Mercurial > repos > yufei-luo > s_mart

comparison SMART/galaxy/clusterizeBySlidingWindows.xml @ 58:5f5c9b74c2dd

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author m-zytnicki
date Fri, 07 Feb 2014 11:53:36 -0500
parents 2c0c0a89fad7
children
comparison
equal deleted inserted replaced
57:36eaa579fdb6 58:5f5c9b74c2dd
2 <description>Produces a GFF3 file that clusters a list of transcripts using a sliding window. Cluster the data into regions (defined by size and overlap with next region).</description> 2 <description>Produces a GFF3 file that clusters a list of transcripts using a sliding window. Cluster the data into regions (defined by size and overlap with next region).</description>
3 <requirements> 3 <requirements>
4 <requirement type="set_environment">PYTHONPATH</requirement> 4 <requirement type="set_environment">PYTHONPATH</requirement>
5 </requirements> 5 </requirements>
6 <command interpreter="python"> 6 <command interpreter="python">
7 ../Java/Python/clusterizeBySlidingWindows.py -i $formatType.inputFileName 7 #set $inputFiles = ",".join(["%s" % (s) for s in $formatType.inputFileName])
8 #if $formatType.FormatInputFileName == 'bed': 8 ../Java/Python/clusterizeBySlidingWindows.py -i $inputFiles -f $formatType.FormatInputFileName -s $size -e $overlap -o $outputFileGff $strands
9 -f bed
10 #elif $formatType.FormatInputFileName == 'gff':
11 -f gff
12 #elif $formatType.FormatInputFileName == 'gff2':
13 -f gff2
14 #elif $formatType.FormatInputFileName == 'gff3':
15 -f gff3
16 #elif $formatType.FormatInputFileName == 'sam':
17 -f sam
18 #elif $formatType.FormatInputFileName == 'gtf':
19 -f gtf
20 #end if
21 -s $size
22 -e $overlap
23 -o $outputFileGff
24 $normalize
25 $strands
26 9
27 #if $OptionTag.tag == "Yes": 10 #if $OptionTag.tag == "Yes":
28 -g $OptionTag.value 11 -g $OptionTag.value
29 #end if 12 #end if
30 13
31 #if $OptionsOperation.operation == "Yes": 14 #if $OptionsOperation.operation == "Yes":
32 -r $OptionsOperation.value 15 -r $OptionsOperation.value
33 #end if 16 #end if
34 17
35 #if $OptionWriteTag.writeTag == "Yes": 18 #if $OptionWriteTag.writeTag == "Yes":
36 -w $OptionWriteTag.value 19 #set $outputTags = ",".join(["%s" % (t["value"]) for t in $OptionWriteTag.writeTags])
20 -w $outputTags
37 #end if 21 #end if
38
39 $strand
40 $plot $plotPng
41 $excel $excelOutput
42
43 22
44 </command> 23 </command>
45 24
46 <inputs> 25 <inputs>
47 <conditional name="formatType"> 26 <conditional name="formatType">
50 <option value="gff">gff</option> 29 <option value="gff">gff</option>
51 <option value="gff2">gff2</option> 30 <option value="gff2">gff2</option>
52 <option value="gff3">gff3</option> 31 <option value="gff3">gff3</option>
53 <option value="sam">sam</option> 32 <option value="sam">sam</option>
54 <option value="gtf">gtf</option> 33 <option value="gtf">gtf</option>
34 <option value="bam">bam</option>
55 </param> 35 </param>
56 <when value="bed"> 36 <when value="bed">
57 <param name="inputFileName" format="bed" type="data" label="Input File"/> 37 <param name="inputFileName" format="bed" type="data" multiple="true" label="Input File"/>
58 </when> 38 </when>
59 <when value="gff"> 39 <when value="gff">
60 <param name="inputFileName" format="gff" type="data" label="Input File"/> 40 <param name="inputFileName" format="gff" type="data" multiple="true" label="Input File"/>
61 </when> 41 </when>
62 <when value="gff2"> 42 <when value="gff2">
63 <param name="inputFileName" format="gff2" type="data" label="Input File"/> 43 <param name="inputFileName" format="gff2" type="data" multiple="true" label="Input File"/>
64 </when> 44 </when>
65 <when value="gff3"> 45 <when value="gff3">
66 <param name="inputFileName" format="gff3" type="data" label="Input File"/> 46 <param name="inputFileName" format="gff3" type="data" multiple="true" label="Input File"/>
67 </when> 47 </when>
68 <when value="sam"> 48 <when value="sam">
69 <param name="inputFileName" format="sam" type="data" label="Input File"/> 49 <param name="inputFileName" format="sam" type="data" multiple="true" label="Input File"/>
70 </when> 50 </when>
71 <when value="gtf"> 51 <when value="gtf">
72 <param name="inputFileName" format="gtf" type="data" label="Input File"/> 52 <param name="inputFileName" format="gtf" type="data" multiple="true" label="Input File"/>
53 </when>
54 <when value="bam">
55 <param name="inputFileName" format="bam" type="data" multiple="true" label="Input File"/>
73 </when> 56 </when>
74 </conditional> 57 </conditional>
75 58
76 59
77 <param name="size" type="text" value="50000" label="Size option" help="Size of the regions."/> 60 <param name="size" type="text" value="50000" label="Size option" help="Size of the regions."/>
78 <param name="overlap" type="text" value="50" label="Overlap option" help="Overlap between two consecutive regions."/> 61 <param name="overlap" type="text" value="50" label="Overlap option" help="Overlap between two consecutive regions."/>
79 <param name="normalize" type="boolean" truevalue="-m" falsevalue="" checked="false" label="Normalize option for only GFF3 file format" help="(only work if the tag nbOccurrences is set)"/>
