Mercurial > repos > iuc > raceid_main

comparison raceid_main.xml @ 0:e01c989c7543 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/raceid commit 39918bfdb08f06862ca395ce58a6f5e4f6dd1a5e
author iuc
date Sat, 03 Mar 2018 17:34:16 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:e01c989c7543
1 <tool id="raceid_main" name="RaceID" version="@VERSION@.0">
2 <description>Race ID pipeline for single-cell RNA analysis</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro="requirements" />
7
8 <command detect_errors="exit_code"><![CDATA[
9 ## Filter
10 echo "Filtering" &&
11 Rscript '@SCRIPT_DIR@/raceID_filter.R' '@SCRIPT_DIR@' '$rconf_source_filter' &&
12
13 ## Kmeans
14 echo "K-means" &&
15 Rscript '@SCRIPT_DIR@/raceID_kmeans_heatmap.R' '@SCRIPT_DIR@' '$rconf_source_kmeans' &&
16
17 mkdir '${out_html.files_path}' &&
18 mv plot_*.svg '${out_html.files_path}' &&
19
20 echo '
21 <html><head></head>
22 <body>
23 <h1>RaceID k-means</title></h1><br />
24 <h3>Gap statistic</h3>
25 <img src="plot_gap.svg" ><br />
26 <h3>Jaccard Similarity</h3>
27 <img src="plot_jaccard.svg" ><br />
28 <h3>Silhouette Plot</h3>
29 <img src="plot_silhouette.svg" ><br />
30 <h3>Cluster Heatmap</h3>
31 <img src="plot_clustheatmap.svg" ><br />
32 ' > '$out_html' &&
33
34 ## Outlier -- relies on kmeans
35 echo "Outlier" &&
36 Rscript '@SCRIPT_DIR@/raceID_outlierdetect.R' '@SCRIPT_DIR@' '$rconf_source_outlier' &&
37
38 mv plot_*.svg '${out_html.files_path}' &&
39 echo '
40 <br/>
41 <h1>RaceID Outlier Detection</h1><br />
42 <h3>Background</h3>
43 <img src="plot_background.svg" ><br />
44 <h3>Sensitivity</h3>
45 <img src="plot_sensitivity.svg" ><br />
46 <h3>Outlier Probability</h3>
47 <img src="plot_outlierprobs.svg" ><br />
48 <h3>Final Heatmap</h3>
49 <img src="plot_finalheat.svg" ><br />
50 ' >> '$out_html' &&
51
52 ## tSNE -- relies on kmeans and outlier
53 echo "tSNE" &&
54 Rscript '@SCRIPT_DIR@/raceID_tsne.R' '@SCRIPT_DIR@' '$rconf_source_tsne' &&
55
56 ##mkdir '${out_html.files_path}' &&
57 mv plot_*.svg '${out_html.files_path}' &&
58
59 echo '
60 <br/>
61 <h1>RaceID tSNE</h1><br />
62 <h3>Initial k-means clusters</h3>
63 <br /><img src="plot_initial.svg" >
64 <h3>Final clusters</h3>
65 <br /><img src="plot_final.svg" >
66 <h3>Labelled</h3>
67 <br /><img src="plot_labels.svg" >
68 <h3>Symbols</h3>
69 <br /><img src="plot_symbols.svg" >
70 ' >> '$out_html' &&
71
72 #if $section_tsne.genexp_select.use_gexpr == "Yes":
73 #for $gene_set in $section_tsne.genexp_select.geneset:
74 echo "<h3>Expression for: [${gene_set.genes.value}]</h3>" >> '$out_html' &&
75 echo "<br /><img src=\"plot_${gene_set.genes.value}\" >" >> '$out_html' &&
76 #end for
77 #end if
78 echo '</body></html>' >> '$out_html'
79
80 ]]></command>
81
82 <configfiles>
83 <configfile name="rconf_source_filter">
84 count_matrix = '$section_filter.inp_count'
85 filtering = as.logical( '$section_filter.filtering.do_filter.value' )
86 output_table = '$out_table_filter'
87 output_rdat = '@out_rdat_filter@'
88
89 # Defaults
90 control_genes_filter="";
91 c_mintotal = 3000; c_minexpr = 5; c_maxexpr = 500; c_minnumber = 1;
92 c_downsample = F; c_dsn = 1; c_rseed = 17000;
93
94 #if $section_filter.filtering.do_filter.value == "T":
95 control_genes_filter = '$section_filter.filtering.remove_nonendog.value'
96 #if $section_filter.filtering.default_filtering_select.do_filter_defaults.value == "advanced_options":
97 c_mintotal = as.integer( '$section_filter.filtering.default_filtering_select.mintotal' )
98 c_minexpr = as.integer( '$section_filter.filtering.default_filtering_select.minexpr' )
99 c_maxexpr = as.integer( '$section_filter.filtering.default_filtering_select.maxexpr' )
100 c_minnumber = as.integer( '$section_filter.filtering.default_filtering_select.minnumber' )
