options(java.parameters = "-Xmx4000M")
library(SELEX)
library(SelexGLM)
library(grid)
workDir = "./cache/"
selex.config(workingDir=workDir, maxThreadNumber=4)
### LOCAL PATHS NEED TO BE RE-DEFINED TO RUN OFF OF MY COMPUTER
##################################################################
selexDir = "/Users/gabriella/Columbia/SELEX/"
#rawdataDir = "/Users/gabriella/Columbia/rawdata/Pufall/"
processedDataDir = "/Users/gabriella/Columbia/SplitFastqData/Pufall/ConcatFiles/"
# CLUSTER VERSIONS ARE COMMENTED OUT
#selexDir = "/vega/hblab/users/gdm2120/SELEX/SELEX/"
#rawdataDir = "/vega/hblab/projects/selex/rawdata/Pufall"
#processedDataDir = "/vega/hblab/users/gdm2120/SplitFastqData/Pufall/"
##################################################################
saveDir = "gabriella/SelexGLMtest/ViewSymmetry"
dir.create(file.path(selexDir, saveDir), showWarnings = FALSE, recursive = TRUE)
shapeTable = read.table(paste(selexDir, "gabriella/ShapeParamData/ShapeTableOrthogonal.txt", sep = ""), sep = "\t",
stringsAsFactors = FALSE)
ST = shapeTable[,c(1, 14:19)]
colnames(ST) = c("Sequence", "MGW", "ProT", "HelTA",
"HelTB", "RollA", "RollB")
selex.defineSample('r0.Pufall',
paste(processedDataDir, "/Demultiplexed.R0.fastq.gz", sep = ""),
'r0',
0, 23, '', 'TGGAA')
selex.defineSample('AR.R8',
paste(processedDataDir,"/AR.R8.fastq.gz",sep = ""),
'AR-DBD',
8, 23, '', 'TGGAA')
selex.defineSample('AR.R7',
paste(processedDataDir,"/AR.R7.fastq.gz",sep = ""),
'AR-DBD',
7, 23, '', 'TGGAA')
r0 = selex.sample(seqName = 'r0.Pufall', sampleName='r0', round = 0)
r0.split = selex.split(r0)
r0.train = r0.split$train
r0.test = r0.split$test
dataSample = selex.sample(seqName = 'AR.R8', sampleName = 'AR-DBD', round = 8)
# MARKOV MODEL BUILT
kmax = selex.kmax(sample = r0.test)
mm = selex.mm(sample = r0.train, order = NA, crossValidationSample =r0.test, Kmax = kmax, mmMethod = "TRANSITION")
mmscores = selex.mmSummary(sample = r0.train)
ido = which(mmscores$R==max(mmscores$R))
mm.order = mmscores$Order[ido]
libLen = as.numeric(as.character(selex.getAttributes(dataSample)$VariableRegionLength))
kLen = 15
#data.probeCounts = getProbeCounts(dataSample, markovModel = mm)
#save(data.probeCounts, file = paste(selexDir, saveDir, "/data.probeCounts.RData", sep = ""))
load(file = paste(selexDir, saveDir, "/data.probeCounts.RData", sep = ""))
#data.kmerTable = getKmerCountAffinities(dataSample, k = kLen, minCount = 100, markovModel = mm)
#save(data.kmerTable, file = paste(selexDir, saveDir, "/data.kmerTable.RData", sep = ""))
load(file = paste(selexDir, saveDir, "/data.kmerTable.RData", sep = ""))
# Inputs about library are data specific
ModelTest = model(name = "AR-DBD R8 Nucleotides+View (Rev. Comp. Sym.)",
varRegLen = libLen,
leftFixedSeq = "GTTCAGAGTTCTACAGTCCGACGATC",
rightFixedSeq ="TGGAATTCTCGGGTGCCAAGG",
consensusSeq = "RGWACANNNTGTWCY",
affinityType = "AffinitySym",
leftFixedSeqOverlap = 5,
minAffinity = 0.01,
missingValueSuppression = .5,
minSeedValue = .01,
upFootprintExtend = 4,
confidenceLevel = .99,
rounds = list(c(8)),
rcSymmetric = TRUE,
verbose = FALSE,
includeView = TRUE)
getFeatureDesign(ModelTest)
## Feature design for object of class 'model'
##
## seedLen: 15
## upFootprintExtend: 4
## downFootprintExtend: 4
## rcSymmetric: TRUE
##
## Slot "N":
## N.upFootprintExtend: 4
## N.downFootprintExtend: 4
## N.set: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
## Number of previous iterations: 0
##
## Slot "Intercept":
## Number of Views per Strand of DNA: 11
## Number of Rounds: 1 (8)
## Number of previous iterations: 0
##
## Slot "Shape":
## "ShapeParamsUsed": NONE
# Add seed model
addSeedPsam(ModelTest) = seedTable2psam(ModelTest, data.kmerTable)
# Model nucleotide Betas after seed PSAM is added
print(getValues(getN(ModelTest)))
## 1 2 3 4 5 6 7 8 9
## N.A 0 0 0 0 0.00000000 -1.2968295 -0.03073087 0.000000 -1.296829
## N.C 0 0 0 0 -0.60728754 -1.2968295 -0.25628921 -1.296829 0.000000
## N.G 0 0 0 0 -0.09864725 0.0000000 -0.34036727 -1.296829 -1.296829
## N.T 0 0 0 0 -0.42644057 -0.5591611 0.00000000 -1.296829 -1.296829
## 10 11 12 13 14 15
## N.A 0.0000000 -0.40799975 -0.1359377 -0.09020211 -0.7968295 -1.296829
## N.C -1.2968295 0.00000000 0.0000000 -0.36546623 -0.3957275 -1.296829
## N.G -0.3957275 -0.36546623 0.0000000 0.00000000 -1.2968295 0.000000
## N.T -0.7968295 -0.09020211 -0.1359377 -0.40799975 0.0000000 -1.296829
## 16 17 18 19 20 21 22 23
## N.A -1.296829 0.00000000 -0.5591611 -0.42644057 0 0 0 0
## N.C -1.296829 -0.34036727 0.0000000 -0.09864725 0 0 0 0
## N.G -1.296829 -0.25628921 -1.2968295 -0.60728754 0 0 0 0
## N.T 0.000000 -0.03073087 -1.2968295 0.00000000 0 0 0 0
plot(ModelTest@features@N, Ntitle = "AR-DBD R8 Nucleotides+View\nSeeding Model", ddG = TRUE)
Next we score the probes using topModelMatch
sample1 = sample(nrow(data.probeCounts), 1000000)
data = data.probeCounts[sample1,]
#data = data.probeCounts
data = topModelMatch(data, ModelTest)
# Uses aligned probes to build design matrix
data = addDesignMatrix(data, ModelTest)
designMatrixSummary = getDesignMatrix(ModelTest, data)
