The NSANormalization class

Description

Package: NSA
Class NSANormalization

Object
~~|
~~+--NSANormalization

Directly known subclasses:

public static class NSANormalization
extends Object

This class represents the NSA normalization method [1], which looks for normal regions within the tumoral samples.

Usage

1

Arguments

data

A named list with data set named "total" and "fracB" where the former should be of class AromaUnitTotalCnBinarySet and the latter of class AromaUnitFracBCnBinarySet. The two data sets must be for the same chip type, have the same number of samples and the same sample names.

tags

Tags added to the output data sets.

...

Not used.

Details

...

Fields and Methods

Methods:

findArraysTodo -
getDataSets -
getFullName -
getName -
getOutputDataSets -
getPath -
getRootPath -
getTags -
nbrOfFiles -
process Finds normal regions within tumoral samples.
setTags -

Methods inherited from Object:
asThis, $, $<-, [[, [[<-, as.character, attach, attachLocally, clearCache, clone, detach, equals, extend, finalize, gc, getEnvironment, getFields, getInstantiationTime, getStaticInstance, hasField, hashCode, ll, load, objectSize, print, registerFinalizer, save

References

[1] ...

See Also

Low-level versions of the NSA normalization method is available via the NSAByTotalAndFracB.matrix() methods.

Examples

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
## Not run: 
  
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# CRMAv2 - Preprocess raw Affymetrix data
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
library("aroma.affymetrix");  # Needed for CRMAv2
#library("calmate");
library(MASS)
source("F:/MOrtiz/curro/Aroma/calmate/R/CalMaTeNormalization.R")
source("F:/MOrtiz/curro/Aroma/calmate/R/calmateByTotalAndFracB.R")
source("F:/MOrtiz/curro/Aroma/calmate/R/calmateByThetaAB.R")
source("F:/MOrtiz/curro/Aroma/calmate/R/fitCalMaTe.R")
source("F:/MOrtiz/curro/Aroma/calmate/R/fitCalMaTeCNprobes.R")
source("F:/MOrtiz/curro/Aroma/calmate/R/thetaAB2TotalAndFracB.R")

source("F:/MOrtiz/curro/Aroma/NSA/R/NSANormalization.R")
source("F:/MOrtiz/curro/Aroma/NSA/R/NSAByTotalAndFracB.R")
source("F:/MOrtiz/curro/Aroma/NSA/R/fitNSA.R")

source("F:/MOrtiz/curro/Aroma/NSA/R/SNPsNormalization.R")
source("F:/MOrtiz/curro/Aroma/NSA/R/SNPsNByTotalAndFracB.R")
source("F:/MOrtiz/curro/Aroma/NSA/R/fitSNPsN.R")

source("F:/MOrtiz/curro/Aroma/NSA/R/SampleNormalization.R")
source("F:/MOrtiz/curro/Aroma/NSA/R/SampleNByTotalAndFracB.R")
source("F:/MOrtiz/curro/Aroma/NSA/R/fitSample.R")
library("DNAcopy");

setwd("I:/aroma")

dataSet <- "breast cancer";
dataSet <- "GSE12702-prostateCancerPaired"
dataSet <- "GSE12702-prostateCancer"
dataSet <- "GSE14996,testSet"

chipType <- "Mapping250K_Nsp";
#chipType <- "GenomeWideSNP_6"
dsList <- doCRMAv2(dataSet, chipType=chipType, combineAlleles=FALSE,
                                             plm="RmaCnPlm", verbose=-10);
print(dsList);


# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# CalMaTe - Post-normalization of ASCNs estimates
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
asn <- CalMaTeNormalization(dsList);
print(asn);

# For speed issues, we will here only process loci on Chromosome 17.
chr <- 22;
ugp <- getAromaUgpFile(dsList$total);
units <- getUnitsOnChromosome(ugp, chr);

dsNList <- process(asn, units=units, verbose=verbose);
#dsNList <- process(asn, references = seq(2,40,2), verbose=verbose);
#dsNList <- process(asn, verbose=verbose);
print(dsNList);

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# NSA - Finding normal regions
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

asnN <- NSANormalization(dsNList);
print(asnN);

dsNNList <- process(asnN, verbose=verbose);
print(dsNNList);