101 #if $section_filter.filtering.default_filtering_select.dsn:
102 c_downsample = T;
103 c_dsn = as.integer( '$section_filter.filtering.default_filtering_select.dsn' )
104 #end if
105 c_rseed = as.integer( '$section_filter.filtering.default_filtering_select.filter_rseed' )
106 #end if
107 #end if
108 </configfile>
109 <configfile name="rconf_source_kmeans">
110 sc = readRDS( '@inp_rdat_kmeans@' )
111 output_rdat = '@out_rdat_kmeans@'
112 c_metric = 'pearson'; c_cln = 0; dogap = T; c_clustnr = 20; bgap = 50;
113 semethod = 'Tibs2001SEmax'; sefactor = .25; c_bootnr = 50; c_rseed = 17000;
114
115 c_metric = '$section_kmeans.metric'
116 c_cln = as.integer( '$section_kmeans.cln' )
117 dogap = as.logical( '$section_kmeans.gapstats.dogap.value' )
118 #if $section_kmeans.gapstats.dogap.value == "T":
119 c_clustnr = as.integer( '$section_kmeans.gapstats.clustnr' )
120 bgap = as.integer( '$section_kmeans.gapstats.bgap' )
121 semethod = '$section_kmeans.gapstats.semethod.value'
122 sefactor = as.numeric( '$section_kmeans.gapstats.sefactor' )
123 #end if
124 c_bootnr = as.integer( '$section_kmeans.bootnr' )
125 c_rseed = as.integer( '$section_kmeans.kmeans_rseed' )
126
127 generate_final_rdata = T
128 </configfile>
129 <configfile name="rconf_source_outlier">
130 sc = readRDS( '@inp_rdat_outlier@' )
131 output_rdat = '@out_rdat_outlier@'
132 output_table= '$out_table_outlier'
133 # set defaults
134 c_outminc = 5; c_outlg = 2; c_probthr = 1e-3; c_outdistquant = 0.75;
135
136 c_outminc = as.integer( '$section_outlier.outminc' )
137 c_outlg = as.integer( '$section_outlier.outlg' )
138 c_probthr = as.numeric( '$section_outlier.probthr' )
139 c_outdistquant = as.numeric( '$section_outlier.probthr' )
140
141 generate_final_rdata = T
142 </configfile>
143 <configfile name="rconf_source_tsne" >
144 sc = readRDS( '@inp_rdat_tsne@' )
145 output_rdat = '$out_rdat_tsne' # final output RData
146 regex_val = ""
147 c_rseed = '$section_tsne.tsne_rseed'
148 gene_sets = ""
149 #if $section_tsne.genexp_select.use_gexpr == 'Yes':
150 gene_sets = '#for $gns in $section_tsne.genexp_select.geneset# $gns.genes.value _split_ #end for#'
151 regex_val = '$section_tsne.genexp_select.regex'
152 #end if
153 final_rdata = T
154 </configfile>
155 </configfiles>
156 <!-- Filter -->
157 <inputs>
158 <section name="section_filter" title="Filtering and Normalisation" expanded="true" >
159 <param name="inp_count" type="data" format="tsv" label="Count matrix" help="A spreadsheet file with the first row indicating cell IDs, and the first column indicating transcript or gene IDs" />
160 <conditional name="filtering" >
161 <param name="do_filter" type="select" label="Perform filtering?" >
162 <option value="T" selected="true" >Yes</option>
163 <option value="F" >No</option>
164 </param>
165 <when value="F" />
166 <when value="T" >
167 <param name="remove_nonendog" type="text" label="Control gene name prefixes" help="If ERCC or other non-endogenous spike-in RNAs are within the data, please specify their prefixes (e.g. 'ERCC, HK00') in order to filter them out. (Leave blank if control genes were not used in the experiment.)" />
168 <conditional name="default_filtering_select" >
169 <param name="do_filter_defaults" type="select" label="Parameters" >
170 <option value="use_defaults" selected="true" >Use Defaults</option>
171 <option value="advanced_options" >Advanced Options</option >
172 </param>
173 <when value="use_defaults" />
174 <when value="advanced_options" >
175 <param name="mintotal" type="integer" value="3000" min="1" label="Minimum total transcripts" help="Discard cells with less than this number of total transcripts before normalisation." />
176 <param name="minexpr" type="integer" value="5" min="1" label="Minimum expressed genes" help="Discard genes that do not express a minimum of this number of transcripts after normalisation."/>
