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/StrandOriNoSymmetry"
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 Nucleotides+Strand",
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,
includeDNAstrand = TRUE,
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": 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 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)
designMatrixSummary = getDesignMatrix(ModelTest, data)
## No shape parameters included in fit.
print("Round summary: ")
## [1] "Round summary: "
print (designMatrixSummary$Round)
## 2 Total
## Round 792570 792570
print("Mono-nucleotide summary: ")
## [1] "Mono-nucleotide summary: "
print (designMatrixSummary$N)
## N.A N.C N.G N.T
## 1 68496 184091 306568 233415
## 2 99347 162896 310750 219577
## 3 137689 86101 374681 194099
## 4 146435 108469 377287 160379
## 5 328153 63671 266543 134203
## 6 113651 24825 23612 630482
## 7 175668 2265 537231 77406
## 8 745166 14530 18441 14433
## 9 48927 17534 48212 677897
## 10 45409 9904 13835 723422
## 11 57354 14092 46827 674297
## 12 767049 6227 14740 4554
## 13 14969 102177 19814 655610
## 14 102996 45976 390490 253108
## 15 331311 51621 282674 126964
## 16 96371 362603 157893 175703
## 17 124602 405401 102589 159978
## 18 236337 321696 91955 142582
## 19 190231 291171 196766 114402
## 20 209892 359609 154772 68297
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 49777 81814 74930 68106 68044 68800 81673 493144
## Strand.R 37088 49990 47561 36366 38042 41022 49357 299426
# # 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.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+Strand.R"
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
## -9.3688 -0.9126 -0.3280 0.1981 11.7321
##
## Coefficients:
## Estimate Std. Error z value Pr(>|z|)
## (Intercept) 25.6279884 0.0039454 6495.732 < 2e-16 ***
## N.A1 0.0198505 0.0016946 11.714 < 2e-16 ***
## N.C1 -0.0092284 0.0015698 -5.879 4.14e-09 ***
## N.T1 -0.0932604 0.0012786 -72.942 < 2e-16 ***
## N.A2 0.0317939 0.0014585 21.800 < 2e-16 ***
## N.C2 -0.1036512 0.0015022 -69.000 < 2e-16 ***
## N.T2 -0.0625370 0.0013601 -45.978 < 2e-16 ***
## N.A3 0.0069157 0.0012222 5.659 1.53e-08 ***
## N.C3 -0.1552996 0.0015281 -101.631 < 2e-16 ***
## N.T3 -0.1589848 0.0012295 -129.312 < 2e-16 ***
## N.A4 -0.0134013 0.0011739 -11.416 < 2e-16 ***
## N.C4 -0.1851083 0.0014256 -129.843 < 2e-16 ***
## N.T4 -0.0954859 0.0011680 -81.750 < 2e-16 ***
## N.C5 -0.8490486 0.0020889 -406.457 < 2e-16 ***
## N.G5 -0.3104101 0.0010059 -308.578 < 2e-16 ***
## N.T5 -0.4934346 0.0011442 -431.252 < 2e-16 ***
## N.A6 -0.9377395 0.0017505 -535.691 < 2e-16 ***
## N.C6 -1.7613313 0.0079820 -220.662 < 2e-16 ***
## N.G6 -2.0013804 0.0107420 -186.313 < 2e-16 ***
## N.A7 -0.6581006 0.0011022 -597.054 < 2e-16 ***
## N.C7 -2.7156126 0.0780883 -34.776 < 2e-16 ***
## N.T7 -1.1948119 0.0020133 -593.449 < 2e-16 ***
## N.C8 -2.3440086 0.0216036 -108.501 < 2e-16 ***
## N.G8 -2.1955931 0.0152957 -143.544 < 2e-16 ***
## N.T8 -2.5606253 0.0204031 -125.502 < 2e-16 ***
## N.A9 -1.3785202 0.0038072 -362.085 < 2e-16 ***
## N.C9 -1.9905989 0.0133015 -149.652 < 2e-16 ***
## N.G9 -1.4094551 0.0039896 -353.287 < 2e-16 ***
## N.A10 -1.5542266 0.0044010 -353.153 < 2e-16 ***
## N.C10 -2.4035791 0.0299936 -80.136 < 2e-16 ***
## N.G10 -2.1961328 0.0216248 -101.556 < 2e-16 ***
## N.A11 -1.1624326 0.0026337 -441.376 < 2e-16 ***
## N.C11 -1.4712352 0.0099652 -147.638 < 2e-16 ***
## N.G11 -1.3906509 0.0041001 -339.177 < 2e-16 ***
## N.C12 -2.6240654 0.0472474 -55.539 < 2e-16 ***
## N.G12 -2.3541136 0.0195457 -120.441 < 2e-16 ***
## N.T12 -2.8610392 0.0524174 -54.582 < 2e-16 ***
## N.A13 -1.9874969 0.0118871 -167.198 < 2e-16 ***
## N.C13 -0.6825546 0.0016062 -424.963 < 2e-16 ***
## N.G13 -1.7683167 0.0091415 -193.438 < 2e-16 ***
## N.A14 -0.7061760 0.0015060 -468.895 < 2e-16 ***
## N.C14 -0.8805787 0.0023854 -369.146 < 2e-16 ***
## N.T14 -0.2063794 0.0008578 -240.584 < 2e-16 ***
## N.C15 -0.9896412 0.0026277 -376.625 < 2e-16 ***
## N.G15 -0.1191107 0.0008847 -134.630 < 2e-16 ***
## N.T15 -0.5762756 0.0012594 -457.574 < 2e-16 ***
## N.A16 -0.4926548 0.0014552 -338.546 < 2e-16 ***
## N.G16 -0.2278245 0.0011530 -197.597 < 2e-16 ***
## N.T16 -0.2668763 0.0010825 -246.539 < 2e-16 ***
## N.A17 -0.2207225 0.0013134 -168.054 < 2e-16 ***
## N.G17 -0.2777073 0.0014555 -190.804 < 2e-16 ***
## N.T17 -0.0880596 0.0011504 -76.549 < 2e-16 ***
## N.A18 -0.1315684 0.0013715 -95.931 < 2e-16 ***
## N.G18 -0.1180771 0.0015648 -75.457 < 2e-16 ***
## N.T18 0.0571583 0.0012773 44.750 < 2e-16 ***
## N.A19 -0.0474186 0.0015512 -30.569 < 2e-16 ***
## N.G19 -0.1270854 0.0015578 -81.582 < 2e-16 ***
## N.T19 0.1369059 0.0014838 92.267 < 2e-16 ***
## N.A20 -0.0372087 0.0012790 -29.092 < 2e-16 ***
## N.G20 -0.0743574 0.0016835 -44.169 < 2e-16 ***
## N.T20 0.0659210 0.0017374 37.942 < 2e-16 ***
## Strand.R 0.0120626 0.0009665 12.481 < 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: 4192188 on 792569 degrees of freedom
## Residual deviance: 1140724 on 792508 degrees of freedom
## AIC: 2168207
##
## Number of Fisher Scoring iterations: 8
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+Strand
## 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 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+Strand.F+Strand.R
##
##
## 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 0.019850520 0.03179387 0.006915687 -0.01340125 0.0000000
## N.C -0.009228379 -0.10365125 -0.155299607 -0.18510835 -0.8490486
## N.G 0.000000000 0.00000000 0.000000000 0.00000000 -0.3104101
## N.T -0.093260408 -0.06253697 -0.158984808 -0.09548586 -0.4934346
## 6 7 8 9 10 11
## N.A -0.9377395 -0.6581006 0.000000 -1.378520 -1.554227 -1.162433
## N.C -1.7613313 -2.7156126 -2.344009 -1.990599 -2.403579 -1.471235
## N.G -2.0013804 0.0000000 -2.195593 -1.409455 -2.196133 -1.390651
## N.T 0.0000000 -1.1948119 -2.560625 0.000000 0.000000 0.000000
## 12 13 14 15 16 17
## N.A 0.000000 -1.9874969 -0.7061760 0.0000000 -0.4926548 -0.22072247
## N.C -2.624065 -0.6825546 -0.8805787 -0.9896412 0.0000000 0.00000000
## N.G -2.354114 -1.7683167 0.0000000 -0.1191107 -0.2278245 -0.27770728
## N.T -2.861039 0.0000000 -0.2063794 -0.5762756 -0.2668763 -0.08805963
## 18 19 20
## N.A -0.13156838 -0.04741856 -0.03720872
## N.C 0.00000000 0.00000000 0.00000000
## N.G -0.11807709 -0.12708539 -0.07435740
## N.T 0.05715835 0.13690588 0.06592104
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001694603 0.001458457 0.001222172 0.001173851 0.000000000
## N.C 0.001569801 0.001502200 0.001528069 0.001425631 0.002088902
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001005937
## N.T 0.001278559 0.001360145 0.001229465 0.001168028 0.001144192
## 6 7 8 9 10 11
## N.A 0.001750524 0.001102246 0.00000000 0.003807173 0.004401004 0.002633657
## N.C 0.007982047 0.078088252 0.02160364 0.013301492 0.029993591 0.009965166
## N.G 0.010742011 0.000000000 0.01529566 0.003989551 0.021624753 0.004100070
## N.T 0.000000000 0.002013335 0.02040314 0.000000000 0.000000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.011887117 0.0015060431 0.0000000000 0.001455208
## N.C 0.04724739 0.001606152 0.0023854497 0.0026276589 0.000000000
## N.G 0.01954572 0.009141528 0.0000000000 0.0008847257 0.001152978
## N.T 0.05241742 0.000000000 0.0008578261 0.0012594162 0.001082491
## 17 18 19 20
## N.A 0.001313405 0.001371483 0.001551206 0.001278999
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001455457 0.001564818 0.001557759 0.001683481
