cm_max_eval" type="float" value="0.001" size="5" label="cm_max_eval" help=""/>
114 <param name="cm_bitscore_sig" type="integer" value="1" size="5" label="cm_bitscore_sig" help=""/>
115 <param name="results_top_num" type="integer" value="5" size="5" label="results_top_num" help=""/>
116
117 <conditional name="advanced_opts">
118 <param name="advanced_opts_selector" type="select" label="Advanced Options">
119 <option value="hide" selected="True">Hide</option>
120 <option value="show">Show</option>
121 </param>
122 <when value="hide"></when>
123 <when value="show">
124
125 <conditional name="param_type">
126 <param name="param_type_selector" type="select" label="Choose the type of parameters">
127 <option value="locarna">LocARNA defaults</option>
128 <option value="gclust" selected="True">GrapClust defaults(changeable)</option>
129 </param>
130 <when value="gclust">
131
132 <param name="p" type="float" value="0.001" size="5" label="minimal probability" help="-p"/>
133 <param name="max_diff_am" type="integer" value="50" size="5" label=" maximal difference for sizes of matched arcs" help="--max-diff-am"/>
134 <param argument="tau" type="integer" value="50" min="0" max="200" label="Sequence contribution at structure match in percent"/>
135 <param name="max_diff" type="integer" value="100" size="5" label="maximal difference for alignment traces" help="--max-diff"/>
136
137 <param name="struct_weight" argument="struct-weight"
138 label="Structure weight" type="integer"
139 value="180" min="0" max="800" />
140 <param name="indel_opening" argument="indel-opening"
141 label="Indel opening score" type="integer"
142 value="-400" max="0" min="-1500" />
143 <param argument="indel" label="Indel score" type="integer"
144 value="-200" min="-1000" max="0" />
145
146 <param name="alifold_consensus_dp"
147 type="boolean" checked="True"
148 truevalue="--alifold-consensus-dp" falsevalue=" "
149 label="Compute consensus dot plot by alifold" />
150
151 </when>
152 <when value="locarna">
153 </when>
154 </conditional>
155
156 </when>
157 </conditional>
158
159 </inputs>
160 <outputs>
161 <data name="final_stats" format="txt" from_work_dir="RESULTS/cluster.final.stats" label="cluster.final.stats" />
162 <data name="tableForEval" format="tabular" from_work_dir="RESULTS/fullTab.tabular" label="tableForEval" />
163 <data name="final_soft" format="txt" from_work_dir="RESULTS/partitions/final_partition.soft" label="soft_part" />
164 <data name="final_used_cmsearch" format="txt" from_work_dir="RESULTS/partitions/final_partition.used_cmsearch" label="final_partition_used_cmsearch" />
165 <data name="evaluation" format="txt" from_work_dir="RESULTS/evaluation.txt" label="evaluation_of_clusters" />
166 <data name="combined_cm_out" format="txt" from_work_dir="combined_cm_out" label="combined_cmsearch_output" />
167 <collection name="clusters" type="list" label="CLUSTERS">
168 <discover_datasets pattern="(?P&lt;name&gt;^.*\.all$)" directory="RESULTS" />
169 </collection>
170 <collection name="partitions" type="list" label="Partitions">
171 <discover_datasets pattern="(?P&lt;name&gt;^.*$)" directory="RESULTS/partitions" />
172 </collection>
173 <collection name="topSecondaryStruct" type="list" label="Top $results_top_num alirna.ps">
174 <discover_datasets format="png" pattern="(?P&lt;name&gt;^.*\.alirna.png$)" />
175 </collection>
176 <collection name="topDot" type="list" label="Top $results_top_num aln.ps">
177 <discover_datasets format="png" pattern="(?P&lt;name&gt;^.*\.aln.png$)" />
178 </collection>
179 <collection name="rscapePlot" type="list" label="R-scape Plot">
180 <discover_datasets format="pdf" pattern="(?P&lt;name&gt;^.*\.pdf$)" />
181 </collection>
182 <data name="RESULTS_zip" format="zip" from_work_dir="RESULTS.zip" label="RESULTS.zip" />
183 </outputs>
184 <tests>
185 <test>
186 <param name="FASTA" value="FASTA.zip" ftype="searchgui_archive"/>
187 <param name="cmsearch_results" value="1.1.tree,1.2.tree"/>
