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/Mann/HM/"
# CLUSTER VERSIONS ARE COMMENTED OUT
#selexDir = "/vega/hblab/users/gdm2120/SELEX/SELEX/"
#rawdataDir = "/vega/hblab/projects/selex/rawdata/Mann/hm/"
##################################################################
saveDir = "gabriella/SelexGLMtest/ShapeNoSymmetry"
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',
paste(rawdataDir, "exp6/mplex1.0b.mplex2.0b.fastq.gz", sep = ""),
'm1r0',
0, 16, 'TGG', 'CCAGCTG')
selex.defineSample('r0',
paste(rawdataDir, "exp6/mplex1.0b.mplex2.0b.fastq.gz", sep = ""),
'm2r0',
0, 16, 'TGG', 'CCACGTC')
selex.defineSample('Ubx4a.R2',
paste(rawdataDir, "exp4/exdUbxiva.exdAntp.L.2.fastq.gz", sep = ""),
'HM.Ubx4a.Exd',
2, 16, 'TGG', 'CCAGCTG')
selex.defineSample('Ubx4a.R3',
paste(rawdataDir,"exp4/exdUbxiva.exdAntp.L.3.fastq.gz", sep = ""),
'HM.Ubx4a.Exd',
3, 16, 'TGG', 'CCAGCTG')
r0.train = selex.sample(seqName = 'r0', sampleName='m1r0', round = 0)
r0.test = selex.sample(seqName = 'r0', sampleName='m2r0', round = 0)
dataSample = selex.sample(seqName = 'Ubx4a.R2', sampleName = 'HM.Ubx4a.Exd', round = 2)
# MARKOV MODEL BUILT
kmax = selex.kmax(sample = r0.test)
# Train Markov model on Hm 16bp library Round 0 data
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))
# For the sake of previous analysis on the Hox data used in this example, I will use kLen = 12 as my k-mer length, even though kLen identified through the information gain analysis has kLen = 13.
kLen = 12
#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 = "HM-Exd-Ubx4a R2 Nucleotide+Shape Model",
varRegLen = libLen,
leftFixedSeq = "GTTCAGAGTTCTACAGTCCGACGATCTGG",
rightFixedSeq ="CCAGCTGTCGTATGCCGTCTTCTGCTTG",
consensusSeq = "NTGAYNNAYNNN",
affinityType = "AffinitySym",
leftFixedSeqOverlap = 5,
minAffinity = 0.00,
missingValueSuppression = 1,
minSeedValue = .001,
upFootprintExtend = 4,
confidenceLevel = .95,
verbose = FALSE,
includeShape = TRUE,
shapeTable = ST,
shapeParamsUsed = list(c("MGW")),
rounds = list(c(2)),
rcSymmetric = FALSE)
getFeatureDesign(ModelTest)
## Feature design for object of class 'model'
##
## seedLen: 12
## upFootprintExtend: 4
## downFootprintExtend: 4
## rcSymmetric: FALSE
##
## 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
## Number of previous iterations: 0
##
## Slot "Intercept":
## Number of Views per Strand of DNA: 7
## Number of Rounds: 1 (2)
## Number of previous iterations: 0
##
## Slot "Shape":
## ShapeParamsUsed: MGW
## Shape.upFootprintExtend: 4
## Shape.downFootprintExtend: 4
## Shape.set: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20
## Number of previous iterations: 0
# 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 10
## N.A 0 0 0 0 0.0000000 -0.8340377 -0.6171102 0.000000 -1.360965 -1.476628
## N.C 0 0 0 0 -0.8162560 -1.8500362 -3.1650820 -2.675131 -1.992603 -2.448111
## N.G 0 0 0 0 -0.2525938 -2.1521858 0.0000000 -2.618543 -1.264517 -2.484039
## N.T 0 0 0 0 -0.4154319 0.0000000 -1.3143951 -2.908717 0.000000 0.000000
## 11 12 13 14 15 16 17 18
## N.A -1.118790 0.000000 -2.022527 -0.86831649 0.0000000 -0.7152829 0 0
## N.C -2.174582 -3.392451 -1.355055 -1.05294403 -1.6266289 0.0000000 0 0
## N.G -1.362605 -2.603949 -1.716115 -0.02638645 -0.0963874 -0.3890593 0 0
## N.T 0.000000 -3.561304 0.000000 0.00000000 -1.0818102 -0.2918482 0 0
## 19 20
## N.A 0 0
## N.C 0 0
## N.G 0 0
## N.T 0 0
plot(ModelTest@features@N, Ntitle = "HM-Ubx4a-Exd R2 Nucleotide Features\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)
if (nrow(data) > 0) {
designMatrixSummary = getDesignMatrix(ModelTest, data)
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)
vPheight = verticalPlot_height(ModelTest)
pM <- plot(ModelTest, plotTitle = "HM-Ubx4a-Exd R2 Nucleotide+Shape 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)
}
## [1] "Round summary: "
## 2 Total
## Round 793174 793174
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 68476 184012 306705 233981
## 2 99593 162624 310887 220070
## 3 138085 86021 374727 194341
## 4 146328 108588 377555 160703
## 5 328974 64094 265609 134497
## 6 114523 24727 23828 630096
## 7 176145 2325 537294 77410
## 8 745682 14621 18514 14357
## 9 48847 17653 48493 678181
## 10 45570 9870 13946 723788
## 11 57770 14287 46875 674242
## 12 767868 6137 14683 4486
## 13 15074 102782 19829 655489
## 14 102435 45997 391016 253726
## 15 331920 51480 282888 126886
## 16 96756 363132 157189 176097
## 17 124692 405736 102523 160223
## 18 235939 321857 92180 143198
## 19 190242 291613 197148 114171
## 20 210546 359267 154557 68804
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 49803 82297 75239 67602 68220 68774 81852 493787
## Strand.R 37176 49801 47214 36470 38110 41172 49444 299387
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.C1+N.T1+N.A2+N.C2+N.T2+N.A3+N.C3+N.T3+N.A4+N.C4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.A7+N.C7+N.T7+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.A10+N.C10+N.G10+N.A11+N.C11+N.G11+N.C12+N.G12+N.T12+N.A13+N.C13+N.G13+N.A14+N.C14+N.T14+N.C15+N.G15+N.T15+N.A16+N.G16+N.T16+N.A17+N.G17+N.T17+N.A18+N.G18+N.T18+N.A19+N.G19+N.T19+N.A20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20"
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a R2 Nucleotide+Shape Model
## Slot "varRegLen": 16
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATCTGG
## Slot "rightFixedSeq": CCAGCTGTCGTATGCCGTCTTCTGCTTG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.95
## Slot "minAffinity": 0
## Slot "missingValueSuppression": 1
## Slot "minSeedValue": 0.001
## Slot "seedLen": 12
## Slot "consensusSeq": [ACGT]TGA[CT][ACGT][ACGT]A[CT][ACGT][ACGT][ACGT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 20
##
## Fits a model of footprint length 20 for mono-nucleotide and shape features (shape = MGW) with 7 view(s) per strand of DNA and 1 round(s) of data (round = 2) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+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+N.G12+N.T12+N.A13+N.C13+N.G13+N.T13+N.A14+N.C14+N.G14+N.T14+N.A15+N.C15+N.G15+N.T15+N.A16+N.C16+N.G16+N.T16+N.A17+N.C17+N.G17+N.T17+N.A18+N.C18+N.G18+N.T18+N.A19+N.C19+N.G19+N.T19+N.A20+N.C20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20
##
## Slot "shapeParamsUsed[[1]]": MGW
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 20 nucleotides for a feature model of length 20.