## N.T 0.001150367 0.001277278 0.001483796 0.001737432
##
##
## An object of class 'Intercept'
## Fits 2 strand orientations and 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## Strand
## Strand.F 25.62799
## Strand.R 25.64005
##
## Intercept beta errors:
## Round.2:
## Strand
## Strand.F 0.003945358
## Strand.R 0.004062008
##
##
##
## 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 Nucleotide+Strand 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.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)
# Features after first round of fitting
summary(ModelTest)
pM <- plot(ModelTest, plotTitle = "HM-Ubx4a-Exd R2 Nucleotide+Strand 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 Total
## Round 776946 776946
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 65503 182546 299603 229294
## 2 97079 156397 308108 215362
## 3 134124 84088 371870 186864
## 4 146157 103325 370658 156806
## 5 326890 62639 256166 131251
## 6 106376 24539 20842 625189
## 7 173220 2488 523885 77353
## 8 732776 13707 16987 13476
## 9 41575 14373 42467 678531
## 10 39271 7934 12051 717690
## 11 50450 15989 42698 667809
## 12 750837 7593 13297 5219
## 13 12123 108688 16410 639725
## 14 103700 46908 390338 236000
## 15 318222 53529 273012 132183
## 16 96305 350604 159960 170077
## 17 122406 395773 100176 158591
## 18 228079 315357 90479 143031
## 19 186079 286868 189395 114604
## 20 204338 354306 151091 67211
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 47909 81710 75017 67919 66760 67203 77670 484188
## Strand.R 35884 49417 47893 35884 36960 39785 46935 292758
## [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+Strand.R"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a Nucleotides+Strand
## 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 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+Strand.F+Strand.R
##
##
## 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 0.02031141 0.03209064 0.006194248 -0.01557362 0.0000000 -0.936658
## N.C -0.01000509 -0.10349595 -0.156690693 -0.18356801 -0.8470523 -1.755215
## N.G 0.00000000 0.00000000 0.000000000 0.00000000 -0.3087140 -2.010913
## N.T -0.09233750 -0.06164871 -0.159957334 -0.09460363 -0.4917945 0.000000
## 7 8 9 10 11 12 13
## N.A -0.658828 0.000000 -1.352819 -1.557620 -1.154499 0.000000 -1.9935956
## N.C -2.759300 -2.364408 -1.998139 -2.455205 -1.376539 -2.531131 -0.6795597
## N.G 0.000000 -2.213856 -1.408948 -2.228813 -1.393728 -2.357064 -1.7690115
## N.T -1.196642 -2.587143 0.000000 0.000000 0.000000 -2.866771 0.0000000
## 14 15 16 17 18 19
## N.A -0.7044907 0.0000000 -0.4907788 -0.22066347 -0.13135823 -0.04649756
## N.C -0.8816842 -0.9862189 0.0000000 0.00000000 0.00000000 0.00000000
## N.G 0.0000000 -0.1193237 -0.2273182 -0.27664867 -0.11876241 -0.12578848
## N.T -0.2052911 -0.5741436 -0.2662425 -0.08713916 0.05675272 0.13717872
## 20
## N.A -0.03680803
## N.C 0.00000000
## N.G -0.07449299
## N.T 0.06538862
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001698569 0.001457935 0.001222850 0.001172445 0.000000000
## N.C 0.001570928 0.001504771 0.001524327 0.001432290 0.002087110
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001007561
## N.T 0.001280485 0.001361189 0.001228632 0.001167543 0.001143988
## 6 7 8 9 10 11
## N.A 0.001753440 0.001095893 0.00000000 0.003964654 0.004572683 0.002701862
## N.C 0.007842662 0.076251095 0.02197551 0.013582310 0.031884383 0.008974047
## N.G 0.010913940 0.000000000 0.01558188 0.004009380 0.022688101 0.004119436
## N.T 0.000000000 0.002003861 0.02089530 0.000000000 0.000000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.012047578 0.0015032186 0.0000000000 0.001451813
## N.C 0.04166795 0.001588862 0.0023595267 0.0026094426 0.000000000
## N.G 0.01962069 0.009201336 0.0000000000 0.0008858754 0.001150158
## N.T 0.05130201 0.000000000 0.0008602558 0.0012529102 0.001083918
## 17 18 19 20
## N.A 0.001312952 0.001370920 0.001551906 0.001279345
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001455526 0.001565130 0.001558199 0.001684191
