Benchmarking detection of DNA copy number variation using high-density methylation microarrays
Code Paper for Benchmarking Project
Hi! This is a very informally written document just to give the beats of what is happening in the code, and the analysis I am doing. It needs to be MUCH more formalized before being shown publicly, but it is useful for understanding!
Preprocessing
All data is in disparate forms. So, I standardized it so that it can be easily utilized in the downstream without having to continuously redo work. I chose to standardize the notation to the Conumee notations, using
chrom for chromosomes.
loc.start for when the location of a segment starts.
loc.end for when the location of a segment ends.
seg.mean for the log2-ratio.
CNVStatus for whether a block represents a deletion, amplification & normal segments.
type is a representative factor to say what method gave that segment, because we compose a database for each case, and we need to distinguish the segments from each other.
we also add an extra factor named “Gene” to label relevant segments which have a gene inside it.
Attached are the pre-processing blocks.
LMS Processing
labLMSProc <- function(STTq, Technology, binSize) {
# Correlate by STT information between methylation
# Sentrix and SNP data.
correlationSheet <- read.csv("~/Work/Analysis/LabData/LMS_SNP_EPIC_array_data/correlative.csv") %>%
filter(STT == STTq)
cnvMatch <- read_delim(paste0("~/Work/Analysis/LabData/LMS_SNP_EPIC_array_data/ChAS/ChAS_data_01Feb2026/ChAS_LMS_Probe_and_segment_level_data_01Feb2026/STT",
STTq, "_Recentered_Segment_level_data_01Feb2026.segment.txt"))
# methylMatch <-
# read.csv(paste0('~/Work/Analysis/Outputs/MethylMaster/LabLMS/',
# paste0(correlationSheet$Sentrix_ID[1],'_',
# correlationSheet$Sentrix_Position[1], '/'),
# 'autocorrected_regions.csv'))
conumeeMatch <- read.csv(paste0("~/Work/Analysis/Outputs/Conumee/LabLMS/",
binSize, "/", paste0(correlationSheet$Sentrix_ID[1],
"_", correlationSheet$Sentrix_Position[1], ".csv")))
sesameMatch <- read.csv(paste0("~/Work/Analysis/Outputs/SeSAMe/LabLMS/",
binSize, "/", paste0("segments_", correlationSheet$Sentrix_ID[1],
"_", correlationSheet$Sentrix_Position[1], ".csv")))
methylMatch <- read.csv(paste0("~/Work/Analysis/Outputs/MethylMaster/LabLMS/",
binSize, "/", correlationSheet$Sentrix_ID[1], "_", correlationSheet$Sentrix_Position[1],
"/autocorrected_regions.csv"))
cnvMatch <- cnvMatch %>%
dplyr::filter(!(Type == "LOH")) %>%
dplyr::filter(Chromosome != 24 & Chromosome != 25) %>%
dplyr::select("Chromosome", "StartPosition", "StopPosition",
"Median Log2 Ratio") %>%
dplyr::rename(chrom = "Chromosome", loc.start = "StartPosition",
loc.end = "StopPosition", seg.mean = "Median Log2 Ratio") %>%
dplyr::mutate(seg.mean = as.numeric(seg.mean)) %>%
dplyr::mutate(CNVStatus = case_when(seg.mean <= -0.2 ~
"Deletion", seg.mean >= 0.2 ~ "Amplification", TRUE ~
"Normal"), type = "SNP")
if (Technology == "MethylMaster") {
methylMatch <- methylMatch %>%
dplyr::rename(seg.mean = "Mean", loc.start = "bp.Start",
loc.end = "bp.End") %>%
dplyr::select(seg.mean, loc.start, loc.end, Chromosome) %>%
mutate(type = "MethylMaster") %>%
dplyr::rename(chrom = "Chromosome") %>%
dplyr::mutate(chrom = as.numeric(gsub("chr", "",
chrom))) %>%
filter(!is.na(chrom)) %>%
dplyr::mutate(loc.start = as.numeric(loc.start),
loc.end = as.numeric(loc.end), seg.mean = as.numeric(seg.mean)) %>%
mutate(CNVStatus = case_when(seg.mean <= -0.2 ~ "Deletion",
seg.mean >= 0.2 ~ "Amplification", TRUE ~ "Normal"))
combinedSet <- rbind(methylMatch, cnvMatch) %>%
mutate(Gene = as.character(0)) %>%
arrange(chrom)
}
if (Technology == "Conumee") {
conumeeMatch <- conumeeMatch %>%
dplyr::select(chrom, loc.start, loc.end, seg.mean) %>%
mutate(CNVStatus = case_when(seg.mean <= -0.2 ~ "Deletion",
seg.mean >= 0.2 ~ "Amplification", TRUE ~ "Normal")) %>%
mutate(chrom = as.numeric(gsub("chr", "", chrom))) %>%
mutate(type = "Conumee")
combinedSet <- rbind(conumeeMatch, cnvMatch) %>%
mutate(Gene = as.character(0)) %>%
arrange(chrom)
}
if (Technology == "Sesame") {
sesameMatch <- sesameMatch %>%
dplyr::select(c("chrom", "loc.start", "loc.end",
"seg.mean")) %>%
dplyr::mutate(chrom = str_remove_all(chrom, "chr")) %>%
filter(!(chrom == "X") & !(chrom == "Y")) %>%
mutate(chrom = as.numeric(chrom)) %>%
arrange(chrom) %>%
mutate(CNVStatus = case_when(seg.mean > 0.3 ~ "Amplification",
seg.mean < -0.3 ~ "Deletion", TRUE ~ "Normal"),
type = "SeSAMe")
combinedSet <- rbind(sesameMatch, cnvMatch) %>%
mutate(Gene = as.character(0), seg.mean = as.numeric(seg.mean)) %>%
arrange(chrom)
}
combinedSet
}It utilizes an unique identifier (STT) to retrieve relevant datasets from inside the files and processes them into the correct format. It then returns the whole dataset.
