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/MultiRoundNoSymmetry"
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)
dataSample.R3 = selex.sample(seqName = 'Ubx4a.R3', sampleName = 'HM.Ubx4a.Exd', round = 3)
# 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 = ""))
#data.probeCounts.R3 = getProbeCounts(dataSample.R3, markovModel = mm)
#save(data.probeCounts.R3, file = paste(selexDir, saveDir, "/data.probeCounts.R3.RData", sep = ""))
load(file = paste(selexDir, saveDir, "/data.probeCounts.R3.RData", sep = ""))
# Inputs about library are data specific
ModelTest = model(name = "HM-Exd-Ubx4a Nucleotides, no-symmetry",
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,
rounds = list(c(2, 3)),
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: 2 (2, 3)
## 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 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+R3 Nucleotide Features\nSeeding Model", ddG = TRUE)
Next we score the probes using topModelMatch
sample1 = sample(nrow(data.probeCounts), 500000)
sample2 = sample(nrow(data.probeCounts.R3), 500000)
data = rbind(data.probeCounts[sample1, ], data.probeCounts.R3[sample2,])
#data = rbind(data.probeCounts, data.probeCounts.R3)
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$Round)
## 2 3 Total
## Round 396683 464232 860915
print("Mono-nucleotide summary: ")
## [1] "Mono-nucleotide summary: "
print (designMatrixSummary$N)
## N.A N.C N.G N.T
## 1 75514 199560 331991 253850
## 2 109766 175597 336439 239113
## 3 152429 93842 402970 211674
## 4 164680 116601 406719 172915
## 5 370370 62988 283365 144192
## 6 104337 21721 19442 715415
## 7 178377 2204 608470 71864
## 8 817832 12445 16700 13938
## 9 42398 16410 42530 759577
## 10 39374 9509 12299 799733
## 11 58362 13341 57417 731795
## 12 836448 5746 13577 5144
## 13 12814 102058 16011 730032
## 14 104690 48171 432746 275308
## 15 371861 49744 303128 136182
## 16 104105 397717 170797 188296
## 17 134102 442813 107989 176011
## 18 256044 349553 98378 156940
## 19 207001 315441 214664 123809
## 20 230394 388305 167856 74360
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 StrandTotal
## Strand.F 53789 87849 80579 73852 75038 75639 89305 536051
## Strand.R 39171 55063 50947 39661 41036 43935 55051 324864
# # 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)+Round.2+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"
fit = glm(regressionFormula,
data=data,
family = poisson(link="log"))
## Warning: glm.fit: fitted rates numerically 0 occurred
summary(fit)
##
## Call:
## glm(formula = regressionFormula, family = poisson(link = "log"),
## data = data)
##
## Deviance Residuals:
## Min 1Q Median 3Q Max
## -14.8689 -0.9578 -0.3368 0.2486 17.1536
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 26.1781175 0.0036421 7187.733 <2e-16 ***