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# NSA - SNPs Normalization
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

asnNsnps <- SNPsNormalization(dsNList);
print(asnNsnps);

dsNNListSNPs <- process(asnNsnps, references = dsNNList, verbose=verbose);
print(dsNNListSNPs);

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# NSA - Sample Normalization
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

asnNsample <- SampleNormalization(dsNNListSNPs);
print(asnNsample);

dsNNListSample <- process(asnNsample, references = dsNNList, verbose=verbose);
print(dsNNListSample);

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# NSA - SNPs Normalization
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

asnNsnps <- SNPsNormalization(dsNNListSample);
print(asnNsnps);

dsListSNPs <- process(asnNsnps, references = dsNNList, verbose=verbose);

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# NSA - Sample Normalization
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

asnNsample <- SampleNormalization(dsListSNPs);
print(asnNsample);

dsListSample <- process(asnNsample, references = dsNNList, verbose=verbose);
print(dsNNListSample);

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# CalMaTe - sigma delta validation  (for CRMAv2)
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

# Alt 1: Calculate CN ratios where the reference is a pool of specific references samples

references <- c(1:20);

dsR <- extract(dsList$total, references);
dfR <- getAverageFile(dsR);
cnm <- CopyNumberChromosomalModel(dsList$total, dfR);

# Alt 2: Calculate CN ratios where the reference is the pool of all samples
cnm <- CopyNumberChromosomalModel(dsList$total);
print(cnm);

# Extract CN ratios - C=theta/thetaR
cn <- extractRawCopyNumbers(cnm, array=ii, chromosome=chr, logBase=NULL);
cn$y <- 2*cn$y;
print(cn);

# As a data frame
#data <- as.data.frame(cn);

# Estimate std dev (via first-order variance estimator)
sigma <- estimateStandardDeviation(cn);
print(sigma);

# Plot
x11();plot(cn, ylim=c(0,6));
sigmaStr <- sprintf("%.3f", sigma);
stext(side=3, pos=0.5, line=-1, substitute(hat(sigma)[Delta]==x, list(x=sigmaStr)));

# Smooth (bins of 1.0Mb)
cnS <- binnedSmoothing(cn, by=1.0e6);
print(cnS);
points(cnS, col="red");
lines(cnS, col="red");

# Segmentation
fit <- segmentByCBS(cn);
cnr <- extractCopyNumberRegions(fit);
print(cnr);
drawLevels(cnr, col="blue", lwd=3);

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# CalMaTe - sigma delta validation  (for CalMaTe)
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

# Alt 1: Calculate CN ratios where the reference is a pool of specific references samples

references <- c(1:24)

# Alt 2: Calculate CN ratios where the reference is the pool of all samples
#cnm <- CopyNumberChromosomalModel(dsNNListSample$total);

#cnm <- CopyNumberChromosomalModel(dsNList$total);
#print(cnm);

# Extract CN ratios - C=theta/thetaR
#cn <- extractRawCopyNumbers(cnm, array=ii, chromosome=chr, logBase=NULL);

dataNSA <- extractMatrix(dsNList$total,units = units);
cnNSA <- cn;
cnNSA$y <- dataNSA[,ii];
cn <- cnNSA;


# As a data frame
data <- as.data.frame(cn);

# Estimate std dev (via first-order variance estimator)
sigma <- estimateStandardDeviation(cn);
print(sigma);

# Plot
x11();plot(cn, ylim=c(0,6));
sigmaStr <- sprintf("%.3f", sigma);
stext(side=3, pos=0.5, line=-1, substitute(hat(sigma)[Delta]==x, list(x=sigmaStr)));
                                                       
# Smooth (bins of 1.0Mb)
cnS <- binnedSmoothing(cn, by=1.0e6);
print(cnS);
points(cnS, col="red");
lines(cnS, col="red");

# Segmentation
fit <- segmentByCBS(cn);
cnr <- extractCopyNumberRegions(fit);
print(cnr);
drawLevels(cnr, col="blue", lwd=3);


#You can obtain the above 'cn' manually as:

dsR <- extract(dsList$total, references);
dfR <- getAverageFile(dsR);

df <- getFile(dsList$total, ii);
theta <- extractRawCopyNumbers(df, chromosome=chr);
print(theta);
thetaR <- extractRawCopyNumbers(dfR, chromosome=chr);
print(thetaR);
cn <- clone(theta);
cn <- divideBy(cn, thetaR);
cn$y <- 2*cn$y;