LM Processing
LMStt <- function(STT, bin) {
corrSheet <- read.csv("~/Work/Analysis/LabData/LM_SNP_EPIC_array_data/EPIC_array_data_LM/idat_files/SampSheet.csv") %>%
dplyr::filter(STT == STT)
sentrixID <- corrSheet$Sentrix_ID[1]
sentrixPos <- corrSheet$Sentrix_Position[1]
SNP <- read_delim(paste0("~/Work/Analysis/LabData/LM_SNP_EPIC_array_data/ChAS/ChAS_data_01Feb2026/ChAS_LM_Probe_and_segment_level_data_01Feb2026/STT",
STT, "_Segment_level_data_01Feb2026.segment.txt"))
SNP <- SNP %>%
dplyr::filter(!(Type == "LOH")) %>%
dplyr::filter(Chromosome != 24 & Chromosome != 25) %>%
dplyr::select("Chromosome", "StartPosition", "StopPosition",
"Median Log2 Ratio") %>%
dplyr::rename(chrom = "Chromosome", loc.start = "StartPosition",
loc.end = "StopPosition", seg.mean = "Median Log2 Ratio") %>%
dplyr::mutate(seg.mean = as.numeric(seg.mean)) %>%
dplyr::mutate(CNVStatus = case_when(seg.mean <= -0.2 ~
"Deletion", seg.mean >= 0.2 ~ "Amplification", TRUE ~
"Normal"), type = "SNP")
# MethylMasteR
outputDirMethyl <- paste0("~/Work/Analysis/Outputs/MethylMaster/LM/",
bin, "/", sentrixID, "_", sentrixPos, "/autocorrected_regions.csv")
cnvMethyl <- read.csv(outputDirMethyl) %>%
dplyr::select(c("Chromosome", "bp.Start", "bp.End", "Mean")) %>%
dplyr::rename(chrom = "Chromosome", loc.start = "bp.Start",
loc.end = "bp.End", seg.mean = "Mean") %>%
dplyr::mutate(CNVStatus = case_when(seg.mean > 0.3 ~
"Amplification", seg.mean < -0.3 ~ "Deletion", TRUE ~
"Normal"), type = "MethylMaster")
cnvMethyl$chrom <- as.numeric(str_remove_all(cnvMethyl$chrom,
pattern = "chr"))
cnvMethyl <- cnvMethyl %>%
filter(!(is.na(chrom))) %>%
arrange(chrom)
# SeSAMe
outputDirSesame <- paste0("~/Work/Analysis/Outputs/SeSAMe/LM/bins/",
bin, "/", "segments_", sentrixID, "_", sentrixPos, ".csv")
sesameOutput <- read.csv(outputDirSesame) %>%
dplyr::select(c("chrom", "loc.start", "loc.end", "seg.mean")) %>%
dplyr::mutate(chrom = str_remove_all(chrom, "chr")) %>%
filter(!(chrom == "X") & !(chrom == "Y")) %>%
mutate(chrom = as.numeric(chrom)) %>%
arrange(chrom) %>%
mutate(CNVStatus = case_when(seg.mean > 0.3 ~ "Amplification",
seg.mean < -0.3 ~ "Deletion", TRUE ~ "Normal"), type = "SeSAMe")
# Conumee
outputDirConumee <- paste0("~/Work/Analysis/Outputs/Conumee/LMData/bins/",
bin, "/", sentrixID, "_", sentrixPos, ".csv")
case <- read.csv(outputDirConumee)
case <- case %>%
dplyr::select(-c("ID", "bstat")) %>%
mutate(CNVStatus = case_when(case$seg.mean > 0.2 ~ "Amplification",
case$seg.mean < -0.2 ~ "Deletion", TRUE ~ "Normal"),
chrom = as.numeric(str_remove_all(chrom, "chr"))) %>%
dplyr::arrange(chrom) %>%
mutate(type = "Conumee") %>%
dplyr::select(-c("num.mark", "pval", "seg.median", "X"))
rbind(SNP, case, sesameOutput, cnvMethyl)
}This does basically the same thing, except for leiomyoma samples instead of leiomyosarcoma samples. It then returns the relevant dataset. The Gene factor is dropped because it is not evaluated for Leiomyoma.