## No shape parameters included in fit.
print("Round summary: ")
## [1] "Round summary: "
print (designMatrixSummary$Round)
## 8 Total
## Round 999419 999419
print("View/strand orientation summary: ")
## [1] "View/strand orientation summary: "
print (designMatrixSummary$Intercept)
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 View.8 View.9
## Strand.F 5114 64609 97214 69970 107435 129518 141254 154187 111083
## Strand.R 0 0 0 0 0 0 0 0 0
## View.10 View.11 StrandTotal
## Strand.F 56898 62137 999419
## Strand.R 0 0 0
print("Mono-nucleotide summary: ")
## [1] "Mono-nucleotide summary: "
print (designMatrixSummary$N)
## N.A N.C N.G N.T
## 1 583106 638621 349297 427814
## 2 719215 470626 372502 436495
## 3 909957 500103 170875 417903
## 4 928055 254670 407530 408583
## 5 1290774 18245 647452 42367
## 6 628 235 1982654 15321
## 7 843239 104864 93707 957028
## 8 1996427 416 1112 883
## 9 567 1997333 351 587
## 10 1880160 651 115054 2973
## 11 80236 1114706 111699 692197
## 12 343341 656078 0 0
# # Constructs regression expression with independent features using design matrix
regressionFormula = updatedRegressionFormula(data, ModelTest)
print("Regression Formula: ")
## [1] "Regression Formula: "
print (regressionFormula)
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.G1+N.T1+N.C2+N.G2+N.T2+N.C3+N.G3+N.T3+N.C4+N.G4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.T6+N.A7+N.C7+N.G7+N.C8+N.G8+N.T8+N.A9+N.G9+N.T9+N.C10+N.G10+N.T10+N.A11+N.G11+N.T11+N.A12+Strand.F1+Strand.F2+Strand.F3+Strand.F4+Strand.F5+Strand.F6+Strand.F7+Strand.F9+Strand.F10+Strand.F11"
fit = glm(regressionFormula,
data=data,
family = poisson(link="log"))
summary(fit)
##
## Call:
## glm(formula = regressionFormula, family = poisson(link = "log"),
## data = data)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -20.438 -1.466 -0.740 0.255 49.993
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 36.7310541 0.0025161 14598.186 < 2e-16 ***
## N.A1 -0.0007886 0.0001885 -4.183 2.88e-05 ***
## N.G1 -0.0013041 0.0001963 -6.643 3.06e-11 ***
## N.T1 -0.0406328 0.0002126 -191.130 < 2e-16 ***
## N.C2 -0.0839757 0.0001967 -426.826 < 2e-16 ***
## N.G2 -0.0201035 0.0001506 -133.452 < 2e-16 ***
## N.T2 -0.0907762 0.0001875 -484.017 < 2e-16 ***
## N.C3 -0.1167444 0.0001886 -618.915 < 2e-16 ***
## N.G3 -0.1663480 0.0002364 -703.674 < 2e-16 ***
## N.T3 -0.1281815 0.0001696 -755.994 < 2e-16 ***
## N.C4 -0.1851119 0.0003186 -581.098 < 2e-16 ***
## N.G4 -0.0858129 0.0001570 -546.607 < 2e-16 ***
## N.T4 -0.1089580 0.0001546 -704.882 < 2e-16 ***
## N.C5 -0.3165167 0.0012400 -255.264 < 2e-16 ***
## N.G5 -0.0836743 0.0001311 -638.204 < 2e-16 ***
## N.T5 -0.2948046 0.0006279 -469.511 < 2e-16 ***
## N.A6 -0.6970147 0.0255158 -27.317 < 2e-16 ***
## N.C6 -0.7379696 0.0472457 -15.620 < 2e-16 ***
## N.T6 -0.3319334 0.0011583 -286.568 < 2e-16 ***
## N.A7 0.0043403 0.0001105 39.269 < 2e-16 ***
## N.C7 -0.1653976 0.0002938 -562.984 < 2e-16 ***
## N.G7 -0.2073225 0.0003989 -519.716 < 2e-16 ***
## N.C8 -0.8847915 0.0721689 -12.260 < 2e-16 ***
## N.G8 -0.6641571 0.0164138 -40.463 < 2e-16 ***
## N.T8 -0.7708278 0.0232124 -33.208 < 2e-16 ***
## N.A9 -0.9143806 0.0625001 -14.630 < 2e-16 ***
## N.G9 -0.9011112 0.0721689 -12.486 < 2e-16 ***
## N.T9 -0.7379939 0.0272505 -27.082 < 2e-16 ***
## N.C10 -0.7201365 0.0286772 -25.112 < 2e-16 ***
## N.G10 -0.2182459 0.0003182 -685.848 < 2e-16 ***
## N.T10 -0.5641030 0.0049090 -114.911 < 2e-16 ***
## N.A11 -0.2781574 0.0004215 -659.994 < 2e-16 ***
## N.G11 -0.2139864 0.0003267 -654.936 < 2e-16 ***
## N.T11 -0.0677985 0.0001205 -562.585 < 2e-16 ***
## N.A12 -0.1076231 0.0001778 -605.444 < 2e-16 ***
## Strand.F1 -0.0663117 0.0022999 -28.833 < 2e-16 ***
## Strand.F2 0.0349913 0.0005637 62.070 < 2e-16 ***
## Strand.F3 0.0494918 0.0004394 112.643 < 2e-16 ***
## Strand.F4 0.0099097 0.0004535 21.849 < 2e-16 ***
## Strand.F5 -0.0043029 0.0002740 -15.702 < 2e-16 ***
## Strand.F6 0.0242601 0.0002834 85.594 < 2e-16 ***
## Strand.F7 0.0184938 0.0003140 58.894 < 2e-16 ***
## Strand.F9 -0.0527175 0.0003470 -151.943 < 2e-16 ***
## Strand.F10 -0.0320581 0.0005529 -57.984 < 2e-16 ***
## Strand.F11 0.0659849 0.0006508 101.385 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for poisson family taken to be 1)
##
## Null deviance: 9127258 on 999418 degrees of freedom
## Residual deviance: 4719719 on 999374 degrees of freedom
## AIC: 6158726
##
## Number of Fisher Scoring iterations: 10
ModelTest = addNewBetas(ModelTest, data, fit)
## No shape parameters included in fit.
# # Nucleotide Features after first round of fitting
summary(ModelTest)
