Mercurial > repos > rnateam > graphclust_nspdk

comparison NSPDK_candidateClusters.xml @ 0:165fe96228be 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/NSPDK commit 21aaee40723b5341b4236edeb0e72995c2054053
author rnateam
date Fri, 16 Dec 2016 07:36:07 -0500
parents
children 90a4a2e7d876
comparison
equal deleted inserted replaced
-1:000000000000 0:165fe96228be
1 <tool id="NSPDK_candidateClust" name="NSPDK_candidateClusters" version="9.2">
2 <requirements>
3 <requirement type="package" version="0.1">graphclust-wrappers</requirement>
4 <requirement type="package" version="0.5">perl-array-utils</requirement>
5 <requirement type="package" version="9.2">nspdk</requirement>
6 </requirements>
7 <stdio>
8 <exit_code range="1:" />
9 </stdio>
10 <command>
11 <![CDATA[
12
13 mkdir -p SVECTOR &&
14
15 cp $data_svector SVECTOR/data.svector &&
16
17 'NSPDK_candidateClusters.pl' '$data_fasta' '$data_names' $noCache $ensf $oc $usn $knn $nhf $nspdk_nhf_max $nspdk_nhf_step $GLOBAL_num_clusters $max_rad $max_dist_relations
18
19 #if $iteration_num.iteration_num_selector:
20 $iteration_num.CI
21 '$blacklist'
22 '$final_partition_soft'
23 '$fast_cluster_last_round'
24 $iteration_num.GLOBAL_hit_blacklist_overlap
25
26 #else:
27 1
28
29 #end if
30
31 ]]>
32 </command>
33 <inputs>
34 <param type="data" name="data_svector" format="zip" />
35 <param type="data" name="data_fasta" format="fasta" />
36 <param type="data" name="data_names" format="txt" />
37 <conditional name="iteration_num">
38 <param name="iteration_num_selector" type="boolean" checked="no" label="Multiple iterations" help="for single iteration- NO, for multiple-YES"/>
39 <when value="true">
40 <param name="CI" type="integer" value="2" size="5" label="Number of current iteration "/>
41 <param type="data" name="blacklist" format="txt" />
42 <param type="data" name="final_partition_soft" format="txt" />
43 <param type="data" name="fast_cluster_last_round" format="txt" />
44 <param name="GLOBAL_hit_blacklist_overlap" type="float" value="0.2" size="5" label="Blacklist hit overlap" />
45 </when>
46 <when value="false" >
47 <param name="CI" type="hidden" value="1" size="5" label="Number of current iteration "></param>
48 </when>
49 </conditional>
50 <param name="max_rad" type="integer" value="3" size="5" label="maximum radius " help="-R"/>
51 <param name="max_dist_relations" type="integer" value="3" size="5" label="maximum distance relations" help="-D"/>
52 <param name="noCache" truevalue="-no-cache" falsevalue="" checked="True" type="boolean"
53 label="Deactivate caching of kernel value computation (-no-cache)" help="to minimize memory usage"/>
54 <param name="ensf" type="integer" value="5" size="5" label="eccess neighbour size factor" help="-ensf"/>
55 <param name="usn" truevalue="-usn" falsevalue="" checked="True" type="boolean"
56 label="Use shared neighbourhood to weight center density (-usn)" help="by default true"/>
57 <param name="oc" truevalue="-oc" falsevalue="" checked="True" type="boolean"
58 label=" flag to output clusters (-oc)" help="by default true"/>
59 <param name="knn" type="integer" value="20" size="5" label="Number of nearest neighbors" help="-knn num"/>
60 <param name="nhf" type="integer" value="500" size="5" label="Number of hash functions " help="-nhf num"/>
61 <param name="nspdk_nhf_max" type="integer" value="1000" size="5" label="Maximal number of hash functions " />
62 <param name="nspdk_nhf_step" type="integer" value="25" size="5" label="Size of step for increasing hash functions " help="The number of hash functions is increased by this value after each iteration."/>
63 <param name="GLOBAL_num_clusters" type="integer" value="100" size="5" label="Maxinum number of clusters " />