Normal Processing
labNmrlProc <- function(Sentrix, Technology, binSize) {
# Correlate by STT information between methylation
# Sentrix and SNP data.
correlationSheet <- read.csv("~/Work/Analysis/LabData/Normal_smooth_muscle_EPIC_data/idat_files/Sample_Sheet_Normal.csv") %>%
filter(Basename == Sentrix)
conumeeMatch <- read.csv(paste0("~/Work/Analysis/Outputs/Conumee/LabNormals/",
binSize, "/", paste0(Sentrix, ".csv")))
sesameMatch <- read.csv(paste0("~/Work/Analysis/Outputs/SeSAMe/Normals/",
binSize, "/", paste0("segments_", Sentrix, ".csv")))
if (Technology == "MethylMaster") {
methylMatch <- methylMatch %>%
dplyr::rename(seg.mean = "Mean", loc.start = "bp.Start",
loc.end = "bp.End") %>%
dplyr::select(seg.mean, loc.start, loc.end, Chromosome) %>%
mutate(type = "MethylMaster") %>%
dplyr::rename(chrom = "Chromosome") %>%
dplyr::mutate(chrom = as.numeric(gsub("chr", "",
chrom))) %>%
filter(!is.na(chrom)) %>%
dplyr::mutate(loc.start = as.numeric(loc.start),
loc.end = as.numeric(loc.end), seg.mean = as.numeric(seg.mean)) %>%
mutate(CNVStatus = case_when(seg.mean <= -0.2 ~ "Deletion",
seg.mean >= 0.2 ~ "Amplification", TRUE ~ "Normal"))
combinedSet <- methylMatch %>%
arrange(chrom)
}
if (Technology == "Conumee") {
conumeeMatch <- conumeeMatch %>%
dplyr::select(chrom, loc.start, loc.end, seg.mean) %>%
mutate(CNVStatus = case_when(seg.mean <= -0.2 ~ "Deletion",
seg.mean >= 0.2 ~ "Amplification", TRUE ~ "Normal")) %>%
mutate(chrom = as.numeric(gsub("chr", "", chrom))) %>%
mutate(type = "Conumee")
combinedSet <- conumeeMatch %>%
arrange(chrom)
}
if (Technology == "Sesame") {
sesameMatch <- sesameMatch %>%
dplyr::select(c("chrom", "loc.start", "loc.end",
"seg.mean")) %>%
dplyr::mutate(chrom = str_remove_all(chrom, "chr")) %>%
filter(!(chrom == "X") & !(chrom == "Y")) %>%
mutate(chrom = as.numeric(chrom)) %>%
arrange(chrom) %>%
mutate(CNVStatus = case_when(seg.mean > 0.3 ~ "Amplification",
seg.mean < -0.3 ~ "Deletion", TRUE ~ "Normal"),
type = "SeSAMe")
combinedSet <- sesameMatch %>%
arrange(chrom)
}
combinedSet
}This is the final processing function to process out the normals, contributing to the genome-wide log2-ratio.
Analysis
We now move onto the actual meat of the analytic code. This will be split into statistics generation & visualization.
Basic Metrics
Bin size vs. accuracy – normal tissue
This was done to evaluate whether the tissues that were being used for normalization were actually normal. The code has been annotated with comments below to gain full understanding of the system.
This entire evaluation is contained in a function, which asks for a set of IDs (essentially the IDs of the normals, and the bin that we want to evaluate the statistics for.
caseCorr <- function(IDs, bin) {
Methyl <- c()
Ses <- c()
Con <- c()
for (ID in IDs) {
MethylMaster <- read.csv(paste0("~/Outputs/MethylMaster/Normals/",
bin, "/", ID, "/autocorrected_regions.csv"))
MethylMaster <- median(MethylMaster$Mean)
Sesame <- read.csv(paste0("~/Outputs/SeSAMe/Normals/",
bin, "/segments_", ID, ".csv"))
Sesame <- median(Sesame$seg.mean)
Conumee <- read.csv(paste0("~/Outputs/Conumee/LabNormals/",
bin, "/", ID, ".csv"))
Conumee <- median(Conumee$seg.mean)
Methyl <- c(Methyl, MethylMaster)
Ses <- c(Ses, Sesame)
Con <- c(Con, Conumee)
}
acc <- data.frame(Conumee_Median = median(Con), Conumee_SD = sd(Con),
Sesame_Median = median(Ses), Sesame_SD = sd(Ses), Methyl_Median = median(Methyl),
Methyl_SD = sd(Methyl))
acc
}It then takes the median log2 ratio of each sample for each software and bin, and returns it as a list, given by the initialized Methyl (MethylMasteR), Ses (SeSAMe) and Con (Conumee) values.
It then returns a data frame for easy post-processing.
To add it to the word document, I just read it off the terminal, but I could also create a dataframe for this purpose quite quickly. The driver code just involves querying the samples across the 3 bin sizes being studied.
Genomic Index for LMS
GenomicIndex <- function(dfCH3, sw) {
if (sw == F) {
dfSNP <- dfCH3 %>%
dplyr::filter(type == "SNP") %>%
dplyr::filter(CNVStatus != "Normal")
modChrom <- length(unique(dfSNP$chrom))
CNVCount <- nrow(dfSNP)
ret <- (CNVCount^2)/modChrom
return(ret)
} else {
# Filter out for clinically significant segments
# %>% filter(CNVStatus != Normal)
dfCH3f <- dfCH3 %>%
dplyr::filter(type == "Conumee" | type == "MethylMaster" |
type == "SeSAMe") %>%
dplyr::filter(CNVStatus != "Normal")
# Count
CNVCount <- nrow(dfCH3f)
modChrom <- length(unique(dfCH3f$chrom))
# Return value
ret <- (CNVCount^2)/modChrom
return(ret)
}
}This code takes a single dataframe from one of the technologies (as given by the preprocessor above for the LMS), filters it out only for that technology, filters for whether it reflects an CNV, and the counts how many there are, then takes the formula:
\[ GI = \frac{CNV^2}{22} \]
As given. It just then returns that value.
