Mercurial > repos > rnateam > graphclust_postprocessing_no_align

comparison glob_report_no_align.xml @ 0:b8bd06d72563 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/GraphClust/CollectResultsNoAlign commit 2a6fd70c1bcec36ffdf0bba2ec82489b39cfc84e
author rnateam
date Sat, 27 Oct 2018 13:50:00 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:b8bd06d72563
1 <tool id="graphclust_glob_report_no_align" name="Graphclust glob_report collect clusters" version="0.5" >
2 <requirements>
3 <requirement type="package" version="0.6.0">graphclust-wrappers</requirement>
4 <requirement type="package" version='0.5'>perl-array-utils</requirement>
5 <requirement type="package" version='0.18.1'>scikit-learn</requirement>
6 <requirement type="package" version='1.8.10'>locarna</requirement>
7 <requirement type="package" version='2.1'>rnaz</requirement>
8 <requirement type="package" version="1.1.2">infernal</requirement>
9 <requirement type="package" version='2.2.10'>viennarna</requirement>
10 <requirement type="package" version='1.3.30'>graphicsmagick</requirement>
11 <requirement type="package" version='0.6.1'>rscape</requirement>
12 <requirement type="package" version='6.0'>unzip</requirement>
13 </requirements>
14 <command detect_errors="exit_code">
15 <![CDATA[
16 unzip $FASTA &> /dev/null &&
17 mkdir ./CMSEARCH &&
18 mkdir ./MODEL &&
19 #import re
20 #for $cms_res in $cmsearch_results:
21 #set $safename_cm = re.sub('[^\w\-_\.]', '_', $cms_res.element_identifier)
22 ln -f -s '$cms_res' ./CMSEARCH/$safename_cm &&
23 #end for
24 #for $mods in $model_tree_files:
25 #set $safename_tr = re.sub('[^\w\-_\.]', '_', $mods.element_identifier)
26 ln -f -s '$mods' ./MODEL/$safename_tr &&
27 #end for
28
29 'glob_res.pl'
30 $merge_cluster_ol
31 $merge_overlap
32 $min_cluster_size
33 $cm_min_bitscore
34 $cm_max_eval
35 1 ## cm_bitscore_sig
36 $partition_type ''
37 $cut_type
38 0 ## zero means do not align
39 #if $iteration_num.iteration_num_selector:
40 $iteration_num.CI
41 $final_partition_soft
42 $final_partition_used_cmsearch
43 '$combined_cm'
44
45 #end if
46
47 &&
48 python '$__tool_directory__/evaluation.py' FASTA/ RESULTS/
49
50 #if $cdhit:
51 &&
52 python '$__tool_directory__/addCdhitseqs.py' '$cdhit'
53 #end if
54 ]]>
55 </command>
56 <inputs>
57 <param type="data" name="FASTA" format="zip" help="FASTA.zip from pre-processing step"/>
58 <param type="data" name="cmsearch_results" format="tabular" multiple="True"
59 help="Tabular cmsearch results of the candidate clusters from the cmsearch step"/>
60 <param type="data" name="model_tree_files" format="txt" multiple="True" label="model-tree-stk"
61 help="model.tree.stk files from pgma_graphclust candidate clustering step"/>
62 <param name="partition_type" type="boolean" checked="True" truevalue="0" falsevalue="1" label="Hard partition"
63 help="Whether to do hard partitioning (no overlap) or soft mode(cluster elements may overlap) "/>
64 <param name="cut_type" type="boolean" checked="True" truevalue="0" falsevalue="1" label="Use CM score for cutoff" help="otherwise use E-value"/>
65 <param name="cm_min_bitscore" type="integer" value="20" size="5" label="cm_min_bitscore" help=""/>
66 <param name="cm_max_eval" type="float" value="0.001" size="5" label="cm_max_E-val" help=""/>
67 <param type="data" name="cdhit" format="txt" optional="true" label="CD-HIT output"
68 help="Optional CD-HIT pre-clustering output to be combined into the final clustering output"/>
69 <param name="merge_cluster_ol" type="float" value="0.66" size="5" label="merge_cluster_ovelap"
70 help="Overlapping ratio criteria to merge overlapping clusters or keep separate clusters (soft partitioning)"/>
71 <param name="merge_overlap" type="float" value="0.51" size="5" label="merge_fraction_overlap"
72 help="Overlapping ratio criteria to merge overlapping sequence fractions from same input sequence"/>
73 <param name="min_cluster_size" type="integer" value="3" size="5" label="minimum cluster size"
74 help="Minimum number of elements that can form a cluster. Higher values discard small clusters and may produce larger merged clusters"/>
75 <!-- <param name="cm_bitscore_sig" type="integer" value="1" size="5" label="cm_bitscore_sig" help=""/> -->
76
77 <conditional name="iteration_num">
78 <param name="iteration_num_selector" type="boolean" checked="no" label="Multiple iterations" help="for single iteration- NO, for multiple-YES"/>
79 <when value="true">
80 <param name="CI" type="integer" value="2" size="5" label="Number of current iteration "/>