## An object of class 'model'
##
## Slot "name": AR-DBD R8 Nucleotides+View (Rev. Comp. Sym.)
## Slot "varRegLen": 23
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATC
## Slot "rightFixedSeq": TGGAATTCTCGGGTGCCAAGG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.99
## Slot "minAffinity": 0.01
## Slot "missingValueSuppression": 0.5
## Slot "minSeedValue": 0.01
## Slot "seedLen": 15
## Slot "consensusSeq": [AG]G[AT]ACA[ACGT][ACGT][ACGT]TGT[AT]C[CT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 23
##
## Fits a model of footprint length 23 for mono-nucleotide features with 11 view(s) per strand of DNA and 1 round(s) of data (round = 8) with reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.8+N.A1+N.C1+N.G1+N.T1+N.A2+N.C2+N.G2+N.T2+N.A3+N.C3+N.G3+N.T3+N.A4+N.C4+N.G4+N.T4+N.A5+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.T6+N.A7+N.C7+N.G7+N.T7+N.A8+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.T9+N.A10+N.C10+N.G10+N.T10+N.A11+N.C11+N.G11+N.T11+N.A12+N.C12+Strand.F1+Strand.F2+Strand.F3+Strand.F4+Strand.F5+Strand.F6+Strand.F7+Strand.F8+Strand.F9+Strand.F10+Strand.F11
##
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 23 nucleotides for a feature model of length 23.
## Nucleotide features are reverse complement symmetric.
## Nucleotide beta values:
## 1 2 3 4 5
## N.A -0.0007886279 0.00000000 0.0000000 0.00000000 0.00000000
## N.C 0.0000000000 -0.08397569 -0.1167444 -0.18511185 -0.31651670
## N.G -0.0013040805 -0.02010354 -0.1663480 -0.08581288 -0.08367433
## N.T -0.0406328207 -0.09077622 -0.1281815 -0.10895800 -0.29480465
## 6 7 8 9 10 11
## N.A -0.6970147 0.00434026 0.0000000 -0.9143806 0.0000000 -0.27815739
## N.C -0.7379696 -0.16539761 -0.8847915 0.0000000 -0.7201365 0.00000000
## N.G 0.0000000 -0.20732247 -0.6641571 -0.9011112 -0.2182459 -0.21398638
## N.T -0.3319334 0.00000000 -0.7708278 -0.7379939 -0.5641030 -0.06779855
## 12 13 14 15 16 17
## N.A -0.1076231 -0.06779855 -0.5641030 -0.7379939 -0.7708278 0.00000000
## N.C 0.0000000 -0.21398638 -0.2182459 -0.9011112 -0.6641571 -0.20732247
## N.G 0.0000000 0.00000000 -0.7201365 0.0000000 -0.8847915 -0.16539761
## N.T -0.1076231 -0.27815739 0.0000000 -0.9143806 0.0000000 0.00434026
## 18 19 20 21 22
## N.A -0.3319334 -0.29480465 -0.10895800 -0.1281815 -0.09077622
## N.C 0.0000000 -0.08367433 -0.08581288 -0.1663480 -0.02010354
## N.G -0.7379696 -0.31651670 -0.18511185 -0.1167444 -0.08397569
## N.T -0.6970147 0.00000000 0.00000000 0.0000000 0.00000000
## 23
## N.A -0.0406328207
## N.C -0.0013040805
## N.G 0.0000000000
## N.T -0.0007886279
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.0001885477 0.0000000000 0.0000000000 0.0000000000 0.0000000000
## N.C 0.0000000000 0.0001967447 0.0001886277 0.0003185556 0.0012399564
## N.G 0.0001962952 0.0001506426 0.0002363993 0.0001569920 0.0001311092
## N.T 0.0002125931 0.0001875475 0.0001695536 0.0001545762 0.0006278971
## 6 7 8 9 10
## N.A 0.025515796 0.0001105268 0.00000000 0.06250013 0.0000000000
## N.C 0.047245671 0.0002937873 0.07216888 0.00000000 0.0286772225
## N.G 0.000000000 0.0003989147 0.01641375 0.07216894 0.0003182131
## N.T 0.001158308 0.0000000000 0.02321237 0.02725052 0.0049090436
## 11 12 13 14 15
## N.A 0.0004214543 0.0001777591 0.0001205125 0.0049090436 0.02725052
## N.C 0.0000000000 0.0000000000 0.0003267288 0.0003182131 0.07216894
## N.G 0.0003267288 0.0000000000 0.0000000000 0.0286772225 0.00000000
## N.T 0.0001205125 0.0001777591 0.0004214543 0.0000000000 0.06250013
## 16 17 18 19 20
## N.A 0.02321237 0.0000000000 0.001158308 0.0006278971 0.0001545762
## N.C 0.01641375 0.0003989147 0.000000000 0.0001311092 0.0001569920
## N.G 0.07216888 0.0002937873 0.047245671 0.0012399564 0.0003185556
## N.T 0.00000000 0.0001105268 0.025515796 0.0000000000 0.0000000000
## 21 22 23
## N.A 0.0001695536 0.0001875475 0.0002125931
## N.C 0.0002363993 0.0001506426 0.0001962952
## N.G 0.0001886277 0.0001967447 0.0000000000
## N.T 0.0000000000 0.0000000000 0.0001885477
##
##
## An object of class 'Intercept'
## Fits 11 views and 1 round(s) (round = 8).
## Intercept beta values:
## Round.8:
## View.1 View.2 View.3 View.4 View.5 View.6 View.7
## StrandView 36.66474 36.76605 36.78055 36.74096 36.72675 36.75531 36.74955
## View.8 View.9 View.10 View.11
## StrandView 36.73105 36.67834 36.699 36.79704
##
## Intercept beta errors:
## Round.8:
## View.1 View.2 View.3 View.4 View.5
## StrandView 0.003408863 0.002578517 0.002554211 0.002556689 0.002531017
## View.6 View.7 View.8 View.9 View.10
## StrandView 0.002532052 0.002535658 0.002516138 0.002539947 0.002576165
## View.11
## StrandView 0.002598949
##
##
##
## An object of class 'Shape'
## Fits 0 shape coefficients for 0 kinds of shape parameter(s) (shape = ) for a feature model of length 23.
vPheight = verticalPlot_height(ModelTest)
pM <- plot(ModelTest, plotTitle = "AR-DBD R8 Nucleotide+View Fit", Nplot.ddG = TRUE, verticalPlots = TRUE)
ggplot2::ggsave(pM, file = paste(selexDir, saveDir, "/modelPlot.pdf", sep = ""), height = vPheight, width = 6)
ggplot2::ggsave(pM, file = paste(selexDir, saveDir, "/modelPlot.",1, ".pdf", sep = ""), height = vPheight, width = 6)
data = data.probeCounts[sample1,]
#data = data.probeCounts
data = topModelMatch(data, ModelTest)
data = addDesignMatrix(data, ModelTest)
if (nrow(data) > 0) {
designMatrixSummary.v2 = getDesignMatrix(ModelTest, data)
if ((all(designMatrixSummary.v2$N == designMatrixSummary$N)) & (all(designMatrixSummary.v2$Round == designMatrixSummary$Round)) & (all(designMatrixSummary.v2$Intercept == designMatrixSummary$Intercept))) {
print ("Stability Reached")