“sw” as an argument in the function is because I wanted to use the function for both SNPs and the methylation CNVs, so it is a convenient way to work with both types without using more if-statements.
Genome Modified
This is a pretty basic metric which works very similarly to the GI calculation above.
GenomeModified <- function(dfCH3) {
df <- dfCH3 %>%
dplyr::filter(type != "SNP", CNVStatus != "Normal") %>%
dplyr::mutate(width = loc.end - loc.start)
modifiedWidth <- sum(df$width)
hg19_info <- getChromInfoFromUCSC("hg19") %>%
dplyr::filter(assembled == "TRUE")
hg19_info <- hg19_info[1:22, ]
hg19_total <- sum(hg19_info$size)
return((modifiedWidth/hg19_total) * 100)
}It simply queries the information for hg19, filters it to the 22 chromosomes we are studying, sums the whole length, and divided it by the length of modified segments we actually have, and returns a percentage.
The driver code is quite important here however. It calculates the genome changed for each case, then adds it to an array. We can guarantee the order pair because the loop happens in the same order as the dataframe of the SNP data and how the cases are ordered in there.
Then, it prints out by taking a Pearson’s correlation on the different arrays, and in place, makes dataframes containing the percentage of genome changed, so that it can be manually inspected.
stts <- c(9202, 9203, 9327, 9328, 9337, 9338, 9350, 9353, 9354,
9355, 9356, 9357, 9358)
bins <- c(10000, 50000, 1e+05, 1e+06)
tech <- c("MethylMaster", "Conumee", "Sesame")
genomeCalc <- read_excel("~/Work/Analysis/LabData/LMS_SNP_EPIC_array_data/ChAS/ChAS_data_01Feb2026/design_13LMS_CNVs_other_info_01Feb2026.xlsx") %>%
dplyr::select("STT", "% Genome Changed") %>%
dplyr::rename(gc = "% Genome Changed")
bin10kb <- genomeCalc
binDef <- genomeCalc
bin100kb <- genomeCalc
bin1Mb <- genomeCalc
for (bin in bins) {
print(bin)
valM <- c()
valS <- c()
valC <- c()
for (stt in stts) {
valM <- c(valM, GenomeModified(labLMSProc(STTq = stt,
Technology = "MethylMaster", binSize = bin)))
valS <- c(valS, GenomeModified(labLMSProc(STTq = stt,
Technology = "Sesame", binSize = bin)))
valC <- c(valC, GenomeModified(labLMSProc(STTq = stt,
Technology = "Conumee", binSize = bin)))
}
if (bin == 10000) {
bin10kb <- data.frame(STT = bin10kb$STT, gc = bin10kb$gc,
pcentmodM = valM, pcentmodS = valS, pcentmodC = valC)
}
if (bin == 50000) {
binDef <- data.frame(STT = binDef$STT, gc = binDef$gc,
pcentmodM = valM, pcentmodS = valS, pcentmodC = valC)
}
if (bin == 1e+05) {
bin100kb <- data.frame(STT = bin100kb$STT, gc = bin100kb$gc,
pcentmodM = valM, pcentmodS = valS, pcentmodC = valC)
}
if (bin == 1e+06) {
bin1Mb <- data.frame(STT = bin1Mb$STT, gc = bin1Mb$gc,
pcentmodM = valM, pcentmodS = valS, pcentmodC = valC)
}
print(paste0("MethylMasteR: ", cor(genomeCalc$gc, valM)))
print(paste0("SeSAMe: ", cor(genomeCalc$gc, valS)))
print(paste0("Conumee: ", cor(genomeCalc$gc, valC)))
}## [1] 10000## [1] "MethylMasteR: 0.687649075571811"
## [1] "SeSAMe: 0.00278326955354341"
## [1] "Conumee: -0.400415556914374"
## [1] 50000## [1] "MethylMasteR: 0.755074036591727"
## [1] "SeSAMe: -0.0217828755036478"
## [1] "Conumee: -0.511121929626427"
## [1] 1e+05## [1] "MethylMasteR: 0.754376210845057"
## [1] "SeSAMe: 0.0390561094591397"
## [1] "Conumee: -0.477686025489507"
## [1] 1e+06## [1] "MethylMasteR: 0.740706152419858"
## [1] "SeSAMe: 0.0605428007233103"
## [1] "Conumee: -0.443940764266878"Advanced Metrics
Accuracy Across Bins
fpCheck <- function(df) {
library(GenomicRanges)
library(dplyr)
df <- df %>%
dplyr::select(-c("Gene")) # Removes genes, it's unnecessary for this purpose
pred_df <- df %>%
filter(!(type == "SNP")) # The methylation dataset
pred_df$chrom <- as.character(pred_df$chrom)
truth_df <- df %>%
filter(type == "SNP") # The SNP dataset
truth_df$chrom <- as.character(truth_df$chrom)
# Both chromosomes are made into characters because we
# want to use them as factors ---- Step 1: hg19
# chromosome sizes (numeric chromosomes 1 to 22) ----
hg19_info <- getChromInfoFromUCSC("hg19") %>%
dplyr::filter(assembled == "TRUE") # Just gets the main dataset from UCSC.
hg19_info <- hg19_info[1:22, ] # Only uses the first 22 chromosomes.
hg19_chr_sizes <- data.frame(Chromosome = as.character(1:22),
Genome_bp = hg19_info$size) # Makes them into a referenceable dataframe.
