annotate CRISPRSeek/offtargetanalysis.xml @ 5:891408eaa9f0 draft

Uploaded
author alperkucukural
date Tue, 03 Nov 2015 10:12:14 -0500
parents 8615e7e7c5be
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
1 <tool id="offTargetAnalysis" name="Off Target Analysis" version="1.0.0">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
2 <description>CRISPRSeek offTargetAnalysis</description>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
3 <macros>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
4 <import>crisprseek_macros.xml</import>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
5 </macros>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
6 <expand macro="requirements" />
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
7 <command detect_errors="exit_code">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
8 Rscript "${offTargetAnalysis}"
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
9 </command>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
10 <configfiles>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
11 <configfile name="offTargetAnalysis"><![CDATA[
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
12 ## code chunk: Load all required libraries quietly
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
13 library(CRISPRseek, quietly=TRUE, warn.conflicts=FALSE,verbose = FALSE)
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
14
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
15 offTargetAnalysis("${s.inputfile}", BSgenomeName="BSgenome.Hsapiens.UCSC.hg19", txdb ="TxDb.Hsapiens.UCSC.hg19.knownGene",orgAnn="org.Hs.egSYMBOL", REpatternFile = system.file('extdata', 'NEBenzymes.fa', package = 'CRISPRseek'), max.mismatch="${maxmismatch}", exportAllgRNAs="${a.exportAllgRNAs}", searchDirection="${a.searchDirection}", findPairedgRNAOnly=${a.fg.fpg_only}, min.gap = "${a.fg.mingap}", max.gap = "${a.fg.maxgap}", gRNA.name.prefix = "gRNA", PAM.size = "${a.PAMsize}", gRNA.size = "${a.gRNAsize}", PAM = "${a.PAM}", PAM.pattern = "${a.PAMPattern}", chromToSearch="${a.chromToSearch}", minscore="${a.minscore}", topN="${a.topN}", topNOfftargetTotalScore="${a.topNOfftargetTotalScore}", annotateExon="${a.annotateExon}", fetchSequence="${a.fs.fetchSequence}", downstream="${a.fs.downstream}", upstream="${a.fs.upstream}", outputDir, weights="${a.weights}" )
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
16
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
17 ]]></configfile>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
18 </configfiles>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
19 <inputs>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
20 <param name="bsgenomename" type="select" label="BS Genome Name" help="BSgenome object. Please refer to available.genomes in BSgenome package. For example, BSgenome.Hsapiens.UCSC.hg19 for hg19, BSgenome.Mmusculus.UCSC.mm10 for mm10, BSgenome.Celegans.UCSC.ce6 for ce6, BSgenome.Rnorvegicus.UCSC.rn5 for rn5, BSgenome.Drerio.UCSC.danRer7 for Zv9, and BSgenome.Dmelanogaster.UCSC.dm3 for dm3">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
21 <option value="hg19">hg19</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
22 <option value="mm10">mm10</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
23 <option value="ce10">ce10</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
24 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
25 <conditional name="s">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
26 <param name="input_source" type="select" label="Select Input File Path" help="Sequence input file path that contains sequences to be searched for potential gRNAs">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
27 <option value="history">History</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
28 <option value="Fasta">Fasta</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
29 <option value="FullPath">Full Path</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
30 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
31 <when value="history">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
32 <param format="fastq,fa,fasta" name="inputfile" type="data" label="Input File Path" />
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
33 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
34 <when value="FullPath">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
35 <param name="inputfile" type="text" area="true" size="2x60" label="Input File Path" help="Full path in the cluster"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
36 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
37 <when value="Fasta">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
38 <param name="inputfile" type="text" area="true" size="2x60" label="Input Fasta Sequence/s" help="Free text fasta sequences"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
39 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
40 </conditional>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
41 <param name="maxmismatch" type="text" label="Max Mismatch" value="3" help="Maximum mismatch allowed in off target search, default 3. Warning: will be considerably slower if set > 3"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
42 <param name="outputdir" type="text" area="true" size="2x60" label="Output Directory" help="Output directory in the cluster"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
43 <conditional name="a">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
44 <param name="advanced" type="select" label="Advanced Options">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
45 <option value="No" selected="True">No</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
46 <option value="Yes">Yes</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
47 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
48 <when value="Yes">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
49 <param name="exportAllgRNAs" type="select" label="Export All gRNAs" help="Indicate whether to output all potential gRNAs to a file in fasta format, genbank format or both. Default to both.">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
50 <option value="all" selected="True">all</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
51 <option value="fasta">fasta</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
