annotate my_VDM_tool.xml @ 3:44e4f5bfebde draft default tip

Uploaded
author fxce
date Mon, 16 Nov 2020 13:59:53 +0000
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
3
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
1 <tool id="my_VDM_tool" name="VDM_tool" version="1.0.0">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
2 <description>Map a mutation using the Variant Discovery Mapping approach (in silico bulk segregant linkage analysis).</description>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
3 <stdio>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
4 <exit_code range="1:"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
5 </stdio>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
6 <requirements>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
7 <requirement type="package" version="3.2.1">R</requirement>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
8 <requirement type="package" version="1.2.0">getopt</requirement>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
9 </requirements>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
10
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
11 <command>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
12 Rscript "${__tool_directory__}/my_VDM_tool.R"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
13 --inf "$inf"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
14 #if $species.species_select=="Celegans"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
15 --itype "$species.ce"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
16 #else if $species.species_select=="Zebrafish"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
17 --itype "$species.ze"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
18 #else if $species.species_select=="Brachypodium"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
19 --itype "$species.br"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
20 #else if $species.species_select=="Arabidopsis"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
21 --itype "$species.ar"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
22 #else if $species.species_select=="other"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
23 --itype "$species.ot"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
24 #end if
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
25
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
26 --qual $qual
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
27
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
28 #if $allfreq.allfreq_select=="AB"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
29 --allr "$allfreq.ab"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
30 #else if $allfreq.allfreq_select=="ratio"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
31 --allr "$allfreq.ratio"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
32 #end if
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
33
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
34 #if $only_snp.only_snp_select=="TRUE"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
35 --snp "$only_snp.true"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
36 #else if $only_snp.only_snp_select=="FALSE"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
37 --snp "$only_snp.false"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
38 #end if
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
39
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
40 --freqthr "$freqthr"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
41
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
42 --lsp $lsp
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
43 --pcol "$pcol"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
44 --lcol "$lcol"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
45
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
46 #if $xaxis.xaxis_select=="TRUE"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
47 --xstand $xaxis.true
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
48 #else if $xaxis.xaxis_select=="FALSE"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
49 --xstand $xaxis.false
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
50 #end if
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
51
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
52 --bsize $bsize
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
53
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
54 #if $binnorm.binnorm_select=="TRUE"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
55 --bnorm $binnorm.true
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
56 #else if $binnorm.binnorm_select=="FALSE"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
57 --bnorm $binnorm.false
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
58 #end if
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
59
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
60 #if $exclfiles.exclfiles_select=="FALSE"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
61 --exclf $exclfiles.false
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
62 #else if $exclfiles.exclfiles_select=="TRUE"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
63 --exclf $exclfiles.true
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
64 #end if
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
65
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
66 --exclcol "$exclcol"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
67
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
68 --outn "$outn"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
69 --pdfn "$pdfn"
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
70 </command>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
71
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
72 <inputs>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
73 <param type="data" name="inf" format="vcf" label="fastq file"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
74
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
75 <conditional name="species">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
76 <param name="species_select" type="select" label="Select the species">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
77 <option value="Celegans">C. elegans</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
78 <option value="Zebrafish">Zebrafish</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
79 <option value="Brachypodium">Brachypodium</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
80 <option value="Arabidopsis">Arabidopsis</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
81 <option value="other">other</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
82 </param>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
83 <when value="Celegans">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
84 <param name="ce" type="hidden" value="C.elegans" label="The C. elegans chromosome numbers and lengths (in Mb)" help=""/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
85 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
86 <when value="Zebrafish">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
87 <param name="ze" type="hidden" value="Zebrafish" label="The Zebrafish chromosome numbers and lengths (in Mb)" help=""/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
88 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
89 <when value="Brachypodium">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
90 <param name="br" type="hidden" value="Brachypodium" label="The Brachypodium chromosome numbers and lengths (in Mb)" help=""/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
91 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
92 <when value="Arabidopsis">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
93 <param name="ar" type="hidden" value="Arabidopsis" label="The Arabidopsis chromosome numbers and lengths (in Mb)" help=""/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
94 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
95 <when value="other">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
96 <param name="ot" type="data" format="tabular" label="Select file with chromosome numbers and lengths (in Mb) from your history" help="Table consisting of chromosome number in column 1 and length (in Mb) in column 2 (e.g. 'CHRI 16' or 'CHR1 16') with no column header names, tab-delimitation, and no quotation marks in a .txt file"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