80 <param name="strands" type="boolean" truevalue="-2" falsevalue="" checked="false" label="Consider the two strands separately"/> 62 <param name="strands" type="boolean" truevalue="-2" falsevalue="" checked="false" label="Consider the two strands separately"/>
81 63
82 <conditional name="OptionTag"> 64 <conditional name="OptionTag">
83 <param name="tag" type="select" label="Use a given tag as input (instead of summing number of features)"> 65 <param name="tag" type="select" label="Use a given tag as input (instead of summing number of features)">
84 <option value="Yes">Yes</option> 66 <option value="Yes">Yes</option>
88 <param name="value" type="select" label="tag name"/> 70 <param name="value" type="select" label="tag name"/>
89 </when> 71 </when>
90 <when value="No"> 72 <when value="No">
91 </when> 73 </when>
92 </conditional> 74 </conditional>
93
94 75
95 <conditional name="OptionsOperation"> 76 <conditional name="OptionsOperation">
96 <param name="operation" type="select" label="combine tag value with given operation"> 77 <param name="operation" type="select" label="combine tag value with given operation">
97 <option value="Yes">Yes</option> 78 <option value="Yes">Yes</option>
98 <option value="No" selected="true">No</option> 79 <option value="No" selected="true">No</option>
108 </when> 89 </when>
109 <when value="No"> 90 <when value="No">
110 </when> 91 </when>
111 </conditional> 92 </conditional>
112 93
113
114 <conditional name="OptionWriteTag"> 94 <conditional name="OptionWriteTag">
115 <param name="writeTag" type="select" label="write a new tag in output file"> 95 <param name="writeTag" type="select" label="use given tag in output file">
116 <option value="Yes">Yes</option> 96 <option value="Yes">Yes</option>
117 <option value="No" selected="true">No</option> 97 <option value="No" selected="true">No</option>
118 </param> 98 </param>
119 <when value="Yes"> 99 <when value="Yes">
120 <param name="value" type="text" value="nbElements" label="write tag option" help="print the result in the given tag (default usually is 'nbElements')"/> 100 <repeat name="writeTags" title="Output Tag" min="1">
101 <param name="value" type="text" value="nbElements" label="write tag option" help="print the result in the given tag (default usually is 'nbElements')"/>
102 </repeat>
121 </when> 103 </when>
122 <when value="No"> 104 <when value="No">
123 </when> 105 </when>
124 </conditional> 106 </conditional>
125 107
130 </outputs> 112 </outputs>
131 113
132 <help> 114 <help>
133 Sliding windows are a convenient ways to clusterize data mapped on the genome. There are two important parameters of a sliding window: the size of the window and the size of the overlap. 115 Sliding windows are a convenient ways to clusterize data mapped on the genome. There are two important parameters of a sliding window: the size of the window and the size of the overlap.
134 116
135 By default, sliding windows count the number of reads in each window. However, you can basically merge any information which is contained in the tags. You can compute the average, sum, median, max or min of the tags for each window. For instance, every window can contain the average cluster size, if you merge clusters instead of reads. 117 By default, sliding windows count the number of reads in each window of each input file. However, you can merge any information which is contained in the tags. You can compute the average, sum, median, max or min of the tags for each window. For instance, every window can contain the average cluster size, if you merge clusters instead of reads.
136 118
137 The output file is a GFF3 file, where each element is a window. There is a special tag for each window, whose name is **nbElements** if you counted the number of transcripts per sliding window. However, if you performed a **min** (resp. **max**, **sum**, **median**, **average**) operation on the tags **value** of the transcripts, then the tag of the window will be **minValue** (resp. **maxValue**, **sumValue**, **medValue**, **avgValue**). You can also specify the name of your tag (which is actually advised: **nbReadsInSample1** will always be more informative than **nbElements**). 119 The output file is a GFF3 file, where each element is a window. There is a special tag for each window, whose name is **nbElements** if you counted the number of transcripts per sliding window. However, if you performed a **min** (resp. **max**, **sum**, **median**, **average**) operation on the tags **value** of the transcripts, then the tag of the window will be **minValue** (resp. **maxValue**, **sumValue**, **medValue**, **avgValue**). You can also specify the name of your tag (which is actually advised: **nbReadsInSample1** will always be more informative than **nbElements**).
138
139 You also have different option, which can select the *n* % highest regions, or the regions with at least *n* features in it, or even the regions with at least *n* unique features. This last option is useful when you want to cluster the reads which have mapped only once, for instance.
140 </help> 120 </help>
141 </tool> 121 </tool>