3
|
1 <tool id="tabix" name="tabix" version="0.0.1">
|
|
2 <description>Generic indexer for TAB-delimited genome position files.</description>
|
|
3 <requirements>
|
|
4 <requirement type="package" version= "0.2.6">tabix</requirement>
|
|
5 </requirements>
|
|
6 <command>
|
|
7 tabix
|
|
8 #if str($position) == "no"
|
|
9 -0
|
|
10 #end if
|
|
11
|
|
12 #if str($options.extension) == "tabular"
|
|
13 #if str($options.columnseq) != ""
|
|
14 -s $options.columnseq
|
|
15 #end if
|
|
16
|
|
17 #if str($options.columnstart) != ""
|
|
18 -b $options.columnstart
|
|
19 #end if
|
|
20
|
|
21 #if str($options.columnend) != ""
|
|
22 -e $options.columnend
|
|
23 #end if
|
|
24
|
|
25 #if str($options.skiplines) != ""
|
|
26 -S $options.skiplines
|
|
27 #end if
|
|
28
|
|
29 #if str($options.skipchar) != ""
|
|
30 -c $options.skipchar
|
|
31 #end if
|
|
32 #else
|
|
33 -p
|
|
34 #end if
|
|
35
|
|
36 $input $region
|
|
37
|
|
38 </command>
|
|
39 <inputs>
|
|
40 <param name="input" type="data" label="Input file" format="gff,bed,sam,vcf,tabular">
|
|
41 </param>
|
|
42 <param name="region" type="text" optional="true" label="Regions (seperate with spaces)"> </param>
|
|
43 <conditional name="optional">
|
|
44 <param name= "extension" type="select" value= "tabular" label= "Input Extension">
|
|
45 <option value="tabular">tabular</option>
|
|
46 <option value="gff">gff</option>
|
|
47 <option value="bed">bed</option>
|
|
48 <option value="sam">sam</option>
|
|
49 <option value="vcf">vcf</option>
|
|
50 </param>
|
|
51 <when value="tabular">
|
|
52 <param name="columnseq" type="integer" optional= "true" label="Column of sequence name" />
|
|
53 <param name="columnstart" type="integer" optional= "true" label="Column of start chromosomal position" />
|
|
54 <param name="columnend" type="integer" optional= "true" label="Column of end chromosomal position" />
|
|
55 <param name="skiplines" type="integer" optional= "true" label="Skip first INT lines" />
|
|
56 <param name="skipchar" type="text" optional= "true" label="Skip lines started with CHAR" />
|
|
57 <param name="position" type= "select" value= "yes" label="1-based? (if not, 0-based)">
|
|
58 <option value= "yes">yes</option>
|
|
59 <option value= "no">no</option>
|
|
60 </param>
|
|
61 </when>
|
|
62 </conditional>
|
|
63 </inputs>
|
|
64
|
|
65 <outputs>
|
|
66 <data format="tabular" name="output" />
|
|
67 </outputs>
|
|
68
|
|
69 <help>
|
|
70 **What it does:**
|
|
71
|
|
72 Tabix indexes a TAB-delimited genome position file in.tab.bgz and creates an index file in.tab.bgz.tbi when region is absent from the command-line. The input data file must be position sorted and compressed by bgzip which has a gzip(1) like interface. After indexing, tabix is able to quickly retrieve data lines overlapping regions specified in the format "chr:beginPos-endPos". Fast data retrieval also works over network if URI is given as a file name and in this case the index file will be downloaded if it is not present locally.
|
|
73
|
|
74 **Citation:**
|
|
75
|
|
76 Tabix was written by Heng Li. The BGZF library was originally implemented by Bob Handsaker and modified by Heng Li for remote file access and in-memory caching.
|
|
77
|
|
78 http://samtools.sourceforge.net/tabix.shtml
|
|
79
|
|
80 **Example:**
|
|
81
|
|
82 (grep ^"#" in.gff; grep -v ^"#" in.gff | sort -k1,1 -k4,4n) | bgzip > sorted.gff.gz;
|
|
83
|
|
84 tabix -p gff sorted.gff.gz;
|
|
85
|
|
86 tabix sorted.gff.gz chr1:10,000,000-20,000,000;
|
|
87
|
|
88 </help>
|
|
89 </tool>
|