Mercurial > repos > rnateam > graphclust_postprocessing

comparison glob_report.xml @ 5:4310ac018d05 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/eteriSokhoyan/galaxytools/tree/branchForIterations/tools/GraphClust/CollectResults commit 80c721dcfe02a2b8baf8e2c64b76cbcd71b23d86
author rnateam
date Sat, 21 Jan 2017 17:39:21 -0500
parents 4a9754d476fe
children 869a6e807d76
comparison
equal deleted inserted replaced
4:4a9754d476fe 5:4310ac018d05
1 <tool id="glob_report" name="Report_Results" version="0.1"> 1 <tool id="glob_report" name="Report_Results" version="0.1">
2 <requirements> 2 <requirements>
3 <requirement type="package" version="0.1">graphclust-wrappers</requirement> 3 <requirement type="package" version="0.1.7">graphclust-wrappers</requirement>
4 <requirement type="package" version='0.5'>perl-array-utils</requirement> 4 <requirement type="package" version='0.5'>perl-array-utils</requirement>
5 <requirement type="package" version='0.18.1'>scikit-learn</requirement> 5 <requirement type="package" version='0.18.1'>scikit-learn</requirement>
6 <requirement type="package" version='1.8.10'>locarna</requirement> 6 <requirement type="package" version='1.8.10'>locarna</requirement>
7 <requirement type="package" version='2.1'>rnaz</requirement> 7 <requirement type="package" version='2.1'>rnaz</requirement>
8 <requirement type="package" version="1.1">infernal</requirement> 8 <requirement type="package" version="1.1">infernal</requirement>
9 <requirement type="package" version='2.2.10'>viennarna</requirement> 9 <requirement type="package" version='2.2.10'>viennarna</requirement>
10 <requirement type="package" version='1.3.23'>graphicsmagick</requirement> 10 <requirement type="package" version='1.3.23'>graphicsmagick</requirement>
11 </requirements> 11 </requirements>
12 <stdio> 12 <stdio>
13 <exit_code range="1:" /> 13 <exit_code range="1:" />
14 </stdio> 14 </stdio>
15 <command> 15 <command>
16 <![CDATA[ 16 <![CDATA[
17 unzip $FASTA &> /dev/null && 17 unzip $FASTA &> /dev/null &&
18 18
19 #set $inputFiles = "" 19 #set $inputFiles = ""
20 20
21 #for $cms_res in $cmsearch_results: 21 #for $cms_res in $cmsearch_results:
27 27
28 #for $mods in $model_tree_files: 28 #for $mods in $model_tree_files:
29 #set $inputFilesTrees += str($mods)+',' 29 #set $inputFilesTrees += str($mods)+','
30 #end for 30 #end for
31 #set $inputFilesTrees = $inputFilesTrees[:-1] 31 #set $inputFilesTrees = $inputFilesTrees[:-1]
32 glob_res.pl 32 'glob_res.pl'
33 '$inputFiles' 33 '$inputFiles'
34 $merge_cluster_ol 34 $merge_cluster_ol
35 $merge_overlap 35 $merge_overlap
36 $min_cluster_size 36 $min_cluster_size
37 $cm_min_bitscore 37 $cm_min_bitscore
45 $iteration_num.CI 45 $iteration_num.CI
46 $final_partition_soft 46 $final_partition_soft
47 $final_partition_used_cmsearch 47 $final_partition_used_cmsearch
48 #end if 48 #end if
49 49
50 #if str($advanced_opts.advanced_opts_selector) == "show":
51 #if str($advanced_opts.param_type.param_type_selector) == "gclust":
52 $advanced_opts.param_type.p
53 $advanced_opts.param_type.max_diff_am
54 $advanced_opts.param_type.max_diff
55 $advanced_opts.param_type.tau
56 $advanced_opts.param_type.struct_weight
57 $advanced_opts.param_type.indel_opening
58 $advanced_opts.param_type.indel
59 $advanced_opts.param_type.alifold_consensus_dp
60 #end if
61 #end if
62
50 && 63 &&
51 python '$__tool_directory__/evaluation.py' 64 python '$__tool_directory__/evaluation.py'
52 #if $cdhit: 65 #if $cdhit:
53 && 66 &&
54 python '$__tool_directory__/addCdhitseqs.py' '$cdhit' 67 python '$__tool_directory__/addCdhitseqs.py' '$cdhit'
55 #end if 68 #end if
56 ]]> 69 ]]>
57 </command> 70 </command>
58 <inputs> 71 <inputs>
59 <param type="data" name="FASTA" format="zip" /> 72 <param type="data" name="FASTA" format="zip" />