52 <option value="genbank">genbank</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
53 <option value="no">no</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
54 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
55 <conditional name="fg">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
56 <param name="fpg_only" type="select" label="Find Paired gRNA Only" help="Choose whether to only search for paired gRNAs in such an orientation that the first one is on minus strand called reverse gRNA and the second one is on plus strand called forward gRNA. TRUE or FALSE, default FALSE">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
57 <option value="False" selected="True">No</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
58 <option value="True">Yes</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
59 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
60 <when value="True">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
61 <param name="mingap" type="text" label="Min Gap" value="0" />
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
62 <param name="maxgap" type="text" label="Max Gap" value="20" />
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
63 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
64 </conditional>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
65 <param name="PAMsize" type="text" label="PAM Size" value="3" help="PAM length, default 3"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
66 <param name="PAM" type="text" label="PAM" value="NGG" help="PAM sequence after the gRNA, default NGG"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
67 <param name="PAMPattern" type="text" label="PAM Pattern" value="N[A_p_G]G_d_" help="Regular expression of protospacer-adjacent motif (PAM), default N[A|G]G$. Please use _p_ for | and _d_ for $ symbols"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
68 <param name="gRNAsize" type="text" label="gRNA Size" value="20" help="The size of the gRNA, default 20"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
69 <param name="minscore" type="text" label="min Score" value="0.5" help="minimum score of an off target to included in the final output, default 0.5"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
70 <param name="topN" type="text" label="topN" value="100" help="top N off targets to be included in the final output, default 100"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
71 <param name="topNOfftargetTotalScore" type="text" label="topN OfftargetTotalScore" value="10" help="top N off target used to calculate the total off target score, default 10"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
72 <param name="annotateExon" type="select" label="Annotate Exon" help="Choose whether or not to indicate whether the off target is inside an exon or not, default TRUE">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
73 <option value="true" selected="True">True</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
74 <option value="false">False</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
75 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
76 <param name="chromToSearch" type="text" label="chromToSearch" value="all" help="Type chromosome (Ex: chrX)"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
77
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
78 <conditional name="fs">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
79 <param name="fetchSequence" type="select" label="Fetch Sequence" help="Fetch flank sequence of off target or not, default TRUE">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
80 <option value="True" selected="True">True</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
81 <option value="False">False</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
82 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
83 <when value="True">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
84 <param name="upstream" type="text" label="upstream" value="200" help="upstream offset from the off target start, default 200"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
85 <param name="downstream" type="text" label="downstream" value="200" help="downstream offset from the off target end default 200"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
86 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
87 </conditional>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
88 <param name="weights" type="text" area="true" size="5x60" value="0, 0, 0.014, 0, 0, 0.395, 0.317, 0, 0.389, 0.079, 0.445, 0.508, 0.613, 0.851, 0.732, 0.828, 0.615, 0.804, 0.685, 0.583" label="Off Target Weights" help="a numeric vector size of gRNA length, default 0, 0, 0.014, 0, 0, 0.395, 0.317, 0, 0.389, 0.079, 0.445, 0.508, 0.613, 0.851, 0.732, 0.828, 0.615, 0.804, 0.685, 0.583 which is used in Hsu et al., 2013 cited in the reference section"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
89 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
90 </conditional>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
91 </inputs>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
92 <outputs>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
93 <data format="gz" name="output"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
94 </outputs>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
95 <help>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
96
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
97 **What it does**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
98
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
99 The package includes functions to find potential guide RNAs for input target se-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
100 quences, optionally filter guide RNAs without restriction enzyme cut site, or with-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
101 out paired guide RNAs, genome-wide search for off-targets, score, rank, fetch flank se-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
102 quence and indicate whether the target and off-targets are located in exon region or not. Poten-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
103 tial guide RNAs are annotated with total score of the top5 and topN off-targets, de-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
104 tailed topN mismatch sites, restriction enzyme cut sites, and paired guide RNAs.