## Nucleotide beta values:
## 1 2 3 4 5 6
## N.A 0.01253234 0.02422729 -0.004104566 -0.02256017 0.0000000 -0.9634024
## N.C -0.00684892 -0.08913195 -0.145321408 -0.14335588 -0.8828338 -1.7860495
## N.G 0.00000000 0.00000000 0.000000000 0.00000000 -0.3307293 -2.0625280
## N.T -0.09519787 -0.04892703 -0.149203769 -0.02932519 -0.5747389 0.0000000
## 7 8 9 10 11 12
## N.A -0.3537259 0.000000 -1.125992 -0.417799 -0.3082163 0.000000
## N.C -2.7547602 -2.406471 -2.114720 -1.382037 -0.3758490 -2.213119
## N.G 0.0000000 -2.189851 -1.202262 -1.513932 -0.5736097 -1.958444
## N.T -1.1756356 -2.420402 0.000000 0.000000 0.0000000 -2.713184
## 13 14 15 16 17 18
## N.A -1.5053420 -0.65732779 0.00000000 -0.4872643 -0.3003743 -0.13422046
## N.C -0.4392728 -0.69212185 -0.96435519 0.0000000 0.0000000 0.00000000
## N.G -1.6782230 0.00000000 -0.09941264 -0.2371231 -0.3375361 -0.13494208
## N.T 0.0000000 0.01153419 -0.50152085 -0.3131210 -0.1186828 0.05193197
## 19 20
## N.A -0.03798651 -0.04430404
## N.C 0.00000000 0.00000000
## N.G -0.11477706 -0.07067889
## N.T 0.12674745 0.04689794
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001730025 0.001515151 0.001309331 0.001203275 0.000000000
## N.C 0.001692673 0.001603213 0.001586115 0.001489542 0.002247789
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001273625
## N.T 0.001318391 0.001431322 0.001270967 0.001315664 0.001818186
## 6 7 8 9 10 11
## N.A 0.002933775 0.007293060 0.00000000 0.005232921 0.01115106 0.009678476
## N.C 0.008006628 0.083141739 0.02380024 0.013457318 0.02933847 0.013680335
## N.G 0.010977468 0.000000000 0.01515640 0.005161231 0.02213771 0.010250919
## N.T 0.000000000 0.006585288 0.02088548 0.000000000 0.00000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.018438536 0.001691740 0.0000000000 0.001509708
## N.C 0.05058025 0.004310961 0.002950786 0.0028247421 0.000000000
## N.G 0.02054346 0.012004657 0.000000000 0.0009323067 0.001186250
## N.T 0.06610678 0.000000000 0.002220033 0.0017555444 0.001198207
## 17 18 19 20
## N.A 0.001444674 0.001459143 0.001622719 0.001289260
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001511270 0.001629345 0.001681206 0.001758219