## Round.2 -0.9313470 0.0017918 -519.778 <2e-16 ***
## N.A1 0.0262916 0.0010918 24.081 <2e-16 ***
## N.C1 0.0098712 0.0010120 9.754 <2e-16 ***
## N.T1 -0.0445393 0.0008265 -53.891 <2e-16 ***
## N.A2 0.0351747 0.0009274 37.928 <2e-16 ***
## N.C2 -0.0660371 0.0009651 -68.425 <2e-16 ***
## N.T2 -0.0421010 0.0008675 -48.533 <2e-16 ***
## N.A3 0.0216562 0.0007838 27.629 <2e-16 ***
## N.C3 -0.1224932 0.0009861 -124.218 <2e-16 ***
## N.T3 -0.1161729 0.0007926 -146.573 <2e-16 ***
## N.A4 0.0125909 0.0007427 16.953 <2e-16 ***
## N.C4 -0.1573905 0.0009365 -168.064 <2e-16 ***
## N.T4 -0.0706402 0.0007565 -93.376 <2e-16 ***
## N.C5 -0.7895035 0.0016076 -491.108 <2e-16 ***
## N.G5 -0.2883261 0.0006572 -438.714 <2e-16 ***
## N.T5 -0.4217330 0.0007443 -566.637 <2e-16 ***
## N.A6 -0.8695684 0.0014589 -596.047 <2e-16 ***
## N.C6 -1.6116968 0.0080345 -200.598 <2e-16 ***
## N.G6 -1.8783556 0.0122525 -153.304 <2e-16 ***
## N.A7 -0.6403078 0.0008225 -778.487 <2e-16 ***
## N.C7 -2.4817627 0.0739364 -33.566 <2e-16 ***
## N.T7 -1.1240562 0.0018239 -616.288 <2e-16 ***
## N.C8 -2.1709242 0.0228325 -95.080 <2e-16 ***
## N.G8 -2.0425258 0.0158577 -128.803 <2e-16 ***
## N.T8 -2.1640586 0.0168431 -128.484 <2e-16 ***
## N.A9 -1.2868781 0.0037114 -346.739 <2e-16 ***
## N.C9 -1.7931551 0.0124522 -144.003 <2e-16 ***
## N.G9 -1.2744780 0.0035761 -356.385 <2e-16 ***
## N.A10 -1.4297831 0.0042796 -334.090 <2e-16 ***
## N.C10 -2.0749872 0.0252099 -82.308 <2e-16 ***
## N.G10 -1.9616505 0.0210470 -93.203 <2e-16 ***
## N.A11 -1.0231291 0.0020594 -496.814 <2e-16 ***
## N.C11 -1.3538228 0.0093079 -145.449 <2e-16 ***
## N.G11 -0.9793158 0.0021775 -449.738 <2e-16 ***
## N.C12 -2.4345865 0.0513663 -47.397 <2e-16 ***
## N.G12 -2.0576933 0.0180386 -114.072 <2e-16 ***
## N.T12 -2.3525643 0.0382507 -61.504 <2e-16 ***
## N.A13 -1.8329160 0.0124866 -146.791 <2e-16 ***
## N.C13 -0.5625691 0.0011216 -501.563 <2e-16 ***
## N.G13 -1.6578347 0.0097312 -170.362 <2e-16 ***
## N.A14 -0.6294627 0.0011123 -565.906 <2e-16 ***
## N.C14 -0.7798483 0.0017850 -436.899 <2e-16 ***
## N.T14 -0.1479848 0.0005425 -272.766 <2e-16 ***
## N.C15 -0.9023721 0.0021536 -419.008 <2e-16 ***
## N.G15 -0.1182600 0.0005599 -211.212 <2e-16 ***
## N.T15 -0.5146147 0.0008720 -590.126 <2e-16 ***
## N.A16 -0.4537721 0.0009930 -456.962 <2e-16 ***
## N.G16 -0.2166355 0.0007381 -293.518 <2e-16 ***
## N.T16 -0.2559818 0.0007003 -365.550 <2e-16 ***
## N.A17 -0.1760533 0.0008456 -208.209 <2e-16 ***
## N.G17 -0.2436129 0.0009636 -252.808 <2e-16 ***
## N.T17 -0.0756030 0.0007380 -102.443 <2e-16 ***
## N.A18 -0.1075614 0.0008981 -119.769 <2e-16 ***
## N.G18 -0.0940778 0.0010222 -92.034 <2e-16 ***
## N.T18 0.0643701 0.0008196 78.534 <2e-16 ***
## N.A19 -0.0514118 0.0010067 -51.070 <2e-16 ***
## N.G19 -0.1200973 0.0010110 -118.794 <2e-16 ***
## N.T19 0.1058977 0.0009521 111.222 <2e-16 ***
## N.A20 -0.0174591 0.0008012 -21.790 <2e-16 ***
## N.G20 -0.0668591 0.0010975 -60.920 <2e-16 ***
## N.T20 0.0685072 0.0011186 61.243 <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: 6054923 on 860914 degrees of freedom
## Residual deviance: 1457917 on 860853 degrees of freedom
## AIC: 2656353
##
## Number of Fisher Scoring iterations: 9
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": HM-Exd-Ubx4a Nucleotides, no-symmetry