}
}
## No shape parameters included in fit.
for (i in 2:20) {
if (nrow(data) == 0) {
break
} else if ((all(designMatrixSummary.v2$N == designMatrixSummary$N)) & (all(designMatrixSummary.v2$Round == designMatrixSummary$Round)) & (all(designMatrixSummary.v2$Intercept == designMatrixSummary$Intercept))) {
break
}
data.nrow = nrow(data)
print (paste("i =",i))
designMatrixSummary = designMatrixSummary.v2
print("Round summary: ")
print (designMatrixSummary$Round)
print("Mono-nucleotide summary: ")
print (designMatrixSummary$N)
print("View/strand orientation summary: ")
print (designMatrixSummary$Intercept)
# # Constructs regression expression with independent features using design matrix
regressionFormula = updatedRegressionFormula(data, ModelTest)
print("Regression Formula: ")
print (regressionFormula)
fit = glm(regressionFormula,
data=data,
family = poisson(link="log"))
summary(fit)
ModelTest = addNewBetas(ModelTest, data, fit)
# # Nucleotide Features after first round of fitting
summary(ModelTest)
pM <- plot(ModelTest, plotTitle = "AR-DBD R8 Nucleotide+View Fit", Nplot.ddG = TRUE, verticalPlots = TRUE)
ggplot2::ggsave(pM, file = paste(selexDir, saveDir, "/modelPlot.",i, ".pdf", sep = ""), height = vPheight, width = 6)
ggplot2::ggsave(pM, file = paste(selexDir, saveDir, "/modelPlot.pdf", sep = ""), height = vPheight, width = 6)
data = topModelMatch(data, ModelTest)
data = addDesignMatrix(data, ModelTest)
print(paste("Number of Observations in Design Matrix: ",nrow(data), sep = ""))
if (nrow(data) > 0) {
designMatrixSummary.v2 = getDesignMatrix(ModelTest, data)
if ((all(designMatrixSummary.v2$N == designMatrixSummary$N)) & (all(designMatrixSummary.v2$Round == designMatrixSummary$Round)) & (all(designMatrixSummary.v2$Intercept == designMatrixSummary$Intercept))) {
print (paste("Stability Reached after ", i, " iterations.", sep = ""))
break
}
} else {
print (paste("Algorithm failed to converge: No probes meet the confidence level requirement (Confidence Level:", ModelTest@confidenceLevel, ")", sep = ""))
}
}
## [1] "i = 2"
## [1] "Round summary: "
## 8 Total
## Round 999499 999499
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 583129 638711 349320 427838
## 2 719251 470686 372545 436516
## 3 910027 500144 170882 417945
## 4 928110 254680 407559 408649
## 5 1290827 18295 647486 42390
## 6 655 260 1982705 15378
## 7 843287 104894 93740 957077
## 8 1996497 428 1149 924
## 9 587 1997417 378 616
## 10 1880189 673 115119 3017
## 11 80276 1114759 111735 692228
## 12 343386 656113 0 0
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 View.8 View.9
## Strand.F 5134 64610 97217 69981 107445 129529 141258 154199 111098
## Strand.R 0 0 0 0 0 0 0 0 0
## View.10 View.11 StrandTotal
## Strand.F 56899 62129 999499
## Strand.R 0 0 0
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.G1+N.T1+N.C2+N.G2+N.T2+N.C3+N.G3+N.T3+N.C4+N.G4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.T6+N.A7+N.C7+N.G7+N.C8+N.G8+N.T8+N.A9+N.G9+N.T9+N.C10+N.G10+N.T10+N.A11+N.G11+N.T11+N.A12+Strand.F1+Strand.F2+Strand.F3+Strand.F4+Strand.F5+Strand.F6+Strand.F7+Strand.F9+Strand.F10+Strand.F11"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": AR-DBD R8 Nucleotides+View (Rev. Comp. Sym.)
## Slot "varRegLen": 23
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATC
## Slot "rightFixedSeq": TGGAATTCTCGGGTGCCAAGG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.99
## Slot "minAffinity": 0.01
## Slot "missingValueSuppression": 0.5
## Slot "minSeedValue": 0.01
## Slot "seedLen": 15
## Slot "consensusSeq": [AG]G[AT]ACA[ACGT][ACGT][ACGT]TGT[AT]C[CT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 23
##
## Fits a model of footprint length 23 for mono-nucleotide features with 11 view(s) per strand of DNA and 1 round(s) of data (round = 8) with reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.8+N.A1+N.C1+N.G1+N.T1+N.A2+N.C2+N.G2+N.T2+N.A3+N.C3+N.G3+N.T3+N.A4+N.C4+N.G4+N.T4+N.A5+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.T6+N.A7+N.C7+N.G7+N.T7+N.A8+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.T9+N.A10+N.C10+N.G10+N.T10+N.A11+N.C11+N.G11+N.T11+N.A12+N.C12+Strand.F1+Strand.F2+Strand.F3+Strand.F4+Strand.F5+Strand.F6+Strand.F7+Strand.F8+Strand.F9+Strand.F10+Strand.F11
##
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 23 nucleotides for a feature model of length 23.