## N.T 0.001173194 0.001337781 0.001525839 0.001806511
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## [1] 23.49162
##
## Intercept beta errors:
## Round.2:
## [1] 0.02267907
##
##
##
## An object of class 'Shape'
## Fits 20 shape coefficients for 1 kinds of shape parameter(s) (shape = MGW) for a feature model of length 20.
## Shape beta values:
## 1 2 3 4 5
## Shape.MGW -0.05714087 -0.01888749 0.008281527 -0.1176119 -0.005593158
## 6 7 8 9 10 11
## Shape.MGW -0.09592255 0.1174069 0.1317001 0.3645446 -0.3005793 -1.370984
## 12 13 14 15 16 17
## Shape.MGW 1.701667 0.1966173 -0.01839352 0.1569843 0.2136021 -0.03073746
## 18 19 20
## Shape.MGW -0.03548669 0.0588744 -0.06665534
##
## Shape beta errors:
## 1 2 3 4 5
## Shape.MGW 0.002757371 0.003161373 0.002772485 0.002706141 0.00270645
## 6 7 8 9 10
## Shape.MGW 0.002777458 0.005645016 0.008375105 0.008153703 0.02007272
## 11 12 13 14 15
## Shape.MGW 0.0316683 0.01152384 0.003762656 0.003578138 0.002640943
## 16 17 18 19 20
## Shape.MGW 0.002766115 0.002930304 0.002985942 0.003388282 0.002880248
data = data.probeCounts[sample1, ]
#data = data.probeCounts
data.nrow = nrow(data)
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$Intercept))) {
print ("Stability Reached")
}
}
for (i in 2:20) {
if (nrow(data) == 0) {
break
} else if ((all(designMatrixSummary.v2$N == designMatrixSummary$N)) & (all(designMatrixSummary.v2$Round == designMatrixSummary$Round)) & (all(designMatrixSummary.v2$Intercept == designMatrixSummary$Intercept))) {
break
}
data.nrow = nrow(data)
print (paste("i =",i))
designMatrixSummary = getDesignMatrix(ModelTest, data)
print("Round summary: ")
print (designMatrixSummary$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 = "HM-Ubx4a-Exd R2 Nucleotide+Shape 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.",i, ".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: "
## 2 Total
## Round 718845 718845
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 59111 171292 274350 214092
## 2 88916 144275 285342 200312
## 3 123530 76181 350696 168438
## 4 136115 94901 347453 140376
## 5 302276 58577 233749 124243
## 6 99669 18577 16649 583950
## 7 173194 1374 476141 68136
## 8 691042 10265 10082 7456
## 9 40561 11430 39323 627531
## 10 42927 8082 9408 658428
## 11 49790 19473 39471 610111
## 12 697942 5807 12278 2818
## 13 9137 107237 13062 589409
## 14 96949 35904 377582 208410
## 15 289732 48119 259884 121110
## 16 89022 324914 151404 153505
## 17 114469 364783 93858 145735
## 18 210253 289583 85325 133684
## 19 170002 266112 174918 107813
## 20 189667 328203 138202 62773
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 43989 76653 70489 61005 59918 59833 69536 441423
## Strand.R 34004 47305 46238 33898 34985 37069 43923 277422
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.C1+N.T1+N.A2+N.C2+N.T2+N.A3+N.C3+N.T3+N.A4+N.C4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.A7+N.C7+N.T7+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.A10+N.C10+N.G10+N.A11+N.C11+N.G11+N.C12+N.G12+N.T12+N.A13+N.C13+N.G13+N.A14+N.C14+N.T14+N.C15+N.G15+N.T15+N.A16+N.G16+N.T16+N.A17+N.G17+N.T17+N.A18+N.G18+N.T18+N.A19+N.G19+N.T19+N.A20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20"
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a R2 Nucleotide+Shape Model
## Slot "varRegLen": 16
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATCTGG
## Slot "rightFixedSeq": CCAGCTGTCGTATGCCGTCTTCTGCTTG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.95
## Slot "minAffinity": 0
## Slot "missingValueSuppression": 1
## Slot "minSeedValue": 0.001
## Slot "seedLen": 12
## Slot "consensusSeq": [ACGT]TGA[CT][ACGT][ACGT]A[CT][ACGT][ACGT][ACGT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 20
##
## Fits a model of footprint length 20 for mono-nucleotide and shape features (shape = MGW) with 7 view(s) per strand of DNA and 1 round(s) of data (round = 2) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+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+N.G12+N.T12+N.A13+N.C13+N.G13+N.T13+N.A14+N.C14+N.G14+N.T14+N.A15+N.C15+N.G15+N.T15+N.A16+N.C16+N.G16+N.T16+N.A17+N.C17+N.G17+N.T17+N.A18+N.C18+N.G18+N.T18+N.A19+N.C19+N.G19+N.T19+N.A20+N.C20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20
##
## Slot "shapeParamsUsed[[1]]": MGW
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 20 nucleotides for a feature model of length 20.
## Nucleotide beta values:
## 1 2 3 4 5 6
## N.A 0.01303624 0.02333854 -0.004448227 -0.02465040 0.0000000 -0.9580722
## N.C -0.00803897 -0.08801543 -0.145762514 -0.14098853 -0.8766590 -1.7741143
## N.G 0.00000000 0.00000000 0.000000000 0.00000000 -0.3257703 -2.0850529
## N.T -0.09478026 -0.04763455 -0.150319230 -0.02889116 -0.5705516 0.0000000
## 7 8 9 10 11 12
## N.A -0.2573452 0.000000 -1.037550 -0.4749251 -0.3030826 0.00000
## N.C -2.9180643 -2.412408 -2.105038 -1.5758723 -0.2296450 -2.14154
## N.G 0.0000000 -2.257469 -1.176598 -1.5766645 -0.5848880 -1.99332
## N.T -1.1355217 -2.449646 0.000000 0.0000000 0.0000000 -3.05351
## 13 14 15 16 17 18
## N.A -1.5120908 -0.65367426 0.0000000 -0.4840579 -0.2978173 -0.13225297
## N.C -0.4320931 -0.65117187 -0.9592219 0.0000000 0.0000000 0.00000000
## N.G -1.6775303 0.00000000 -0.1048427 -0.2360431 -0.3335634 -0.13479915
## N.T 0.0000000 0.02054396 -0.5005907 -0.3075896 -0.1159250 0.05339655
## 19 20
## N.A -0.03556321 -0.04494359
## N.C 0.00000000 0.00000000
## N.G -0.11278880 -0.07155572
## N.T 0.12777052 0.04566769
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001753968 0.001533149 0.001320215 0.001209217 0.000000000
## N.C 0.001707870 0.001623550 0.001599954 0.001511712 0.002271029
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001286486
## N.T 0.001330850 0.001446912 0.001289105 0.001322918 0.001833499
## 6 7 8 9 10 11
## N.A 0.002967534 0.006746663 0.00000000 0.005084237 0.01074577 0.009644028
## N.C 0.008897488 0.124721841 0.02499635 0.014297701 0.03682919 0.012075984
## N.G 0.011756618 0.000000000 0.01909055 0.005165673 0.02655919 0.010153420
## N.T 0.000000000 0.006560644 0.02555518 0.000000000 0.00000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.018834406 0.001700033 0.0000000000 0.001519906
## N.C 0.05320096 0.004241282 0.003070782 0.0028696272 0.000000000
## N.G 0.02113605 0.012131875 0.000000000 0.0009430028 0.001189164
## N.T 0.07917382 0.000000000 0.002199117 0.0017724552 0.001214297
## 17 18 19 20
## N.A 0.001451942 0.001465615 0.001633269 0.001300938
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001519798 0.001638723 0.001690583 0.001771719