60 <param type="data" name="cmsearch_results" format="tabular" multiple="True"/> 73 <param type="data" name="cmsearch_results" format="tabular" multiple="True"/>
61 <param type="data" name="model_tree_files" format="txt" multiple="True"/> 74 <param type="data" name="model_tree_files" format="txt" multiple="True"/>
62 <param name="partition_type" type="boolean" checked="True" truevalue="0" falsevalue="1" label="Hard partition"/> 75 <param name="partition_type" type="boolean" checked="True" truevalue="0" falsevalue="1" label="Hard partition"/>
63 <param name="cut_type" type="boolean" checked="True" truevalue="0" falsevalue="1" label="Use CM score for cutoff" help="otherwise use E-value"/> 76 <param name="cut_type" type="boolean" checked="True" truevalue="0" falsevalue="1" label="Use CM score for cutoff" help="otherwise use E-value"/>
64 <param type="data" name="cdhit" format="txt" optional="true"/> 77 <param type="data" name="cdhit" format="txt" optional="true"/>
65 <conditional name="iteration_num"> 78 <conditional name="iteration_num">
66 <param name="iteration_num_selector" type="boolean" checked="no" label="Multiple iterations" help="for single iteration- NO, for multiple-YES"/> 79 <param name="iteration_num_selector" type="boolean" checked="no" label="Multiple iterations" help="for single iteration- NO, for multiple-YES"/>
67 <when value="true"> 80 <when value="true">
68 <param name="CI" type="integer" value="2" size="5" label="Number of current iteration "/> 81 <param name="CI" type="integer" value="2" size="5" label="Number of current iteration "/>
69 <param type="data" name="final_partition_soft" format="txt" /> 82 <param type="data" name="final_partition_soft" format="txt" />
70 <param type="data" name="final_partition_used_cmsearch" format="txt" /> 83 <param type="data" name="final_partition_used_cmsearch" format="txt" />
71 </when> 84 </when>
72 <when value="false" ></when> 85 <when value="false" ></when>
73 </conditional> 86 </conditional>
74 <param name="merge_cluster_ol" type="float" value="0.66" size="5" label="merge_cluster_ol" help=""/> 87 <param name="merge_cluster_ol" type="float" value="0.66" size="5" label="merge_cluster_ol" help=""/>
75 <param name="merge_overlap" type="float" value="0.51" size="5" label="merge_overlap" help=""/> 88 <param name="merge_overlap" type="float" value="0.51" size="5" label="merge_overlap" help=""/>
76 <param name="min_cluster_size" type="integer" value="3" size="5" label="min_cluster_size" help=""/> 89 <param name="min_cluster_size" type="integer" value="3" size="5" label="min_cluster_size" help=""/>
77 <param name="cm_min_bitscore" type="integer" value="20" size="5" label="cm_min_bitscore" help=""/> 90 <param name="cm_min_bitscore" type="integer" value="20" size="5" label="cm_min_bitscore" help=""/>
78 <param name="cm_max_eval" type="float" value="0.001" size="5" label="cm_max_eval" help=""/> 91 <param name="cm_max_eval" type="float" value="0.001" size="5" label="cm_max_eval" help=""/>
79 <param name="cm_bitscore_sig" type="integer" value="1" size="5" label="cm_bitscore_sig" help=""/> 92 <param name="cm_bitscore_sig" type="integer" value="1" size="5" label="cm_bitscore_sig" help=""/>
80 <param name="results_top_num" type="integer" value="5" size="5" label="results_top_num" help=""/> 93 <param name="results_top_num" type="integer" value="5" size="5" label="results_top_num" help=""/>
81 </inputs> 94
82 <outputs> 95 <conditional name="advanced_opts">
83 <data name="final_stats" format="txt" from_work_dir="RESULTS/cluster.final.stats" label="cluster.final.stats" /> 96 <param name="advanced_opts_selector" type="select" label="Advanced Options">
