annotate annotatePeaks.xml @ 28:f0b5827b6051 draft default tip

Uploaded
author kevyin
date Thu, 20 Dec 2012 18:28:03 -0500
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
28
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
1 <tool id="homer_annotatePeaks" name="homer_annotatePeaks" version="0.0.5">
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
2 <requirements>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
3 <requirement type="package" version="4.1">homer</requirement>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
4 </requirements>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
5 <description></description>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
6 <!--<version_command></version_command>-->
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
7 <command>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
8 annotatePeaks.pl $input_bed $genome_selector 1&gt; $out_annotated
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
9 2&gt; $out_log || echo "Error running annotatePeaks." >&amp;2
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
10 </command>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
11 <inputs>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
12 <param format="tabular,bed" name="input_bed" type="data" label="Homer peaks OR BED format"/>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
13 <param name="genome_selector" type="select" label="Genome version">
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
14 <option value="hg19" selected="true">hg19</option>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
15 </param>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
16 <param type="text" name="options" label="Extra options" value="" help="See link below for more options">
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
17 <sanitizer>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
18 <valid initial="string.printable">
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
19 <remove value="&apos;"/>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
20 <remove value="/"/>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
21 </valid>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
22 <mapping initial="none">
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
23 <add source="&apos;" target="__sq__"/>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
24 </mapping>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
25 </sanitizer>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
26 </param>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
27 </inputs>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
28 <outputs>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
29 <!--<data format="html" name="html_outfile" label="index" />-->
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
30 <!--<data format="html" hidden="True" name="html_outfile" label="index.html" />-->
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
31 <data format="csv" name="out_annotated" label="${tool.name} on #echo os.path.splitext(str($input_bed.name))[0]#_genome_${genome_selector}" />
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
32 <data format="txt" name="out_log" label="${tool.name} on #echo os.path.splitext(str($input_bed.name))[0]#_genome_${genome_selector}.log" />
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
33 </outputs>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
34 <tests>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
35 <test>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
36 <!--<param name="input_file" value="extract_genomic_dna.fa" />-->
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
37 <!--<output name="html_file" file="sample_output.html" ftype="html" />-->
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
38 </test>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
39 </tests>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
40
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
41 <help>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
42
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
43 .. class:: infomark
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
44
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
45 **Homer annoatePeaks**
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
46
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
47 More information on accepted formats and options
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
48
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
49 http://biowhat.ucsd.edu/homer/ngs/annotation.html
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
50
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
51 TIP: use homer_bed2pos and homer_pos2bed to convert between the homer peak positions and the BED format.
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
52
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
53 **Parameter list**
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
54
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
55 Command line options (not all of them are supported)::
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
56
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
57 Usage: annotatePeaks.pl &lt;peak file | tss&gt; &lt;genome version&gt; [additional options...]
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
58
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
59 Available Genomes (required argument): (name,org,directory,default promoter set)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
60 -- or --
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
61 Custom: provide the path to genome FASTA files (directory or single file)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
62
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
63 User defined annotation files (default is UCSC refGene annotation):
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
64 annotatePeaks.pl accepts GTF (gene transfer formatted) files to annotate positions relative
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
65 to custom annotations, such as those from de novo transcript discovery or Gencode.
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
66 -gtf &lt;gtf format file&gt; (-gff and -gff3 can work for those files, but GTF is better)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
67
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
68 Peak vs. tss/tts/rna mode (works with custom GTF file):
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
69 If the first argument is &quot;tss&quot; (i.e. annotatePeaks.pl tss hg18 ...) then a TSS centric
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
70 analysis will be carried out. Tag counts and motifs will be found relative to the TSS.
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
71 (no position file needed) [&quot;tts&quot; now works too - e.g. 3&apos; end of gene]
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
72 [&quot;rna&quot; specifies gene bodies, will automaticall set &quot;-size given&quot;]
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
73 NOTE: The default TSS peak size is 4000 bp, i.e. +/- 2kb (change with -size option)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
74 -list &lt;gene id list&gt; (subset of genes to perform analysis [unigene, gene id, accession,
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
75 probe, etc.], default = all promoters)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
76 -cTSS &lt;promoter position file i.e. peak file&gt; (should be centered on TSS)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
77
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
78 Primary Annotation Options:
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
79 -mask (Masked repeats, can also add &apos;r&apos; to end of genome name)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
80 -m &lt;motif file 1&gt; [motif file 2] ... (list of motifs to find in peaks)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
81 -mscore (reports the highest log-odds score within the peak)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
82 -nmotifs (reports the number of motifs per peak)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
83 -mdist (reports distance to closest motif)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
84 -mfasta &lt;filename&gt; (reports sites in a fasta file - for building new motifs)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
85 -fm &lt;motif file 1&gt; [motif file 2] (list of motifs to filter from above)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
86 -rmrevopp &lt;#&gt; (only count sites found within &lt;#&gt; on both strands once, i.e. palindromic)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
87 -matrix &lt;prefix&gt; (outputs a motif co-occurrence files:
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
88 prefix.count.matrix.txt - number of peaks with motif co-occurrence
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
89 prefix.ratio.matrix.txt - ratio of observed vs. expected co-occurrence
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
90 prefix.logPvalue.matrix.txt - co-occurrence enrichment
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
91 prefix.stats.txt - table of pair-wise motif co-occurrence statistics
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
92 additional options:
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
93 -matrixMinDist &lt;#&gt; (minimum distance between motif pairs - to avoid overlap)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
94 -matrixMaxDist &lt;#&gt; (maximum distance between motif pairs)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
95 -mbed &lt;filename&gt; (Output motif positions to a BED file to load at UCSC (or -mpeak))
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
96 -mlogic &lt;filename&gt; (will output stats on common motif orientations)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
97 -d &lt;tag directory 1&gt; [tag directory 2] ... (list of experiment directories to show
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
98 tag counts for) NOTE: -dfile &lt;file&gt; where file is a list of directories in first column
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
99 -bedGraph &lt;bedGraph file 1&gt; [bedGraph file 2] ... (read coverage counts from bedGraph files)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
100 -wig &lt;wiggle file 1&gt; [wiggle file 2] ... (read coverage counts from wiggle files)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
101 -p &lt;peak file&gt; [peak file 2] ... (to find nearest peaks)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
102 -pdist to report only distance (-pdist2 gives directional distance)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
103 -pcount to report number of peaks within region
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
104 -vcf &lt;VCF file&gt; (annotate peaks with genetic variation infomation, one col per individual)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
105 -editDistance (Computes the # bp changes relative to reference)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
106 -individuals &lt;name1&gt; [name2] ... (restrict analysis to these individuals)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
107 -gene &lt;data file&gt; ... (Adds additional data to result based on the closest gene.