## N.T 0.001181133 0.001343961 0.001532647 0.001817516
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## [1] 23.43328
##
## Intercept beta errors:
## Round.2:
## [1] 0.02241826
##
##
##
## An object of class 'Shape'
## Fits 20 shape coefficients for 1 kinds of shape parameter(s) (shape = MGW) for a feature model of length 20.
## Shape beta values:
## 1 2 3 4 5
## Shape.MGW -0.05406993 -0.02191307 0.009408218 -0.1164705 -0.001892145
## 6 7 8 9 10 11
## Shape.MGW -0.09635434 0.1128344 0.145007 0.4778974 -0.3592074 -1.406691
## 12 13 14 15 16 17
## Shape.MGW 1.740155 0.2007012 -0.0234718 0.1500717 0.208626 -0.02488117
## 18 19 20
## Shape.MGW -0.04036182 0.05921694 -0.06481593
##
## Shape beta errors:
## 1 2 3 4 5
## Shape.MGW 0.00278487 0.003191742 0.002801293 0.002738043 0.002721193
## 6 7 8 9 10
## Shape.MGW 0.00280957 0.00572684 0.008536869 0.007543474 0.02002219
## 11 12 13 14 15
## Shape.MGW 0.03113991 0.01139374 0.003800725 0.00360467 0.002680351
## 16 17 18 19 20
## Shape.MGW 0.002789965 0.002945868 0.003002845 0.003408552 0.002900904
##
## [1] "Number of Observations in Design Matrix: 699130"
## [1] "i = 3"
## [1] "Round summary: "
## 2 Total
## Round 699130 699130
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 56665 168214 264054 210197
## 2 85613 140651 276791 196075
## 3 119456 72238 345460 161976
## 4 131410 90636 342050 135034
## 5 290602 57507 228320 122701
## 6 98200 18111 15791 567028
## 7 170621 1167 460403 66939
## 8 673262 9849 9303 6716
## 9 39428 10834 38187 610681
## 10 41596 7195 8763 641576
## 11 47214 19167 38913 593836
## 12 679810 5664 11498 2158
## 13 8342 104866 12294 573628
## 14 92884 34560 371500 200186
## 15 281973 45874 254391 116892
## 16 85962 315752 148330 149086
## 17 111930 353447 91829 141924
## 18 204156 279990 83847 131137
## 19 165117 257587 169901 106525
## 20 183410 319872 133913 61935
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 43408 75667 69603 58566 57406 57455 66904 429009
## Strand.R 33654 46795 45783 32501 33568 35637 42183 270121
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.C1+N.T1+N.A2+N.C2+N.T2+N.A3+N.C3+N.T3+N.A4+N.C4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.A7+N.C7+N.T7+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.A10+N.C10+N.G10+N.A11+N.C11+N.G11+N.C12+N.G12+N.T12+N.A13+N.C13+N.G13+N.A14+N.C14+N.T14+N.C15+N.G15+N.T15+N.A16+N.G16+N.T16+N.A17+N.G17+N.T17+N.A18+N.G18+N.T18+N.A19+N.G19+N.T19+N.A20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20"
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a R2 Nucleotide+Shape Model
## Slot "varRegLen": 16
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATCTGG
## Slot "rightFixedSeq": CCAGCTGTCGTATGCCGTCTTCTGCTTG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.95
## Slot "minAffinity": 0
## Slot "missingValueSuppression": 1
## Slot "minSeedValue": 0.001
## Slot "seedLen": 12
## Slot "consensusSeq": [ACGT]TGA[CT][ACGT][ACGT]A[CT][ACGT][ACGT][ACGT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 20
##
## Fits a model of footprint length 20 for mono-nucleotide and shape features (shape = MGW) with 7 view(s) per strand of DNA and 1 round(s) of data (round = 2) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+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+N.G12+N.T12+N.A13+N.C13+N.G13+N.T13+N.A14+N.C14+N.G14+N.T14+N.A15+N.C15+N.G15+N.T15+N.A16+N.C16+N.G16+N.T16+N.A17+N.C17+N.G17+N.T17+N.A18+N.C18+N.G18+N.T18+N.A19+N.C19+N.G19+N.T19+N.A20+N.C20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20
##
## Slot "shapeParamsUsed[[1]]": MGW
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 20 nucleotides for a feature model of length 20.
## Nucleotide beta values:
## 1 2 3 4 5
## N.A 0.012687703 0.02260129 -0.004656464 -0.02392586 0.0000000
## N.C -0.008055089 -0.08806905 -0.144630919 -0.13988636 -0.8748547
## N.G 0.000000000 0.00000000 0.000000000 0.00000000 -0.3256181
## N.T -0.095076571 -0.04705239 -0.150461346 -0.02920608 -0.5705499
## 6 7 8 9 10 11
## N.A -0.9551653 -0.2555156 0.000000 -1.030846 -0.4778655 -0.3015363
## N.C -1.7711088 -2.8792341 -2.420839 -2.101860 -1.5732519 -0.2184761
## N.G -2.0824627 0.0000000 -2.264459 -1.174437 -1.5770758 -0.5815238
## N.T 0.0000000 -1.1363703 -2.455421 0.000000 0.0000000 0.0000000
## 12 13 14 15 16 17
## N.A 0.000000 -1.506122 -0.65274276 0.0000000 -0.4838935 -0.2967293
## N.C -2.142158 -0.429365 -0.64772353 -0.9571588 0.0000000 0.0000000
## N.G -1.995837 -1.674018 0.00000000 -0.1070622 -0.2357167 -0.3322427
## N.T -3.062612 0.000000 0.02393941 -0.4996213 -0.3060875 -0.1146964
## 18 19 20
## N.A -0.13148401 -0.03507989 -0.04555541
## N.C 0.00000000 0.00000000 0.00000000
## N.G -0.13407305 -0.11276265 -0.07174431
## N.T 0.05421768 0.12749467 0.04482250
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001771546 0.001549350 0.001327064 0.001216803 0.000000000
## N.C 0.001719655 0.001642013 0.001618895 0.001529093 0.002285507
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001295281
## N.T 0.001338833 0.001461037 0.001308017 0.001329070 0.001844515
## 6 7 8 9 10 11
## N.A 0.002979793 0.006781411 0.00000000 0.005125349 0.01082920 0.009784637
## N.C 0.008971405 0.133426486 0.02541509 0.014540500 0.03796657 0.012159251
## N.G 0.011985925 0.000000000 0.02015799 0.005203450 0.02728049 0.010253218
## N.T 0.000000000 0.006584864 0.02701274 0.000000000 0.00000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.019219536 0.001729111 0.0000000000 0.001534469
## N.C 0.05431124 0.004278847 0.003130293 0.0029312876 0.000000000
## N.G 0.02179885 0.012321899 0.000000000 0.0009502936 0.001194557
## N.T 0.08401565 0.000000000 0.002228664 0.0017988642 0.001223215
## 17 18 19 20
## N.A 0.001459690 0.001471214 0.001638759 0.001310574
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001528324 0.001645518 0.001696934 0.001779261