## N.T 0.001148843 0.001275531 0.001484349 0.001738025
##
##
## An object of class 'Intercept'
## Fits 2 strand orientations and 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## Strand
## Strand.F 25.62131
## Strand.R 25.63357
##
## Intercept beta errors:
## Round.2:
## Strand
## Strand.F 0.003946877
## Strand.R 0.004063368
##
##
##
## 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: 773652"
## No shape parameters included in fit.
## [1] "i = 3"
## No shape parameters included in fit.
## [1] "Round summary: "
## 2 Total
## Round 773652 773652
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 65087 182036 297947 228582
## 2 96537 155761 306712 214642
## 3 133421 83519 370922 185790
## 4 145144 102638 369679 156191
## 5 324999 62413 255309 130931
## 6 106055 24426 20550 622621
## 7 172243 2391 522070 76948
## 8 730182 13491 16775 13204
## 9 40979 14086 42113 676474
## 10 39117 7725 11662 715148
## 11 50112 15948 42381 665211
## 12 747852 7582 13126 5092
## 13 11947 108174 16232 637299
## 14 103112 46550 389080 234910
## 15 316991 53144 271991 131526
## 16 95813 349085 159441 169313
## 17 122012 393900 99830 157910
## 18 227009 313799 90210 142634
## 19 185241 285530 188532 114349
## 20 203372 352879 150388 67013
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 47781 81557 74861 67492 66395 66841 77196 482123
## Strand.R 35802 49310 47800 35696 36735 39516 46670 291529
## [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+Strand.R"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a Nucleotides+Strand
## 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 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+Strand.F+Strand.R
##
##
## 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 0.02034188 0.03223089 0.006229381 -0.01528119 0.0000000 -0.9367151
## N.C -0.01001772 -0.10335065 -0.156403618 -0.18351123 -0.8471549 -1.7552454
## N.G 0.00000000 0.00000000 0.000000000 0.00000000 -0.3087729 -2.0109812
## N.T -0.09236654 -0.06150582 -0.159888618 -0.09460922 -0.4918460 0.0000000
## 7 8 9 10 11 12
## N.A -0.6585601 0.000000 -1.351469 -1.557667 -1.154465 0.000000
## N.C -2.7712644 -2.364739 -1.997120 -2.458244 -1.375427 -2.531114
## N.G 0.0000000 -2.213332 -1.408998 -2.241810 -1.393804 -2.358995
## N.T -1.1964425 -2.588603 0.000000 0.000000 0.000000 -2.869448
## 13 14 15 16 17 18
## N.A -1.9935806 -0.7043613 0.0000000 -0.4907015 -0.22064371 -0.13120502
## N.C -0.6795559 -0.8813868 -0.9862437 0.0000000 0.00000000 0.00000000
## N.G -1.7686628 0.0000000 -0.1193702 -0.2272734 -0.27663835 -0.11868071
## N.T 0.0000000 -0.2052466 -0.5741743 -0.2661466 -0.08711893 0.05682415
## 19 20
## N.A -0.04647602 -0.03688921
## N.C 0.00000000 0.00000000
## N.G -0.12583864 -0.07448543
## N.T 0.13716315 0.06532163
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001699688 0.001458800 0.001223267 0.001173115 0.000000000
## N.C 0.001571560 0.001505748 0.001525454 0.001433358 0.002087354
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001007974
## N.T 0.001280992 0.001362032 0.001229743 0.001167937 0.001144172
## 6 7 8 9 10 11
## N.A 0.001753589 0.001097597 0.00000000 0.003999884 0.004573268 0.002703044
## N.C 0.007843629 0.078088671 0.02199675 0.013622471 0.032014762 0.008975514
## N.G 0.010921737 0.000000000 0.01559701 0.004009895 0.023120048 0.004120260
## N.T 0.000000000 0.002005085 0.02098702 0.000000000 0.000000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.012068558 0.0015041146 0.0000000000 0.001452524
## N.C 0.04166788 0.001589509 0.0023611912 0.0026117648 0.000000000
## N.G 0.01966609 0.009202914 0.0000000000 0.0008862001 0.001150480
## N.T 0.05185066 0.000000000 0.0008606033 0.0012535635 0.001084332
## 17 18 19 20
## N.A 0.001313301 0.001371265 0.001552136 0.001279935
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001455958 0.001565528 0.001558637 0.001684485