84 <data name="tableForEval" format="tabular" from_work_dir="RESULTS/fullTab.tabular" label="tableForEval" /> 97 <option value="hide" selected="True">Hide</option>
85 <data name="final_soft" format="txt" from_work_dir="RESULTS/partitions/final_partition.soft" label="soft_part" /> 98 <option value="show">Show</option>
86 <data name="final_used_cmsearch" format="txt" from_work_dir="RESULTS/partitions/final_partition.used_cmsearch" label="final_partition_used_cmsearch" /> 99 </param>
87 <data name="evaluation" format="txt" from_work_dir="RESULTS/evaluation.txt" label="evaluation_of_clusters" /> 100 <when value="hide"></when>
88 <collection name="clusters" type="list" label="CLUSTERS"> 101 <when value="show">
89 <discover_datasets pattern="(?P&lt;name&gt;^.*\.all$)" directory="RESULTS" /> 102
90 </collection> 103 <conditional name="param_type">
91 <collection name="partitions" type="list" label="Partitions"> 104 <param name="param_type_selector" type="select" label="Choose the type of parameters">
92 <discover_datasets pattern="(?P&lt;name&gt;^.*$)" directory="RESULTS/partitions" /> 105 <option value="locarna">LocARNA defaults</option>
93 </collection> 106 <option value="gclust" selected="True">GrapClust defaults(changeable)</option>
94 <collection name="topSecondaryStruct" type="list" label="Top $results_top_num alirna.ps"> 107 </param>
95 <discover_datasets format="png" pattern="(?P&lt;name&gt;^.*\.alirna.png$)" /> 108 <when value="gclust">
96 </collection> 109
97 <collection name="topDot" type="list" label="Top $results_top_num aln.ps"> 110 <param name="p" type="float" value="0.001" size="5" label="minimal probability" help="-p"/>
98 <discover_datasets format="png" pattern="(?P&lt;name&gt;^.*\.aln.png$)" /> 111 <param name="max_diff_am" type="integer" value="50" size="5" label=" maximal difference for sizes of matched arcs" help="--max-diff-am"/>
99 </collection> 112 <param argument="tau" type="integer" value="50" min="0" max="200" label="Sequence contribution at structure match in percent"/>
100 </outputs> 113 <param name="max_diff" type="integer" value="100" size="5" label="maximal difference for alignment traces" help="--max-diff"/>
101 <tests> 114
102 <test> 115 <param name="struct_weight" argument="struct-weight"
103 <param name="FASTA" value="FASTA.zip" ftype="searchgui_archive"/> 116 label="Structure weight" type="integer"
104 <param name="cmsearch_results" value="1.tabular,2.tabular"/> 117 value="180" min="0" max="800" />
105 <param name="model_tree_files" value="1.1.model.tree.fa,1.2.model.tree.fa"/> 118 <param name="indel_opening" argument="indel-opening"
106 <param name="partition_type" value="0"/> 119 label="Indel opening score" type="integer"
107 <param name="cut_type" value="0"/> 120 value="-400" max="0" min="-1500" />
108 <conditional name="iteration_num"> 121 <param argument="indel" label="Indel score" type="integer"
109 <param name="iteration_num_selector" value="false"/> 122 value="-200" min="-1000" max="0" />
110 </conditional> 123
111 <param name="merge_cluster_ol" value="0.66"/> 124 <param name="alifold_consensus_dp"
112 <param name="merge_overlap" value="0.51"/> 125 type="boolean" checked="True"
113 <param name="min_cluster_size" value="3"/> 126 truevalue="--alifold-consensus-dp" falsevalue=" "
114 <param name="cm_min_bitscore" value="20"/> 127 label="Compute consensus dot plot by alifold" />
115 <param name="cm_max_eval" value="0.001"/> 128
116 <param name="cm_bitscore_sig" value="1"/> 129 </when>
117 <output name="final_stats" file="RESULTS/cluster.final.stats" /> 130 <when value="locarna">
118 <output_collection name="clusters" type="list"> 131 </when>
119 <element name="1.cluster.all" file="RESULTS/1.cluster.all" compare="contains"/> 132 </conditional>