#sigma delta
mad(diff(cn$y))

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Calculating the differences between CN and SNP probes
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -


cnCNP <- RawCopyNumbers(...);
cnSNP <- RawCopyNumbers(...);

xRange <- range(xRange(cnCNP), xRange(cnSNP));

by <- 50e3; # 50kb bins; you may want to try with other amounts of smoothing xOut <- seq(from=xRange[1], to=xRange[2], by=by);

cnCNPS <- binnedSmoothing(cnCNP, xOut=xOut); cnSNPS <- binnedSmoothing(cnSNP, xOut=xOut);

Clim <- c(0,5);
plot(cnCNPS, ylim=Clim);
points(cnSNPS, col="blue");

plot(getSignals(cnCNPS), getSignals(cnSNPS), xlim=Clim, ylim=Clim); abline(a=0, b=1, col="red", lwd=2);


# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Plot allele B fractions (before and after calmate)
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Sample #1 and Chromosome 17
ii <- 1;
chr <- 17;
df <- getFile(dsList$fracB, ii);
dfN <- getFile(dsNList$fracB, ii);

beta <- extractRawAlleleBFractions(df, chromosome=chr);
betaN <- extractRawAlleleBFractions(dfN, chromosome=chr);
x11();
subplots(2, ncol=1);
plot(beta);
title(sprintf("%s", getName(beta)));
plot(betaN);
title(sprintf("%s (CalMaTe)", getName(betaN)));


for(ii in 1:24){
  df <- getFile(dsList$total, ii);
  CN <- extractRawCopyNumbers(df, chromosome=chr);
  if(ii == 1){
    aux <- CN$y;
  }else{
    aux <- aux + CN$y;
  }
}
ref <- aux/24;

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Plot copy numbers (before and after calmate)
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Sample #1 and Chromosome 17
ii <- 3;
chr <- 1;

df <- getFile(dsList$total, ii);
#dfN <- getFile(dsNList$total, ii);

#units <- getUnitsOnChromosome(gi, ii);
#pos <- getPositions(gi, units = units);
#units <- units[order(pos)];

CN <- extractRawCopyNumbers(df, chromosome=chr);
#CNN <- extractRawCopyNumbers(dfN, chromosome=chr);
#CNN <- extractMatrix(dsNList$total, units = units);
#CNN <- CNN[,ii];


x11();
subplots(2, ncol=1);
plot(CN$x, log2(CN$y));
title(sprintf("%s", getName(CN)));
plot(CNN);
title(sprintf("%s (CalMaTe)", getName(CNN)));

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Plot Normal Regions
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Sample #3 and Chromosome 6
ii <- 1;
chr <- 6;
dfNN <- getFile(dsNNList$normalReg, ii);

betaNN <- extractRawAlleleBFractions(dfNN, chromosome=chr);

plot(betaNN);
title(sprintf("%s (NSA)", getName(betaNN)));

# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Plot Normalized by SNP data
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Sample #9 and Chromosome 8
ii <- 9;
chr <- 8;
dfN <- getFile(dsNNListSNPs$fracB, ii);
fracBN <- extractRawAlleleBFractions(dfN, chromosome=chr);

dfN <- getFile(dsNNListSNPs$total, ii);
totalN <- extractRawCopyNumbers(dfN, chromosome=chr);

x11();
subplots(2, ncol=1);
plot(fracBN);
title(sprintf("%s", getName(fracBN)));
plot(totalN);
title(sprintf("%s ", getName(totalN)));


# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Plot Normalized by Sample data
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Sample #3 and Chromosome 6
ii <- 9;
chr <- 8;

dfC <- getFile(dsNList$total, ii);
CNC <- extractRawCopyNumbers(dfC, chromosome=chr);

dfN <- getFile(dsNNListSample$fracB, ii);
fracBN <- extractRawAlleleBFractions(dfN, chromosome=chr);

dfN <- getFile(dsNNListSample$total, ii);
totalN <- extractRawCopyNumbers(dfN, chromosome=chr);

x11();
subplots(2, ncol=1);
plot(fracBN);
title(sprintf("%s", getName(fracBN)));
plot(totalN$x, 2^totalN$y);
title(sprintf("%s ", getName(totalN)));

x11();
plot(CNC);
points(totalN, col="green");

 
## End(Not run)