97 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
98 </conditional>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
99
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
100 <param type="float" name="qual" value="200" label="Filter by quality" help=""/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
101
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
102 <conditional name="allfreq">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
103 <param name="allfreq_select" type="select" label="Select how allele ratios is calculated">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
104 <option value="AB">AB</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
105 <option value="ratio">AO/(AO+RO)</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
106 </param>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
107 <when value="AB">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
108 <param name="ab" type="hidden" value="AB" label="Use AB field from Freebayes" help="Use AB field (from Freebayes) as the value for allele frequency"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
109 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
110 <when value="ratio">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
111 <param name="ratio" type="hidden" value="ratio" label="Use AO/(AO+RO) calculation from Freebayes" help="Use AO/(AO+RO) calculation (from Freebayes) as the value for allele frequency"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
112 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
113 </conditional>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
114
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
115 <conditional name="only_snp">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
116 <param name="only_snp_select" type="select" label="Select type of variants to use for plotting">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
117 <option value="TRUE">only SNP variants</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
118 <option value="FALSE">all variant types</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
119 </param>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
120 <when value="TRUE">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
121 <param name="true" type="hidden" value="TRUE" label="Use only SNP variants" help="Use only SNP variants"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
122 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
123 <when value="FALSE">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
124 <param name="false" type="hidden" value="FALSE" label="Use all types of variants" help="Use all types of variants"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
125 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
126 </conditional>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
127
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
128 <param type="float" name="lsp" value="0.4" label="Loess span" help="Parameter that controls the smoothing of the Loess curve"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
129 <param type="text" name="pcol" value="black" label="Colour of scatterplot points" help="See below for list of supported colors"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
130 <param type="text" name="lcol" value="red" label="Colour of Loess curve" help="See below for list of supported colors"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
131
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
132
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
133 <conditional name="xaxis">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
134 <param name="xaxis_select" type="select" label="Spacing of x-axis intervals">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
135 <option value="TRUE">Uniform lengths for Mb</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
136 <option value="FALSE">Chromosome-scaled lengths for Mb</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
137 </param>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
138 <when value="TRUE">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
139 <param name="true" type="hidden" value="TRUE" label="Uniform spacing of the x-axis based on Mb" help="Scale of x-axis (in Mb) is fixed for the scatter plots and frequency plots across all chromosomes"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
140 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
141 <when value="FALSE">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
142 <param name="false" type="hidden" value="FALSE" label="Variable spacing of the x-axis based on chromosome lengths" help="Scale of x-axis (in Mb) is dependent on chromosome length for the scatter plots and frequency plots for all chromosomes"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
143 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
144 </conditional>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
145
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
146 <param type="integer" name="bsize" value="1000000" label="Bin-size for frequency plots of homozygous variants" help=""/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
147 <param type="text" name="freqthr" value="0.0-1.0" label="Limits of allele ratios for variant to be considered homozygous" help="For frequency plots"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
148
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
149 <conditional name="binnorm">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
150 <param name="binnorm_select" type="select" label="Normalization of y-axis in frequency plots">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
151 <option value="FALSE">Actual Frequency</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
152 <option value="TRUE">Normalized Frequency</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
153 </param>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
154 <when value="TRUE">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
155 <param name="true" type="hidden" value="TRUE" label="Normalized y-axis frequency values based on formula" help="Normalisation formula as in cloudmap paper"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
156 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
157 <when value="FALSE">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
158 <param name="false" type="hidden" value="FALSE" label="Original frequency y-axis values" help=" "/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
159 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
160 </conditional>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
161
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
162 <conditional name="exclfiles">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
163 <param name="exclfiles_select" type="select" label="Additional exclusion of variants by subtraction">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
164 <option value="FALSE">No</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
165 <option value="TRUE">Yes</option>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
166 </param>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
167 <when value="FALSE">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
168 <param name="false" type="hidden" value="FALSE" label="No additional variant subtraction" help=""/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
169 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
170 <when value="TRUE">
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
171 <param name="true" type="data" format="tabular" label="Select variant lists to subtract from your history" help="Requires .txt file with tab-delimited columns for CHR POS REF ALT. Recommend directly using the tables generated by this tool from other samples or as a reference for the required format"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
172 </when>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
173 </conditional>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
174
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
175 <param type="text" name="exclcol" value="green" label="Colour of original Loess curve (before additional variant subtraction)" help="See below for list of supported colors"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