## N.T 0.001187605 0.001349333 0.001536424 0.001822586
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## [1] 23.42008
##
## Intercept beta errors:
## Round.2:
## [1] 0.02269594
##
##
##
## An object of class 'Shape'
## Fits 20 shape coefficients for 1 kinds of shape parameter(s) (shape = MGW) for a feature model of length 20.
## Shape beta values:
## 1 2 3 4 5
## Shape.MGW -0.05511533 -0.01993296 0.008875318 -0.1162269 -0.002697394
## 6 7 8 9 10 11
## Shape.MGW -0.09556691 0.1172337 0.1463935 0.4806218 -0.3558159 -1.42573
## 12 13 14 15 16 17
## Shape.MGW 1.752843 0.2006908 -0.0232093 0.1456909 0.2055637 -0.0211876
## 18 19 20
## Shape.MGW -0.04238618 0.05896871 -0.06430968
##
## Shape beta errors:
## 1 2 3 4 5
## Shape.MGW 0.002806957 0.003223197 0.002829792 0.002763356 0.002743727
## 6 7 8 9 10
## Shape.MGW 0.002845153 0.005787962 0.008568842 0.007582752 0.02020919
## 11 12 13 14 15
## Shape.MGW 0.03140508 0.01155582 0.003862309 0.003633595 0.002707491
## 16 17 18 19 20
## Shape.MGW 0.002814435 0.002965056 0.003016957 0.003421953 0.002914562
##
## [1] "Number of Observations in Design Matrix: 697770"
## [1] "i = 4"
## [1] "Round summary: "
## 2 Total
## Round 697770 697770
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 56489 168024 263322 209935
## 2 85372 140382 276231 195785
## 3 119140 71998 345142 161490
## 4 131089 90371 341743 134567
## 5 289763 57468 227959 122580
## 6 98118 18086 15757 565809
## 7 170385 1167 459354 66864
## 8 672113 9789 9235 6633
## 9 39369 10804 38101 609496
## 10 41488 7163 8711 640408
## 11 47008 19149 38849 592764
## 12 678559 5651 11422 2138
## 13 8316 104718 12247 572489
## 14 92642 34466 370974 199688
## 15 281534 45731 253910 116595
## 16 85716 315139 148105 148810
## 17 111776 352660 91685 141649
## 18 203751 279283 83759 130977
## 19 164767 256999 169552 106452
## 20 182955 319325 133610 61880
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 43370 75612 69551 58409 57202 57289 66710 428143
## Strand.R 33632 46769 45760 32413 33467 35527 42059 269627
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.C1+N.T1+N.A2+N.C2+N.T2+N.A3+N.C3+N.T3+N.A4+N.C4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.A7+N.C7+N.T7+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.A10+N.C10+N.G10+N.A11+N.C11+N.G11+N.C12+N.G12+N.T12+N.A13+N.C13+N.G13+N.A14+N.C14+N.T14+N.C15+N.G15+N.T15+N.A16+N.G16+N.T16+N.A17+N.G17+N.T17+N.A18+N.G18+N.T18+N.A19+N.G19+N.T19+N.A20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20"
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a R2 Nucleotide+Shape Model
## Slot "varRegLen": 16
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATCTGG
## Slot "rightFixedSeq": CCAGCTGTCGTATGCCGTCTTCTGCTTG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.95
## Slot "minAffinity": 0
## Slot "missingValueSuppression": 1
## Slot "minSeedValue": 0.001
## Slot "seedLen": 12
## Slot "consensusSeq": [ACGT]TGA[CT][ACGT][ACGT]A[CT][ACGT][ACGT][ACGT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 20
##
## Fits a model of footprint length 20 for mono-nucleotide and shape features (shape = MGW) with 7 view(s) per strand of DNA and 1 round(s) of data (round = 2) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+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+N.G12+N.T12+N.A13+N.C13+N.G13+N.T13+N.A14+N.C14+N.G14+N.T14+N.A15+N.C15+N.G15+N.T15+N.A16+N.C16+N.G16+N.T16+N.A17+N.C17+N.G17+N.T17+N.A18+N.C18+N.G18+N.T18+N.A19+N.C19+N.G19+N.T19+N.A20+N.C20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20
##
## Slot "shapeParamsUsed[[1]]": MGW
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 20 nucleotides for a feature model of length 20.
