|
0
|
1 <tool id="kmersvm_seqprofile" name="Sequence Profiles">
|
|
|
2 <description>provide length, gc content, and repeat fraction of each sequence</description>
|
|
|
3 <command interpreter="python">scripts/make_profile.py $input $dbkey ${indices_path.fields.path} seq_profile.txt</command>
|
|
|
4 <inputs>
|
|
|
5 <param format="interval" name="input" type="data" label="BED File of Regions of interest" />
|
|
|
6 <validator type="unspecified_build" />
|
|
|
7 <validator type="dataset_metadata_in_file" filename="nullseq_indices.loc" metadata_name="dbkey" metadata_column="0" message="Sequences are currently unavailable for the specified build." />
|
|
|
8 <param name="indices_path" type="select" label="Available Datasets">
|
|
|
9 <options from_file="nullseq_indices.loc">
|
|
|
10 <column name="dbkey" index="0"/>
|
|
|
11 <column name="value" index="0"/>
|
|
|
12 <column name="name" index="1"/>
|
|
|
13 <column name="path" index="2"/>
|
|
|
14 <filter type="data_meta" ref="input" key="dbkey" column="0" />
|
|
|
15 </options>
|
|
|
16 </param>
|
|
|
17 </inputs>
|
|
|
18 <outputs>
|
|
|
19 <data format="tabular" name="seq_profile.txt" from_work_dir="seq_profile.txt" />
|
|
|
20 </outputs>
|
|
|
21 <help>
|
|
|
22
|
|
|
23 **What it does**
|
|
|
24
|
|
|
25 Takes as input a BED file and the file's corresponding genome build.
|
|
|
26
|
|
|
27 Returns length, GC and repeat content information for each interval in bed file.
|
|
|
28
|
|
|
29 ----
|
|
|
30
|
|
|
31 **Example**
|
|
|
32
|
|
|
33 Profile file::
|
|
|
34
|
|
|
35 mm9_chr10_6238300_6238926_+ 626 0.525559105431 0.0
|
|
|
36 mm9_chr10_7757450_7758801_+ 1351 0.451517394523 0.0384900074019
|
|
|
37 mm9_chr10_8992150_8992551_+ 401 0.411471321696 0.0
|
|
|
38 mm9_chr10_9265550_9266026_+ 476 0.38025210084 0.0
|
|
|
39
|
|
|
40 </help>
|
|
|
41 </tool>
|
