|
16
|
1 <tool id="homer_findPeaks" name="homer_findPeaks" version="0.1.2">
|
|
|
2 <requirements>
|
|
|
3 <requirement type="package" version="4.1">homer</requirement>
|
|
|
4 </requirements>
|
|
|
5 <description>Homer's peakcaller. Requires tag directories (see makeTagDirectory)</description>
|
|
|
6 <!--<version_command></version_command>-->
|
|
|
7 <command>
|
|
|
8 findPeaks $tagDir.extra_files_path $options -o $outputPeakFile
|
|
|
9
|
|
|
10 #if $control_tagDir:
|
|
|
11 -i $control_tagDir.extra_files_path
|
|
|
12 #end if
|
|
|
13
|
|
|
14 2> $out_log || echo "Error running findPeaks." >&2
|
|
|
15 </command>
|
|
|
16 <inputs>
|
|
|
17 <param format="homerTagDirectory" name="tagDir" type="data" label="tag directory" help="Must be made with homer_makeTagDirectory" />
|
|
|
18 <param format="homerTagDirectory" name="control_tagDir" type="data" optional="True" label="Control tag directory" help="Must be made with homer_makeTagDirectory" />
|
|
|
19 <param type="text" name="options" label="Extra options" value="" help="See link below for more options">
|
|
|
20 <sanitizer>
|
|
|
21 <valid initial="string.printable">
|
|
|
22 <remove value="'"/>
|
|
|
23 <remove value="/"/>
|
|
|
24 </valid>
|
|
|
25 <mapping initial="none">
|
|
|
26 <add source="'" target="__sq__"/>
|
|
|
27 </mapping>
|
|
|
28 </sanitizer>
|
|
|
29 </param>
|
|
|
30 </inputs>
|
|
|
31 <outputs>
|
|
|
32 <!--<data format="html" name="html_outfile" label="index" />-->
|
|
|
33 <!--<data format="html" hidden="True" name="html_outfile" label="index.html" />-->
|
|
|
34 <data format="txt" name="outputPeakFile" label="${tool.name} on #echo os.path.splitext(str($tagDir.name))[0]#.txt" />
|
|
|
35 <data format="txt" name="out_log" label="${tool.name} on #echo os.path.splitext(str($tagDir.name))[0]#.log" />
