comparison king.xml @ 0:ec2bc87ebd7b draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/king/ commit 7e521e5df8cac36549fed2488034c9d1c4376a3a"
author iuc
date Tue, 16 Nov 2021 20:14:31 +0000
parents
children 1932808c6fab
comparison
equal deleted inserted replaced
-1:000000000000 0:ec2bc87ebd7b
1 <?xml version="1.0" encoding="utf-8"?>
2 <tool id="king" name="KING" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
3 <description>Kinship-based INference for GWAS</description>
4 <macros>
5 <token name="@TOOL_VERSION@">2.2.4</token>
6 <token name="@VERSION_SUFFIX@">0</token>
7 </macros>
8 <requirements>
9 <requirement type="package" version="@TOOL_VERSION@">king</requirement>
10 <requirement type="package" version="1.6.4">r-kinship2</requirement>
11 <requirement type="package" version="1.2.2">r-igraph</requirement>
12 </requirements>
13 <version_command>
14 king | head -1 | cut -d' ' -f 2
15 </version_command>
16 <command detect_errors="exit_code"><![CDATA[
17 ln -s '$genotype' input.bed &&
18 ln -s '$family' input.fam &&
19 ln -s '$map' input.bim &&
20
21 king -b input.bed --fam input.fam --bim input.bim
22 $related
23 $duplicate
24 $kinship
25 $ibdseg
26 $ibs
27 $homog
28 #if str($degree):
29 --degree $degree
30 #end if
31 #if str($projection):
32 --projection $projection
33 #end if
34 $unrelated
35 $build
36 $cluster
37 $rplot
38
39 > '$kingoutlog'
40 ]]></command>
41 <inputs>
42 <param name="genotype" type="data" format="pbed,binary" label="Binary Genotype File" />
43 <param name="family" type="data" format="lped,txt" label="Family File" />
44 <param name="map" type="data" format="tabular" label="Map File" />
45 <!-- Beginning of the optional paramters -->
46 <param argument="--related" type="boolean" truevalue="--related" falsevalue="" label="Relationship Inference" help="Implements the fastest and integrated relationship inference." />
47 <param argument="--duplicate" type="boolean" truevalue="--duplicate" falsevalue="" label="Duplicate Analysis" help="Implements the fastest (and accurate) algorithm to identify duplicates or MZ twins" />
48 <param argument="--kinship" type="boolean" truevalue="--kinship" falsevalue="" label="Kinship Inference" help="Estimates pair-wise kinship coefficients" />
49 <param argument="--ibdseg" type="boolean" truevalue="--ibdseg" falsevalue="" label="IBD Segment Analysis" help="IBD segment analysis determines all IBD (IBD1 and IBD2) segments shared between relatives" />
50 <param argument="--ibs" type="boolean" truevalue="--ibs" falsevalue="" label="IBS Summary Statistics" help="Counts and average of IBS" />
51 <param argument="--homog" type="boolean" truevalue="--homog" falsevalue="" label="Homogeneous Population" help="Estimates pair-wise kinship coefficients assuming a homogeneous population." />
52 <param argument="--degree" type="integer" min="0" optional="true" label="Degrees of relatedness" help="Filters relative pairs based on kinship coefficients." />
53 <param argument="--projection" type="integer" min="0" optional="true" label="Projection N" help="Includes the first N samples of a subset." />
54 <param argument="--unrelated" type="boolean" truevalue="--unrelated" falsevalue="" label="Unrelated Option" help="Extract a list of unrelated individuals." />
55 <param argument="--build" type="boolean" truevalue="--build" falsevalue="" label="Reconstruct Pedigree" help="Reconstructs pedigrees using SNP data" />
56 <param argument="--cluster" type="boolean" truevalue="--cluster" falsevalue="" label="Cluster Parameter" help="Clusters relatives into families by generating an updateid file." />
57 <param argument="--rplot" type="boolean" truevalue="--rplot" falsevalue="" label="R Code and Plots" help="Generates R code first and then calls R program to make plots in a PDF file." />
58 <param name="use_log" type="boolean" checked="false" label="Output a Log?" />