## N.T 0.001149187 0.001275879 0.001484528 0.001738282
##
##
## An object of class 'Intercept'
## Fits 2 strand orientations and 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## Strand
## Strand.F 25.62079
## Strand.R 25.63308
##
## Intercept beta errors:
## Round.2:
## Strand
## Strand.F 0.003948296
## Strand.R 0.004064843
##
##
##
## 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: 773483"
## No shape parameters included in fit.
## [1] "i = 4"
## No shape parameters included in fit.
## [1] "Round summary: "
## 2 Total
## Round 773483 773483
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 65067 182015 297868 228533
## 2 96506 155734 306636 214607
## 3 133389 83496 370874 185724
## 4 145103 102597 369632 156151
## 5 324911 62403 255258 130911
## 6 106035 24422 20541 622485
## 7 172188 2366 521996 76933
## 8 730031 13487 16770 13195
## 9 40975 14082 42095 676331
## 10 39115 7717 11600 715051
## 11 50092 15940 42359 665092
## 12 747707 7581 13115 5080
## 13 11940 108142 16224 637177
## 14 103083 46537 389021 234842
## 15 316939 53122 271930 131492
## 16 95788 349007 159414 169274
## 17 121989 393804 99809 157881
## 18 226955 313728 90196 142604
## 19 185202 285461 188484 114336
## 20 203320 352795 150360 67008
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 47775 81551 74850 67468 66373 66828 77172 482017
## Strand.R 35798 49303 47792 35690 36728 39504 46651 291466
## [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+Strand.R"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a Nucleotides+Strand
## 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 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+Strand.F+Strand.R
##
##
## 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 0.02034008 0.03224256 0.006221008 -0.01526673 0.0000000 -0.9367145
## N.C -0.01002021 -0.10334066 -0.156401691 -0.18355263 -0.8471500 -1.7552433
## N.G 0.00000000 0.00000000 0.000000000 0.00000000 -0.3087729 -2.0109437
## N.T -0.09239436 -0.06151044 -0.159903209 -0.09461453 -0.4918451 0.0000000
## 7 8 9 10 11 12 13
## N.A -0.6585834 0.000000 -1.351471 -1.557663 -1.154472 0.000000 -1.993563
## N.C -2.7781256 -2.364743 -1.997081 -2.458237 -1.374946 -2.531075 -0.679556
## N.G 0.0000000 -2.213334 -1.409000 -2.244338 -1.393838 -2.358901 -1.768650
## N.T -1.1964546 -2.588551 0.000000 0.000000 0.000000 -2.869235 0.000000
## 14 15 16 17 18 19
## N.A -0.7043731 0.0000000 -0.4907015 -0.22065576 -0.13120149 -0.04647865
## N.C -0.8813718 -0.9862412 0.0000000 0.00000000 0.00000000 0.00000000
## N.G 0.0000000 -0.1193696 -0.2272811 -0.27664723 -0.11865801 -0.12585110
## N.T -0.2052408 -0.5741708 -0.2661393 -0.08712742 0.05684507 0.13716325
## 20
## N.A -0.03691411
## N.C 0.00000000
## N.G -0.07450737
## N.T 0.06530943
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001699741 0.001458848 0.001223289 0.001173151 0.000000000
## N.C 0.001571585 0.001505798 0.001525568 0.001433498 0.002087362
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001008010
## N.T 0.001281033 0.001362098 0.001229843 0.001167966 0.001144190
## 6 7 8 9 10 11
## N.A 0.001753601 0.001097784 0.00000000 0.003999885 0.004573269 0.002703120
## N.C 0.007843630 0.079058643 0.02199675 0.013622474 0.032014762 0.008975510
## N.G 0.010921739 0.000000000 0.01559701 0.004009897 0.023194468 0.004120396
## N.T 0.000000000 0.002005129 0.02098702 0.000000000 0.000000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.012068560 0.0015041840 0.0000000000 0.001452555
## N.C 0.04166787 0.001589533 0.0023611955 0.0026119268 0.000000000
## N.G 0.01966610 0.009202916 0.0000000000 0.0008862298 0.001150518
## N.T 0.05185067 0.000000000 0.0008606345 0.0012536083 0.001084365
## 17 18 19 20
## N.A 0.001313329 0.001371281 0.001552153 0.001279969
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001455989 0.001565558 0.001558661 0.001684513