## 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 features with 7 view(s) per strand of DNA and 2 round(s) of data (round = 2, 3) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+Round.3+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
##
##
## 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 0.026291559 0.03517468 0.02165625 0.01259090 0.0000000 -0.8695684
## N.C 0.009871185 -0.06603707 -0.12249317 -0.15739051 -0.7895035 -1.6116968
## N.G 0.000000000 0.00000000 0.00000000 0.00000000 -0.2883261 -1.8783556
## N.T -0.044539268 -0.04210096 -0.11617291 -0.07064019 -0.4217330 0.0000000
## 7 8 9 10 11 12
## N.A -0.6403078 0.000000 -1.286878 -1.429783 -1.0231291 0.000000
## N.C -2.4817627 -2.170924 -1.793155 -2.074987 -1.3538228 -2.434586
## N.G 0.0000000 -2.042526 -1.274478 -1.961650 -0.9793158 -2.057693
## N.T -1.1240562 -2.164059 0.000000 0.000000 0.0000000 -2.352564
## 13 14 15 16 17 18
## N.A -1.8329160 -0.6294627 0.0000000 -0.4537721 -0.17605331 -0.10756141
## N.C -0.5625691 -0.7798483 -0.9023721 0.0000000 0.00000000 0.00000000
## N.G -1.6578347 0.0000000 -0.1182600 -0.2166355 -0.24361292 -0.09407783
## N.T 0.0000000 -0.1479848 -0.5146147 -0.2559818 -0.07560298 0.06437008
## 19 20
## N.A -0.05141179 -0.01745912
## N.C 0.00000000 0.00000000
## N.G -0.12009729 -0.06685912
## N.T 0.10589767 0.06850716
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.0010918055 0.0009274159 0.0007838279 0.0007427130 0.0000000000
## N.C 0.0010119973 0.0009651061 0.0009861179 0.0009364935 0.0016075966
## N.G 0.0000000000 0.0000000000 0.0000000000 0.0000000000 0.0006572079
## N.T 0.0008264673 0.0008674770 0.0007925964 0.0007565134 0.0007442741
## 6 7 8 9 10
## N.A 0.001458893 0.0008225027 0.00000000 0.003711375 0.004279632
## N.C 0.008034476 0.0739363690 0.02283253 0.012452179 0.025209940
## N.G 0.012252479 0.0000000000 0.01585771 0.003576129 0.021047000
## N.T 0.000000000 0.0018239152 0.01684305 0.000000000 0.000000000
## 11 12 13 14 15
## N.A 0.002059382 0.00000000 0.012486554 0.001112309 0.0000000000
## N.C 0.009307872 0.05136626 0.001121633 0.001784961 0.0021535909
## N.G 0.002177525 0.01803857 0.009731224 0.000000000 0.0005599107
## N.T 0.000000000 0.03825068 0.000000000 0.000542534 0.0008720417
## 16 17 18 19 20
## N.A 0.0009930186 0.0008455614 0.0008980725 0.0010066892 0.0008012335
## N.C 0.0000000000 0.0000000000 0.0000000000 0.0000000000 0.0000000000
## N.G 0.0007380663 0.0009636300 0.0010222086 0.0010109682 0.0010974963
## N.T 0.0007002639 0.0007380020 0.0008196440 0.0009521272 0.0011186067
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 2 round(s) (round = 2, 3).
## Intercept beta values:
## Round.2:
## [1] 25.24677
##
## Round.3:
## [1] 26.17812
##
## Intercept beta errors:
## Round.2:
## [1] 0.004058962
##
## Round.3:
## [1] 0.003642055
##
##
##
## An object of class 'Shape'
## Fits 0 shape coefficients for 0 kinds of shape parameter(s) (shape = ) for a feature model of length 20.
vPheight = verticalPlot_height(ModelTest)
pM <- plot(ModelTest, plotTitle = "HM-Ubx4a-Exd R2+R3 Nucleotide 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 = rbind(data.probeCounts[sample1, ], data.probeCounts.R3[sample2,])
#data = rbind(data.probeCounts, data.probeCounts.R3)
data.nrow = nrow(data)
data = topModelMatch(data, ModelTest)
data = addDesignMatrix(data, ModelTest)
designMatrixSummary.v2 = getDesignMatrix(ModelTest, data)