59 </inputs>
60 <outputs>
61 <data name="kingoutlog" format="txt" label="${tool.name} on ${on_string} : Log" >
62 <filter>use_log == True</filter>
63 </data>
64 <collection name="kingoutput_txt" type="list" label="${tool.name} on ${on_string}: Metrics">
65 <discover_datasets pattern="king(?P&lt;designation&gt;.+)\.txt" format="txt" />
66 </collection>
67 <collection name="kingoutput_log" type="list" label="${tool.name} on ${on_string}: Metrics Logs" >
68 <filter>use_log == True</filter>
69 <discover_datasets pattern="king(?P&lt;designation&gt;.+)\.log" format="txt" />
70 </collection>
71 <collection name="kingoutput_pdf" type="list" label="${tool.name} on ${on_string}: Plots">
72 <discover_datasets pattern="king_(?P&lt;designation&gt;.+)\.pdf" format="pdf" />
73 </collection>
74 </outputs>
75 <tests>
76 <test>
77 <param name="genotype" value="new.6000.bed"/>
78 <param name="family" value="new.6000.fam"/>
79 <param name="map" value="new.6000.bim"/>
80 <param name="related" value="true" />
81 <param name="use_log" value="true" />
82 <output name="kingoutlog">
83 <assert_contents>
84 <has_text text="Total length of 6 chromosomal segments usable for IBD segment analysis is"/>
85 <has_text text="Information of these chromosomal segments can be found in file kingallsegs.txt" />
86 <has_text text="--related" />
87 <has_text text="Relationship summary (total relatives: 200 by pedigree, 200 by inference)" />
88 </assert_contents>
89 </output>
90 </test>
91 <test>
92 <param name="genotype" value="new.6000.bed"/>
93 <param name="family" value="new.6000.fam"/>
94 <param name="map" value="new.6000.bim"/>
95 <param name="related" value="true" />
96 <param name="degree" value="2" />
97 <param name="use_log" value="true" />
98 <output name="kingoutlog">
99 <assert_contents>
100 <has_text text="Total length of 6 chromosomal segments usable for IBD segment analysis is"/>
101 <has_text text="Information of these chromosomal segments can be found in file kingallsegs.txt" />
102 <has_text text="--related" />
103 <has_text text="--degree 2" />
104 <has_text text="Relationship summary (total relatives: 200 by pedigree, 200 by inference)" />
105 </assert_contents>
106 </output>
107 </test>
108 <test>
109 <param name="genotype" value="new.6000.bed"/>
110 <param name="family" value="new.6000.fam"/>
111 <param name="map" value="new.6000.bim"/>
112 <param name="related" value="true" />
113 <param name="degree" value="2" />
114 <param name="rplot" value="true" />
115 <param name="use_log" value="true" />
116 <output name="kingoutlog">
117 <assert_contents>
118 <has_text text="Autosome genotypes stored in 94 words for each of 332 individuals."/>
119 <has_text text="Total length of 6 chromosomal segments usable for IBD segment analysis is" />
120 <has_text text="--related" />
121 <has_text text="--degree 2" />
122 <has_text text="--rplot" />
123 <has_text text="(with 6000 SNPs): 8 pairs of relatives are detected (with kinship > 0.0625)" />
124 <has_text text="Relationship summary (total relatives: 0 by pedigree, 6 by inference)" />
125 </assert_contents>
126 </output>
127 </test>
128 <test>
129 <param name="genotype" value="new.6000.bed"/>
130 <param name="family" value="new.6000.fam"/>
131 <param name="map" value="new.6000.bim"/>
132 <param name="duplicate" value="true" />
133 <param name="use_log" value="true" />
134 <output name="kingoutlog">
135 <assert_contents>
136 <has_text text="Autosome genotypes stored in 94 words for each of 332 individuals."/>
137 <has_text text="--duplicate" />
138 <has_text text="No duplicates are found with heterozygote concordance rate > 80%." />
139 </assert_contents>
140 </output>
141 </test>
142 <test>
143 <param name="genotype" value="new.6000.bed"/>
144 <param name="family" value="new.6000.fam"/>
145 <param name="map" value="new.6000.bim"/>
146 <param name="kinship" value="true" />
