comparison macros_cluster.xml @ 0:e0e9b24d76aa draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/raceid3 commit f880060c478d42202df5b78a81329f8af56b1138
author iuc
date Thu, 22 Nov 2018 04:42:18 -0500
parents
children 4164c0da0a5d
comparison
equal deleted inserted replaced
-1:000000000000 0:e0e9b24d76aa
1 <macros>
2 <macro name="cluster_inputs" >
3 <param name="intable" type="data" format="tabular" label="Count Matrix" />
4 <section name="filt" title="Filtering" expanded="true" >
5 <param name="mintotal" type="integer" min="1" value="3000" label="Min Transcripts" help="The minimum total transcripts required. Cells with less than mintotal transcripts are filtered out." />
6 <param name="minexpr" type="integer" min="1" value="5" label="Min Expression" help="The minimum required transcript counts of a gene in the minimum number of cells (below)" />
7 <param name="minnumber" type="integer" min="1" value="5" label="Min Cells" help="The minumum number of cells for gene expression to be counted" />
8 <expand macro="use_defaults_no" >
9 <param name="knn" type="integer" min="0" value="10" label="K-nearest-neighbours" help="Number of nearest neighbors used to infer corresponding cell types in different batches" />
10 <param name="CGenes" type="text" optional="true" label="CGenes" help="Filter out genes with correlated expression for cell type inference" >
11 <expand macro="sanitize_string_vector" />
12 </param>
13 <param name="FGenes" type="text" optional="true" label="FGenes" help="Explicitly filter out genes for cell type inference" >
14 <expand macro="sanitize_string_vector" />
15 </param>
16 <param name="LBatch_regexes" type="text" optional="true" label="Batch Regex" help="List of regexes to capture experimental batches for batch effect correction" >
17 <expand macro="sanitize_string_vector" />
18 </param>
19 <param name="ccor" type="float" value="0.4" label="CCor" help="Correlation coefficient used as a threshold for determining correlated genes" />
20 <param name="bmode" type="select" label="Batch Mode" help="Method to regress out batch effects" >
21 <option value="RaceID" selected="true" >RaceID</option>
22 <option value="scran">SCRAN</option>
23 </param>
24 <conditional name="ccc" >
25 <param name="use" type="select" label="Perform Cell-cycle correction?" >
26 <option value="yes" >Yes</option>
27 <option value="no" selected="true" >No</option>
28 </param>
29 <when value="no" />
30 <when value="yes" >
31 <param name="vset" type="text" optional="true" label="List of Gene Sets" >
32 <expand macro="sanitize_string_vector" />
33 </param>
34 <param name="pvalue" type="float" value="0.01" min="0" max="1" label="P-value Cutoff" help="P-value cutoff for determining enriched components" />
35 <param name="quant" type="float" value="0.01" min="0" max="1" label="Quantification Fraction" help="Upper and lower fraction of gene loadings use for determining enriched components" />
36 <param name="ncomp" type="integer" min="0" optional="true" label="Number of components to use" help="If left blank, the maximum number of components are used" /><!-- 0 = NULL -->
37 <param name="dimr" type="boolean" value="true" label="Derive Components from saturation criterion" />
38 <param name="mode" type="select" label="Type of Component Analysis" help="If ICA is selected, ensure that the number of components value above is sufficiently high" >
39 <option value="pca" selected="true">PCA</option>
40 <option value="ica">ICA</option>
41 </param>
42 <param name="logscale" type="boolean" value="false" label="Log-transform data prior to PCA or ICA" help="" />
43 </when>
44 </conditional>
45 </expand>
46 </section>
47 <section name="clust" title="Clustering" expanded="true" >
48 <!-- CompDist -->
49 <param name="metric" type="select" label="Distance Metric" >
50 <option value="pearson" selected="true" >Pearson</option>