177 <param name="maxexpr" type="integer" value="500" min="0" label="Maximum expressed genes" help="Discard genes that express more than this number of transcripts after normalisation. Useful if genes have oversaturated counts derived from UMI data. Set to 0 to disable this step." />
178
179 <param name="minnumber" type="integer" value="1" label="Minimum Cells" help="Discard genes that do not have the minimum expressed transcripts in at least this number of cells" />
180
181 <param name="dsn" type="integer" value="1" min="1" optional="true" label="Downsample counts" help="Average transcripts across this many samples. If this is set to 1, then sampling noise should be comparable across cells. For higher values, the data approximates median normalisation." />
182 <param name="filter_rseed" type="integer" value="17000" min="0" label="Seed value (for reproducibility)" />
183 </when>
184 </conditional>
185 </when>
186 </conditional>
187 <param name="filter_table_output" type="boolean" checked="false" label="Generate output table of filtered matrix?" />
188 </section>
189
190 <!-- Kmeans -->
191 <section name="section_kmeans" title="Clustering (k-means)" expanded="true" >
192 <param name="metric" type="select" label="Distance metric">
193 <option value="pearson" selected="true" />
194 <option value="spearman" />
195 <option value="kendall" />
196 <option value="euclidean" />
197 <option value="maximum" />
198 <option value="manhattan" />
199 <option value="canberra" />
200 <option value="binary" />
201 <option value="minkowski" />
202 </param>
203
204 <param name="cln" type="integer" value="0" min="0" label="Number of clusters for k-means" help="Leave as zero to automatically determine the number based on gap statistics" />
205
206 <conditional name="gapstats">
207 <param name="dogap" type="select" label="Use gap statistics to determine clusters" >
208 <option value="T" selected="true" >Yes</option>
209 <option value="F" >No</option>
210 </param>
211
212 <when value="F" />
213 <when value="T" >
214 <param name="clustnr" type="integer" value="2" min="0" label="Maximum number of clusters for the computation of the gap statistic" help="If more major cell types are expected, a higher number than 2 should bde chosen." />
215 <param name="bgap" type="integer" value="50" min="1" label="Number of bootstraps to run the gap statistic calculation" />
216 <param name="semethod" type="select" label="Method used for determining first local maximum" >
217 <option value="Tibs2001SEmax" selected="true" />
218 <option value="globalmax" />
219 <option value="firstmax" />
220 <option value="firstSEmax" />
221 <option value="globalSEmax" />
222 </param>
223
224 <param name="sefactor" type="float" value="0.25" min="0.0001" max="1" label="Fraction of the standard deviation that the local maximum must differ from neighbouring points." />
225 </when>
226 </conditional>
227
228 <param name="bootnr" type="integer" value="50" min="1" label="Number of bootstraps for clustering" />
229 <param name="kmeans_rseed" type="integer" value="17000" min="1" label="Seed value (for reproducibility)" />
230 </section>
231 <!-- Outlier -->
232 <section name="section_outlier" title="Outlier Detection" expanded="true" >
233 <param name="outminc" type="integer" value="5" min="1" label="Expression cutoff threshold for outlier genes" />
234 <param name="probthr" type="float" value="1e-3" min="1e-8" max="1" label="Probability threshold of observing a given gene expression level in a cell" help="If lower than this cutoff, the cell is considered an outlier for this gene." />
235 <param name="outlg" type="integer" value="2" min="1" label="Minimal number of outlier genes required to flag an outlier cells" />