# ---- Step 2: Convert to GRanges ---- Does what it
# says on the tin
truth_gr <- GRanges(seqnames = truth_df$chrom, ranges = IRanges(start = truth_df$loc.start,
end = truth_df$loc.end), CNV = truth_df$CNVStatus)
pred_gr <- GRanges(seqnames = pred_df$chrom, ranges = IRanges(start = pred_df$loc.start,
end = pred_df$loc.end), CNV = pred_df$CNVStatus)
# ---- Step 3: Overlaps and TP ----
hits <- findOverlaps(pred_gr, truth_gr) # Finds the overlaps between the two GRanges
overlap_ranges <- pintersect(pred_gr[queryHits(hits)], truth_gr[subjectHits(hits)])
pred_cnv <- mcols(pred_gr)$CNV[queryHits(hits)] # Returns whether the intersections are deletions, amplifications or normals
truth_cnv <- mcols(truth_gr)$CNV[subjectHits(hits)] # Returns whether the intersections are deletions, amplifications or normals
# The returns are for the corresponding datasets.
tp_df <- data.frame(Chromosome = as.character(seqnames(overlap_ranges)),
width = width(overlap_ranges), pred_cnv = pred_cnv, truth_cnv = truth_cnv) # Creates a dataframe from the given data
tp_df <- tp_df %>%
filter(pred_cnv == truth_cnv) %>%
group_by(Chromosome) %>%
summarise(TP_bp = sum(width), .groups = "drop")
# ---- Step 4: False Positives ----
fp_df <- data.frame(Chromosome = as.character(seqnames(overlap_ranges)),
width = width(overlap_ranges), pred_cnv = pred_cnv, truth_cnv = truth_cnv) %>%
filter(pred_cnv != truth_cnv, truth_cnv == "Normal") %>%
group_by(Chromosome) %>%
summarise(FP_bp = sum(width), .groups = "drop") # Calculates the false positives
# ---- Step 5: False Negatives ----
fn_df <- data.frame(Chromosome = as.character(seqnames(overlap_ranges)),
width = width(overlap_ranges), pred_cnv = pred_cnv, truth_cnv = truth_cnv) %>%
filter(pred_cnv != truth_cnv, pred_cnv == "Normal") %>%
group_by(Chromosome) %>%
summarise(FN_bp = sum(width), .groups = "drop") # Calculates the false negatives
# ---- Step 6: Merge and compute accuracy ----
final_eval <- hg19_chr_sizes %>%
left_join(tp_df, by = "Chromosome") %>%
left_join(fp_df, by = "Chromosome") %>%
left_join(fn_df, by = "Chromosome") %>%
mutate(across(c(TP_bp, FP_bp, FN_bp), ~replace_na(.,
0))) %>%
mutate(CNV_bp = TP_bp + FP_bp + FN_bp, TN_bp = Genome_bp -
CNV_bp, Accuracy = (TP_bp + TN_bp)/Genome_bp, CNV_Only_Accuracy = ifelse((TP_bp +
FP_bp + FN_bp) == 0, NA, TP_bp/(TP_bp + FP_bp + FN_bp))) %>%
arrange(as.numeric(Chromosome)) # Joins all the analysis together, so it can be seen at once, and then calculates the accuracy across each case
accuracy <- sum(final_eval$Accuracy)/22
return(list(final_eval, accuracy))
}This takes the processed dataframes from above, and checks against all possibilities, true negatives, true positives, and their false counterparts. It has been commented appropriately for understanding, as they all interact with each other.
Gene level analysis
There are a lot of moving parts to this visualization. This is done step by step. The below function annotates the dataframe from org.Hs.eg.db (a database of Homo Sapiens genomes), using Entrez genes. This will then enable a post processing step to generate the graphs which I showed earlier.
This happens by:
Annotating the genes initially with the Entrez gene database
It then puts both of them into GRanges to intersect the two to make sure that we don’t call segments that aren’t a part of the genes we are studying
It then annotates the segments with their relevant genes.
It can happen that sometimes genes are split across two software-generated segments or SNP segments. In these cases, we take the average of the segments.