51 <option value="spearman">Spearman</option>
52 <option value="logpearson">Log Pearson</option>
53 <option value="euclidean">Euclidean</option>
54 </param>
55 <!-- ClustExp -->
56 <param name="funcluster" type="select" label="Clustering method" >
57 <option value="kmedoids" selected="true" >K-medoids</option>
58 <option value="kmeans">K-means</option>
59 <option value="hclust">H-Clust</option>
60 </param>
61 <expand macro="use_defaults_no" >
62 <!-- CompDist -->
63 <param name="fselect" type="boolean" value="true" label="Perform feature selection" />
64 <param name="knn" type="integer" min="0" optional="true" label="KNN" help="Number of nearest neighbours for imputing gene expression" /><!-- 0: NULL -->
65 <!-- ClustExp -->
66 <param name="sat" type="boolean" checked="true" label="Saturation-based clustering?" help="Determine number of clusters on saturation point of the mean within-cluster dispersion as a function of the cluster number." />
67 <param name="clustnr" type="integer" min="0" value="30" label="Max number of clusters using Saturation-by-mean" help="Max number of clusters for the derivation of the cluster number by the saturation of mean within-cluster-dispersion." />
68 <param name="samp" type="integer" min="0" optional="true" label="Sample random number of cells" help="Number of random sample of cells used for the inference of cluster number and Jaccard similarity" /><!-- 0:NULL -->
69 <param name="cln" type="integer" min="0" optional="true" label="Number of clusters" /><!-- 0:Null -->
70 <param name="bootnr" type="integer" min="0" value="50" label="Number of booststrapping runs" />
71 <param name="rseed" type="integer" value="17000" label="Random seed" />
72 </expand>
73 </section>
74 <section name="outlier" title="Outliers" expanded="true" >
75 <!-- Find Outliers -->
76 <param name="outminc" type="integer" min="0" value="5" label="Minimum Transcripts" help="minimal transcript count of a gene in a clusters to be tested for being an outlier gene" />
77 <param name="outlg" type="integer" min="1" value="2" label="Minimum Genes" help="Minimum number of outlier genes required for being an outlier cell" />
78 <!-- RFCorrect -->
79 <param name="final" type="boolean" value="true" label="Plot Final Clusters?" help="Reclassification of cell types using out-of-bag analysis is performed based on the final clusters after outlier identification. If 'FALSE', then the cluster partition prior to outlier identification is used for reclassification." />
80 <expand macro="use_defaults_no" >
81 <!-- Find Outliers -->
82 <param name="probthr" type="float" min="0" value="0.001" label="Outlier Probability Threshold" help="Probability threshold for the above specified minimum number of genes to be an outlier cell. This probability is computed from a negative binomial background model of expression in a cluster" />
83 <param name="outdistquant" type="float" min="0" max="1" value="0.95" label="Outlier Distance Quantile" help="Outlier cells are merged to outlier clusters if their distance smaller than the outdistquant-quantile of the distance distribution of pairs of cells in the orginal clusters after outlier removal" />
84 <!-- RFCorrect -->
85 <param name="nbtree" type="integer" optional="true" label="Number of trees to be built" /><!-- 0:Null -->
86 <param name="nbfactor" type="integer" min="0" value="5" label="Tree Factor" help="Number of trees based on the number of cells multiplied by this factor. Effective only if the number of trees parameter is set to 0" />
87 <param name="rfseed" type="integer" value="12345" label="Random Seed" />
88 </expand>
89 </section>
90 <section name="tsne" title="tSNE and FR" expanded="true" >
91 <!-- CompTSNE -->
92 <param name="perplexity" type="integer" min="0" value="30" label="Perplexity" help="Perplexity of the t-SNE map" />
93 <!-- CompFR -->