## No shape parameters included in fit.
if ((all(designMatrixSummary.v2$N == designMatrixSummary$N)) & (all(designMatrixSummary.v2$Round == designMatrixSummary$Round)) & (all(designMatrixSummary.v2$Intercept == designMatrixSummary$Intercept))) {
print ("Stability Reached")
}
for (i in 2:20) {
if (data.nrow == nrow(data)) {
break
}
data.nrow = nrow(data)
print (paste("i =",i))
designMatrixSummary = getDesignMatrix(ModelTest, data)
print("Round summary: ")
print (designMatrixSummary$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+R3 Nucleotide 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 = ""))
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 if (nrow(data) == 0) {
print ("Algorithm failed to converge: No probes meet the confidence level requirement (Confidence Level:", ModelTest@confidenceLevel, ")", sep = "")
}
}
## [1] "i = 2"
## No shape parameters included in fit.
## [1] "Round summary: "
## 2 3 Total
## Round 376135 459421 835556
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 71695 195972 321251 246638
## 2 106256 168658 328628 232014
## 3 147299 91129 394391 202737
## 4 161263 110880 395912 167501
## 5 364017 60987 270929 139623
## 6 96120 20308 16193 702935
## 7 170749 2055 593859 68893
## 8 797615 10810 13878 13253
## 9 33873 13204 36996 751483
## 10 32935 7636 10374 784611
## 11 50944 12935 54870 716807
## 12 811724 6067 11703 6062
## 13 9763 105641 12596 707556
## 14 103041 47347 427750 257418
## 15 356268 50021 291393 137874
## 16 101177 384031 170438 179910
## 17 130537 428812 104595 171612
## 18 246002 339076 95444 155034
## 19 200003 307380 206063 122110
## 20 222762 378156 162245 72393
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 51639 86606 79318 72492 72830 73074 85115 521074
## Strand.R 37567 54008 50073 38639 39591 42133 52471 314482
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+Round.2+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"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a Nucleotides, no-symmetry
## 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 features with 7 view(s) per strand of DNA and 2 round(s) of data (round = 2, 3) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+Round.3+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
##
##
## 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 0.026462679 0.03527034 0.02155505 0.01214840 0.0000000 -0.8692177
## N.C 0.009519406 -0.06576296 -0.12296153 -0.15703815 -0.7892678 -1.6119673
## N.G 0.000000000 0.00000000 0.00000000 0.00000000 -0.2877967 -1.8911188
## N.T -0.044519232 -0.04153710 -0.11645340 -0.07045342 -0.4211381 0.0000000
## 7 8 9 10 11 12
## N.A -0.6407228 0.000000 -1.275271 -1.429216 -1.0150900 0.000000
## N.C -2.5778524 -2.183092 -1.799039 -2.110501 -1.3398638 -2.409188
## N.G 0.0000000 -2.071588 -1.275309 -1.979032 -0.9801195 -2.066346
## N.T -1.1250503 -2.165210 0.000000 0.000000 0.0000000 -2.352951
## 13 14 15 16 17 18
## N.A -1.844328 -0.6286418 0.0000000 -0.4533564 -0.17615502 -0.10761165
## N.C -0.562126 -0.7804193 -0.9016697 0.0000000 0.00000000 0.00000000
## N.G -1.655499 0.0000000 -0.1185571 -0.2165623 -0.24349059 -0.09449161
## N.T 0.000000 -0.1474689 -0.5139725 -0.2557485 -0.07540824 0.06422439
## 19 20
## N.A -0.05099609 -0.01757505
## N.C 0.00000000 0.00000000
## N.G -0.11972047 -0.06719864
## N.T 0.10597301 0.06808539
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.0010934728 0.0009278856 0.0007843290 0.0007428868 0.0000000000
## N.C 0.0010127430 0.0009662239 0.0009862563 0.0009386911 0.0016084496
## N.G 0.0000000000 0.0000000000 0.0000000000 0.0000000000 0.0006579489
## N.T 0.0008272209 0.0008683590 0.0007927631 0.0007566550 0.0007447128
## 6 7 8 9 10
## N.A 0.001461370 0.0008220558 0.00000000 0.003886721 0.004389374
## N.C 0.008019163 0.0823858904 0.02322770 0.012711780 0.026648347
## N.G 0.012588822 0.0000000000 0.01665974 0.003593546 0.021882235
## N.T 0.000000000 0.0018246082 0.01684335 0.000000000 0.000000000
## 11 12 13 14 15
## N.A 0.002080612 0.00000000 0.012783386 0.0011117964 0.0000000000
## N.C 0.009122609 0.04950916 0.001116705 0.0017819469 0.0021486843
## N.G 0.002180945 0.01831873 0.009781631 0.0000000000 0.0005604478
## N.T 0.000000000 0.03707909 0.000000000 0.0005432739 0.0008703152
## 16 17 18 19 20
## N.A 0.0009930684 0.0008458215 0.0008982657 0.0010071903 0.0008017088
## N.C 0.0000000000 0.0000000000 0.0000000000 0.0000000000 0.0000000000
## N.G 0.0007375597 0.0009640844 0.0010228516 0.0010114224 0.0010980458
## N.T 0.0007011001 0.0007379849 0.0008195246 0.0009525917 0.0011190661
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 2 round(s) (round = 2, 3).