|
|
|
36 </outputs>
|
|
|
37 <tests>
|
|
|
38 <test>
|
|
|
39 <!--<param name="input_file" value="extract_genomic_dna.fa" />-->
|
|
|
40 <!--<output name="html_file" file="sample_output.html" ftype="html" />-->
|
|
|
41 </test>
|
|
|
42 </tests>
|
|
|
43
|
|
|
44 <help>
|
|
|
45
|
|
|
46 .. class:: infomark
|
|
|
47
|
|
|
48 **Homer findPeaks**
|
|
|
49
|
|
|
50 For more options, look under: "Command line options for findPeaks"
|
|
|
51
|
|
|
52 http://biowhat.ucsd.edu/homer/ngs/peaks.html
|
|
|
53
|
|
|
54 TIP: use homer_bed2pos and homer_pos2bed to convert between the homer peak positions and the BED format.
|
|
|
55
|
|
|
56 **Parameter list**
|
|
|
57
|
|
|
58 Command line options (not all of them are supported)::
|
|
|
59
|
|
|
60 Usage: findPeaks <tag directory> [options]
|
|
|
61
|
|
|
62 Finds peaks in the provided tag directory. By default, peak list printed to stdout
|
|
|
63
|
|
|
64 General analysis options:
|
|
|
65 -o <filename|auto> (file name for to output peaks, default: stdout)
|
|
|
66 "-o auto" will send output to "<tag directory>/peaks.txt", ".../regions.txt",
|
|
|
67 or ".../transcripts.txt" depending on the "-style" option
|
|
|
68 -style <option> (Specialized options for specific analysis strategies)
|
|
|
69 factor (transcription factor ChIP-Seq, uses -center, output: peaks.txt, default)
|
|
|
70 histone (histone modification ChIP-Seq, region based, uses -region -size 500 -L 0, regions.txt)
|
|
|
71 groseq (de novo transcript identification from GroSeq data, transcripts.txt)
|
|
|
72 tss (TSS identification from 5' RNA sequencing, tss.txt)
|
|
|
73 dnase (Hypersensitivity [crawford style (nicking)], peaks.txt)
|
|
|
74
|
|
|
75 chipseq/histone options:
|
|
|
76 -i <input tag directory> (Experiment to use as IgG/Input/Control)
|
|
|
77 -size <#> (Peak size, default: auto)
|
|
|
78 -minDist <#> (minimum distance between peaks, default: peak size x2)
|
|
|
79 -gsize <#> (Set effective mappable genome size, default: 2e9)
|
|
|
80 -fragLength <#|auto> (Approximate fragment length, default: auto)
|
|
|
81 -inputFragLength <#|auto> (Approximate fragment length of input tags, default: auto)
|
|
|
82 -tbp <#> (Maximum tags per bp to count, 0 = no limit, default: auto)
|
|
|
83 -inputtbp <#> (Maximum tags per bp to count in input, 0 = no limit, default: auto)
|
|
|
84 -strand <both|separate> (find peaks using tags on both strands or separate, default:both)
|
|
|
85 -norm # (Tag count to normalize to, default 10000000)
|
|
|
86 -region (extends start/stop coordinates to cover full region considered "enriched")
|
|
|
87 -center (Centers peaks on maximum tag overlap and calculates focus ratios)
|
|
|
88 -nfr (Centers peaks on most likely nucleosome free region [works best with mnase data])
|
|
|
89 (-center and -nfr can be performed later with "getPeakTags"
|
|
|
90
|
|
|
91 Peak Filtering options: (set -F/-L/-C to 0 to skip)
|
|
|
92 -F <#> (fold enrichment over input tag count, default: 4.0)
|
|
|
93 -P <#> (poisson p-value threshold relative to input tag count, default: 0.0001)
|
|
|
94 -L <#> (fold enrichment over local tag count, default: 4.0)
|
|
|
95 -LP <#> (poisson p-value threshold relative to local tag count, default: 0.0001)
|
|
|
96 -C <#> (fold enrichment limit of expected unique tag positions, default: 2.0)
|
|
|
97 -localSize <#> (region to check for local tag enrichment, default: 10000)
|
|
|
98 -inputSize <#> (Size of region to search for control tags, default: 2x peak size)
|
|
|
99 -fdr <#> (False discovery rate, default = 0.001)
|
|
|
100 -poisson <#> (Set poisson p-value cutoff, default: uses fdr)
|
|
|
101 -tagThreshold <#> (Set # of tags to define a peak, default: 25)
|
|
|
102 -ntagThreshold <#> (Set # of normalized tags to define a peak, by default uses 1e7 for norm)
|
|
|
103 -minTagThreshold <#> (Absolute minimum tags per peak, default: expected tags per peak)
|
|
|
104
|
|
|
105 GroSeq Options: (Need to specify "-style groseq"):
|
|
|
106 -tssSize <#> (size of region for initiation detection/artifact size, default: 250)
|
|
|
107 -minBodySize <#> (size of regoin for transcript body detection, default: 1000)
|
|
|
108 -maxBodySize <#> (size of regoin for transcript body detection, default: 10000)
|
|
|
109 -tssFold <#> (fold enrichment for new initiation dectection, default: 4.0)
|
|
|
110 -bodyFold <#> (fold enrichment for new transcript dectection, default: 4.0)
|
|
|
111 -endFold <#> (end transcript when levels are this much less than the start, default: 10.0)
|
|
|
112 -fragLength <#> (Approximate fragment length, default: 150)
|
|
|
113 -uniqmap <directory> (directory of binary files specifying uniquely mappable locations)
|
|
|
114 Download from http://biowhat.ucsd.edu/homer/groseq/
|
|
|
115 -confPvalue <#> (confidence p-value: 1.00e-05)
|
|
|
116 -minReadDepth <#> (Minimum initial read depth for transcripts, default: auto)
|
|
|
117 -pseudoCount <#> (Pseudo tag count, default: 2.0)
|
|
|
118 -gtf <filename> (Output de novo transcripts in GTF format)
|
|
|
119 "-o auto" will produce <dir>/transcripts.txt and <dir>/transcripts.gtf
|
|
|
120 </help>
|
|
|
121 </tool>
|
|
|
122
|
