annotate ltr.xml @ 2:2fd354a78c56 draft

Uploaded
author hyungrolee
date Sat, 14 Jun 2014 19:08:39 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
2
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
1 <?xml version="1.0"?>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
2
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
3 <tool name="MGEScan-LTR" id="mgescan-ltr" version="0.0.1" workflow_compatible="false">
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
4 <description>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
5 de novo identification of LTR retroelements
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
6 </description>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
7 <!--
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
8 <action module="galaxy.tools.actions.nonltr" class="nonltrToolAction"/>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
9 <requirements>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
10 <requirement type="package">HMMER</requirement>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
11 <requirement type="package">EMBOSS</requirement>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
12 </requirements>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
13 -->
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
14 <command interpreter="bash">
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
15 <!--
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
16 /u/lee212/retrotminer/MGEScan_LTR/find_ltr.pl -genome=/u/lee212/retrotminer/MGEScan_nonLTR_v2/anoGam1/
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
17 -data=/u/lee212/retrotminer/MGEScan_LTR/example/data/ -program=/u/lee212/retrotminer/MGEScan_LTR/
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
18 -->
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
19 <!--mgescan.sh $input $input.name $hmmver $output L None None None $ltr_gff3 None-->
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
20 <!--mgescan.sh $input $input.name 3 $output L None None None $ltr_gff3 None-->
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
21 mgescan.sh $input $input.name 3 $output L None None None $ltr_gff3 None $sw_rm "$scaffold" $min_dist $max_dist $min_len_ltr $max_len_ltr $ltr_sim_condition $cluster_sim_condition $len_condition $repeatmasker
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
22 </command>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
23 <inputs>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
24 <!--
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
25 <param name="genome" type="text" label="directory where input genome data exists" />
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
26 <param name="data" type="text" label="directory of the output" />
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
27 -->
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
28 <param format="txt" name="input" type="data" label="From"/>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
29 <!--param name="hmmver" type="select" label="Hmmsearch version">
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
30 <option selected="selected" value="3">3</option>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
31 <option value="2">2</option>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
32 </param-->
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
33 <!-- path.conf -->
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
34 <param name="sw_rm" type="select" display="checkboxes" multiple="True" label="enable repeatmasker, if necessary" help="Use this option if you are enable repeatmasker">
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
35 <option value="Yes">Yes</option>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
36 </param>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
37 <param name="scaffold" type="text" label="path for the big file that has all scaffolds"/>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
38 <!-- value.conf -->
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
39 <param name="min_dist" type="text" value="2000" label="minimum distance(bp) between LTRs" />
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
40 <param name="max_dist" type="text" value="20000" label="maximum distance(bp) between LTRs" />
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
41 <param name="min_len_ltr" type="text" value="130" label="minimum length(bp) of LTR"/>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
42 <param name="max_len_ltr" type="text" value="2000" label="maximum length(bp) of LTR"/>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
43 <param name="ltr_sim_condition" type="text" value="70" label="minimum similarity(%) for LTRs in an element"/>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
44 <param name="cluster_sim_condition" type="text" value="70" label="inimum similarity(%) for LTRs in a cluster"/>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
45 <param name="len_condition" type="text" value="70" label="minimum length(bp) for LTRs aligned in local alignment"/>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
46 </inputs>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
47 <outputs>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
48 <data format="ltr.out" name="output" />
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
49 <data format="gff3" name="ltr_gff3" />
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
50 <data format="repeatmasker" name="repeatmasker" >
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
51 <filter>sw_rm == "Yes"</filter>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
52 </data>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
53 </outputs>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
54 <help>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
55 Running the program
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
56 ===================
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
57
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
58 To run MGEScan-LTR, follow the steps below,
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
59
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
60 1. Specify options that you like to have:
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
61
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
62 * Check repeatmasker if you want to preprocess
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
63 * Check scaffold if the input file has all scaffolds.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
64
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
65 2. Update values:
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
66
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
67 * min_dist: minimum distance(bp) between LTRs.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
68 * max_dist: maximum distance(bp) between LTRS
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
69 * min_len_ltr: minimum length(bp) of LTR.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
70 * max_len_ltr: maximum length(bp) of LTR.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
71 * ltr_sim_condition: minimum similarity(%) for LTRs in an element.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
72 * cluster_sim_condition: minimum similarity(%) for LTRs in a cluster
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
73 * len_condition: minimum length(bp) for LTRs aligned in local alignment.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
74
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
75 4. Click 'Execute'
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
76
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
77 * mask known repeats other than LTR retrotransposons
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
78 * identify LTRs
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
79
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
80 Output
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
81 ======
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
82
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
83 Upon completion, MGEScan-LTR generates a file ltr.out. This output file has information
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
84 about clusters and coordinates of LTR retrotransposons identified. Each cluster of LTR
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
85 retrotransposons starts with the head line of [cluster_number]---------, followed by
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
86 the information of LTR retrotransposons in the cluster. The columns for LTR
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
87 retrotransposons are as follows.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
88
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
89 1. LTR_id: unique id of LTRs identified. It consist of two components, sequence file name and id in the file. For example, chr1_2 is the second LTR retrotransposon in the chr1 file.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
90 2. start position of 5 LTR.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
91 3. end position of 5 LTR.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
92 4. start position of 3 LTR.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
93 5. end position of 3 LTR.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
94 6. strand: + or -.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
95 7. length of 5 LTR.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
96 8. length of 3 LTR.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
97 9. length of the LTR retrotransposon.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
98 10. TSD on the left side of the LTR retotransposons.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
99 11. TSD on the right side of the LTR retrotransposons.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
100 12. di(tri)nucleotide on the left side of 5LTR
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
101 13. di(tri)nucleotide on the right side of 5LTR
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
102 14. di(tri)nucleotide on the left side of 3LTR
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
103 15. di(tri)nucleotide on the right side of 3LTR
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
104
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
105 License
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
106 ============
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
107
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
108 Copyright 2014 Mina Rho, Haixu Tang.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
109 You may redistribute this software under the terms of the GNU General Public License.
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
110 </help>
2fd354a78c56 Uploaded
hyungrolee
parents:
diff changeset
111 </tool>