## Intercept beta values:
## Round.2:
## [1] 25.24721
##
## Round.3:
## [1] 26.17594
##
## Intercept beta errors:
## Round.2:
## [1] 0.004062728
##
## Round.3:
## [1] 0.003644745
##
##
##
## An object of class 'Shape'
## Fits 0 shape coefficients for 0 kinds of shape parameter(s) (shape = ) for a feature model of length 20.
## [1] "Number of Observations in Design Matrix: 834539"
## No shape parameters included in fit.
## [1] "i = 3"
## No shape parameters included in fit.
## [1] "Round summary: "
## 2 3 Total
## Round 375487 459052 834539
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 71574 195802 320770 246393
## 2 106106 168480 328165 231788
## 3 147095 90975 394036 202433
## 4 160971 110682 395573 167313
## 5 363452 60927 270645 139515
## 6 96030 20275 16092 702142
## 7 170374 1878 593554 68733
## 8 796826 10760 13734 13219
## 9 33833 13134 36922 750650
## 10 32917 7553 10295 783774
## 11 50908 12909 54796 715926
## 12 810788 6062 11656 6033
## 13 9701 105520 12557 706761
## 14 102859 47250 427437 256993
## 15 355830 49921 291097 137691
## 16 101034 383534 170272 179699
## 17 130402 428256 104478 171403
## 18 245698 338605 95356 154880
## 19 199767 306936 205823 122013
## 20 222458 377704 162044 72333
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 51591 86532 79248 72385 72704 72981 84991 520432
## Strand.R 37542 53980 50031 38571 39522 42061 52400 314107
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+Round.2+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"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a Nucleotides, no-symmetry
## 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 features with 7 view(s) per strand of DNA and 2 round(s) of data (round = 2, 3) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+Round.3+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
##
##
## 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 0.026482751 0.03526733 0.02155224 0.01220516 0.0000000 -0.8692458
## N.C 0.009540026 -0.06575718 -0.12290849 -0.15706252 -0.7892854 -1.6119281
## N.G 0.000000000 0.00000000 0.00000000 0.00000000 -0.2878248 -1.8916493
## N.T -0.044522030 -0.04155492 -0.11642683 -0.07045358 -0.4211542 0.0000000
## 7 8 9 10 11 12
## N.A -0.6406178 0.000000 -1.275095 -1.429243 -1.0150920 0.000000
## N.C -2.7238745 -2.183898 -1.798782 -2.112268 -1.3392841 -2.409205
## N.G 0.0000000 -2.075230 -1.275289 -1.977448 -0.9801764 -2.066809
## N.T -1.1249311 -2.166724 0.000000 0.000000 0.0000000 -2.351845
## 13 14 15 16 17 18
## N.A -1.8436289 -0.6285929 0.0000000 -0.4533057 -0.17612835 -0.10762155
## N.C -0.5621454 -0.7803760 -0.9016096 0.0000000 0.00000000 0.00000000
## N.G -1.6554351 0.0000000 -0.1185660 -0.2165527 -0.24347690 -0.09448428
## N.T 0.0000000 -0.1474546 -0.5139782 -0.2557464 -0.07539279 0.06420238
## 19 20
## N.A -0.05098977 -0.01757241
## N.C 0.00000000 0.00000000
## N.G -0.11970212 -0.06719989
## N.T 0.10598369 0.06808189
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001093592 0.0009279777 0.0007843706 0.0007429232 0.0000000000