## Nucleotide features are reverse complement symmetric.
## Nucleotide beta values:
## 1 2 3 4 5
## N.A -0.0007896198 0.00000000 0.0000000 0.00000000 0.00000000
## N.C 0.0000000000 -0.08396499 -0.1167259 -0.18511354 -0.31652166
## N.G -0.0013046356 -0.02010428 -0.1663337 -0.08579961 -0.08366557
## N.T -0.0406326555 -0.09076936 -0.1281664 -0.10894253 -0.29474760
## 6 7 8 9 10 11
## N.A -0.6969883 0.004345207 0.0000000 -0.7195810 0.0000000 -0.27812246
## N.C -0.5264337 -0.165372011 -0.8488055 0.0000000 -0.6510970 0.00000000
## N.G 0.0000000 -0.207274056 -0.5972905 -0.6264243 -0.2181908 -0.21394646
## N.T -0.3315207 0.000000000 -0.7131216 -0.7643796 -0.5574950 -0.06778797
## 12 13 14 15 16 17
## N.A -0.1076119 -0.06778797 -0.5574950 -0.7643796 -0.7131216 0.000000000
## N.C 0.0000000 -0.21394646 -0.2181908 -0.6264243 -0.5972905 -0.207274056
## N.G 0.0000000 0.00000000 -0.6510970 0.0000000 -0.8488055 -0.165372011
## N.T -0.1076119 -0.27812246 0.0000000 -0.7195810 0.0000000 0.004345207
## 18 19 20 21 22
## N.A -0.3315207 -0.29474760 -0.10894253 -0.1281664 -0.09076936
## N.C 0.0000000 -0.08366557 -0.08579961 -0.1663337 -0.02010428
## N.G -0.5264337 -0.31652166 -0.18511354 -0.1167259 -0.08396499
## N.T -0.6969883 0.00000000 0.00000000 0.0000000 0.00000000
## 23
## N.A -0.0406326555
## N.C -0.0013046356
## N.G 0.0000000000
## N.T -0.0007896198
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.0001885457 0.0000000000 0.0000000000 0.0000000000 0.0000000000
## N.C 0.0000000000 0.0001967431 0.0001886260 0.0003185814 0.0012401360
## N.G 0.0001962929 0.0001506426 0.0002364026 0.0001569925 0.0001311098
## N.T 0.0002125927 0.0001875480 0.0001695537 0.0001545747 0.0006278391
## 6 7 8 9 10
## N.A 0.025515795 0.0001105268 0.00000000 0.02867724 0.0000000000
## N.C 0.020016271 0.0002937798 0.06250011 0.00000000 0.0217600440
## N.G 0.000000000 0.0003988762 0.01256356 0.02404406 0.0003181755
## N.T 0.001156562 0.0000000000 0.01843081 0.03031726 0.0047819218
## 11 12 13 14 15
## N.A 0.0004214381 0.0001777579 0.0001205125 0.0047819218 0.03031726
## N.C 0.0000000000 0.0000000000 0.0003267069 0.0003181755 0.02404406
## N.G 0.0003267069 0.0000000000 0.0000000000 0.0217600440 0.00000000
## N.T 0.0001205125 0.0001777579 0.0004214381 0.0000000000 0.02867724
## 16 17 18 19 20
## N.A 0.01843081 0.0000000000 0.001156562 0.0006278391 0.0001545747
## N.C 0.01256356 0.0003988762 0.000000000 0.0001311098 0.0001569925
## N.G 0.06250011 0.0002937798 0.020016271 0.0012401360 0.0003185814
## N.T 0.00000000 0.0001105268 0.025515795 0.0000000000 0.0000000000
## 21 22 23
## N.A 0.0001695537 0.0001875480 0.0002125927
## N.C 0.0002364026 0.0001506426 0.0001962929
## N.G 0.0001886260 0.0001967431 0.0000000000
## N.T 0.0000000000 0.0000000000 0.0001885457
##
##
## An object of class 'Intercept'
## Fits 11 views and 1 round(s) (round = 8).
## Intercept beta values:
## Round.8:
## View.1 View.2 View.3 View.4 View.5 View.6 View.7
## StrandView 36.66472 36.76554 36.78 36.74043 36.72621 36.75478 36.74901
## View.8 View.9 View.10 View.11
## StrandView 36.73052 36.67781 36.69849 36.79652
##
## Intercept beta errors:
## Round.8:
## View.1 View.2 View.3 View.4 View.5
## StrandView 0.003406914 0.002578583 0.002554277 0.002556754 0.002531084
## View.6 View.7 View.8 View.9 View.10
## StrandView 0.002532118 0.002535724 0.002516205 0.002540013 0.002576221
## View.11
## StrandView 0.002599016
##
##
##
## An object of class 'Shape'
## Fits 0 shape coefficients for 0 kinds of shape parameter(s) (shape = ) for a feature model of length 23.
## [1] "Number of Observations in Design Matrix: 999462"
## No shape parameters included in fit.
## [1] "i = 3"
## [1] "Round summary: "
## 8 Total
## Round 999462 999462
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 583114 638677 349311 427822
## 2 719230 470664 372528 436502
## 3 910009 500115 170873 417927
## 4 928090 254655 407544 408635
## 5 1290800 18283 647473 42368
## 6 637 258 1982663 15366
## 7 843266 104882 93727 957049
## 8 1996461 418 1140 905
## 9 579 1997368 378 599
## 10 1880162 667 115096 2999
## 11 80256 1114740 111720 692208
## 12 343364 656098 0 0
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 View.8 View.9
## Strand.F 5129 64607 97216 69977 107444 129527 141257 154188 111094
## Strand.R 0 0 0 0 0 0 0 0 0
## View.10 View.11 StrandTotal
## Strand.F 56898 62125 999462
## Strand.R 0 0 0
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.G1+N.T1+N.C2+N.G2+N.T2+N.C3+N.G3+N.T3+N.C4+N.G4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.T6+N.A7+N.C7+N.G7+N.C8+N.G8+N.T8+N.A9+N.G9+N.T9+N.C10+N.G10+N.T10+N.A11+N.G11+N.T11+N.A12+Strand.F1+Strand.F2+Strand.F3+Strand.F4+Strand.F5+Strand.F6+Strand.F7+Strand.F9+Strand.F10+Strand.F11"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": AR-DBD R8 Nucleotides+View (Rev. Comp. Sym.)
## Slot "varRegLen": 23
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATC
## Slot "rightFixedSeq": TGGAATTCTCGGGTGCCAAGG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.99
## Slot "minAffinity": 0.01
## Slot "missingValueSuppression": 0.5
## Slot "minSeedValue": 0.01
## Slot "seedLen": 15
## Slot "consensusSeq": [AG]G[AT]ACA[ACGT][ACGT][ACGT]TGT[AT]C[CT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 23
##
## Fits a model of footprint length 23 for mono-nucleotide features with 11 view(s) per strand of DNA and 1 round(s) of data (round = 8) with reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.8+N.A1+N.C1+N.G1+N.T1+N.A2+N.C2+N.G2+N.T2+N.A3+N.C3+N.G3+N.T3+N.A4+N.C4+N.G4+N.T4+N.A5+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.T6+N.A7+N.C7+N.G7+N.T7+N.A8+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.T9+N.A10+N.C10+N.G10+N.T10+N.A11+N.C11+N.G11+N.T11+N.A12+N.C12+Strand.F1+Strand.F2+Strand.F3+Strand.F4+Strand.F5+Strand.F6+Strand.F7+Strand.F8+Strand.F9+Strand.F10+Strand.F11
##
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 23 nucleotides for a feature model of length 23.
