annotate CRISPRSeek/compare2sequences.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="compare2sequences" name="compare2sequences" version="1.0.0">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
2 <description>CRISPRSeek compare2sequences</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 "${compare2sequences}"
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
9 </command>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
10 <configfiles>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
11 <configfile name="compare2sequences"><![CDATA[
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
12 ## code chunk: Load all required libraries quietly
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
13 library(CRISPRseek, quietly=TRUE, warn.conflicts=FALSE,verbose = FALSE)
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
14
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
15 compare2Sequences("${s1.inputfile}", "${s2.inputfile}", inputNames=c("Seq1", "Seq2"), REpatternFile = system.file('extdata', 'NEBenzymes.fa', package = 'CRISPRseek'), max.mismatch="${maxmismatch}", 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}", 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 <conditional name="s1">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
21 <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
22 <option value="history">History</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
23 <option value="FullPath">Free Text</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
24 <option value="Fasta">Fasta</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
25 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
26 <when value="FullPath">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
27 <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
28 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
29 <when value="Fasta">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
30 <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
31 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
32 <when value="history">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
33 <param format="fastq,fa,fasta" name="inputfile" type="data" label="Input File Path" />
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
34 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
35 </conditional>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
36 <conditional name="s2">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
37 <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
38 <option value="history">History</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
39 <option value="FullPath">Free Text</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
40 <option value="Fasta">Fasta</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
41 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
42 <when value="FullPath">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
43 <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
44 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
45 <when value="Fasta">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
46 <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
47 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
48 <when value="history">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
49 <param format="fastq,fa,fasta" name="inputfile" type="data" label="Input File Path" />
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
50 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
51 </conditional>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
52 <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
53 <param name="outputdir" type="text" area="true" size="2x60" label="Output Directory" help="Output directory in the cluster"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
54 <conditional name="a">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
55 <param name="advanced" type="select" label="Advanced Options">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
56 <option value="No" selected="True">No</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
57 <option value="Yes">Yes</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
58 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
59 <when value="Yes">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
60 <param name="searchDirection" type="select" label="Search Direction">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
61 <option value="both" selected="True">both</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
62 <option value="1to2">1to2</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
63 <option value="2to1">2to1</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
64 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
65 <conditional name="fg">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
66 <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
67 <option value="FALSE" selected="True">No</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
68 <option value="TRUE">Yes</option>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
69 </param>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
70 <when value="True">
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
71 <param name="mingap" type="text" label="Min Gap" value="0" />
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
72 <param name="maxgap" type="text" label="Max Gap" value="20" />
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
73 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
74 </conditional>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
75 <param name="PAMsize" type="text" label="PAM Size" value="3" help="PAM length, default 3"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
76 <param name="PAM" type="text" label="PAM" value="NGG" help="PAM sequence after the gRNA, default NGG"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
77 <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
78 <param name="gRNAsize" type="text" label="gRNA Size" value="20" help="The size of the gRNA, default 20"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
79 <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
80 </when>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
81 </conditional>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
82 </inputs>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
83 <outputs>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
84 <data format="gz" name="output"/>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
85 </outputs>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
86 <help>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
87
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
88 **What it does**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
89
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
90 The package includes functions to find potential guide RNAs for input target se-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
91 quences, optionally filter guide RNAs without restriction enzyme cut site, or with-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
92 out paired guide RNAs, genome-wide search for off-targets, score, rank, fetch flank se-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
93 quence and indicate whether the target and off-targets are located in exon region or not. Poten-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
94 tial guide RNAs are annotated with total score of the top5 and topN off-targets, de-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
95 tailed topN mismatch sites, restriction enzyme cut sites, and paired guide RNAs.
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
96
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
97 **Description**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
98
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
99 Generate all possible guide RNAs (gRNAs) for two input sequences, or two sets of sequences and generate scores for potential off-targets in the other sequence.
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
100
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
101 **Usage**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
102
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
103 compare2Sequences(inputFile1Path, inputFile2Path, inputNames=c("Seq1", "Seq2"), format = "fasta", findgRNAsWithREcutOnly = FALSE, searchDirection=c("both","1to2", "2to1"), REpatternFile=system.file("extdata", "NEBenzymes.fa", package = "CRISPRseek"), minREpatternSize = 6, overlap.gRNA.positions = c(17, 18), findPairedgRNAOnly = FALSE, min.gap = 0, max.gap = 20, gRNA.name.prefix = "gRNA", PAM.size = 3, gRNA.size = 20, PAM = "NGG", PAM.pattern = "N[A|G]G$", max.mismatch = 3, outputDir, weights = c(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), overwrite = FALSE)
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
104
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
105 **Author(s)**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
106
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
107 Lihua Julie Zhu and Michael Brodsky Maintainer: julie.zhu@umassmed.edu
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
108
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
109 Alper Kucukural, Galaxy Maintainer: alper.kucukural@umassmed.edu
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
110
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
111 **Citation**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
112
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
113 (from within R, enter citation("CRISPRseek")):
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
114
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
115 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
116
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
117 **References**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
118
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
119 Patrick D Hsu, David A Scott, Joshua A Weinstein, F Ann Ran, Silvana Konermann, Vineeta Agar-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
120 wala, Yinqing Li, Eli J Fine, Xuebing Wu, Ophir Shalem, Thomas J Cradick, Luciano A Marraffini,
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
121 Gang Bao, Feng Zhang (2013) DNA targeting specificity of rNA-guided Cas9 nucleases. Nature
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
122 Biotechnology 31:827-83
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
123
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
124 Mali P, Aach J, Stranges PB, Esvelt KM, Moosburner M, Kosuri S, Yang L, Church GM.CAS9
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
125 transcriptional activators for target specificity screening and paired nickases for cooperative genome
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
126 engineering. Nat Biotechnol. 2013. 31(9):833-8 Patrick D Hsu, David A Scott, Joshua A Wein-
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
127 stein, F Ann Ran, Silvana Konermann, Vineeta Agarwala, Yinqing Li, Eli J Fine, Xuebing Wu,
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
128 Ophir Shalem, Thomas J Cradick, Luciano A Marraffini, Gang Bao, Feng Zhang. DNA targeting
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
129 specificity of rNA-guided Cas9 nucleases. Nat Biotechnol. 2013. 31:827-834
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
130
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
131 **Reference Manual and Materials**
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
132
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
133 http://www.bioconductor.org/packages/release/bioc/vignettes/CRISPRseek/inst/doc/CRISPRseek.pdf
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
134
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
135 http://www.bioconductor.org/packages/release/bioc/manuals/CRISPRseek/man/CRISPRseek.pdf
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
136
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
137 http://www.bioconductor.org/packages/release/bioc/vignettes/CRISPRseek/inst/doc/CRISPRseek.R
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
138
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
139
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
140
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
141
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
142
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
143 </help>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
144 <expand macro="citations" />
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
145
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
146 </tool>
8615e7e7c5be Uploaded
alperkucukural
parents:
diff changeset
147