176 </inputs>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
177
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
178 <outputs>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
179 <data name="outn" format="txt"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
180 <data name="pdfn" format="pdf"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
181 </outputs>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
182
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
183
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
184 <tests>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
185 <test>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
186 <param name="inf" value="nor22.vcf"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
187 <output name="outn" file="output.txt"/>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
188 </test>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
189 </tests>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
190
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
191 <help><![CDATA[
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
192
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
193 **What it does**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
194
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
195 This tool generates plots based on variant allele ratios along the genome to facilitate mutation mapping using the Variant Discovery Mapping approach (a form of bulk segregant linkage analysis). It has a few basic filtering options built-in for improved functionality as it serves as the last step in the VDM pipeline [ref].
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
196
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
197 Note that this tool is only compatible with VCF file generated by Freebayes variant calling and annotated with SnpEff.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
198
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
199 It is a replacement for the deprecated cloudmap pipeline and plotting tool. For more details and see paper [link pending].
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
200
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
201 A standalone R version of this code with additional data/metric outputs can be found at https://github.com/fxce/vdm_plot.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
202
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
203
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
204
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
205 ------
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
206
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
207 **OUTPUT**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
208
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
209 ------
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
210
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
211 This tool generates a text file and a pdf file.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
212
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
213 The text file lists the variants that have passed quality filtering along with information on position, allele ratio, details on the mutation, and gene annotation (as parsed from the Freebayes VCF INFO and SnpEff annotation). This offers an easy reference to check for variants after identifying a region of interest from the plots and the parsed format facilitates sorting in e.g. Excel for ones that affect protein-coding.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
214
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
215 The pdf consists of (1) scatterplots based on allele ratios and their corresponding Loess curves along each chromosome; (2) barplots for the frequency of homozygous (ratio=1) variants along each chromosome.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
216
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
217
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
218
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
219 ------
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
220
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
221 **INPUT**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
222
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
223 ------
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
224
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
225 **Select data**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
226
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
227 Load VCF file from history (generated by Freebayes and then annotated with SnpEff).
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
228
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
229
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
230
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
231 **Select species**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
232
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
233 The configuration of chromosomes and sizes needs to be known and this tool is preloaded with this information for for C. elegans, Zebrafish, Brachypodium, and Arabidopsis. To use a custom chromosome configuration, a table containing chromosome numbers in column 1 and their corresponding sizes in Mb in column 2 should be prepared and saved as a tab-delimited .txt file with no column header names, and no quotation marks. Once uploaded to your Galaxy workspace/history, selecting option 'other' will allow for your custom file to be loaded from your history and used instead. e.g.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
234
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
235 CHR1 16
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
236
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
237 CHR2 17
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
238
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
239
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
240
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
241 **Filter Quality**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
242
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
243 Filter by quality, only variants with greater or equal quality values will be retained. Normally, a filter of quality 200 produces a good balance between reliable data and a reasonable amount of variants for plotting although this is dependent on your dataset. It may be useful to test with other quality values (e.g. 100 and 300) if too few or too many variants pass the filter.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
244
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
245
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
246
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
247 **How allele ratio is calculated**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
248
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
249 Option 'AB' uses the AB value from parsed from the VCF INFO that is generated by Freebayes. Option 'AO/(AO+RO)' calculates this ratio value from AO and RO values parsed from the VCF INFO that is generated by Freebayes.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
250
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
251 The AB should equal AO/(AO+RO) in almost all cases, this option is included because there are reports that AB deviates for variants with low quality.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
252
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
253
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
254
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
255 **Type of variants**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
256
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
257 A choice between using only SNP variants or using all variants.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
258
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
259 (The main reason to consider looking at only SNP variants is that Freebayes identifies a number of variants to have arisen from complex substitution/insertion/deletion/other events and it is uncertain how reproducibly some of these long stretches of sequence would be reported across different sequencing reactions. If inconsistent, some of these might be missed by subtraction of the variants in the reference/background leading to false positives.)