## Nucleotide features are reverse complement symmetric.
## Nucleotide beta values:
## 1 2 3 4 5 6
## N.A -0.0007890804 0.00000000 0.0000000 0.00000000 0.0000000 -0.7023137
## N.C 0.0000000000 -0.08396657 -0.1167290 -0.18511814 -0.3165396 -0.5264819
## N.G -0.0013038695 -0.02010472 -0.1663383 -0.08580149 -0.0836681 0.0000000
## N.T -0.0406333798 -0.09077066 -0.1281696 -0.10894495 -0.2947557 -0.3315261
## 7 8 9 10 11 12
## N.A 0.004345295 0.0000000 -0.7491354 0.0000000 -0.27813239 -0.1076146
## N.C -0.165379542 -0.8488090 0.0000000 -0.6809039 0.00000000 0.0000000
## N.G -0.207282190 -0.5985633 -0.6264306 -0.2181970 -0.21395878 0.0000000
## N.T 0.000000000 -0.7186853 -0.8945679 -0.5578688 -0.06778933 -0.1076146
## 13 14 15 16 17 18
## N.A -0.06778933 -0.5578688 -0.8945679 -0.7186853 0.000000000 -0.3315261
## N.C -0.21395878 -0.2181970 -0.6264306 -0.5985633 -0.207282190 0.0000000
## N.G 0.00000000 -0.6809039 0.0000000 -0.8488090 -0.165379542 -0.5264819
## N.T -0.27813239 0.0000000 -0.7491354 0.0000000 0.004345295 -0.7023137
## 19 20 21 22 23
## N.A -0.2947557 -0.10894495 -0.1281696 -0.09077066 -0.0406333798
## N.C -0.0836681 -0.08580149 -0.1663383 -0.02010472 -0.0013038695
## N.G -0.3165396 -0.18511814 -0.1167290 -0.08396657 0.0000000000
## N.T 0.0000000 0.00000000 0.0000000 0.00000000 -0.0007890804
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.0001885460 0.0000000000 0.0000000000 0.0000000000 0.0000000000
## N.C 0.0000000000 0.0001967433 0.0001886261 0.0003185830 0.0012401957
## N.G 0.0001962933 0.0001506427 0.0002364037 0.0001569924 0.0001311099
## N.T 0.0002125932 0.0001875481 0.0001695540 0.0001545749 0.0006278464
## 6 7 8 9 10
## N.A 0.026064573 0.0001105268 0.00000000 0.03227511 0.000000000
## N.C 0.020268780 0.0002937842 0.06250011 0.00000000 0.024514816
## N.G 0.000000000 0.0003988833 0.01262749 0.02405663 0.000318178
## N.T 0.001156562 0.0000000000 0.01884502 0.05103122 0.004788921
## 11 12 13 14 15
## N.A 0.0004214464 0.0001777585 0.0001205124 0.004788921 0.05103122
## N.C 0.0000000000 0.0000000000 0.0003267171 0.000318178 0.02405663
## N.G 0.0003267171 0.0000000000 0.0000000000 0.024514816 0.00000000
## N.T 0.0001205124 0.0001777585 0.0004214464 0.000000000 0.03227511
## 16 17 18 19 20
## N.A 0.01884502 0.0000000000 0.001156562 0.0006278464 0.0001545749
## N.C 0.01262749 0.0003988833 0.000000000 0.0001311099 0.0001569924
## N.G 0.06250011 0.0002937842 0.020268780 0.0012401957 0.0003185830
## N.T 0.00000000 0.0001105268 0.026064573 0.0000000000 0.0000000000
## 21 22 23
## N.A 0.0001695540 0.0001875481 0.0002125932
## N.C 0.0002364037 0.0001506427 0.0001962933
## N.G 0.0001886261 0.0001967433 0.0000000000
## N.T 0.0000000000 0.0000000000 0.0001885460
##
##
## An object of class 'Intercept'
## Fits 11 views and 1 round(s) (round = 8).
## Intercept beta values:
## Round.8:
## View.1 View.2 View.3 View.4 View.5 View.6 View.7
## StrandView 36.66482 36.76563 36.7801 36.74052 36.72631 36.75487 36.7491
## View.8 View.9 View.10 View.11
## StrandView 36.73061 36.6779 36.69859 36.79661
##
## Intercept beta errors:
## Round.8:
## View.1 View.2 View.3 View.4 View.5
## StrandView 0.003406929 0.002578573 0.002554267 0.002556745 0.002531074
## View.6 View.7 View.8 View.9 View.10
## StrandView 0.002532108 0.002535714 0.002516195 0.002540003 0.002576212
## View.11
## StrandView 0.002599008
##
##
##
## An object of class 'Shape'
## Fits 0 shape coefficients for 0 kinds of shape parameter(s) (shape = ) for a feature model of length 23.
## [1] "Number of Observations in Design Matrix: 999457"
## No shape parameters included in fit.
## [1] "i = 4"
## [1] "Round summary: "
## 8 Total
## Round 999457 999457
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 583111 638672 349310 427821
## 2 719228 470663 372524 436499
## 3 910003 500114 170872 417925
## 4 928085 254654 407543 408632
## 5 1290797 18281 647468 42368
## 6 637 257 1982657 15363
## 7 843262 104878 93726 957048
## 8 1996456 416 1138 904
## 9 578 1997364 377 595
## 10 1880158 667 115091 2998
## 11 80253 1114736 111719 692206
## 12 343363 656094 0 0
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 View.8 View.9
## Strand.F 5127 64607 97215 69977 107444 129526 141257 154188 111093
## Strand.R 0 0 0 0 0 0 0 0 0
## View.10 View.11 StrandTotal
## Strand.F 56898 62125 999457
## Strand.R 0 0 0
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.G1+N.T1+N.C2+N.G2+N.T2+N.C3+N.G3+N.T3+N.C4+N.G4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.T6+N.A7+N.C7+N.G7+N.C8+N.G8+N.T8+N.A9+N.G9+N.T9+N.C10+N.G10+N.T10+N.A11+N.G11+N.T11+N.A12+Strand.F1+Strand.F2+Strand.F3+Strand.F4+Strand.F5+Strand.F6+Strand.F7+Strand.F9+Strand.F10+Strand.F11"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": AR-DBD R8 Nucleotides+View (Rev. Comp. Sym.)
## Slot "varRegLen": 23
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATC
## Slot "rightFixedSeq": TGGAATTCTCGGGTGCCAAGG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.99
## Slot "minAffinity": 0.01
## Slot "missingValueSuppression": 0.5
## Slot "minSeedValue": 0.01
## Slot "seedLen": 15
## Slot "consensusSeq": [AG]G[AT]ACA[ACGT][ACGT][ACGT]TGT[AT]C[CT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 23
##
## Fits a model of footprint length 23 for mono-nucleotide features with 11 view(s) per strand of DNA and 1 round(s) of data (round = 8) with reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.8+N.A1+N.C1+N.G1+N.T1+N.A2+N.C2+N.G2+N.T2+N.A3+N.C3+N.G3+N.T3+N.A4+N.C4+N.G4+N.T4+N.A5+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.T6+N.A7+N.C7+N.G7+N.T7+N.A8+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.T9+N.A10+N.C10+N.G10+N.T10+N.A11+N.C11+N.G11+N.T11+N.A12+N.C12+Strand.F1+Strand.F2+Strand.F3+Strand.F4+Strand.F5+Strand.F6+Strand.F7+Strand.F8+Strand.F9+Strand.F10+Strand.F11
##
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 23 nucleotides for a feature model of length 23.