## N.C 0.001012789 0.0009663028 0.0009863507 0.0009388670 0.0016084919
## N.G 0.000000000 0.0000000000 0.0000000000 0.0000000000 0.0006579925
## N.T 0.000827259 0.0008684325 0.0007928539 0.0007566812 0.0007447274
## 6 7 8 9 10
## N.A 0.001461428 0.0008223808 0.00000000 0.003886614 0.004389408
## N.C 0.008019209 0.1027989951 0.02325549 0.012725807 0.026793579
## N.G 0.012601787 0.0000000000 0.01676857 0.003593536 0.021877725
## N.T 0.000000000 0.0018248430 0.01687583 0.000000000 0.000000000
## 11 12 13 14 15
## N.A 0.002080641 0.00000000 0.012782155 0.0011119416 0.0000000000
## N.C 0.009123106 0.04950935 0.001116796 0.0017822713 0.0021488610
## N.G 0.002181160 0.01833241 0.009781578 0.0000000000 0.0005604787
## N.T 0.000000000 0.03707370 0.000000000 0.0005433037 0.0008703847
## 16 17 18 19 20
## N.A 0.0009931400 0.0008458524 0.0008982889 0.0010072109 0.0008017673
## N.C 0.0000000000 0.0000000000 0.0000000000 0.0000000000 0.0000000000
## N.G 0.0007375892 0.0009641565 0.0010228817 0.0010114513 0.0010980725
## N.T 0.0007011471 0.0007380176 0.0008195583 0.0009526087 0.0011190928
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 2 round(s) (round = 2, 3).
## Intercept beta values:
## Round.2:
## [1] 25.24724
##
## Round.3:
## [1] 26.17581
##
## Intercept beta errors:
## Round.2:
## [1] 0.004062956
##
## Round.3:
## [1] 0.003644913
##
##
##
## An object of class 'Shape'
## Fits 0 shape coefficients for 0 kinds of shape parameter(s) (shape = ) for a feature model of length 20.
## [1] "Number of Observations in Design Matrix: 834279"
## No shape parameters included in fit.
## [1] "i = 4"
## No shape parameters included in fit.
## [1] "Round summary: "
## 2 3 Total
## Round 375341 458938 834279
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 71554 195751 320659 246315
## 2 106087 168428 328048 231716
## 3 147049 90956 393904 202370
## 4 160925 110656 395444 167254
## 5 363338 60905 270562 139474
## 6 95979 20269 16083 701948
## 7 170364 1653 593537 68725
## 8 796626 10745 13708 13200
## 9 33807 13123 36901 750448
## 10 32914 7546 10291 783528
## 11 50900 12893 54767 715719
## 12 810559 6053 11641 6026
## 13 9695 105458 12547 706579
## 14 102832 47230 427304 256913
## 15 355750 49897 290980 137652
## 16 101002 383418 170204 179655
## 17 130335 428148 104445 171351
## 18 245616 338512 95324 154827
## 19 199719 306824 205770 121966
## 20 222384 377570 162011 72314
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 51577 86508 79219 72357 72670 72965 84974 520270
## Strand.R 37527 53961 50006 38558 39517 42054 52386 314009
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+Round.2+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"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a Nucleotides, no-symmetry
## 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 features with 7 view(s) per strand of DNA and 2 round(s) of data (round = 2, 3) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+Round.3+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
##
##
## 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 0.026482189 0.03526756 0.02155358 0.01220696 0.0000000 -0.8692467
## N.C 0.009538379 -0.06575797 -0.12290828 -0.15706183 -0.7892861 -1.6119300
## N.G 0.000000000 0.00000000 0.00000000 0.00000000 -0.2878242 -1.8916495
## N.T -0.044522679 -0.04155334 -0.11642779 -0.07045319 -0.4211544 0.0000000
## 7 8 9 10 11 12
## N.A -0.6406199 0.000000 -1.275110 -1.429245 -1.0150935 0.000000
## N.C -2.7257488 -2.183885 -1.798784 -2.112074 -1.3392859 -2.409205
## N.G 0.0000000 -2.076382 -1.275316 -1.977451 -0.9801776 -2.066354
## N.T -1.1249374 -2.166720 0.000000 0.000000 0.0000000 -2.351845
## 13 14 15 16 17 18
## N.A -1.843629 -0.6285941 0.0000000 -0.4533064 -0.17612721 -0.10762321
## N.C -0.562148 -0.7803892 -0.9016109 0.0000000 0.00000000 0.00000000
## N.G -1.655437 0.0000000 -0.1185666 -0.2165528 -0.24347740 -0.09448532
## N.T 0.000000 -0.1474551 -0.5139788 -0.2557481 -0.07539191 0.06420289
## 19 20
## N.A -0.05098894 -0.01757234
## N.C 0.00000000 0.00000000
## N.G -0.11969939 -0.06719835
## N.T 0.10598625 0.06808155
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.0010935925 0.0009279781 0.0007843717 0.0007429238 0.0000000000