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
260
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
261
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
262
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
263 **Loess span**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
264
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
265 This parameter controls the degree of smoothing for the Loess curve and can have a value between 0 and 1, higher values will result in smoother curves.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
266
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
267
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
268
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
269 **Colour of the scatterplot points**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
270
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
271 Any colour names compatible with default R can be used, e.g. can refer to http://www.stat.columbia.edu/~tzheng/files/Rcolor.pdf.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
272
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
273
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
274
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
275 **Colour of Loess curve**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
276
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
277 Any colour names compatible with default R can be used, e.g. can refer to http://www.stat.columbia.edu/~tzheng/files/Rcolor.pdf.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
278
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
279
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
280
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
281 **Spacing of x-axis**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
282
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
283 'Uniform spacing ...' sets the x-axis to be scaled the identically, i.e. the interval for 1Mb, across all chromosomes and for both scatterplots and barplots. 'Variable spacing...' sets the x-axis to scale depending on the length of the chromosome being plotted.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
284
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
285
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
286
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
287 **Bin-size**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
288
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
289 Specifies how the frequency for homozygous variants is binned (in bp) and plotted in the barplot with the default 1000000 setting each bar to span 1Mb.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
290
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
291
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
292
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
293 **Limits for allele ratio to be considered homozygous**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
294
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
295 Variants with allele ratios below the lower value will be considered homozygous REF and above the upper value will be considered homozygous ALT, this option only affects the barplots for the frequency of homozygous variants along chromosomes. Default "0-1" means allele ratios of 0 is considered homozygous for the reference allele and 1 is considered homozygous for the alternate allele. Using <1.0 for the upper limit can be used to visualise the profile of near-homozygous variants and may be more informative if the frequency of homozygous variants (allele ratio=1.0) is low e.g. due to suspected contamination of pooled sample with non-homozygous lines.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
296
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
297
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
298
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
299 **Normalized y-axis frequency values**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
300
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
301 Select between the actual frequency values for homozygous variants in the barplots and normalized frequency. Normalized frequency applies the formula from the Cloudmap paper (Minevich et al., 2012 Genetics 192(4):1249-1269) to improve mapping signal, though it is more relevant for Hawaiian mapping.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
302
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
303
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
304
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
305 **Additional exclusion of variants**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
306
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
307 This provides the option for a user submitted list of variants to be subtracted from the sample list before plotting and is compatible with the variant table generated by this tool. The subtraction is based on matching variants with identical chromosomal location, reference nucleotide, and alternate nucleotide which are then removed. Therefore, formatting of the subtraction list requires columns for chromosome, position, reference nucleotide, and alternate nucleotide which are named 'CHR POS REF ALT', e.g. (+RATIO)
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
308
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
309 CHR POS REF ALT
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
310
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
311 III 12 G A
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
312
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
313
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
314
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
315 Note that selecting multiple subtraction files here is not cumulative, only one variant list is subtracted from the sample each time before the an output is generated. Merging variant lists from different samples would have to be performed manually before being uploaded and selected as a subtraction list.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
316
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
317
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
318
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
319 **Colour of original Loess curve**
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
320
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
321 Any colour names compatible with default R can be used, e.g. can refer to http://www.stat.columbia.edu/~tzheng/files/Rcolor.pdf.
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
322
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
323
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
324
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
325
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
326 ]]>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
327 </help>
44e4f5bfebde Uploaded
fxce
parents:
diff changeset
328 </tool>