236 <param name="outdistquant" type="select" label="Merge cells into outlier clusters if their similarity exceeds this quantile in a similarity distribution for all cell pairs" >
237 <option value="0.25">first (0.25)</option>
238 <option value="0.50">second (0.50)</option>
239 <option value="0.75">third (0.75)</option>
240 </param>
241 </section>
242 <section name="section_tsne" title="tSNE plots" expanded="true" >
243 <!-- tSNE -->
244 <conditional name="genexp_select" >
245 <param name="use_gexpr" type="select" label="Highlight the expression of a set of (related) genes over all clusters?" >
246 <option value="Yes" />
247 <option value="No" selected="true" />
248 </param>
249 <when value="No" />
250 <when value="Yes" >
251 <repeat name="geneset" title="Gene sets" >
252 <param name="genes" type="text" label="Gene(s) of interest" help="e.g. 'Apoa1__chr9+Apoa1bp__chr6'" >
253 <sanitizer invalid_char="" >
254 <valid initial="string.letters,string.digits">
255 <add value="+" /><add value="_" /><add value="-" />
256 </valid>
257 </sanitizer>
258 </param>
259 </repeat>
260 <param name="regex" type="text" value="" label="Regular expression to apply over cell labels to identify cell types" help="e.g. for barcodes [ cl_1_ACCAG, cl_1_ACGGA, cl_2_TTAC, ... ] can be grouped into [ cl_1, cl_2, ... ] by the expression: '_[ACTG]+', which removes the last '_' and any following characters belonging to A C T or G." >
261 <sanitizer invalid_char="" >
262 <valid initial="string.printable" />
263 </sanitizer>
264 </param>
265 </when>
266 </conditional>
267 <param name="tsne_rseed" type="integer" min="1" value="15555" label="Seed (for reproducibility)" />
268 </section>
269 </inputs>
270
271 <outputs>
272 <!-- Filter -->
273 <data name="out_table_filter" format="tabular" label="${tool.name} on ${on_string}: Filter Table" >
274 <filter>section_filter['filtering']['do_filter'] == "T"</filter>
275 </data>
276 <!-- Outlier -->
277 <data name="out_table_outlier" format="tabular" label="${tool.name} on ${on_string}: Outliers" />
278 <!-- TSNE -->
279 <data name="out_html" format="html" label="${tool.name} on ${on_string}: Web Report" />
280 <data name="out_rdat_tsne" format="rdata" label="${tool.name} on ${on_string}: tSNE RData" />
281 </outputs>
282
283 <tests>
284 <!-- vanilla run on all but filter -->
285 <test>
286 <!-- Filter -->
287 <param name="inp_count" value="transcript_counts_intestine_sub.tsv" />
288 <!-- These test params are MANDATORY due to the reduced size of the
289 input set (due to file size constraints) -->
290 <param name="do_filter" value="T" />
291 <param name="do_filter_defaults" value="advanced_options" />
292 <param name="mintotal" value="10" />
293 <param name="minexpr" value="1" />
294 <param name="maxexpr" value="2000" />
295 <!-- Outlier -->
296 <!-- ... With reduced minc -->
297 <param name="inp_rdat_outlier" value="trans_outlier_in.rds" />
298 <param name="outminc" value="1" />
299 <output name="out_table_outlier" value="out_outlier1.table" />
300 <!-- tSNE -->
301 <output name="out_html" value="out_1.html" />
302 <output name="out_rdat_tsne" value="out_tsne1.rdat" />
303 </test>
304 <!-- manual gap statistics -->
305 <test>
306 <!-- Filter -->
307 <param name="inp_count" value="transcript_counts_intestine_sub.tsv" />
308 <param name="filter_table_output" value="T" />
309 <!-- See message from previous test .. -->
310 <param name="do_filter" value="T" />
311 <param name="do_filter_defaults" value="advanced_options" />
312 <param name="mintotal" value="10" />
313 <param name="minexpr" value="1" />
314 <param name="maxexpr" value="2000" />
315 <output name="out_table_filter" value="out_filter2.table" />
316 <!-- Kmeans -->
317 <!-- ... Auto gap with gap params -->
318 <param name="inp_rdat_kmeans" value="trans_filter_ds.rds" />
319 <param name="clustnr" value="5" />