## Nucleotide features are reverse complement symmetric.
## Nucleotide beta values:
## 1 2 3 4 5
## N.A -0.0007887409 0.00000000 0.0000000 0.00000000 0.00000000
## N.C 0.0000000000 -0.08396690 -0.1167294 -0.18511966 -0.31654095
## N.G -0.0013035035 -0.02010488 -0.1663394 -0.08580208 -0.08366877
## N.T -0.0406334158 -0.09077118 -0.1281703 -0.10894551 -0.29475700
## 6 7 8 9 10 11
## N.A -0.7023149 0.004345195 0.0000000 -0.7491367 0.0000000 -0.27813608
## N.C -0.5264832 -0.165381492 -0.8488103 0.0000000 -0.6809052 0.00000000
## N.G 0.0000000 -0.207284316 -0.5998463 -0.6311497 -0.2181994 -0.21396041
## N.T -0.3315486 0.000000000 -0.7186869 -0.9452524 -0.5578707 -0.06778956
## 12 13 14 15 16 17
## N.A -0.1076152 -0.06778956 -0.5578707 -0.9452524 -0.7186869 0.000000000
## N.C 0.0000000 -0.21396041 -0.2181994 -0.6311497 -0.5998463 -0.207284316
## N.G 0.0000000 0.00000000 -0.6809052 0.0000000 -0.8488103 -0.165381492
## N.T -0.1076152 -0.27813608 0.0000000 -0.7491367 0.0000000 0.004345195
## 18 19 20 21 22
## N.A -0.3315486 -0.29475700 -0.10894551 -0.1281703 -0.09077118
## N.C 0.0000000 -0.08366877 -0.08580208 -0.1663394 -0.02010488
## N.G -0.5264832 -0.31654095 -0.18511966 -0.1167294 -0.08396690
## N.T -0.7023149 0.00000000 0.00000000 0.0000000 0.00000000
## 23
## N.A -0.0406334158
## N.C -0.0013035035
## N.G 0.0000000000
## N.T -0.0007887409
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.0001885461 0.0000000000 0.0000000000 0.0000000000 0.0000000000
## N.C 0.0000000000 0.0001967433 0.0001886260 0.0003185838 0.0012401957
## N.G 0.0001962934 0.0001506428 0.0002364040 0.0001569925 0.0001311100
## N.T 0.0002125934 0.0001875482 0.0001695541 0.0001545749 0.0006278464
## 6 7 8 9 10
## N.A 0.026064573 0.0001105268 0.00000000 0.03227511 0.0000000000
## N.C 0.020267419 0.0002937855 0.06250011 0.00000000 0.0245148161
## N.G 0.000000000 0.0003988850 0.01269241 0.02451494 0.0003181797
## N.T 0.001156658 0.0000000000 0.01884502 0.06250015 0.0047889212
## 11 12 13 14 15
## N.A 0.0004214505 0.0001777585 0.0001205123 0.0047889212 0.06250015
## N.C 0.0000000000 0.0000000000 0.0003267180 0.0003181797 0.02451494
## N.G 0.0003267180 0.0000000000 0.0000000000 0.0245148161 0.00000000
## N.T 0.0001205123 0.0001777585 0.0004214505 0.0000000000 0.03227511
## 16 17 18 19 20
## N.A 0.01884502 0.0000000000 0.001156658 0.0006278464 0.0001545749
## N.C 0.01269241 0.0003988850 0.000000000 0.0001311100 0.0001569925
## N.G 0.06250011 0.0002937855 0.020267419 0.0012401957 0.0003185838
## N.T 0.00000000 0.0001105268 0.026064573 0.0000000000 0.0000000000
## 21 22 23
## N.A 0.0001695541 0.0001875482 0.0002125934
## N.C 0.0002364040 0.0001506428 0.0001962934
## N.G 0.0001886260 0.0001967433 0.0000000000
## N.T 0.0000000000 0.0000000000 0.0001885461
##
##
## An object of class 'Intercept'
## Fits 11 views and 1 round(s) (round = 8).
## Intercept beta values:
## Round.8:
## View.1 View.2 View.3 View.4 View.5 View.6 View.7
## StrandView 36.66485 36.76565 36.78012 36.74055 36.72633 36.7549 36.74912
## View.8 View.9 View.10 View.11
## StrandView 36.73063 36.67792 36.69861 36.79663
##
## Intercept beta errors:
## Round.8:
## View.1 View.2 View.3 View.4 View.5
## StrandView 0.003406927 0.002578571 0.002554265 0.002556742 0.002531071
## View.6 View.7 View.8 View.9 View.10
## StrandView 0.002532106 0.002535712 0.002516193 0.002540001 0.002576209
## View.11
## StrandView 0.002599006
##
##
##
## An object of class 'Shape'
## Fits 0 shape coefficients for 0 kinds of shape parameter(s) (shape = ) for a feature model of length 23.
## [1] "Number of Observations in Design Matrix: 999455"
## No shape parameters included in fit.
## [1] "i = 5"
## [1] "Round summary: "
## 8 Total
## Round 999455 999455
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 583109 638672 349310 427819
## 2 719228 470661 372522 436499
## 3 910001 500112 170872 417925
## 4 928083 254653 407543 408631
## 5 1290796 18279 647467 42368
## 6 637 257 1982654 15362
## 7 843262 104877 93725 957046
## 8 1996454 416 1137 903
## 9 578 1997362 377 593
## 10 1880157 667 115090 2996
## 11 80252 1114733 111719 692206
## 12 343362 656093 0 0
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 View.8 View.9
## Strand.F 5127 64607 97215 69976 107444 129525 141257 154188 111093
## Strand.R 0 0 0 0 0 0 0 0 0
## View.10 View.11 StrandTotal
## Strand.F 56898 62125 999455
## Strand.R 0 0 0
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.G1+N.T1+N.C2+N.G2+N.T2+N.C3+N.G3+N.T3+N.C4+N.G4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.T6+N.A7+N.C7+N.G7+N.C8+N.G8+N.T8+N.A9+N.G9+N.T9+N.C10+N.G10+N.T10+N.A11+N.G11+N.T11+N.A12+Strand.F1+Strand.F2+Strand.F3+Strand.F4+Strand.F5+Strand.F6+Strand.F7+Strand.F9+Strand.F10+Strand.F11"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": AR-DBD R8 Nucleotides+View (Rev. Comp. Sym.)