147 <param name="use_log" value="true" />
148 <output name="kingoutlog">
149 <assert_contents>
150 <has_text text="Autosome genotypes stored in 94 words for each of 332 individuals."/>
151 <has_text text="--kinship" />
152 <has_text text="Relationship summary (total relatives: 200 by pedigree, 200 by inference)" />
153 </assert_contents>
154 </output>
155 </test>
156 <test>
157 <param name="genotype" value="new.6000.bed"/>
158 <param name="family" value="new.6000.fam"/>
159 <param name="map" value="new.6000.bim"/>
160 <param name="related" value="true" />
161 <param name="projection" value="100000" />
162 <param name="use_log" value="true" />
163 <output name="kingoutlog">
164 <assert_contents>
165 <has_text text="Autosome genotypes stored in 94 words for each of 332 individuals."/>
166 <has_text text="--related" />
167 <has_text text="Relationship summary (total relatives: 200 by pedigree, 200 by inference)" />
168 <has_text text="PLINK pedigrees loaded: 332 samples" />
169 <has_text text="PLINK maps loaded: 6000 SNPs" />
170 <has_text text="Autosome genotypes stored in 94 words for each of 332 individuals." />
171 </assert_contents>
172 </output>
173 </test>
174 <test>
175 <param name="genotype" value="new.6000.bed"/>
176 <param name="family" value="new.6000.fam"/>
177 <param name="map" value="new.6000.bim"/>
178 <param name="ibdseg" value="true" />
179 <param name="use_log" value="true" />
180 <output name="kingoutlog">
181 <assert_contents>
182 <has_text text="--ibdseg" />
183 <has_text text="Sample pairs without any long IBD segments (>10Mb) are excluded." />
184 <has_text text="IBD segments saved in a gzipped file king.segments.gz" />
185 <has_text text="Total length of 6 chromosomal segments usable for IBD segment analysis is" />
186 </assert_contents>
187 </output>
188 </test>
189 <test>
190 <param name="genotype" value="new.6000.bed"/>
191 <param name="family" value="new.6000.fam"/>
192 <param name="map" value="new.6000.bim"/>
193 <param name="ibdseg" value="true" />
194 <param name="degree" value="3" />
195 <param name="rplot" value="true" />
196 <param name="use_log" value="true" />
197 <output name="kingoutlog">
198 <assert_contents>
199 <has_text text="--ibdseg" />
200 <has_text text="--rplot" />
201 <has_text text="--degree 3" />
202 <has_text text="Summary statistics of IBD segments for individual pairs saved in file king.seg" />
203 <has_text text="Genotype data consist of 6000 autosome SNPs" />
204 </assert_contents>
205 </output>
206 </test>
207 <test>
208 <param name="genotype" value="new.6000.bed"/>
209 <param name="family" value="new.6000.fam"/>
210 <param name="map" value="new.6000.bim"/>
211 <param name="ibs" value="true" />
212 <param name="use_log" value="true" />
213 <output name="kingoutlog">
214 <assert_contents>
215 <has_text text="Autosome genotypes stored in 94 words for each of 332 individuals." />
216 <has_text text="Within-family IBS data saved in file king.ibs" />
217 <has_text text="--ibs" />
218 <has_text text="Total length of 6 chromosomal segments usable for IBD segment analysis is" />
219 <has_text text="Information of these chromosomal segments can be found in file kingallsegs.txt" />
220 <has_text text="Between-family IBS data saved in file king.ibs0" />
221 <has_text text="Relationship summary (total relatives: 200 by pedigree, 200 by inference)" />
222 </assert_contents>
223 </output>
224 </test>
225 <test>
226 <param name="genotype" value="new.6000.bed"/>
227 <param name="family" value="new.6000.fam"/>
228 <param name="map" value="new.6000.bim"/>
229 <param name="homog" value="true" />
230 <param name="use_log" value="true" />
231 <output name="kingoutlog">
232 <assert_contents>
233 <has_text text="Autosome genotypes stored in 375 words for each of 332 individuals." />
234 <has_text text="--homo" />