## N.C 0.0010127902 0.0009663038 0.0009863511 0.0009388686 0.0016084920
## N.G 0.0000000000 0.0000000000 0.0000000000 0.0000000000 0.0006579925
## N.T 0.0008272603 0.0008684330 0.0007928551 0.0007566820 0.0007447276
## 6 7 8 9 10
## N.A 0.001461428 0.0008223838 0.00000000 0.003886868 0.004389409
## N.C 0.008019211 0.1078810584 0.02325545 0.012725810 0.026792553
## N.G 0.012601786 0.0000000000 0.01679552 0.003593650 0.021877729
## N.T 0.000000000 0.0018248568 0.01687581 0.000000000 0.000000000
## 11 12 13 14 15
## N.A 0.002080641 0.00000000 0.012782153 0.0011119417 0.0000000000
## N.C 0.009123107 0.04950934 0.001116799 0.0017822987 0.0021488611
## N.G 0.002181160 0.01833106 0.009781580 0.0000000000 0.0005604796
## N.T 0.000000000 0.03707370 0.000000000 0.0005433043 0.0008703847
## 16 17 18 19 20
## N.A 0.0009931400 0.0008458528 0.0008982906 0.0010072127 0.000801769
## N.C 0.0000000000 0.0000000000 0.0000000000 0.0000000000 0.000000000
## N.G 0.0007375898 0.0009641581 0.0010228836 0.0010114523 0.001098073
## N.T 0.0007011484 0.0007380189 0.0008195591 0.0009526098 0.001119095
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 2 round(s) (round = 2, 3).
## Intercept beta values:
## Round.2:
## [1] 25.24724
##
## Round.3:
## [1] 26.17581
##
## Intercept beta errors:
## Round.2:
## [1] 0.004062965
##
## Round.3:
## [1] 0.003644921
##
##
##
## An object of class 'Shape'
## Fits 0 shape coefficients for 0 kinds of shape parameter(s) (shape = ) for a feature model of length 20.
## [1] "Number of Observations in Design Matrix: 834273"
## No shape parameters included in fit.
## [1] "i = 5"
## No shape parameters included in fit.
## [1] "Round summary: "
## 2 3 Total
## Round 375338 458935 834273
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 71553 195750 320658 246312
## 2 106085 168427 328045 231716
## 3 147048 90956 393902 202367
## 4 160924 110655 395441 167253
## 5 363335 60905 270560 139473
## 6 95978 20269 16083 701943
## 7 170364 1650 593534 68725
## 8 796624 10745 13706 13198
## 9 33806 13122 36901 750444
## 10 32914 7546 10290 783523
## 11 50900 12892 54766 715715
## 12 810553 6053 11641 6026
## 13 9695 105455 12547 706576
## 14 102831 47229 427300 256913
## 15 355748 49896 290980 137649
## 16 101002 383415 170203 179653
## 17 130334 428143 104445 171351
## 18 245612 338510 95324 154827
## 19 199715 306823 205769 121966
## 20 222382 377568 162009 72314
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 51577 86508 79217 72357 72670 72963 84974 520266
## Strand.R 37526 53961 50006 38558 39517 42054 52385 314007
## [1] "Regression Formula: "
## [1] "ObservedCount ~ offset(logProb)+Round.2+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"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a Nucleotides, no-symmetry
## 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 features with 7 view(s) per strand of DNA and 2 round(s) of data (round = 2, 3) without reverse complement symmetry.