## Nucleotide beta values:
## 1 2 3 4 5
## N.A 0.012776502 0.02264659 -0.004647323 -0.02385512 0.0000000
## N.C -0.008030879 -0.08806749 -0.144561974 -0.13989597 -0.8747420
## N.G 0.000000000 0.00000000 0.000000000 0.00000000 -0.3255616
## N.T -0.095061345 -0.04707393 -0.150384721 -0.02928513 -0.5704149
## 6 7 8 9 10 11
## N.A -0.9549841 -0.255143 0.000000 -1.030202 -0.478055 -0.3012370
## N.C -1.7711888 -2.879014 -2.419229 -2.101402 -1.572153 -0.2170151
## N.G -2.0812580 0.000000 -2.264085 -1.174293 -1.583068 -0.5813464
## N.T 0.0000000 -1.136136 -2.451443 0.000000 0.000000 0.0000000
## 12 13 14 15 16 17
## N.A 0.000000 -1.5051969 -0.65271632 0.0000000 -0.4839734 -0.2966605
## N.C -2.140323 -0.4290305 -0.64725282 -0.9572071 0.0000000 0.0000000
## N.G -1.994335 -1.6741505 0.00000000 -0.1072729 -0.2357775 -0.3320890
## N.T -3.061542 0.0000000 0.02438108 -0.4994464 -0.3060860 -0.1146854
## 18 19 20
## N.A -0.13152955 -0.03504545 -0.04560906
## N.C 0.00000000 0.00000000 0.00000000
## N.G -0.13414399 -0.11279821 -0.07174297
## N.T 0.05413316 0.12749785 0.04471630
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001772879 0.001550539 0.001327644 0.001217217 0.000000000
## N.C 0.001720533 0.001643416 0.001620204 0.001530397 0.002285944
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001295953
## N.T 0.001339601 0.001462087 0.001309844 0.001329570 0.001845319
## 6 7 8 9 10 11
## N.A 0.002980530 0.006785264 0.00000000 0.005126340 0.01083996 0.009792744
## N.C 0.008972891 0.133426583 0.02541682 0.014552561 0.03796720 0.012162726
## N.G 0.011986089 0.000000000 0.02020690 0.005206358 0.02746254 0.010259124
## N.T 0.000000000 0.006587119 0.02708114 0.000000000 0.00000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.019235062 0.001731078 0.0000000000 0.001535690
## N.C 0.05431678 0.004282054 0.003133956 0.0029366980 0.000000000
## N.G 0.02186391 0.012340437 0.000000000 0.0009508814 0.001195069
## N.T 0.08404050 0.000000000 0.002230417 0.0018006997 0.001223803
## 17 18 19 20
## N.A 0.001460306 0.001471552 0.001639206 0.001311320
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001528968 0.001646111 0.001697561 0.001779824
## N.T 0.001188196 0.001349736 0.001536756 0.001823026
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## [1] 23.41884
##
## Intercept beta errors:
## Round.2:
## [1] 0.02271335
##
##
##
## An object of class 'Shape'
## Fits 20 shape coefficients for 1 kinds of shape parameter(s) (shape = MGW) for a feature model of length 20.
## Shape beta values:
## 1 2 3 4 5
## Shape.MGW -0.05506762 -0.01968537 0.008683173 -0.1161283 -0.002834394
## 6 7 8 9 10 11
## Shape.MGW -0.09522785 0.117143 0.1464175 0.4811505 -0.3558083 -1.426013
## 12 13 14 15 16 17
## Shape.MGW 1.753254 0.201283 -0.02304012 0.145302 0.205417 -0.0210041
## 18 19 20
## Shape.MGW -0.04252736 0.05893101 -0.06433716
##
## Shape beta errors:
## 1 2 3 4 5
## Shape.MGW 0.002808571 0.003225623 0.002832017 0.002765359 0.002745584
## 6 7 8 9 10
## Shape.MGW 0.002848689 0.005793769 0.008572253 0.007587244 0.02021872
## 11 12 13 14 15
## Shape.MGW 0.03143309 0.01156429 0.00386651 0.00363618 0.002709255
## 16 17 18 19 20
## Shape.MGW 0.002816233 0.00296657 0.003018063 0.003423154 0.002915597
##
## [1] "Number of Observations in Design Matrix: 697592"
## [1] "i = 5"
## [1] "Round summary: "
## 2 Total
## Round 697592 697592
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 56470 168002 263225 209895
## 2 85343 140343 276153 195753
## 3 119097 71972 345101 161422
## 4 131046 90337 341690 134519
## 5 289655 57461 227910 122566
## 6 98105 18083 15754 565650
## 7 170360 1167 459208 66857
## 8 671946 9787 9226 6633
## 9 39356 10801 38081 609354
## 10 41473 7162 8682 640275
## 11 46983 19146 38837 592626
## 12 678388 5651 11419 2134
## 13 8311 104698 12243 572340
## 14 92600 34448 370909 199635
## 15 281480 45713 253840 116559
## 16 85678 315069 148083 148762
## 17 111749 352571 91661 141611
## 18 203704 279191 83746 130951
## 19 164715 256918 169515 106444
## 20 182901 319254 133569 61868
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 43358 75606 69543 58379 57180 57269 66692 428027
## Strand.R 33628 46762 45756 32407 33452 35511 42049 269565
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.C1+N.T1+N.A2+N.C2+N.T2+N.A3+N.C3+N.T3+N.A4+N.C4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.A7+N.C7+N.T7+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.A10+N.C10+N.G10+N.A11+N.C11+N.G11+N.C12+N.G12+N.T12+N.A13+N.C13+N.G13+N.A14+N.C14+N.T14+N.C15+N.G15+N.T15+N.A16+N.G16+N.T16+N.A17+N.G17+N.T17+N.A18+N.G18+N.T18+N.A19+N.G19+N.T19+N.A20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20"
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a R2 Nucleotide+Shape Model
## Slot "varRegLen": 16
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATCTGG
## Slot "rightFixedSeq": CCAGCTGTCGTATGCCGTCTTCTGCTTG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.95
## Slot "minAffinity": 0
## Slot "missingValueSuppression": 1
## Slot "minSeedValue": 0.001
## Slot "seedLen": 12
## Slot "consensusSeq": [ACGT]TGA[CT][ACGT][ACGT]A[CT][ACGT][ACGT][ACGT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 20
##
## Fits a model of footprint length 20 for mono-nucleotide and shape features (shape = MGW) with 7 view(s) per strand of DNA and 1 round(s) of data (round = 2) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+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+N.G12+N.T12+N.A13+N.C13+N.G13+N.T13+N.A14+N.C14+N.G14+N.T14+N.A15+N.C15+N.G15+N.T15+N.A16+N.C16+N.G16+N.T16+N.A17+N.C17+N.G17+N.T17+N.A18+N.C18+N.G18+N.T18+N.A19+N.C19+N.G19+N.T19+N.A20+N.C20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20
##
## Slot "shapeParamsUsed[[1]]": MGW
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 20 nucleotides for a feature model of length 20.