188 <param name="model_tree_files" value="1.1.model.tree.fa,1.2.model.tree.fa"/>
189 <param name="combined_cm_out" value="combined_cm_out"/>
190 <param name="partition_type" value="0"/>
191 <param name="cut_type" value="0"/>
192 <conditional name="iteration_num">
193 <param name="iteration_num_selector" value="false"/>
194 </conditional>
195 <param name="merge_cluster_ol" value="0.66"/>
196 <param name="merge_overlap" value="0.51"/>
197 <param name="min_cluster_size" value="3"/>
198 <param name="cm_min_bitscore" value="20"/>
199 <param name="cm_max_eval" value="0.001"/>
200 <param name="cm_bitscore_sig" value="0"/>
201 <output name="final_stats" file="RESULTS/cluster.final.stats" />
202 <output_collection name="clusters" type="list">
203 <element name="1.cluster.all" file="RESULTS/1.cluster.all" compare="contains"/>
204 <element name="2.cluster.all" file="RESULTS/2.cluster.all" compare="contains"/>
205
206 </output_collection>
207 <output_collection name="partitions">
208 <element name="final_overlap.map" file="RESULTS/partitions/final_overlap.map" compare="contains">
209 <assert_contents>
210 <has_text text="1.1 1.1 " />
211 <has_text text="1.2 1.2" />
212 </assert_contents>
213 </element>
214 <element name="final_overlap.matrix" file="RESULTS/partitions/final_overlap.matrix" compare="contains">
215 <assert_contents>
216 <has_text text="MODEL CLASS 0 0" />
217 <!--has_text text="1.2" />
218 <has_text text="1.1" /-->
219 </assert_contents>
220 </element>
221 <element name="final_partition.hard.best" file="RESULTS/partitions/final_partition.hard.best" />
222 <element name="final_partition.hard.merged" file="RESULTS/partitions/final_partition.hard.merged" />
223 <element name="final_partition.soft" file="RESULTS/partitions/final_partition.soft" />
224 <element name="final_partition.used_cmsearch" file="RESULTS/partitions/final_partition.used_cmsearch" compare="contains"/>
225 </output_collection>
226 <param name="results_top_num" value="5"/>
227 <output_collection name="topSecondaryStruct" type="list">
228 <element name="1.cluster.top5.alirna.png" file="1.cluster.top5.alirna.png" ftype="png" compare="sim_size" />
229 <element name="2.cluster.top5.alirna.png" file="2.cluster.top5.alirna.png" ftype="png" compare="sim_size" />
230 </output_collection>
231 <output_collection name="topDot" type="list">
232 <element name="1.cluster.top5.aln.png" file="1.cluster.top5.aln.png" ftype="png" compare="sim_size" />
233 <element name="2.cluster.top5.aln.png" file="2.cluster.top5.aln.png" ftype="png" compare="sim_size" />
234 </output_collection>
235
236 <output_collection name="rscapePlot" type="list">
237 <element name="1.cluster.top5.result.aln_1.R2R.sto.pdf" file="1.cluster.top5.result.aln_1.R2R.sto.pdf" ftype="pdf" compare="sim_size" />
238 <element name="2.cluster.top5.result.aln_1.R2R.sto.pdf" file="2.cluster.top5.result.aln_1.R2R.sto.pdf" ftype="pdf" compare="sim_size" />
239 </output_collection>
240
241 <output name="RESULTS_zip" file="RESULTS.zip" ftype="zip" compare="sim_size" delta="20000"/>
242
243 </test>
244 </tests>
245 <help>
246 <![CDATA[
247
248 **What it does**
249
250 Post-processing. Redundant clusters are merged and instances that belong to multiple clusters
251 are assigned unambiguously. For every pair of clusters, the relative overlap (i.e. the fraction of
252 instances that occur in both clusters) is computed and clusters are merged if the overlap exceeds 50%.
253 Cluster members are finally ranked by their CM bitscore.
254
255 ]]>
256 </help>
257 <citations>
258 <citation type="bibtex">@inproceedings{costa2010fast,
259 title={Fast neighborhood subgraph pairwise distance kernel},
260 author={Costa, Fabrizio and De Grave, Kurt},
261 booktitle={Proceedings of the 26th International Conference on Machine Learning},
262 pages={255--262},
263 year={2010},
264 organization={Omnipress}
265 }
266 </citation>
267 </citations>
268 </tool>