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
108 This is useful for adding gene expression data. The file must have a header,
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
109 and the first column must be a GeneID, Accession number, etc. If the peak
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
110 cannot be mapped to data in the file then the entry will be left empty.
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
111 -go &lt;output directory&gt; (perform GO analysis using genes near peaks)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
112 -genomeOntology &lt;output directory&gt; (perform genomeOntology analysis on peaks)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
113 -gsize &lt;#&gt; (Genome size for genomeOntology analysis, default: 2e9)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
114
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
115 Annotation vs. Histogram mode:
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
116 -hist &lt;bin size in bp&gt; (i.e 1, 2, 5, 10, 20, 50, 100 etc.)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
117 The -hist option can be used to generate histograms of position dependent features relative
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
118 to the center of peaks. This is primarily meant to be used with -d and -m options to map
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
119 distribution of motifs and ChIP-Seq tags. For ChIP-Seq peaks for a Transcription factor
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
120 you might want to use the -center option (below) to center peaks on the known motif
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
121 ** If using &quot;-size given&quot;, histogram will be scaled to each region (i.e. 0-100%), with
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
122 the -hist parameter being the number of bins to divide each region into.
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
123 Histogram Mode specific Options:
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
124 -nuc (calculated mononucleotide frequencies at each position,
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
125 Will report by default if extracting sequence for other purposes like motifs)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
126 -di (calculated dinucleotide frequencies at each position)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
127 -histNorm &lt;#&gt; (normalize the total tag count for each region to 1, where &lt;#&gt; is the
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
128 minimum tag total per region - use to avoid tag spikes from low coverage
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
129 -ghist (outputs profiles for each gene, for peak shape clustering)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
130 -rm &lt;#&gt; (remove occurrences of same motif that occur within # bp)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
131
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
132 Peak Centering: (other options are ignored)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
133 -center &lt;motif file&gt; (This will re-center peaks on the specified motif, or remove peak
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
134 if there is no motif in the peak. ONLY recentering will be performed, and all other
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
135 options will be ignored. This will output a new peak file that can then be reanalyzed
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
136 to reveal fine-grain structure in peaks (It is advised to use -size &lt; 200) with this
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
137 to keep peaks from moving too far (-mirror flips the position)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
138 -multi (returns genomic positions of all sites instead of just the closest to center)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
139
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
140 Advanced Options:
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
141 -len &lt;#&gt; / -fragLength &lt;#&gt; (Fragment length, default=auto, might want to set to 0 for RNA)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
142 -size &lt;#&gt; (Peak size[from center of peak], default=inferred from peak file)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
143 -size #,# (i.e. -size -10,50 count tags from -10 bp to +50 bp from center)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
144 -size &quot;given&quot; (count tags etc. using the actual regions - for variable length regions)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
145 -log (output tag counts as log2(x+1+rand) values - for scatter plots)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
146 -sqrt (output tag counts as sqrt(x+rand) values - for scatter plots)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
147 -strand &lt;+|-|both&gt; (Count tags on specific strands relative to peak, default: both)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
148 -pc &lt;#&gt; (maximum number of tags to count per bp, default=0 [no maximum])
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
149 -cons (Retrieve conservation information for peaks/sites)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
150 -CpG (Calculate CpG/GC content)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
151 -ratio (process tag values as ratios - i.e. chip-seq, or mCpG/CpG)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
152 -nfr (report nuclesome free region scores instead of tag counts, also -nfrSize &lt;#&gt;)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
153 -norevopp (do not search for motifs on the opposite strand [works with -center too])
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
154 -noadj (do not adjust the tag counts based on total tags sequenced)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
155 -norm &lt;#&gt; (normalize tags to this tag count, default=1e7, 0=average tag count in all directories)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
156 -pdist (only report distance to nearest peak using -p, not peak name)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
157 -map &lt;mapping file&gt; (mapping between peak IDs and promoter IDs, overrides closest assignment)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
158 -noann, -nogene (skip genome annotation step, skip TSS annotation)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
159 -homer1/-homer2 (by default, the new version of homer [-homer2] is used for finding motifs)
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
160
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
161
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
162 </help>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
163 </tool>
f0b5827b6051 Uploaded
kevyin
parents:
diff changeset
164