NoGraphGeneGen <- function(Gene, db = NULL, case) {
# Updated function.
# This section annotates the processed dataframe with
# genes by Querying Entrez to get the genes we want to,
# get their locations Overlap those locations onto the
# existing dataframe, and voila We know where the genes
# are!
entrez_idsDB <- mapIds(org.Hs.eg.db, keys = Gene, column = "ENTREZID",
keytype = "SYMBOL", multiVals = "first")
chr_locations <- AnnotationDbi::select(org.Hs.eg.db, keys = entrez_idsDB,
columns = c("CHR", "CHRLOC", "CHRLOCEND"), keytype = "ENTREZID")
txdb <- TxDb.Hsapiens.UCSC.hg19.knownGene
gene_ranges <- genes(txdb)
target_genes_ranges <- gene_ranges[gene_ranges$gene_id %in%
entrez_idsDB]
coords_df <- as.data.frame(target_genes_ranges)
coords_df$entrez_id <- target_genes_ranges$gene_id
coords_final <- coords_df[, c("entrez_id", "seqnames", "start",
"end", "strand", "width")] %>%
dplyr::mutate(chrom = seqnames) %>%
dplyr::mutate(chrom = as.numeric(gsub("chr", "", chrom)),
Gene = Gene) %>%
dplyr::select(-c(seqnames))
rownames(coords_final) <- Gene
if (!is.null(db)) {
print("is here")
dt <- db %>%
dplyr::filter((Gene == "0")) %>%
dplyr::mutate(Gene = NA) # We make sure we don't hold onto anything that
# is not associated with a gene
gcoords <- coords_final %>%
dplyr::mutate(loc.start = as.numeric(start), loc.end = as.numeric(end)) %>%
dplyr::mutate(seg.mean = 0, CNVStatus = "Normal",
type = "Gene") %>%
dplyr::mutate(Gene = Gene) %>%
dplyr::select(-c("strand", "width", "entrez_id",
"start", "end"))
grC <- makeGRangesFromDataFrame(gcoords, start.field = "loc.start",
end.field = "loc.end", keep.extra.columns = TRUE)
grDt <- makeGRangesFromDataFrame(dt, start.field = "loc.start",
end.field = "loc.end", keep.extra.columns = TRUE)
overlaps <- findOverlaps(grDt, grC)
# Extract intersection and bind gene annotation
# immediately before any row changes
intersection_df <- as.data.frame(pintersect(grDt[queryHits(overlaps)],
grC[subjectHits(overlaps)])) %>%
dplyr::select(-c("strand", "width", "hit", "Gene")) %>%
dplyr::rename(loc.start = start, loc.end = end) %>%
dplyr::mutate(chrom = as.numeric(seqnames)) %>%
dplyr::select(-c("seqnames"))
gene_annotations <- coords_final[subjectHits(overlaps),
"Gene", drop = FALSE]
overlapping_regions <- cbind(intersection_df, Gene = gene_annotations$Gene)
# Find genes with no overlap for each type
all_types <- unique(dt$type)
missing_rows <- list()
for (t in all_types) {
# Detects if the gene is split between two or
# more segments by taking the average instead
dt_type <- dt %>%
dplyr::filter(type == t)
grDt_type <- makeGRangesFromDataFrame(dt_type, start.field = "loc.start",
end.field = "loc.end", keep.extra.columns = TRUE)
matched_genes <- unique(overlapping_regions$Gene[overlapping_regions$type ==
t])
missing_genes <- setdiff(rownames(coords_final),
matched_genes)
for (g in missing_genes) {
gene_row <- coords_final[g, ]
gene_mid <- (gene_row$start + gene_row$end)/2
# Find flanking segments on same chromosome
dt_chr <- dt_type %>%
dplyr::filter(chrom == gene_row$chrom)
if (nrow(dt_chr) == 0)
next
# Left flank: segments ending before gene
# midpoint
left <- dt_chr %>%
dplyr::filter(loc.end < gene_mid) %>%
dplyr::slice_max(loc.end, n = 1)
# Right flank: segments starting after gene
# midpoint
right <- dt_chr %>%
dplyr::filter(loc.start > gene_mid) %>%
dplyr::slice_min(loc.start, n = 1)
if (nrow(left) == 0 || nrow(right) == 0)
next
avg_seg <- mean(c(left$seg.mean, right$seg.mean))
avg_cnv <- ifelse(left$CNVStatus == right$CNVStatus,
left$CNVStatus, "Normal")
missing_rows[[length(missing_rows) + 1]] <- data.frame(chrom = gene_row$chrom,
loc.start = gene_row$start, loc.end = gene_row$end,
seg.mean = avg_seg, type = t, CNVStatus = avg_cnv,
Gene = g, stringsAsFactors = FALSE)
}
}
if (length(missing_rows) > 0)
{
overlapping_regions <- rbind(overlapping_regions,
dplyr::bind_rows(missing_rows))
} # Makes sure we have gotten everything
overlapping_regions <- unique(overlapping_regions[c(6,
1, 2, 3, 4, 5, 7)])
overlapping_regions$type <- ifelse(overlapping_regions$type ==
"Conumee", "Gene_Conumee", ifelse(overlapping_regions$type ==
"SeSAMe", "Gene_SeSAMe", ifelse(overlapping_regions$type ==
"MethylMaster", "Gene_MMasteR", ifelse(overlapping_regions$type ==
"SNP", "Gene_SNP", "Unknown"))))
overlapping_regions <- overlapping_regions %>%
dplyr::mutate(case = case)
overlapping_regions
} else {
coords_final
}
}We then now have to deal with visualizations.
ap10000 <- NULL
ap50000 <- NULL
ap1e05 <- NULL
ap1e06 <- NULL
Gene <- c("MYC", "MYOCD", "CCNE1", "CDKN2A", "PTEN", "RB1", "TP53")
for (stt in stts) {
ap10000 <- rbind(ap10000, NoGraphGeneGen(Gene = Gene, db = rbind(labLMSProc(stt,
"MethylMaster", 10000), labLMSProc(stt, "Conumee", 10000),
labLMSProc(stt, "Sesame", 10000)), case = stt))
ap50000 <- rbind(ap50000, NoGraphGeneGen(Gene = Gene, db = rbind(labLMSProc(stt,
"MethylMaster", 50000), labLMSProc(stt, "Conumee", 50000),
labLMSProc(stt, "Sesame", 50000)), case = stt))
ap1e05 <- rbind(ap1e05, NoGraphGeneGen(Gene = Gene, db = rbind(labLMSProc(stt,
"MethylMaster", 1e+05), labLMSProc(stt, "Conumee", 1e+05),
labLMSProc(stt, "Sesame", 1e+05)), case = stt))
ap1e06 <- rbind(ap1e06, NoGraphGeneGen(Gene = Gene, db = rbind(labLMSProc(stt,
"MethylMaster", 1e+06), labLMSProc(stt, "Conumee", 1e+06),
labLMSProc(stt, "Sesame", 1e+06)), case = stt))
}## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"## [1] "is here"We go through all the potential cases to understand what we are dealing with and so that we can implement the visualization by processing the data appropriately.