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
105
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
106 **Description**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
107
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
108 Design of target-specific gRNAs for the CRISPR-Cas9 system by automatically finding potential
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
109 gRNAs (paired/not paired), with/without restriction enzyme cut site(s) in a given sequence, search-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
110 ing for off targets with user defined maximum number of mismatches, calculating score of each
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
111 off target based on mismatch positions in the off target and a penalty weight matrix, filtering off
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
112 targets with user-defined criteria, and annotating off targets with flank sequences, whether located
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
113 in exon or not. Summary report is also generated with gRNAs ranked by total topN off target
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
114 score, annotated with restriction enzyme cut sites and possible paired gRNAs. Detailed paired gR-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
115 NAs information and restriction enzyme cut sites are stored in separate files in the output directory
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
116 specified by the user. In total, four tab delimited files are generated in the output directory: Off-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
117 targetAnalysis.xls (off target details), Summary.xls (gRNA summary), REcutDetails.xls (restriction
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
118 enzyme cut sites of each gRNA), and pairedgRNAs.xls (potential paired gRNAs).
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
119
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
120 **Author(s)**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
121
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
122 Lihua Julie Zhu and Michael Brodsky Maintainer: julie.zhu@umassmed.edu
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
123
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
124 **Citation**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
125
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
126 (from within R, enter citation("CRISPRseek")):
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
127
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
128 Zhu LJ, Holmes BR, Aronin N and Brodsky MH (2014). “CRISPRseek: A Bioconductor Package to Identify Target-Specific Guide RNAs for CRISPR-Cas9 Genome-Editing Systems.” PLoS one, 9(9). http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4172692/.
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
129
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
130 **References**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
131
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
132 http://bioconductor.org/packages/2.8/bioc/vignettes/BSgenome/inst/doc/GenomeSearching.pdf
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
133
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
134 Patrick D Hsu, David A Scott, Joshua A Weinstein, F Ann Ran, Silvana Konermann, Vineeta Agar-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
135 wala, Yinqing Li, Eli J Fine, Xuebing Wu, Ophir Shalem, Thomas J Cradick, Luciano A Marraffini,
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
136 Gang Bao, Feng Zhang (2013) DNA targeting specificity of rNA-guided Cas9 nucleases. Nature
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
137 Biotechnology 31:827-83
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
138
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
139 Mali P, Aach J, Stranges PB, Esvelt KM, Moosburner M, Kosuri S, Yang L, Church GM.CAS9
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
140 transcriptional activators for target specificity screening and paired nickases for cooperative genome
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
141 engineering. Nat Biotechnol. 2013. 31(9):833-8 Patrick D Hsu, David A Scott, Joshua A Wein-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
142 stein, F Ann Ran, Silvana Konermann, Vineeta Agarwala, Yinqing Li, Eli J Fine, Xuebing Wu,
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
143 Ophir Shalem, Thomas J Cradick, Luciano A Marraffini, Gang Bao, Feng Zhang. DNA targeting
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
144 specificity of rNA-guided Cas9 nucleases. Nat Biotechnol. 2013. 31:827-834
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
145
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
146 **Reference Manual and Materials**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
147
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
148 http://www.bioconductor.org/packages/release/bioc/vignettes/CRISPRseek/inst/doc/CRISPRseek.pdf
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
149
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
150 http://www.bioconductor.org/packages/release/bioc/manuals/CRISPRseek/man/CRISPRseek.pdf
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
151
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
152 http://www.bioconductor.org/packages/release/bioc/vignettes/CRISPRseek/inst/doc/CRISPRseek.R
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
153
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
154
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
155
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
156
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
157
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
158 </help>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
159 <expand macro="citations" />
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
160
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
161 </tool>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
162