|
0
|
1 <tool id="cshl_word_list_grep" name="Select lines">
|
|
|
2 <description>by word list</description>
|
|
|
3 <command interpreter="perl">
|
|
|
4 word_list_grep.pl
|
|
|
5 #if $searchwhere.choice == "column":
|
|
|
6 -c $searchwhere.column
|
|
|
7 #end if
|
|
|
8 -o $output
|
|
|
9 $inverse
|
|
|
10 $caseinsensitive
|
|
|
11 $wholewords
|
|
|
12 $skip_first_line
|
|
|
13 $wordlist
|
|
|
14 $input
|
|
|
15 </command>
|
|
|
16
|
|
|
17 <inputs>
|
|
|
18 <param name="input" format="txt" type="data" label="input file" />
|
|
|
19 <param name="wordlist" format="txt" type="data" label="word list file" />
|
|
|
20
|
|
|
21
|
|
|
22 <param name="inverse" type="boolean" checked="false" truevalue="-v" falsevalue="" label="Inverse filter"
|
|
|
23 help="Report lines NOT matching the word list" />
|
|
|
24
|
|
|
25 <param name="caseinsensitive" type="boolean" checked="false" truevalue="-i" falsevalue="" label="Case-Insensitive search"
|
|
|
26 help="" />
|
|
|
27
|
|
|
28 <param name="wholewords" type="boolean" checked="false" truevalue="-w" falsevalue="" label="find whole-words"
|
|
|
29 help="ignore partial matches (e.g. 'apple' will not match 'snapple') " />
|
|
|
30
|
|
|
31 <param name="skip_first_line" type="boolean" checked="false" truevalue="-s" falsevalue="" label="Ignore first line"
|
|
|
32 help="Select this option if the first line contains column headers. First line will not be filtered. " />
|
|
|
33
|
|
|
34 <conditional name="searchwhere">
|
|
|
35 <param name="choice" type="select" label="Search words in">
|
|
|
36 <option value="line" selected="true">entire line</option>
|
|
|
37 <option value="column">specific column</option>
|
|
|
38 </param>
|
|
|
39
|
|
|
40 <when value="line">
|
|
|
41 </when>
|
|
|
42
|
|
|
43 <when value="column">
|
|
|
44 <param name="column" label="in column" type="data_column" data_ref="input" accept_default="true" />
|
|
|
45 </when>
|
|
|
46 </conditional>
|
|
|
47
|
|
|
48 </inputs>
|
|
|
49
|
|
|
50 <outputs>
|
|
|
51 <data name="output" format="input" metadata_source="input" />
|
|
|
52 </outputs>
|
|
|
53
|
|
|
54 <help>
|
|
|
55 **What it does**
|
|
|
56
|
|
|
57 This tool selects lines that match words from a word list.
|
|
|
58
|
|
|
59 --------
|
|
|
60
|
|
|
61 **Example**
|
|
|
62
|
|
|
63 Input file (UCSC's rmsk track from dm3)::
|
|
|
64
|
|
|
65 585 787 66 241 11 chrXHet 2860 3009 -201103 - DNAREP1_DM LINE Penelope 0 594 435 1
|
|
|
66 585 1383 78 220 0 chrXHet 3012 3320 -200792 - DNAREP1_DM LINE Penelope -217 377 2 1
|
|
|
67 585 244 103 0 0 chrXHet 3737 3776 -200336 - DNAREP1_DM LINE Penelope -555 39 1 1
|
|
|
68 585 2270 83 144 0 chrXHet 7907 8426 -195686 + DNAREP1_DM LINE Penelope 1 594 0 1
|
|
|
69 585 617 189 73 68 chrXHet 10466 10671 -193441 + DNAREP1_DM LINE Penelope 368 573 -21 1
|
|
|
70 586 1122 71 185 0 chrXHet 173138 173322 -30790 - PROTOP DNA P -4033 447 230 1
|
|
|
71 ...
|
|
|
72 ...
|
|
|
73
|
|
|
74
|
|
|
75 Word list file::
|
|
|
76
|
|
|
77 STALKER
|
|
|
78 PROTOP
|
|
|
79
|
|
|
80
|
|
|
81
|
|
|
82 Output sequence (searching in column 11)::
|
|
|
83
|
|
|
84 586 1122 71 185 0 chrXHet 173138 173322 -30790 - PROTOP DNA P -4033 447 230 1
|
|
|
85 586 228 162 0 0 chrXHet 181026 181063 -23049 + STALKER4_I LTR Gypsy 9 45 -6485 1
|
|
|
86 585 245 105 26 0 chr3R 41609 41647 -27863406 + PROTOP_B DNA P 507 545 -608 4
|
|
|
87 586 238 91 0 0 chr3R 140224 140257 -27764796 - PROTOP_B DNA P -617 536 504 4
|
|
|
88 ...
|
|
|
89 ...
|
|
|
90
|
|
|
91 ( With **find whole-words** not selected, *PROTOP* matched *PROTOP_B*, *STALKER* matched *STALKER4_I* )
|
|
|
92
|
|
|
93
|
|
|
94
|
|
|
95
|
|
|
96 Output sequence (searching in column 11, and whole-words only)::
|
|
|
97
|
|
|
98 586 670 90 38 57 chrXHet 168356 168462 -35650 - PROTOP DNA P -459 4021 3918 1
|
|
|
99 586 413 139 70 0 chrXHet 168462 168548 -35564 - PROTOP DNA P -3406 1074 983 1
|
|
|
100 586 1122 71 185 0 chrXHet 173138 173322 -30790 - PROTOP DNA P -4033 447 230 1
|
|
|
101 ...
|
|
|
102 ...
|
|
|
103
|
|
|
104 </help>
|
|
|
105
|
|
|
106 </tool>
|