# Saving raw data
ap10000 <- ap10000 %>%
dplyr::mutate(bin = 10000)
ap50000 <- ap50000 %>%
dplyr::mutate(bin = 50000)
ap1e05 <- ap1e05 %>%
dplyr::mutate(bin = 1e+05)
ap1e06 <- ap1e06 %>%
dplyr::mutate(bin = 1e+06)
ap <- rbind(ap10000, ap50000, ap1e05, ap1e06) %>%
dplyr::select(-c("chrom")) %>%
dplyr::mutate(width = loc.end - loc.start)
ap <- split(ap, ap$Gene)
for (i in seq_along(ap)) {
file_name <- paste0(names(ap)[i], ".csv")
write.csv(ap[[i]], file = paste0("~/Work/Analysis/Statistics/LabLMS/GeneConcordance/rawData/",
file_name), row.names = FALSE)
}
ap[[Gene[1]]] <- split(ap[[Gene[1]]], ap[[Gene[1]]]$bin)
ap[[Gene[2]]] <- split(ap[[Gene[2]]], ap[[Gene[2]]]$bin)
ap[[Gene[3]]] <- split(ap[[Gene[3]]], ap[[Gene[3]]]$bin)
ap[[Gene[4]]] <- split(ap[[Gene[4]]], ap[[Gene[4]]]$bin)
ap[[Gene[5]]] <- split(ap[[Gene[5]]], ap[[Gene[5]]]$bin)
ap[[Gene[6]]] <- split(ap[[Gene[6]]], ap[[Gene[6]]]$bin)
ap[[Gene[7]]] <- split(ap[[Gene[7]]], ap[[Gene[7]]]$bin)We split everything across into genes, so that we can visualize it by gene instead of by just bin or case, as those aren’t really interesting by themselves for this usecase.
# Looking for concordance
genes <- names(ap)
bins <- c("50000", "10000", "1e+05", "1e+06")
states <- c("Conumee – default bin size", "Conumee – 10kb",
"Conumee – 100kb", "Conumee – 1Mb", "Sesame – default bin size",
"Sesame – 10kb", "Sesame – 100kb", "Sesame – 1Mb",
"MethylMasteR – default bin size", "MethylMasteR – 10kb",
"MethylMasteR – 100kb", "MethylMasteR – 1Mb")
CCNE1 <- c(1:length(states))
CDKN2A <- c(1:length(states))
MYC <- c(1:length(states))
MYOCD <- c(1:length(states))
PTEN <- c(1:length(states))
RB1 <- c(1:length(states))
TP53 <- c(1:length(states))
output.df <- data.frame(states, CCNE1, CDKN2A, MYC, MYOCD, PTEN,
RB1, TP53)
i <- 0
j <- 0
for (i in seq_along(ap)) {
for (j in bins) {
Methyl <- ap[[i]][[j]] %>%
dplyr::filter(type == "Gene_MMasteR") %>%
dplyr::mutate(seg.mean = as.numeric(seg.mean))
Ses <- ap[[i]][[j]] %>%
dplyr::filter(type == "Gene_SeSAMe") %>%
dplyr::mutate(seg.mean = as.numeric(seg.mean))
Con <- ap[[i]][[j]] %>%
dplyr::filter(type == "Gene_Conumee") %>%
dplyr::mutate(seg.mean = as.numeric(seg.mean))
Snp <- ap[[i]][[j]] %>%
dplyr::filter(type == "Gene_SNP") %>%
dplyr::mutate(seg.mean = as.numeric(seg.mean))
Snp <- Snp %>%
group_by(case) %>%
summarize(log2ratio = mean(seg.mean))
mCorr <- cor(Methyl$seg.mean, Snp$log2ratio)
sCorr <- cor(Ses$seg.mean, Snp$log2ratio)
cCorr <- cor(Con$seg.mean, Snp$log2ratio)
print(paste0(mCorr, " ", sCorr, " ", cCorr))
tag <- 0
if (j == "50000") {
tag <- 1
}
if (j == "10000") {
tag <- 2
}
if (j == "1e+05") {
tag <- 3
}
if (j == "1e+06") {
tag <- 4
}
output.df[tag, i + 1] <- mCorr
output.df[tag + 4, i + 1] <- sCorr
output.df[tag + 8, i + 1] <- cCorr
}
}## [1] "0.826417880352618 0.813440323796319 0.845943210618849"
## [1] "0.849134403884159 0.836896340412142 0.844368393910045"
## [1] "0.843005346823355 0.829474876393488 0.831894387147325"
## [1] "0.79489252657153 0.805152583360047 0.845781813166039"
## [1] "0.770286775383964 0.824711869003358 0.820810622368492"
## [1] "0.784476652907735 0.842870595760608 0.837815008814301"
## [1] "0.828431908549295 0.863729216325694 0.814386084893461"
## [1] "0.776951840796653 0.809258743289404 0.843185857302898"
## [1] "0.550119920847339 0.533111942514943 0.623517986495779"
## [1] "0.594882099031743 0.513851869692022 0.379050348014905"
## [1] "0.728429963922226 0.590602707782826 0.616991728990406"
## [1] "0.599560636492384 0.493157855491004 0.613060168297233"
## [1] "0.703082777869045 0.737155429945174 0.757266803619211"
## [1] "0.759241487110125 0.721856082001065 0.743062822010953"
## [1] "0.788779978335249 0.738024751153176 0.744233670582984"
## [1] "0.737604178197128 0.736457605970674 0.755436379247107"
## [1] "0.173994453322823 0.201614441620541 0.158087271330171"
## [1] "0.183646163979431 0.212871187889706 0.0466493488085179"
## [1] "0.156183661438954 0.212959236115107 