64 </inputs>
65 <outputs>
66 <data name="fast_cluster" format="txt" from_work_dir="SVECTOR/data.svector.1.fast_cluster" label="fast_cluster.1" >
67 <filter> iteration_num['iteration_num_selector'] is False</filter>
68 </data>
69 <data name="fast_cluster_sim" format="txt" from_work_dir="SVECTOR/data.svector.1.fast_cluster_sim" label="fast_cluster_sim.1" >
70 <filter> iteration_num['iteration_num_selector'] is False </filter>
71 </data>
72 <data name="black_list" format="txt" from_work_dir="SVECTOR/data.svector.blacklist.1" label="blacklist.1" >
73 <filter> iteration_num['iteration_num_selector'] is False </filter>
74 </data>
75 <data name="fast_cluster_m" format="txt" from_work_dir="SVECTOR/data.svector.*.fast_cluster" label="fast_cluster.$iteration_num.CI" >
76 <filter> iteration_num['iteration_num_selector'] is True</filter>
77 </data>
78 <data name="fast_cluster_sim_m" format="txt" from_work_dir="SVECTOR/data.svector.*.fast_cluster_sim" label="fast_cluster_sim.$iteration_num.CI" >
79 <filter> iteration_num['iteration_num_selector'] is True</filter>
80 </data>
81 <data name="black_list_m" format="txt" from_work_dir="SVECTOR/data.svector.blacklist.*" label="blacklist.$iteration_num.CI" >
82 <filter> iteration_num['iteration_num_selector'] is True</filter>
83 </data>
84 </outputs>
85 <tests>
86 <test>
87 <param name="data_fasta" value="data.fasta"/>
88 <param name="data_names" value="data.names"/>
89 <param name="data_svector" value="data.svector.1" ftype="zip" />
90 <conditional name="iteration_num">
91 <param name="iteration_num_selector" value="false"/>
92 </conditional>
93 <param name="noCache" value="-no-cache"/>
94 <param name="ensf" value="5"/>
95 <param name="oc" value="-oc"/>
96 <param name="max_rad" value="3"/>
97 <param name="max_dist_relations" value="3"/>
98 <param name="usn" value="-usn"/>
99 <param name="knn" value="20"/>
100 <param name="nhf" value="500"/>
101 <param name="nspdk_nhf_max" value="1000"/>
102 <param name="nspdk_nhf_step" value="25"/>
103 <param name="GLOBAL_num_clusters" value="100"/>
104 <output name="fast_cluster" file="SVECTOR/data.svector.1.fast_cluster" />
105 <output name="fast_cluster_sim" file="SVECTOR/data.svector.1.fast_cluster_sim" />
106 <output name="black_list" file="SVECTOR/data.svector.blacklist.1" />
107 </test>
108 </tests>
109 <help>
110 <![CDATA[
111
112 **What it does**
113
114 Copmutes global feature index and returns top dense sets.
115 The candidate clusters are chosen as the top ranking neighborhoods provided that the size of their overlap
116 is below a specified threshold.
117 For more information see *Fast neighborhood subgraph pairwise distance kernel* paper.
118
119
120 **Parameters**
121
122 + **-knn** : <num nearest neighbors> (default: 10)
123
124 + **-otknn** : flag to output true (i.e. implies full kernel matrix evaluation) k-nearest neighburs (default: 0)
125
126 + **-oc** : flag to output clusters (default: 0)
127
128 + **-nhf** : <num hash functions> for the Locality Sensitive Hashing function (default: 250)
129
130 + **-ensf** : <eccess neighbour size factor> (default: 10) (0 to avoid trimming)
131
132 + **-usn** : use shared neighbourhood to weight center density (default: 0)
133
134
135 ]]>
136 </help>
137 <citations>
138 <citation type="doi">10.1093/bioinformatics/bts224</citation>
139 <citation type="bibtex">@inproceedings{costa2010fast,
140 title={Fast neighborhood subgraph pairwise distance kernel},
141 author={Costa, Fabrizio and De Grave, Kurt},
142 booktitle={Proceedings of the 26th International Conference on Machine Learning},
143 pages={255--262},
144 year={2010},
145 organization={Omnipress}
146 }
147 </citation>
148 </citations>
149 </tool>