## Nucleotide beta values:
## 1 2 3 4 5
## N.A 0.012744252 0.02264977 -0.004687214 -0.02386194 0.0000000
## N.C -0.008049514 -0.08811801 -0.144558287 -0.13998282 -0.8747553
## N.G 0.000000000 0.00000000 0.000000000 0.00000000 -0.3255398
## N.T -0.095100729 -0.04712163 -0.150359848 -0.02927223 -0.5704330
## 6 7 8 9 10 11
## N.A -0.9549791 -0.2552831 0.000000 -1.030283 -0.4779833 -0.3010150
## N.C -1.7711825 -2.8790840 -2.419320 -2.101381 -1.5721796 -0.2166494
## N.G -2.0812650 0.0000000 -2.263474 -1.174332 -1.5818781 -0.5812482
## N.T 0.0000000 -1.1361968 -2.451529 0.000000 0.0000000 0.0000000
## 12 13 14 15 16 17
## N.A 0.000000 -1.5055604 -0.65278057 0.0000000 -0.4840297 -0.2966354
## N.C -2.140170 -0.4289966 -0.64711529 -0.9571888 0.0000000 0.0000000
## N.G -1.994141 -1.6741526 0.00000000 -0.1073306 -0.2358088 -0.3320629
## N.T -3.060795 0.0000000 0.02443892 -0.4993938 -0.3060675 -0.1146569
## 18 19 20
## N.A -0.13153263 -0.03503336 -0.04565277
## N.C 0.00000000 0.00000000 0.00000000
## N.G -0.13414479 -0.11277085 -0.07176264
## N.T 0.05416546 0.12748960 0.04472283
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001773103 0.001550715 0.001327758 0.001217286 0.000000000
## N.C 0.001720638 0.001643609 0.001620323 0.001530617 0.002286043
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001296043
## N.T 0.001339694 0.001462189 0.001309998 0.001329608 0.001845423
## 6 7 8 9 10 11
## N.A 0.002980572 0.006785444 0.00000000 0.005126806 0.01083991 0.009793094
## N.C 0.008972890 0.133426480 0.02541694 0.014552585 0.03796722 0.012162462
## N.G 0.011986095 0.000000000 0.02020700 0.005206871 0.02746282 0.010259370
## N.T 0.000000000 0.006587184 0.02708122 0.000000000 0.00000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.019241316 0.001731480 0.0000000000 0.001535832
## N.C 0.05431659 0.004282021 0.003134800 0.0029370363 0.000000000
## N.G 0.02186398 0.012340406 0.000000000 0.0009509743 0.001195134
## N.T 0.08404012 0.000000000 0.002230575 0.0018009052 0.001223867
## 17 18 19 20
## N.A 0.001460375 0.001471590 0.001639244 0.001311411
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001528997 0.001646145 0.001697670 0.001779887
## N.T 0.001188290 0.001349777 0.001536782 0.001823055
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## [1] 23.41875
##
## Intercept beta errors:
## Round.2:
## [1] 0.022714
##
##
##
## An object of class 'Shape'
## Fits 20 shape coefficients for 1 kinds of shape parameter(s) (shape = MGW) for a feature model of length 20.
## Shape beta values:
## 1 2 3 4 5
## Shape.MGW -0.05501172 -0.01972374 0.008743479 -0.1161907 -0.002832508
## 6 7 8 9 10 11
## Shape.MGW -0.09519958 0.1172086 0.1463444 0.4810134 -0.3557753 -1.42591
## 12 13 14 15 16 17
## Shape.MGW 1.753295 0.2013939 -0.0230635 0.145377 0.2052127 -0.02095977
## 18 19 20
## Shape.MGW -0.04252325 0.05899002 -0.06434919
##
## Shape beta errors:
## 1 2 3 4 5
## Shape.MGW 0.002808812 0.003226165 0.002832343 0.002765659 0.002745839
## 6 7 8 9 10
## Shape.MGW 0.002849048 0.005794301 0.00857221 0.007587422 0.02021945
## 11 12 13 14 15
## Shape.MGW 0.03143324 0.01156496 0.003867042 0.003636432 0.002709631
## 16 17 18 19 20
## Shape.MGW 0.002816774 0.002966755 0.003018221 0.003423318 0.002915755
##
## [1] "Number of Observations in Design Matrix: 697588"
## [1] "i = 6"
## [1] "Round summary: "
## 2 Total
## Round 697588 697588
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 56470 168002 263221 209895
## 2 85343 140342 276152 195751
## 3 119095 71971 345101 161421
## 4 131044 90337 341689 134518
## 5 289653 57460 227910 122565
## 6 98105 18083 15753 565647
## 7 170360 1167 459204 66857
## 8 671942 9787 9226 6633
## 9 39355 10801 38080 609352
## 10 41472 7162 8682 640272
## 11 46983 19146 38836 592623
## 12 678384 5651 11419 2134
## 13 8311 104697 12243 572337
## 14 92599 34447 370909 199633
## 15 281478 45713 253839 116558
## 16 85677 315068 148082 148761
## 17 111748 352569 91661 141610
## 18 203704 279187 83746 130951
## 19 164713 256916 169515 106444
## 20 182899 319254 133567 61868
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 43358 75606 69543 58379 57178 57268 66692 428024
## Strand.R 33628 46762 45756 32407 33452 35510 42049 269564
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+N.A1+N.C1+N.T1+N.A2+N.C2+N.T2+N.A3+N.C3+N.T3+N.A4+N.C4+N.T4+N.C5+N.G5+N.T5+N.A6+N.C6+N.G6+N.A7+N.C7+N.T7+N.C8+N.G8+N.T8+N.A9+N.C9+N.G9+N.A10+N.C10+N.G10+N.A11+N.C11+N.G11+N.C12+N.G12+N.T12+N.A13+N.C13+N.G13+N.A14+N.C14+N.T14+N.C15+N.G15+N.T15+N.A16+N.G16+N.T16+N.A17+N.G17+N.T17+N.A18+N.G18+N.T18+N.A19+N.G19+N.T19+N.A20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20"
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a R2 Nucleotide+Shape Model
## Slot "varRegLen": 16
## Slot "leftFixedSeq": GTTCAGAGTTCTACAGTCCGACGATCTGG
## Slot "rightFixedSeq": CCAGCTGTCGTATGCCGTCTTCTGCTTG
## Slot "leftFixedSeqOverlap": 5
## Slot "rightFixedSeqOverlap": 5
## Slot "confidenceLevel": 0.95
## Slot "minAffinity": 0
## Slot "missingValueSuppression": 1
## Slot "minSeedValue": 0.001
## Slot "seedLen": 12
## Slot "consensusSeq": [ACGT]TGA[CT][ACGT][ACGT]A[CT][ACGT][ACGT][ACGT]
## Slot "upFootprintExtend": 4
## Slot "downFootprintExtend": 4
## Slot "fpLen": 20
##
## Fits a model of footprint length 20 for mono-nucleotide and shape features (shape = MGW) with 7 view(s) per strand of DNA and 1 round(s) of data (round = 2) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+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+N.G12+N.T12+N.A13+N.C13+N.G13+N.T13+N.A14+N.C14+N.G14+N.T14+N.A15+N.C15+N.G15+N.T15+N.A16+N.C16+N.G16+N.T16+N.A17+N.C17+N.G17+N.T17+N.A18+N.C18+N.G18+N.T18+N.A19+N.C19+N.G19+N.T19+N.A20+N.C20+N.G20+N.T20+Shape.MGW1+Shape.MGW2+Shape.MGW3+Shape.MGW4+Shape.MGW5+Shape.MGW6+Shape.MGW7+Shape.MGW8+Shape.MGW9+Shape.MGW10+Shape.MGW11+Shape.MGW12+Shape.MGW13+Shape.MGW14+Shape.MGW15+Shape.MGW16+Shape.MGW17+Shape.MGW18+Shape.MGW19+Shape.MGW20