235 <has_text text="Within-family kinship data saved in file king.kin" />
236 <has_text text="Genotype data consist of 6000 autosome SNPs" />
237 </assert_contents>
238 </output>
239 </test>
240 <test>
241 <param name="genotype" value="new.6000.bed"/>
242 <param name="family" value="new.6000.fam"/>
243 <param name="map" value="new.6000.bim"/>
244 <param name="unrelated" value="true" />
245 <param name="use_log" value="true" />
246 <output name="kingoutlog">
247 <assert_contents>
248 <has_text text="--unrelated" />
249 <has_text text="Total length of 6 chromosomal segments usable for IBD segment analysis is" />
250 <has_text text="Y028,Y117" />
251 <has_text text="An alternative list of 114 to-be-removed individuals saved in file kingunrelated_toberemoved.txt" />
252 </assert_contents>
253 </output>
254 </test>
255 <test>
256 <param name="genotype" value="new.6000.bed"/>
257 <param name="family" value="new.6000.fam"/>
258 <param name="map" value="new.6000.bim"/>
259 <param name="unrelated" value="true" />
260 <param name="degree" value="2" />
261 <param name="use_log" value="true" />
262 <output name="kingoutlog" >
263 <assert_contents>
264 <has_text text="--unrelated" />
265 <has_text text="--degree 2" />
266 <has_text text="Autosome genotypes stored in 94 words for each of 332 individuals." />
267 <has_text text="An alternative list of 114 to-be-removed individuals saved in file kingunrelated_toberemoved.txt" />
268 </assert_contents>
269 </output>
270 </test>
271 <test>
272 <param name="genotype" value="new.6000.bed"/>
273 <param name="family" value="new.6000.fam"/>
274 <param name="map" value="new.6000.bim"/>
275 <param name="build" value="true" />
276 <param name="use_log" value="true" />
277 <output name="kingoutlog" >
278 <assert_contents>
279 <has_text text="--build" />
280 <has_text text="Autosome genotypes stored in 94 words for each of 332 individuals." />
281 <has_text text="Update-ID information is saved in file kingupdateids.txt" />
282 <has_text text="Total length of 6 chromosomal segments usable for IBD segment analysis is" />
283 </assert_contents>
284 </output>
285 </test>
286 <test>
287 <param name="genotype" value="new.6000.bed"/>
288 <param name="family" value="new.6000.fam"/>
289 <param name="map" value="new.6000.bim"/>
290 <param name="build" value="true" />
291 <param name="degree" value="2" />
292 <param name="use_log" value="true" />
293 <output name="kingoutlog">
294 <assert_contents>
295 <has_text text="--build" />
296 <has_text text="--degree 2" />
297 <has_text text="Total length of 6 chromosomal segments usable for IBD segment analysis is" />
298 <has_text text="Update-parent information is saved in file kingupdateparents.txt" />
299 </assert_contents>
300 </output>
301 </test>
302 <test>
303 <param name="genotype" value="new.6000.bed"/>
304 <param name="family" value="new.6000.fam"/>
305 <param name="map" value="new.6000.bim"/>
306 <param name="cluster" value="true" />
307 <param name="use_log" value="true" />
308 <output name="kingoutlog">
309 <assert_contents>
310 <has_text text="--cluster" />
311 <has_text text="Total length of 6 chromosomal segments usable for IBD segment analysis is" />
312 <has_text text="Pair-wise relatedness in newly clustered families saved in kingcluster.kin." />
313 </assert_contents>
314 </output>
315 </test>
316 </tests>
317 <help><![CDATA[
318
319 `KING <http://people.virginia.edu/~wc9c/KING/>`_ is a toolset that makes use of high-throughput SNP data typically seen in a genome-wide association study (GWAS)
320 or a sequencing project. Applications of KING include family relationship inference and pedigree error checking,
321 quality control, population substructure identification, forensics, gene mapping, etc.
322
323 ]]>
324 </help>
325 <citations>
326 <citation type="doi">10.1093/bioinformatics/btq559</citation>
327 </citations>
328 </tool>