81 <param type="data" name="final_partition_soft" format="txt" />
82 <param type="data" name="final_partition_used_cmsearch" format="txt" />
83 <param type="data" name="combined_cm" format="txt" />
84 </when>
85 <when value="false" ></when>
86 </conditional>
87
88 </inputs>
89 <outputs>
90 <data name="final_stats" format="txt" from_work_dir="RESULTS/cluster.final.stats" label="cluster.final.stats" />
91 <data name="tableForEval" format="tabular" from_work_dir="RESULTS/fullTab.tabular" label="tableForEval" />
92 <data name="final_soft" format="txt" from_work_dir="RESULTS/partitions/final_partition.soft" label="soft_part" />
93 <data name="final_used_cmsearch" format="txt" from_work_dir="RESULTS/partitions/final_partition.used_cmsearch" label="final_partition_used_cmsearch" />
94 <data name="evaluation" format="txt" from_work_dir="RESULTS/evaluation.txt" label="evaluation_of_clusters" />
95 <data name="combined_cm_out" format="txt" from_work_dir="combined_cm_out" label="combined_cmsearch_output" />
96 <collection name="clusters" type="list" label="CLUSTERS-cmsearch">
97 <discover_datasets format="txt" pattern="(?P&lt;name&gt;^.*\.all$)" directory="RESULTS" />
98 </collection>
99 <collection name="allFastaSorted" type="list" label="cluster-sequences-sorted">
100 <discover_datasets format="fasta" pattern="(?P&lt;name&gt;^.*\.sorted.fa$)" directory="RESULTS" />
101 </collection>
102
103 <collection name="partitions" type="list" label="Partitions">
104 <discover_datasets pattern="(?P&lt;name&gt;^.*$)" directory="RESULTS/partitions" />
105 </collection>
106 <data name="RESULTS_zip" format="zip" from_work_dir="RESULTS.zip" label="RESULTS.zip" />
107 </outputs>
108 <tests>
109 <test>
110 <param name="FASTA" value="FASTA.zip" ftype="searchgui_archive"/>
111 <param name="cmsearch_results" value="1.1.tree,1.2.tree"/>
112 <param name="model_tree_files" value="1.1.model.tree.fa,1.2.model.tree.fa"/>
113 <param name="partition_type" value="0"/>
114 <param name="cut_type" value="0"/>
115 <conditional name="iteration_num">
116 <param name="iteration_num_selector" value="false"/>
117 </conditional>
118 <param name="merge_cluster_ol" value="0.66"/>
119 <param name="merge_overlap" value="0.51"/>
120 <param name="min_cluster_size" value="3"/>
121 <param name="cm_min_bitscore" value="20"/>
122 <param name="cm_max_eval" value="0.001"/>
123 <!-- <param name="cm_bitscore_sig" value="0"/> -->
124 <output name="final_stats" file="RESULTS/cluster.final.stats" />
125 <output name="combined_cm_out" file="combined_cm_out"/>
126 <output name="evaluation" file="evaluation1.txt"/>
127 <output_collection name="clusters" type="list">
128 <element name="1.cluster.all" file="RESULTS/1.cluster.all" compare="contains"/>
129 <element name="2.cluster.all" file="RESULTS/2.cluster.all" compare="contains"/>
130
131 </output_collection>
132 <output_collection name="partitions">
133 <element name="final_overlap.map" file="RESULTS/partitions/final_overlap.map" compare="contains">
134 <assert_contents>
135 <has_text text="1.1 1.1 " />
136 <has_text text="1.2 1.2" />
137 </assert_contents>
138 </element>
139 <element name="final_overlap.matrix" file="RESULTS/partitions/final_overlap.matrix" compare="contains">
140 <assert_contents>
141 <has_text text="MODEL CLASS 0 0" />
142 <!--has_text text="1.2" />
143 <has_text text="1.1" /-->
144 </assert_contents>
145 </element>
146 <element name="final_partition.hard.best" file="RESULTS/partitions/final_partition.hard.best" />
147 <element name="final_partition.hard.merged" file="RESULTS/partitions/final_partition.hard.merged" />
148 <element name="final_partition.soft" file="RESULTS/partitions/final_partition.soft" />
149 <element name="final_partition.used_cmsearch" file="RESULTS/partitions/final_partition.used_cmsearch" compare="contains"/>
150 </output_collection>
151
152 <output name="RESULTS_zip" file="RESULTS.zip" ftype="zip" compare="sim_size" delta="20000"/>
153
154 </test>
155 </tests>
156 <help>
157 <![CDATA[
158
159 **What it does**
160
161 Post-processing. Redundant clusters are merged and instances that belong to multiple clusters
162 are assigned unambiguously. For every pair of clusters, the relative overlap (i.e. the fraction of
163 instances that occur in both clusters) is computed and clusters are merged if the overlap exceeds 50%.
164 Cluster members are finally ranked by their CM bitscore.
165
166 ]]>
167 </help>
168 <citations>
169 <citation type="doi">10.5281/zenodo.597695</citation>
170 </citations>
171 </tool>