## N.T 0.001149216 0.001275921 0.001484541 0.001738294
##
##
## An object of class 'Intercept'
## Fits 2 strand orientations and 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## Strand
## Strand.F 25.62084
## Strand.R 25.63312
##
## Intercept beta errors:
## Round.2:
## Strand
## Strand.F 0.003948383
## Strand.R 0.004064934
##
##
##
## 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: 773449"
## No shape parameters included in fit.
## [1] "i = 5"
## No shape parameters included in fit.
## [1] "Round summary: "
## 2 Total
## Round 773449 773449
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 65065 182009 297850 228525
## 2 96500 155730 306621 214598
## 3 133385 83492 370858 185714
## 4 145096 102591 369617 156145
## 5 324896 62400 255247 130906
## 6 106028 24421 20541 622459
## 7 172185 2356 521977 76931
## 8 729999 13486 16770 13194
## 9 40968 14079 42089 676313
## 10 39115 7716 11584 715034
## 11 50086 15939 42351 665073
## 12 747677 7579 13114 5079
## 13 11939 108136 16220 637154
## 14 103078 46532 389008 234831
## 15 316929 53119 271913 131488
## 16 95783 348993 159406 169267
## 17 121981 393789 99807 157872
## 18 226948 313711 90191 142599
## 19 185195 285445 188477 114332
## 20 203312 352777 150355 67005
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 47775 81548 74848 67464 66367 66826 77167 481995
## Strand.R 35794 49301 47789 35689 36728 39503 46650 291454
## [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+Strand.R"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a Nucleotides+Strand
## 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 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+Strand.F+Strand.R
##
##
## 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 0.02034073 0.03223747 0.006223869 -0.01526806 0.0000000 -0.9367151
## N.C -0.01001519 -0.10334848 -0.156401946 -0.18354456 -0.8471514 -1.7552442
## N.G 0.00000000 0.00000000 0.000000000 0.00000000 -0.3087749 -2.0109447
## N.T -0.09239140 -0.06151582 -0.159893614 -0.09461651 -0.4918483 0.0000000
## 7 8 9 10 11 12
## N.A -0.6585836 0.000000 -1.351431 -1.557664 -1.154471 0.000000
## N.C -2.8006901 -2.364743 -1.996942 -2.458237 -1.374946 -2.531075
## N.G 0.0000000 -2.213336 -1.409029 -2.244315 -1.393872 -2.358901
## N.T -1.1964359 -2.588552 0.000000 0.000000 0.000000 -2.869235
## 13 14 15 16 17 18
## N.A -1.9935634 -0.7043727 0.0000000 -0.4907047 -0.22065637 -0.13120187
## N.C -0.6795564 -0.8813708 -0.9862406 0.0000000 0.00000000 0.00000000
## N.G -1.7686508 0.0000000 -0.1193672 -0.2272791 -0.27664786 -0.11866174
## N.T 0.0000000 -0.2052389 -0.5741728 -0.2661403 -0.08712911 0.05684218
## 19 20
## N.A -0.0464789 -0.03691098
## N.C 0.0000000 0.00000000
## N.G -0.1258478 -0.07450807
## N.T 0.1371646 0.06531133
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001699741 0.001458849 0.001223290 0.001173152 0.000000000
## N.C 0.001571585 0.001505802 0.001525573 0.001433497 0.002087362
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001008012
## N.T 0.001281035 0.001362097 0.001229847 0.001167967 0.001144191
## 6 7 8 9 10 11
## N.A 0.001753601 0.001097784 0.00000000 0.003999891 0.004573269 0.002703121
## N.C 0.007843630 0.081112024 0.02199675 0.013622474 0.032014762 0.008975510
## N.G 0.010921739 0.000000000 0.01559701 0.004010021 0.023194469 0.004120531
## N.T 0.000000000 0.002005129 0.02098702 0.000000000 0.000000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.012068560 0.0015041841 0.0000000000 0.001452558
## N.C 0.04166788 0.001589533 0.0023611958 0.0026119270 0.000000000
## N.G 0.01966610 0.009202916 0.0000000000 0.0008862308 0.001150518
## N.T 0.05185067 0.000000000 0.0008606356 0.0012536108 0.001084366
## 17 18 19 20
## N.A 0.001313329 0.001371280 0.001552155 0.001279968
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001455989 0.001565561 0.001558660 0.001684514