94 <param name="knn" type="integer" min="0" value="10" label="KNN" help="Number of nearest neighbours used for the inference of the Fruchterman-Rheingold layout" />
95 <expand macro="use_defaults_no" >
96 <!-- CompTSNE -->
97 <param name="initial_cmd" type="boolean" checked="true" label="tSNE map initialised by classical multidimensional scaling" />
98 <param name="rseed_tsne" type="integer" value="15555" label="Random Seed (tSNE)" />
99 <!-- CompFR -->
100 <param name="rseed_fr" type="integer" min="0" value="15555" label="Random Seed (FR)" />
101 </expand>
102 </section>
103 <section name="extra" title="Extra Parameters" expanded="false" >
104 <param name="tablelim" type="integer" min="1" value="25" label="Table Limit" help="Top N genes to print per cluster" />
105 <param name="plotlim" type="integer" min="1" value="10" label="Plot Limit" help="Top N genes to plot. Must be less than or equal to the Table Limit" />
106 <param name="foldchange" type="float" min="0" value="1" label="Fold change" />
107 <param name="pvalue" type="float" min="0" max="1" value="0.01" label="P-value Cutoff" help="P-value cutoff for the inference of differential gene expression" />
108 </section>
109 </macro>
110 <macro name="cluster_tests" >
111 <test>
112 <!-- default test -->
113 <conditional name="tool" >
114 <param name="mode" value="cluster" />
115 <!-- This is a file with a single word 'test', which prompts the scripts to use the test intestinalData in the library -->
116 <param name="intable" value="use.intestinal" />
117 </conditional>
118 <output name="outgenelist" value="intestinal.genelist" />
119 <output name="outpdf" value="intestinal.pdf" compare="sim_size" delta="50" />
120 </test>
121 <test>
122 <!-- defaults, feeding in a matrix with reduced filtering -->
123 <conditional name="tool" >
124 <param name="mode" value="cluster" />
125 <param name="intable" value="matrix.tabular" />
126 <section name="filt" >
127 <param name="mintotal" value="1000" />
128 <param name="minexpr" value="1" />
129 <param name="minnumber" value="3" />
130 </section>
131 <param name="use_log" value="true" />
132 <output name="outgenelist" value="matrix.genelist" />
133 <output name="outrdat" value="matrix.rdat" compare="sim_size" delta="15" />
134 <output name="outpdf" value="matrix.pdf" compare="sim_size" delta="10" />
135 <output name="outlog" value="matrix.log" />
136 </conditional>
137 </test>
138 <test>
139 <!-- defaults, but manually specified. No opts, no CC. Generates identical to above -->
140 <conditional name="tool" >
141 <param name="mode" value="cluster" />
142 <param name="intable" value="use.intestinal" />
143 <section name="filt" >
144 <param name="mintotal" value="3000" />
145 <param name="minexpr" value="5" />
146 <param name="minnumber" value="5" />
147 <expand macro="test_nondef" >
148 <param name="knn" value="10" />
149 <param name="ccor" value="0.4" />
150 <param name="bmode" value="RaceID" />
151 </expand>
152 </section>
153 <section name="clust" >
154 <param name="metric" value="pearson" />
155 <param name="funcluster" value="kmedoids" />
156 <expand macro="test_nondef" >
157 <param name="fselect" value="true" />
158 <param name="sat" value="true" />
159 <param name="clustnr" value="30" />
160 <param name="bootnr" value="50" />
161 <param name="rseed" value="17000" />
162 </expand>
163 </section>
164 <section name="outlier" >
165 <param name="outminc" value="5" />
166 <param name="outlg" value="2" />
167 <param name="final" value="false" />
168 <expand macro="test_nondef" section_name="outlier" >
169 <param name="probthr" value="0.001" />
170 <param name="outdistquant" value="0.95" />
171 <param name="rfseed" value="12345" />
172 <param name="nbfactor" value="5" />
173 </expand>
174 </section>
175 <section name="tsne" >
176 <param name="perplexity" value="30" />
177 <param name="knn" value="10" />