120 <element name="2.cluster.all" file="RESULTS/2.cluster.all" compare="contains"/> 133
121 </output_collection> 134 </when>
122 <output_collection name="partitions"> 135 </conditional>
123 <element name="final_overlap.map" file="RESULTS/partitions/final_overlap.map" compare="contains"> 136
124 <assert_contents> 137 </inputs>
125 <has_text text="1.1 1.1" /> 138 <outputs>
126 <has_text text="1.2 1.2" /> 139 <data name="final_stats" format="txt" from_work_dir="RESULTS/cluster.final.stats" label="cluster.final.stats" />
127 </assert_contents> 140 <data name="tableForEval" format="tabular" from_work_dir="RESULTS/fullTab.tabular" label="tableForEval" />
128 </element> 141 <data name="final_soft" format="txt" from_work_dir="RESULTS/partitions/final_partition.soft" label="soft_part" />
129 <element name="final_overlap.matrix" file="RESULTS/partitions/final_overlap.matrix" compare="contains"> 142 <data name="final_used_cmsearch" format="txt" from_work_dir="RESULTS/partitions/final_partition.used_cmsearch" label="final_partition_used_cmsearch" />
130 <assert_contents> 143 <data name="evaluation" format="txt" from_work_dir="RESULTS/evaluation.txt" label="evaluation_of_clusters" />
131 <has_text text="MODEL CLASS 0 0" /> 144 <collection name="clusters" type="list" label="CLUSTERS">
132 <has_text text="1.2" /> 145 <discover_datasets pattern="(?P&lt;name&gt;^.*\.all$)" directory="RESULTS" />
133 <has_text text="1.1" /> 146 </collection>
134 </assert_contents> 147 <collection name="partitions" type="list" label="Partitions">
135 </element> 148 <discover_datasets pattern="(?P&lt;name&gt;^.*$)" directory="RESULTS/partitions" />
136 <element name="final_partition.hard.best" file="RESULTS/partitions/final_partition.hard.best" /> 149 </collection>
137 <element name="final_partition.hard.merged" file="RESULTS/partitions/final_partition.hard.merged" /> 150 <collection name="topSecondaryStruct" type="list" label="Top $results_top_num alirna.ps">
138 <element name="final_partition.soft" file="RESULTS/partitions/final_partition.soft" /> 151 <discover_datasets format="png" pattern="(?P&lt;name&gt;^.*\.alirna.png$)" />
139 <element name="final_partition.used_cmsearch" file="RESULTS/partitions/final_partition.used_cmsearch" compare="contains"/> 152 </collection>
140 </output_collection> 153 <collection name="topDot" type="list" label="Top $results_top_num aln.ps">
141 <param name="results_top_num" value="5"/> 154 <discover_datasets format="png" pattern="(?P&lt;name&gt;^.*\.aln.png$)" />
142 <output_collection name="topSecondaryStruct" type="list"> 155 </collection>
143 <element name="1.cluster.top5.alirna.png" file="1.cluster.top5.alirna.png" ftype="png" compare="sim_size" /> 156 <data name="RESULTS_zip" format="zip" from_work_dir="RESULTS.zip" label="RESULTS.zip" />
144 <element name="2.cluster.top5.alirna.png" file="2.cluster.top5.alirna.png" ftype="png" compare="sim_size" /> 157 </outputs>
145 </output_collection> 158 <tests>
146 <output_collection name="topDot" type="list"> 159 <test>
147 <element name="1.cluster.top5.aln.png" file="1.cluster.top5.aln.png" ftype="png" compare="sim_size"/> 160 <param name="FASTA" value="FASTA.zip" ftype="searchgui_archive"/>
148 <element name="2.cluster.top5.aln.png" file="2.cluster.top5.aln.png" ftype="png" compare="sim_size"/> 161 <param name="cmsearch_results" value="1.tabular,2.tabular"/>
149 </output_collection> 162 <param name="model_tree_files" value="1.1.model.tree.fa,1.2.model.tree.fa"/>
150 </test> 163 <param name="partition_type" value="0"/>
151 </tests> 164 <param name="cut_type" value="0"/>
152 <help> 165 <conditional name="iteration_num">
153 <![CDATA[ 166 <param name="iteration_num_selector" value="false"/>
167 </conditional>
168 <param name="merge_cluster_ol" value="0.66"/>