## N.T 0.001149218 0.001275922 0.001484541 0.001738294
##
##
## An object of class 'Intercept'
## Fits 2 strand orientations and 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## Strand
## Strand.F 25.62084
## Strand.R 25.63312
##
## Intercept beta errors:
## Round.2:
## Strand
## Strand.F 0.003948383
## Strand.R 0.004064934
##
##
##
## 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: 773417"
## No shape parameters included in fit.
## [1] "i = 6"
## No shape parameters included in fit.
## [1] "Round summary: "
## 2 Total
## Round 773417 773417
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 65062 182003 297835 228517
## 2 96492 155724 306611 214590
## 3 133380 83488 370843 185706
## 4 145089 102586 369601 156141
## 5 324882 62399 255233 130903
## 6 106023 24416 20541 622437
## 7 172185 2324 521977 76931
## 8 729976 13484 16766 13191
## 9 40966 14074 42083 676294
## 10 39113 7715 11583 715006
## 11 50086 15938 42350 665043
## 12 747646 7579 13113 5079
## 13 11939 108129 16220 637129
## 14 103077 46530 388984 234826
## 15 316920 53118 271898 131481
## 16 95779 348978 159398 169262
## 17 121975 393775 99801 157866
## 18 226941 313696 90186 142594
## 19 185191 285429 188473 114324
## 20 203299 352764 150350 67004
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 47773 81543 74844 67462 66362 66825 77163 481972
## Strand.R 35792 49300 47789 35687 36725 39502 46650 291445
## [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+Strand.R"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a Nucleotides+Strand
## 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 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+Strand.F+Strand.R
##
##
## 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 0.02034138 0.03223543 0.006222472 -0.01526898 0.0000000 -0.9367149
## N.C -0.01001520 -0.10334863 -0.156402148 -0.18354437 -0.8471511 -1.7552437
## N.G 0.00000000 0.00000000 0.000000000 0.00000000 -0.3087745 -2.0109447
## N.T -0.09239320 -0.06151658 -0.159893650 -0.09461630 -0.4918481 0.0000000
## 7 8 9 10 11 12
## N.A -0.6585835 0.000000 -1.351430 -1.557664 -1.154470 0.000000
## N.C -2.8072621 -2.364743 -1.996941 -2.458236 -1.374946 -2.531075
## N.G 0.0000000 -2.213336 -1.409028 -2.244314 -1.393872 -2.358901
## N.T -1.1964361 -2.588552 0.000000 0.000000 0.000000 -2.869235
## 13 14 15 16 17 18
## N.A -1.9935629 -0.7043727 0.0000000 -0.4907040 -0.2206561 -0.13120152
## N.C -0.6795562 -0.8813708 -0.9862409 0.0000000 0.0000000 0.00000000
## N.G -1.7686504 0.0000000 -0.1193682 -0.2272787 -0.2766474 -0.11866195
## N.T 0.0000000 -0.2052399 -0.5741732 -0.2661396 -0.0871290 0.05684214
## 19 20
## N.A -0.0464791 -0.03691026
## N.C 0.0000000 0.00000000
## N.G -0.1258473 -0.07450884
## N.T 0.1371650 0.06531106
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001699741 0.001458851 0.001223291 0.001173153 0.000000000
## N.C 0.001571585 0.001505802 0.001525573 0.001433497 0.002087362
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001008012
## N.T 0.001281036 0.001362097 0.001229847 0.001167968 0.001144192
## 6 7 8 9 10 11
## N.A 0.001753601 0.001097784 0.00000000 0.003999891 0.004573269 0.002703121
## N.C 0.007843630 0.082200698 0.02199675 0.013622474 0.032014762 0.008975511
## N.G 0.010921739 0.000000000 0.01559701 0.004010021 0.023194469 0.004120531
## N.T 0.000000000 0.002005129 0.02098702 0.000000000 0.000000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.012068560 0.001504184 0.0000000000 0.001452559
## N.C 0.04166788 0.001589533 0.002361196 0.0026119270 0.000000000
## N.G 0.01966610 0.009202916 0.000000000 0.0008862313 0.001150519
## N.T 0.05185067 0.000000000 0.000860636 0.0012536108 0.001084367
## 17 18 19 20
## N.A 0.001313329 0.001371280 0.001552155 0.001279968
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001455989 0.001565561 0.001558660 0.001684515