## Slot "varRegLen": 23
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATC
## Slot "rightFixedSeq": TGGAATTCTCGGGTGCCAAGG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.99
## Slot "minAffinity": 0.01
## Slot "missingValueSuppression": 0.5
## Slot "minSeedValue": 0.01
## Slot "seedLen": 15
## Slot "consensusSeq": [AG]G[AT]ACA[ACGT][ACGT][ACGT]TGT[AT]C[CT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 23
##
## Fits a model of footprint length 23 for mono-nucleotide features with 11 view(s) per strand of DNA and 1 round(s) of data (round = 8) with reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.8+N.A1+N.C1+N.G1+N.T1+N.A2+N.C2+N.G2+N.T2+N.A3+N.C3+N.G3+N.T3+N.A4+N.C4+N.G4+N.T4+N.A5+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.T6+N.A7+N.C7+N.G7+N.T7+N.A8+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.T9+N.A10+N.C10+N.G10+N.T10+N.A11+N.C11+N.G11+N.T11+N.A12+N.C12+Strand.F1+Strand.F2+Strand.F3+Strand.F4+Strand.F5+Strand.F6+Strand.F7+Strand.F8+Strand.F9+Strand.F10+Strand.F11
##
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 23 nucleotides for a feature model of length 23.
## Nucleotide features are reverse complement symmetric.
## Nucleotide beta values:
## 1 2 3 4 5
## N.A -0.0007887409 0.00000000 0.0000000 0.00000000 0.00000000
## N.C 0.0000000000 -0.08396690 -0.1167294 -0.18511966 -0.31654095
## N.G -0.0013035035 -0.02010488 -0.1663394 -0.08580208 -0.08366877
## N.T -0.0406334158 -0.09077118 -0.1281703 -0.10894551 -0.29475700
## 6 7 8 9 10 11
## N.A -0.7023149 0.004345195 0.0000000 -0.7491367 0.0000000 -0.27813608
## N.C -0.5264832 -0.165381492 -0.8488103 0.0000000 -0.6809052 0.00000000
## N.G 0.0000000 -0.207284316 -0.5998463 -0.6311497 -0.2181994 -0.21396041
## N.T -0.3315486 0.000000000 -0.7186869 -0.9452524 -0.5578707 -0.06778956
## 12 13 14 15 16 17
## N.A -0.1076152 -0.06778956 -0.5578707 -0.9452524 -0.7186869 0.000000000
## N.C 0.0000000 -0.21396041 -0.2181994 -0.6311497 -0.5998463 -0.207284316
## N.G 0.0000000 0.00000000 -0.6809052 0.0000000 -0.8488103 -0.165381492
## N.T -0.1076152 -0.27813608 0.0000000 -0.7491367 0.0000000 0.004345195
## 18 19 20 21 22
## N.A -0.3315486 -0.29475700 -0.10894551 -0.1281703 -0.09077118
## N.C 0.0000000 -0.08366877 -0.08580208 -0.1663394 -0.02010488
## N.G -0.5264832 -0.31654095 -0.18511966 -0.1167294 -0.08396690
## N.T -0.7023149 0.00000000 0.00000000 0.0000000 0.00000000
## 23
## N.A -0.0406334158
## N.C -0.0013035035
## N.G 0.0000000000
## N.T -0.0007887409
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.0001885461 0.0000000000 0.0000000000 0.0000000000 0.0000000000
## N.C 0.0000000000 0.0001967433 0.0001886260 0.0003185838 0.0012401957
## N.G 0.0001962934 0.0001506428 0.0002364040 0.0001569925 0.0001311100
## N.T 0.0002125934 0.0001875482 0.0001695541 0.0001545749 0.0006278464
## 6 7 8 9 10
## N.A 0.026064573 0.0001105268 0.00000000 0.03227511 0.0000000000
## N.C 0.020267181 0.0002937855 0.06250011 0.00000000 0.0245148161
## N.G 0.000000000 0.0003988850 0.01269241 0.02451494 0.0003181797
## N.T 0.001156658 0.0000000000 0.01884502 0.06250015 0.0047889212
## 11 12 13 14 15
## N.A 0.0004214505 0.0001777585 0.0001205123 0.0047889212 0.06250015
## N.C 0.0000000000 0.0000000000 0.0003267180 0.0003181797 0.02451494
## N.G 0.0003267180 0.0000000000 0.0000000000 0.0245148161 0.00000000
## N.T 0.0001205123 0.0001777585 0.0004214505 0.0000000000 0.03227511
## 16 17 18 19 20
## N.A 0.01884502 0.0000000000 0.001156658 0.0006278464 0.0001545749
## N.C 0.01269241 0.0003988850 0.000000000 0.0001311100 0.0001569925
## N.G 0.06250011 0.0002937855 0.020267181 0.0012401957 0.0003185838
## N.T 0.00000000 0.0001105268 0.026064573 0.0000000000 0.0000000000
## 21 22 23
## N.A 0.0001695541 0.0001875482 0.0002125934
## N.C 0.0002364040 0.0001506428 0.0001962934
## N.G 0.0001886260 0.0001967433 0.0000000000
## N.T 0.0000000000 0.0000000000 0.0001885461
##
##
## An object of class 'Intercept'
## Fits 11 views and 1 round(s) (round = 8).
## Intercept beta values:
## Round.8:
## View.1 View.2 View.3 View.4 View.5 View.6 View.7
## StrandView 36.66485 36.76565 36.78012 36.74055 36.72633 36.7549 36.74912
## View.8 View.9 View.10 View.11
## StrandView 36.73063 36.67792 36.69861 36.79663
##
## Intercept beta errors:
## Round.8:
## View.1 View.2 View.3 View.4 View.5
## StrandView 0.003406927 0.002578571 0.002554265 0.002556742 0.002531071
## View.6 View.7 View.8 View.9 View.10
## StrandView 0.002532106 0.002535712 0.002516193 0.002540001 0.002576209
## View.11
## StrandView 0.002599006
##
##
##
## An object of class 'Shape'
## Fits 0 shape coefficients for 0 kinds of shape parameter(s) (shape = ) for a feature model of length 23.
## [1] "Number of Observations in Design Matrix: 999455"
## No shape parameters included in fit.
## [1] "Stability Reached after 5 iterations."
ModelTest <- finalizeFeatureBetas(ModelTest)
pM <- plot(ModelTest, plotTitle = "AR-DBD R8 Nucleotide+View Fit", Nplot.ddG = TRUE, verticalPlots = TRUE)
ggplot2::ggsave(pM, file = paste(selexDir, saveDir, "/modelPlot.pdf", sep = ""), height = vPheight, width = 6)
save(ModelTest, file = paste(selexDir, saveDir, "/model.RData",sep = ""))
saveRDS(ModelTest, file = paste(selexDir, saveDir, "/model.rds",sep = ""))