##
## Slot "shapeParamsUsed[[1]]": MGW
##
## Includes the following feature sub-classes:
## An object of class 'N'
## Fits 20 nucleotides for a feature model of length 20.
## Nucleotide beta values:
## 1 2 3 4 5 6
## N.A 0.012749371 0.02265232 -0.004690446 -0.02386412 0.0000000 -0.954981
## N.C -0.008045092 -0.08811580 -0.144557317 -0.13998251 -0.8747618 -1.771183
## N.G 0.000000000 0.00000000 0.000000000 0.00000000 -0.3255396 -2.081266
## N.T -0.095097533 -0.04712206 -0.150360767 -0.02927159 -0.5704319 0.000000
## 7 8 9 10 11 12
## N.A -0.2552734 0.000000 -1.030320 -0.4779673 -0.3010071 0.000000
## N.C -2.8790823 -2.419330 -2.101380 -1.5721828 -0.2166363 -2.140170
## N.G 0.0000000 -2.263476 -1.174324 -1.5818709 -0.5812401 -1.994155
## N.T -1.1361888 -2.451536 0.000000 0.0000000 0.0000000 -3.060783
## 13 14 15 16 17 18
## N.A -1.5055499 -0.65277823 0.0000000 -0.4840297 -0.2966344 -0.13153316
## N.C -0.4289946 -0.64712599 -0.9571887 0.0000000 0.0000000 0.00000000
## N.G -1.6741458 0.00000000 -0.1073322 -0.2358106 -0.3320626 -0.13414525
## N.T 0.0000000 0.02443775 -0.4993964 -0.3060694 -0.1146565 0.05416547
## 19 20
## N.A -0.03503763 -0.04565314
## N.C 0.00000000 0.00000000
## N.G -0.11277470 -0.07176628
## N.T 0.12748637 0.04472113
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001773108 0.001550718 0.001327762 0.001217289 0.000000000
## N.C 0.001720641 0.001643620 0.001620334 0.001530617 0.002286060
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001296044
## N.T 0.001339697 0.001462193 0.001309999 0.001329610 0.001845431
## 6 7 8 9 10 11
## N.A 0.002980572 0.006785453 0.00000000 0.005127084 0.01083988 0.009793102
## N.C 0.008972890 0.133426466 0.02541695 0.014552584 0.03796723 0.012162462
## N.G 0.011986095 0.000000000 0.02020700 0.005206883 0.02746280 0.010259377
## N.T 0.000000000 0.006587194 0.02708123 0.000000000 0.00000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.019241294 0.001731498 0.0000000000 0.001535832
## N.C 0.05431656 0.004282012 0.003134826 0.0029370362 0.000000000
## N.G 0.02186398 0.012340396 0.000000000 0.0009509777 0.001195135
## N.T 0.08404003 0.000000000 0.002230575 0.0018009071 0.001223869
## 17 18 19 20
## N.A 0.001460380 0.001471591 0.001639246 0.001311411
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001528998 0.001646146 0.001697672 0.001779890
## N.T 0.001188291 0.001349777 0.001536783 0.001823055
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## [1] 23.41874
##
## Intercept beta errors:
## Round.2:
## [1] 0.02271399
##
##
##
## An object of class 'Shape'
## Fits 20 shape coefficients for 1 kinds of shape parameter(s) (shape = MGW) for a feature model of length 20.
## Shape beta values:
## 1 2 3 4 5
## Shape.MGW -0.05501243 -0.01972045 0.008743257 -0.1161918 -0.002832891
## 6 7 8 9 10 11
## Shape.MGW -0.09519731 0.1172034 0.1463412 0.4810231 -0.3558136 -1.425888
## 12 13 14 15 16 17
## Shape.MGW 1.753294 0.2013958 -0.02306705 0.1453743 0.2052172 -0.020963
## 18 19 20
## Shape.MGW -0.04252105 0.05898847 -0.06434858
##
## Shape beta errors:
## 1 2 3 4 5
## Shape.MGW 0.002808814 0.003226174 0.002832358 0.002765664 0.002745845
## 6 7 8 9 10
## Shape.MGW 0.002849073 0.00579433 0.008572195 0.007587426 0.02021954
## 11 12 13 14 15
## Shape.MGW 0.03143318 0.01156496 0.003867044 0.003636436 0.002709638
## 16 17 18 19 20
## Shape.MGW 0.002816778 0.002966763 0.003018227 0.003423319 0.002915755
##
## [1] "Number of Observations in Design Matrix: 697588"
## [1] "Stability Reached after 6 iterations."
ModelTest <- finalizeFeatureBetas(ModelTest)
pM <- plot(ModelTest, plotTitle = "HM-Ubx4a-Exd R2 Nucleotide+Shape 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 = ""))