178 <expand macro="test_nondef" section_name="tsne" >
179 <param name="initial_cmd" value="true" />
180 <param name="rseed_tsne" value="15555" />
181 <param name="rfseed_fr" value="15555" />
182 </expand>
183 </section>
184 </conditional>
185 <output name="outgenelist" value="intestinal.genelist" />
186 <output name="outpdf" value="intestinal.pdf" compare="sim_size" delta="50" />
187 </test>
188 <test>
189 <!-- Advanced. Opts, CC used -->
190 <conditional name="tool" >
191 <param name="mode" value="cluster" />
192 <param name="intable" value="use.intestinal" />
193 <section name="filt" >
194 <param name="mintotal" value="2000" />
195 <param name="minexpr" value="3" />
196 <param name="minnumber" value="2" />
197 <expand macro="test_nondef" >
198 <param name="knn" value="5" />
199 <param name="ccor" value="0.5" />
200 <param name="CGenes" value="Gga3,Ggact,Ggct" />
201 <param name="FGenes" value="Zxdc,Zyg11a,Zyg11b,Zyx" />
202 <param name="LBatch_regexes" value="^I5,^II5,^III5,^IV5d,^V5d" />
203 <param name="bmode" value="scran" />
204 <conditional name="ccc" >
205 <param name="use" value="yes" />
206 <param name="pvalue" value="0.05" />
207 <param name="quant" value="0.05" />
208 <param name="ncomp" value="3" />
209 <param name="dimr" value="true" />
210 <param name="mode" value="pca" />
211 <param name="logscale" value="true" />
212 </conditional>
213 </expand>
214 </section>
215 <section name="clust" >
216 <param name="metric" value="euclidean" />
217 <param name="funcluster" value="hclust" />
218 <expand macro="test_nondef" >
219 <param name="fselect" value="false" />
220 <param name="knn" value="5" />
221 <param name="sat" value="false" />
222 <param name="samp" value="10" />
223 <param name="cln" value="10" />
224 <param name="clustnr" value="10" />
225 <param name="bootnr" value="30" />
226 <param name="rseed" value="17000" />
227 </expand>
228 </section>
229 <section name="outlier" >
230 <param name="outminc" value="3" />
231 <param name="outlg" value="5" />
232 <param name="final" value="true" />
233 <expand macro="test_nondef" >
234 <param name="probthr" value="0.01" />
235 <param name="outdistquant" value="0.5" />
236 <param name="rfseed" value="12345" />
237 <param name="nbfactor" value="5" />
238 <param name="nbtree" value="10" />
239 </expand>
240 </section>
241 <section name="tsne" >
242 <param name="perplexity" value="20" />
243 <param name="knn" value="6" />
244 <expand macro="test_nondef" >
245 <param name="initial_cmd" value="false" />
246 <param name="rseed_tsne" value="15555" />
247 <param name="rfseed_fr" value="15555" />
248 </expand>
249 </section>
250 </conditional>
251 <output name="outgenelist" value="intestinal_advanced.genelist" />
252 <output name="outpdf" value="intestinal_advanced.pdf" compare="sim_size" delta="150" />
253 </test>
254 </macro>
255 <token name="@FILTNORM_CHEETAH@"><![CDATA[
256 ## Perform do.filter
257 use.filtnormconf = TRUE
258
259 ## Perform do.cluster, do.outlier, do.clustmap, mkgenelist
260 use.cluster = FALSE
261
262 in.table = read.table(
263 '${intable}',
264 stringsAsFactors = F,
265 na.strings=c("NA", "-", "?", "."),
266 sep='\t',
267 header=TRUE,
268 row.names=1
269 )
270
271 ## Hidden flag to use test data instead
272 ## see: test-data/use.intestinal
273
274 use.test.data = (names(in.table)[1] == "test")
275
276 sc = NULL
277 if (use.test.data) {
278 sc = SCseq(intestinalData)
279 message("Loading test data from library")
280 } else {
281 sc = SCseq(in.table)
282 }
283
284
285 filt = formals(filterdata)
286 filt.ccc = formals(CCcorrect)
287 filt.use.ccorrect = FALSE
288 filt.lbatch.regexes = NULL
289
290 filt\$mintotal = as.integer( '$filt.mintotal' )
291 filt\$minexpr = as.integer( '$filt.minexpr' )
292 filt\$minnumber = as.integer( '$filt.minnumber' )
293 #if str($filt.use.def) == "no":
294 filt\$knn = as.integer( '$filt.use.knn' )
