Mercurial > repos > rnateam > graphclust_preprocessing

comparison preprocessing.xml @ 5:f4ad5dceb619 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 commit 9a3dc91fa984be18fabc0d968360634d787c9589
author rnateam
date Wed, 24 May 2017 09:56:11 -0400
parents a82b46966340
children e31c659be8bc
comparison
equal deleted inserted replaced
4:a82b46966340 5:f4ad5dceb619
1 <tool id="preproc" name="Preprocessing" version="0.1"> 1 <tool id="preproc" name="Preprocessing" version="0.2">
2 <requirements> 2 <requirements>
3 <requirement type="package" version="0.1.12">graphclust-wrappers</requirement> 3 <requirement type="package" version="0.1.12">graphclust-wrappers</requirement>
4 </requirements> 4 </requirements>
5 <stdio> 5 <stdio>
6 <exit_code range="1:" /> 6 <exit_code range="1:" />
7 </stdio> 7 </stdio>
8 <command> 8 <command>
9 <![CDATA[ 9 <![CDATA[
10 preprocessing.pl
11 '$fastaFile'
12 $max_length
13 $in_winShift
14 $min_seq_length
10 15
11 'preprocessing.pl' 16 #if $SHAPEdata:
12 '$fastaFile' $max_length $in_winShift $min_seq_length 17 &&
13 18 python '$__tool_directory__/splitSHAPE.py'
19 '$SHAPEdata'
20 $max_length
21 #end if
14 ]]> 22 ]]>
15 </command> 23 </command>
16 <inputs> 24 <inputs>
17 <param type="data" name="fastaFile" format="fasta" /> 25 <param type="data" name="fastaFile" format="fasta" />
26 <param type="data" name="SHAPEdata" format="txt" optional="true" label="SHAPE data"/>
18 <param name="max_length" type="integer" value="10000" size="5" label="window size"/> 27 <param name="max_length" type="integer" value="10000" size="5" label="window size"/>
19 <param name="in_winShift" type="integer" value="100" size="5" label="window shift in percent"/> 28 <param name="in_winShift" type="integer" value="100" size="5" label="window shift in percent"/>
20 <param name="min_seq_length" type="integer" value="5" size="5" label="minimum sequence length"/> 29 <param name="min_seq_length" type="integer" value="5" size="5" label="minimum sequence length"/>
21 </inputs> 30 </inputs>
22
23 <outputs> 31 <outputs>
24 <data name="data.fasta" format="fasta" from_work_dir="FASTA/data.fasta" label="data.fasta"/> 32 <data name="data.fasta" format="fasta" from_work_dir="FASTA/data.fasta" label="data.fasta"/>
25 <data name="data.map" format="txt" from_work_dir="FASTA/data.map" label="data.map"/> 33 <data name="data.map" format="txt" from_work_dir="FASTA/data.map" label="data.map"/>
26 <data name="data.names" format="txt" from_work_dir="FASTA/data.names" label="data.names"/> 34 <data name="data.names" format="txt" from_work_dir="FASTA/data.names" label="data.names"/>
27 <data name="data.fasta.scan" format="fasta" from_work_dir="FASTA/data.fasta.scan" label="data.fasta.scan"/> 35 <data name="data.fasta.scan" format="fasta" from_work_dir="FASTA/data.fasta.scan" label="data.fasta.scan"/>
28 <data name="FASTA" format="zip" from_work_dir="FASTA.zip" label="FASTA.ZIP"/> 36 <data name="FASTA" format="zip" from_work_dir="FASTA.zip" label="FASTA.ZIP"/>
37 <data name="shape_data_split" format="txt" from_work_dir="shape_data_split.react" label="SHAPE data splited"/>
29 </outputs> 38 </outputs>
39 <tests>
40 <test>
41 <param name="fastaFile" value="input.fa"/>
42 <param name="max_length" value="10000"/>
43 <param name="in_winShift" value="100"/>
44 <param name="min_seq_length" value="5"/>
45 <output name="data.fasta" file="FASTA/data.fasta"/>
46 <output name="data.map" file="FASTA/data.map" />
47 <output name="data.names" file="FASTA/data.names"/>
48 <output name="data.fasta.scan" file="FASTA/data.fasta.scan" />
49 </test>
30 50
31 51 <test>
32 <tests> 52 <param name="fastaFile" value="sample_3.fa"/>
33 <test> 53 <param name="SHAPEdata" value="sample_3.react"/>
34 <param name="fastaFile" value="input.fa"/> 54 <param name="max_length" value="100"/>
35 <param name="max_length" value="10000"/> 55 <param name="in_winShift" value="50"/>
36 <param name="in_winShift" value="100"/> 56 <param name="min_seq_length" value="5"/>
37 <param name="min_seq_length" value="5"/> 57 <output name="shape_data_split" file="sample_3_shape_data_split.react" />
38 <output name="data.fasta" file="FASTA/data.fasta"/> 58 </test>
39 <output name="data.map" file="FASTA/data.map" /> 59 </tests>
40 <output name="data.names" file="FASTA/data.names"/>
41 <output name="data.fasta.scan" file="FASTA/data.fasta.scan" />
42 </test>
43 </tests>
44
45 <help> 60 <help>
46 <![CDATA[ 61 <![CDATA[
47 62
48 **What it does** 63 **What it does**
49 64
55 The shift of the sliding window can be defined via option *window shift in percent*. 70 The shift of the sliding window can be defined via option *window shift in percent*.
56 This paramter reflects the expected length of signals to be found. 71 This paramter reflects the expected length of signals to be found.
57 Slightly larger windows are usually ok. Too small windows can disturb existing signals. 72 Slightly larger windows are usually ok. Too small windows can disturb existing signals.
58 73
59 74
60
61
62 + **window shift in percent** : Relative window size in % for window shift during input preprocessing. 75 + **window shift in percent** : Relative window size in % for window shift during input preprocessing.
63 Please note that a small shift results in much more fragments for clustering. The benefit is that RNA 76 Please note that a small shift results in much more fragments for clustering. The benefit is that RNA
64 motifs/structures are not destroyed by arbitrary split points. Smaller 77 motifs/structures are not destroyed by arbitrary split points. Smaller
65 shifts usually increase the cluster quality. Too small shifts (<20) are not 78 shifts usually increase the cluster quality. Too small shifts (<20) are not
66 recommended as a dense center is "polluted" by overlapping fragments and 79 recommended as a dense center is "polluted" by overlapping fragments and
67 no other occurences in the dataset can be found. 80 no other occurences in the dataset can be found.
68 81
69 82
70
71
72
73 + **minimum sequence length** : Minimal length of input sequences. 83 + **minimum sequence length** : Minimal length of input sequences.
74 Every input sequence below that length is ignored completely during clustering. 84 Every input sequence below that length is ignored completely during clustering.
75 85
76
77 ]]></help> 86 ]]></help>
78
79
80 <citations> 87 <citations>
81 <citation type="doi">10.1093/bioinformatics/bts224</citation> 88 <citation type="doi">10.1093/bioinformatics/bts224</citation>
82 </citations> 89 </citations>
83
84
85 </tool> 90 </tool>