320 <param name="bgap" value="10" />
321 <param name="semethod" value="globalSEmax" />
322 <param name="sefactor" value="0.6" />
323 <!-- Outlier -->
324 <!-- ... With reduced minc -->
325 <param name="inp_rdat_outlier" value="trans_outlier_in.rds" />
326 <param name="outminc" value="1" />
327 <output name="out_table_outlier" value="out_outlier2.table" />
328 <!-- tSNE -->
329 <output name="out_html" value="out_2.html" />
330 <output name="out_rdat_tsne" value="out_tsne2.rdat" />
331 </test>
332 <!-- complex run -->
333 <test>
334 <!-- Filter -->
335 <param name="inp_count" value="transcript_counts_intestine_sub.tsv" />
336 <param name="do_filter" value="T" />
337 <param name="do_filter_defaults" value="advanced_options" />
338 <param name="mintotal" value="10" />
339 <param name="minexpr" value="1" />
340 <param name="maxexpr" value="2000" />
341 <param name="dsn" value="3" />
342 <output name="out_table_filter" value="out_filter3.table" />
343 <!-- Kmeans -->
344 <!-- ... Set k-value, no gap, no R obj, metrics and bootrepl. -->
345 <param name="inp_rdat_kmeans" value="trans_filter_ds.rds" />
346 <param name="metric" value="manhattan" />
347 <param name="cln" value="6" />
348 <param name="dogap" value="T" />
349 <param name="bootnr" value="10" />
350 <!-- Outlier -->
351 <!-- ... No R out, other opts-->
352 <param name="inp_rdat_outlier" value="trans_outlier_in.rds" />
353 <param name="outminc" value="1" />
354 <param name="probthr" value="1e-5" />
355 <param name="outlg" value="10" />
356 <param name="outdistquant" value="0.50" />
357 <output name="out_table_outlier" value="out_outlier3.table" />
358 <!-- tSNE -->
359 <param name="use_gexpr" value="Yes" />
360 <repeat name="geneset">
361 <param name="genes" value="1110007C09Rik__chr13+1110037F02Rik__chr4+1300002K09Rik__chr4" />
362 </repeat>
363 <repeat name="geneset">
364 <param name="genes" value="0610010K14Rik__chr11+1500009L16Rik__chr10" />
365 </repeat>
366 <param name="regex" value="[^_]+__" />
367 <output name="out_html" value="out_3.html" />
368 <output name="out_rdat_tsne" value="out_tsne3.rdat" />
369 </test>
370 </tests>
371
372 <help><![CDATA[
373
374 ******
375 RaceID
376 ******
377
378 RaceID(v2) pipeline for scRNA, performs:
379 * filtering
380 * normalisation
381 * k-means clustering
382 * outlier detection
383
384 Generates heatmaps, tSNE plots, and an R object which can be passed into the RaceID DiffGenes tool for expression analysis between different sets of clusters.
385
386 **Filtering**
387
388 This takes a count matrix/spreadsheet with cellIDs as columns and geneIDs/transcriptIDs as rows, and filters based on standard single-cell RNA pre-processing methods (minimum/maximum transcript expression in a minimum of X number of cells). A filtered matrix is produced as output
389
390 **K-means Clustering**
391
392 This performs k-means clustering and plots gap statistics, jaccard similarity, silhoutte plots, and preliminary heatmap.
393
394 **Outlier Detection**
395
396 This performs outlier detection by calibrating against a background noise model within each cluster, and searching for cells that fall outside of the transcript count distribution for that gene (modelled as a negative binomial). Cells that are outliers for more than a user-set amount of genes are suspected as being outlier cells.
397
398 **tSNE plots**
399
400 Generates multiple tSNE plots with custom expression highlighting for gene subsets of interest. A tSNE map can be drawn for original clusters (derived via k-means) and final clustering (derived from outliers). Any number of genes subsets of interest can be specified to measure expression within clusters for related marker genes or genes characterising a cell type.
401
402 ]]></help>
403 <expand macro="citations" />
404 </tool>