##
## Slot "regressionFormula": ObservedCount ~ offset(logProb)+Round.2+Round.3+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
##
##
## 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 0.026482206 0.03526757 0.02155358 0.01220695 0.0000000 -0.8692467
## N.C 0.009538382 -0.06575798 -0.12290828 -0.15706184 -0.7892861 -1.6119300
## N.G 0.000000000 0.00000000 0.00000000 0.00000000 -0.2878242 -1.8916495
## N.T -0.044522677 -0.04155334 -0.11642778 -0.07045320 -0.4211544 0.0000000
## 7 8 9 10 11 12
## N.A -0.6406199 0.000000 -1.275110 -1.429245 -1.0150935 0.000000
## N.C -2.7257049 -2.183885 -1.798784 -2.112074 -1.3392859 -2.409205
## N.G 0.0000000 -2.076374 -1.275316 -1.977451 -0.9801776 -2.066354
## N.T -1.1249374 -2.166720 0.000000 0.000000 0.0000000 -2.351845
## 13 14 15 16 17 18
## N.A -1.843629 -0.6285941 0.0000000 -0.4533064 -0.17612721 -0.10762320
## N.C -0.562148 -0.7803892 -0.9016109 0.0000000 0.00000000 0.00000000
## N.G -1.655437 0.0000000 -0.1185666 -0.2165528 -0.24347740 -0.09448531
## N.T 0.000000 -0.1474551 -0.5139788 -0.2557481 -0.07539191 0.06420289
## 19 20
## N.A -0.05098894 -0.01757233
## N.C 0.00000000 0.00000000
## N.G -0.11969939 -0.06719835
## N.T 0.10598625 0.06808155
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.0010935925 0.0009279781 0.0007843717 0.0007429238 0.0000000000
## N.C 0.0010127902 0.0009663038 0.0009863511 0.0009388686 0.0016084920
## N.G 0.0000000000 0.0000000000 0.0000000000 0.0000000000 0.0006579925
## N.T 0.0008272603 0.0008684330 0.0007928551 0.0007566820 0.0007447276
## 6 7 8 9 10
## N.A 0.001461428 0.0008223838 0.00000000 0.003886868 0.004389409
## N.C 0.008019211 0.1078828928 0.02325545 0.012725810 0.026792553
## N.G 0.012601786 0.0000000000 0.01679550 0.003593650 0.021877729
## N.T 0.000000000 0.0018248568 0.01687581 0.000000000 0.000000000
## 11 12 13 14 15
## N.A 0.002080641 0.00000000 0.012782153 0.0011119417 0.0000000000
## N.C 0.009123107 0.04950934 0.001116799 0.0017822987 0.0021488611
## N.G 0.002181160 0.01833106 0.009781580 0.0000000000 0.0005604796
## N.T 0.000000000 0.03707370 0.000000000 0.0005433043 0.0008703847
## 16 17 18 19 20
## N.A 0.0009931400 0.0008458528 0.0008982906 0.0010072127 0.000801769
## N.C 0.0000000000 0.0000000000 0.0000000000 0.0000000000 0.000000000
## N.G 0.0007375898 0.0009641581 0.0010228836 0.0010114523 0.001098073
## N.T 0.0007011484 0.0007380189 0.0008195591 0.0009526098 0.001119095
##
##
## An object of class 'Intercept'
## Fits intercept(s) for 2 round(s) (round = 2, 3).
## Intercept beta values:
## Round.2:
## [1] 25.24724
##
## Round.3:
## [1] 26.17581
##
## Intercept beta errors:
## Round.2:
## [1] 0.004062965
##
## Round.3:
## [1] 0.003644921
##
##
##
## An object of class 'Shape'
## Fits 0 shape coefficients for 0 kinds of shape parameter(s) (shape = ) for a feature model of length 20.
## [1] "Number of Observations in Design Matrix: 834273"
## No shape parameters included in fit.
## [1] "Stability Reached after 5 iterations."
ModelTest <- finalizeFeatureBetas(ModelTest)
pM <- plot(ModelTest, plotTitle = "HM-Ubx4a-Exd R2+R3 Nucleotide 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 = ""))