## N.T 0.001149218 0.001275922 0.001484542 0.001738293
##
##
## An object of class 'Intercept'
## Fits 2 strand orientations and 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## Strand
## Strand.F 25.62084
## Strand.R 25.63312
##
## Intercept beta errors:
## Round.2:
## Strand
## Strand.F 0.003948383
## Strand.R 0.004064935
##
##
##
## 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: 773407"
## No shape parameters included in fit.
## [1] "i = 7"
## No shape parameters included in fit.
## [1] "Round summary: "
## 2 Total
## Round 773407 773407
## [1] "Mono-nucleotide summary: "
## N.A N.C N.G N.T
## 1 65060 181999 297832 228516
## 2 96490 155720 306610 214587
## 3 133377 83488 370839 185703
## 4 145087 102586 369594 156140
## 5 324876 62398 255231 130902
## 6 106019 24416 20541 622431
## 7 172185 2314 521977 76931
## 8 729968 13482 16766 13191
## 9 40965 14074 42083 676285
## 10 39112 7715 11583 714997
## 11 50085 15938 42348 665036
## 12 747637 7579 13112 5079
## 13 11939 108126 16220 637122
## 14 103075 46530 388979 234823
## 15 316917 53118 271892 131480
## 16 95776 348972 159397 169262
## 17 121973 393771 99799 157864
## 18 226938 313691 90186 142592
## 19 185190 285426 188469 114322
## 20 203295 352760 150349 67003
## [1] "View/strand orientation summary: "
## View.1 View.2 View.3 View.4 View.5 View.6 View.7 StrandTotal
## Strand.F 47773 81541 74844 67462 66361 66825 77160 481966
## Strand.R 35791 49299 47789 35687 36724 39501 46650 291441
## [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+Strand.R"
## No shape parameters included in fit.
## An object of class 'model'
##
## Slot "name": HM-Exd-Ubx4a Nucleotides+Strand
## 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 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+Strand.F+Strand.R
##
##
## 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 0.02034153 0.03223548 0.00622246 -0.01526898 0.0000000 -0.9367149
## N.C -0.01001517 -0.10334873 -0.15640215 -0.18354442 -0.8471511 -1.7552437
## N.G 0.00000000 0.00000000 0.00000000 0.00000000 -0.3087745 -2.0109447
## N.T -0.09239320 -0.06151664 -0.15989346 -0.09461637 -0.4918480 0.0000000
## 7 8 9 10 11 12
## N.A -0.6585835 0.000000 -1.351430 -1.557664 -1.154470 0.000000
## N.C -2.8059636 -2.364742 -1.996941 -2.458236 -1.374946 -2.531075
## N.G 0.0000000 -2.213336 -1.409028 -2.244314 -1.393872 -2.358901
## N.T -1.1964360 -2.588552 0.000000 0.000000 0.000000 -2.869235
## 13 14 15 16 17 18
## N.A -1.9935629 -0.7043727 0.0000000 -0.4907038 -0.22065606 -0.13120155
## N.C -0.6795562 -0.8813708 -0.9862410 0.0000000 0.00000000 0.00000000
## N.G -1.7686504 0.0000000 -0.1193682 -0.2272787 -0.27664740 -0.11866199
## N.T 0.0000000 -0.2052398 -0.5741732 -0.2661396 -0.08712893 0.05684207
## 19 20
## N.A -0.04647913 -0.03691026
## N.C 0.00000000 0.00000000
## N.G -0.12584731 -0.07450888
## N.T 0.13716492 0.06531103
##
## Nucleotide beta errors:
## 1 2 3 4 5
## N.A 0.001699742 0.001458851 0.001223291 0.001173153 0.000000000
## N.C 0.001571585 0.001505802 0.001525573 0.001433497 0.002087362
## N.G 0.000000000 0.000000000 0.000000000 0.000000000 0.001008012
## N.T 0.001281036 0.001362097 0.001229847 0.001167968 0.001144192
## 6 7 8 9 10 11
## N.A 0.001753601 0.001097784 0.00000000 0.003999891 0.004573269 0.002703121
## N.C 0.007843630 0.082200731 0.02199675 0.013622474 0.032014762 0.008975511
## N.G 0.010921739 0.000000000 0.01559701 0.004010021 0.023194469 0.004120531
## N.T 0.000000000 0.002005129 0.02098702 0.000000000 0.000000000 0.000000000
## 12 13 14 15 16
## N.A 0.00000000 0.012068560 0.001504184 0.0000000000 0.001452559
## N.C 0.04166788 0.001589533 0.002361196 0.0026119270 0.000000000
## N.G 0.01966610 0.009202916 0.000000000 0.0008862313 0.001150519
## N.T 0.05185067 0.000000000 0.000860636 0.0012536108 0.001084367
## 17 18 19 20
## N.A 0.001313329 0.001371280 0.001552155 0.001279968
## N.C 0.000000000 0.000000000 0.000000000 0.000000000
## N.G 0.001455989 0.001565561 0.001558660 0.001684515
## N.T 0.001149218 0.001275922 0.001484542 0.001738293
##
##
## An object of class 'Intercept'
## Fits 2 strand orientations and 1 round(s) (round = 2).
## Intercept beta values:
## Round.2:
## Strand
## Strand.F 25.62084
## Strand.R 25.63312
##
## Intercept beta errors:
## Round.2:
## Strand
## Strand.F 0.003948383
## Strand.R 0.004064935
##
##
##
## 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: 773407"
## No shape parameters included in fit.
## [1] "Stability Reached after 7 iterations."
ModelTest <- finalizeFeatureBetas(ModelTest)
pM <- plot(ModelTest, plotTitle = "HM-Ubx4a-Exd R2 Nucleotide+Strand 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 = ""))