295 filt\$ccor = as.numeric( '$filt.use.ccor' )
296 filt\$bmode = as.character( '$filt.use.bmode' )
297 #if $filt.use.LBatch_regexes:
298 filt.lbatch.regexes = string2textvector( '$filt.use.LBatch_regexes' )
299 #end if
300 #if $filt.use.CGenes:
301 filt\$CGenes = string2textvector( '$filt.use.CGenes' )
302 #end if
303 #if $filt.use.FGenes:
304 filt\$FGenes = string2textvector( '$filt.use.FGenes' )
305 #end if
306 #if str($filt.use.ccc.use) == "yes"
307 filt.use.ccorrect = TRUE
308 #if $filt.use.ccc.vset:
309 filt.ccc\$vset = string2textvector( '$filt.use.ccc.vset' )
310 #end if
311 #if $filt.use.ccc.ncomp:
312 filt.ccc\$nComp = as.integer( '$filt.use.ccc.ncomp' )
313 #end if
314 filt.ccc\$pvalue = as.numeric( '$filt.use.ccc.pvalue' )
315 filt.ccc\$quant = as.numeric( '$filt.use.ccc.quant' )
316 filt.ccc\$dimR = as.logical( '$filt.use.ccc.dimr' )
317 filt.ccc\$mode = as.character( '$filt.use.ccc.mode.value' )
318 filt.ccc\$logscale = as.logical( '$filt.use.ccc.logscale' )
319 #end if
320 #end if
321
322 out.pdf = '${outpdf}'
323 out.rdat = '${outrdat}'
324
325 ]]></token>
326 <token name="@CLUSTER_CHEETAH@"><![CDATA[
327
328 in.rdat = readRDS('${inputrds}')
329
330 sc = in.rdat
331
332 ## Perform do.filter
333 use.filtnormconf = FALSE
334
335 ## Perform do.cluster, do.outlier, do.clustmap, mkgenelist
336 use.cluster = TRUE
337
338
339 clust.compdist = formals(compdist)
340 clust.clustexp = formals(clustexp)
341 clust.compdist\$metric = as.character( '$clust.metric' )
342 clust.clustexp\$FUNcluster = as.character( '$clust.funcluster' )
343
344 #if str($clust.use.def) == "no":
345
346 clust.compdist\$FSelect = as.logical( '$clust.use.fselect' )
347 #if $clust.use.knn:
348 clust.compdist\$knn = as.integer( '$clust.use.knn' )
349 #end if
350 clust.clustexp\$sat = as.logical( '$clust.use.sat' )
351 #if $clust.use.samp:
352 clust.clustexp\$samp = as.integer( '$clust.use.samp' )
353 #end if
354 #if $clust.use.cln:
355 clust.clustexp\$cln = as.integer( '$clust.use.cln' )
356 clust.clustexp\$clustnr = as.integer( '$clust.use.clustnr' )
357 clust.clustexp\$bootnr = as.integer( '$clust.use.bootnr' )
358 ##clust.clustexp\$rseed = as.integer( '$clust.use.rseed' )
359 #end if
360 #end if
361
362 outlier.use.randomforest = FALSE
363 outlier.findoutliers = formals(findoutliers)
364 outlier.clustheatmap = formals(clustheatmap)
365 outlier.rfcorrect = formals(rfcorrect)
366
367 outlier.findoutliers\$outminc = as.integer( '$outlier.outminc' )
368 outlier.findoutliers\$outlg = as.integer( '$outlier.outlg' )
369 outlier.rfcorrect\$final = as.logical( '$outlier.final' )
370
371 #if str($outlier.use.def) == "no":
372 #if $outlier.use.nbtree:
373 outlier.rfcorrect\$nbtree = as.integer( '$outlier.use.nbtree' )
374 #end if
375 outlier.findoutliers\$probthr = as.numeric( '$outlier.use.probthr' )
376 outlier.findoutliers\$outdistquant = as.numeric( '$outlier.use.outdistquant' )
377 ##outlier.rfcorrect\$rfseed = as.integer( '$outlier.use.rfseed' )
378 outlier.rfcorrect\$nbfactor = as.integer( '$outlier.use.nbfactor' )
379 #end if
380
381 cluster.comptsne = formals(comptsne)
382 cluster.compfr = formals(compfr)
383
384 cluster.comptsne\$perplexity = as.integer( '$tsne.perplexity' )
385 cluster.compfr\$knn = as.integer( '$tsne.knn' )
386 #if str($tsne.use.def) == "no":
387 cluster.comptsne\$initial_cmd = as.logical( '$tsne.use.initial_cmd' )
388 cluster.comptsne\$rseed = as.integer( '$tsne.use.rseed_tsne' )
389 cluster.compfr\$rseed = as.integer( '$tsne.use.rseed_fr' )
390 #end if
391
392 genelist.tablelim = as.integer( '$extra.tablelim' )
393 genelist.plotlim = as.integer( '$extra.plotlim' )
394 genelist.foldchange = as.integer( '$extra.foldchange' )
395 genelist.pvalue = as.numeric( '$extra.pvalue' )
396
397 out.pdf = '${outpdf}'
398 out.rdat = '${outrdat}'
399 out.genelist = '${outgenelist}'
400
401 ]]>
402 </token>
403 </macros>