169 <param name="merge_overlap" value="0.51"/>
170 <param name="min_cluster_size" value="3"/>
171 <param name="cm_min_bitscore" value="20"/>
172 <param name="cm_max_eval" value="0.001"/>
173 <param name="cm_bitscore_sig" value="1"/>
174 <output name="final_stats" file="RESULTS/cluster.final.stats" />
175 <output_collection name="clusters" type="list">
176 <element name="1.cluster.all" file="RESULTS/1.cluster.all" compare="contains"/>
177 <element name="2.cluster.all" file="RESULTS/2.cluster.all" compare="contains"/>
178 </output_collection>
179 <output_collection name="partitions">
180 <element name="final_overlap.map" file="RESULTS/partitions/final_overlap.map" compare="contains">
181 <assert_contents>
182 <has_text text="1.1 1.1" />
183 <has_text text="1.2 1.2" />
184 </assert_contents>
185 </element>
186 <element name="final_overlap.matrix" file="RESULTS/partitions/final_overlap.matrix" compare="contains">
187 <assert_contents>
188 <has_text text="MODEL CLASS 0 0" />
189 <has_text text="1.2" />
190 <has_text text="1.1" />
191 </assert_contents>
192 </element>
193 <element name="final_partition.hard.best" file="RESULTS/partitions/final_partition.hard.best" />
194 <element name="final_partition.hard.merged" file="RESULTS/partitions/final_partition.hard.merged" />
195 <element name="final_partition.soft" file="RESULTS/partitions/final_partition.soft" />
196 <element name="final_partition.used_cmsearch" file="RESULTS/partitions/final_partition.used_cmsearch" compare="contains"/>
197 </output_collection>
198 <param name="results_top_num" value="5"/>
199 <output_collection name="topSecondaryStruct" type="list">
200 <element name="1.cluster.top5.alirna.png" file="1.cluster.top5.alirna.png" ftype="png" compare="sim_size" />
201 <element name="2.cluster.top5.alirna.png" file="2.cluster.top5.alirna.png" ftype="png" compare="sim_size" />
202 </output_collection>
203 <output_collection name="topDot" type="list">
204 <element name="1.cluster.top5.aln.png" file="1.cluster.top5.aln.png" ftype="png" compare="sim_size" />
205 <element name="2.cluster.top5.aln.png" file="2.cluster.top5.aln.png" ftype="png" compare="sim_size" />
206 </output_collection>
207 <output name="RESULTS_zip" file="RESULTS.zip" ftype="zip" compare="sim_size" />
208
209 </test>
210 </tests>
211 <help>
212 <![CDATA[
154 213
155 **What it does** 214 **What it does**
156 215
157 Post-processing. Redundant clusters are merged and instances that belong to multiple clusters 216 Post-processing. Redundant clusters are merged and instances that belong to multiple clusters
158 are assigned unambiguously. For every pair of clusters, the relative overlap (i.e. the fraction of 217 are assigned unambiguously. For every pair of clusters, the relative overlap (i.e. the fraction of
159 instances that occur in both clusters) is computed and clusters are merged if the overlap exceeds 50%. 218 instances that occur in both clusters) is computed and clusters are merged if the overlap exceeds 50%.
160 Cluster members are finally ranked by their CM bitscore. 219 Cluster members are finally ranked by their CM bitscore.
161 220
162 ]]> 221 ]]>
163 </help> 222 </help>
164 <citations> 223 <citations>
165 <citation type="bibtex">@inproceedings{costa2010fast, 224 <citation type="bibtex">@inproceedings{costa2010fast,
166 title={Fast neighborhood subgraph pairwise distance kernel}, 225 title={Fast neighborhood subgraph pairwise distance kernel},
167 author={Costa, Fabrizio and De Grave, Kurt}, 226 author={Costa, Fabrizio and De Grave, Kurt},
168 booktitle={Proceedings of the 26th International Conference on Machine Learning}, 227 booktitle={Proceedings of the 26th International Conference on Machine Learning},
169 pages={255--262}, 228 pages={255--262},