0.174572305471204"
## [1] "-0.00562029336073261 0.0525883803472474 0.00346858286312494"
## [1] "0.284964544161419 -0.103117646873573 0.55669826414135"
## [1] "0.273210786726921 0.0727401864100489 0.409547861912897"
## [1] "0.444760905459316 -0.022745446473997 0.34792966700185"
## [1] "0.395649026750018 0.328853019174688 0.689928235069948"
## [1] "0.92032642794316 0.895923294419126 0.889208352500564"
## [1] "0.91015423233901 0.887451563223858 0.831874713823817"
## [1] "0.925389940484122 0.898103823567314 0.894178403267808"
## [1] "0.838169101292533 0.911586067526427 0.898609062298142"# Melt to long format
df_long <- melt(output.df, id.vars = "states", variable.name = "gene",
value.name = "correlation")
# Keep row order
df_long$states <- factor(df_long$states, levels = rev(output.df$states))
# Plot
p <- ggplot(df_long, aes(x = gene, y = states, fill = correlation)) +
geom_tile(color = "black", linewidth = 0.5) + geom_text(aes(label = sprintf("%.2f",
correlation)), size = 3, color = "black") + scale_fill_gradient2(low = "#2166ac",
mid = "#f7f7f7", high = "#50C878", midpoint = 0.5, limits = c(min(df_long$correlation),
1), name = "Correlation") + labs(title = "CNV Method Comparison by Gene",
x = "Gene", y = "Method & Bin Size") + theme_minimal(base_size = 12) +
theme(plot.title = element_text(hjust = 0.5, face = "bold",
size = 14), axis.text.x = element_text(angle = 30, hjust = 1,
face = "bold"), axis.text.y = element_text(size = 9),
panel.grid = element_blank(), legend.position = "right")This code develops the correlation by using the “cor” function.
This correlation is taking the correlation of the log2 ratios of the genes we are studying across the cases.
What this means is that each case being studied has a log2 ratio value associated to a gene. The PCC is taken across those values for each genes.
It is pretty simplistic, it places the correlation value from Pearson’s Correlation Coefficient into an output dataframe. It then melts the gene into the appropriate matrix, and then makes it into a plot.
Visualizations
The visualization suite is pretty simple.
plot_cnv_segments <- function(df, anno = NULL) {
df <- df %>%
mutate(
type_group = ifelse(type == "SNP", "SNP", "non-SNP")
) %>%
arrange(chrom, loc.start)
df$seg.mean <- as.numeric(df$seg.mean)
# Calculate chromosome cumulative positions
chr_lengths <- df %>%
dplyr::group_by(chrom) %>%
dplyr::summarize(chr_len = max(loc.end), .groups = "drop") %>%
arrange(chrom) %>%
mutate(chr_start = lag(cumsum(chr_len), default = 0)) %>%
mutate(chr_mid = chr_start + chr_len / 2)
print(chr_lengths)
df <- df %>%
left_join(chr_lengths, by = "chrom") %>%
mutate(
start_cum = loc.start + chr_start,
end_cum = loc.end + chr_start
) %>%mutate(type = ifelse(type == "SNP", "SNP", type)) %>%
mutate(type = as.factor(type))
# Vertical chromosome boundaries
chr_boundaries <- chr_lengths %>%
mutate(x = chr_start) %>%
dplyr::select(chrom, x)
x_breaks <- chr_lengths$chr_mid
x_labels <- paste0("chr", chr_lengths$chrom)
x_labels <- c(x_labels)
print(x_labels)
print(df)
df$Gene[df$Gene == "0"] <- NA
# Plot
p <- ggplot(df, aes(x = start_cum, xend = end_cum, y = seg.mean, yend = seg.mean, label = Gene)) +
geom_segment(aes(color = type), size = 0.7, alpha = 0.8) +
geom_point(data = subset(df, type == "Gene_Conumee"), aes(x = start_cum, y = seg.mean, label = Gene), color = "green", size = 3) +
geom_point(data = subset(df, type == "Gene_SNP"), aes(x = start_cum, y = seg.mean, label = Gene), color = "gray40", size = 3) +
geom_point(data = subset(df, type == "Gene_SeSAMe"), aes(x = start_cum, y = seg.mean, label = Gene), color = "red", size = 3) +
geom_point(data = subset(df, type == "Gene_MMasteR"), aes(x = start_cum, y = seg.mean, label = Gene), color = "blue", size = 3) +
geom_text_repel(
box.padding = unit(0.35, "lines"), # Adjust padding around the label
point.padding = unit(0.3, "lines"), # Adjust padding around the point
segment.color = 'grey' # Color of the connecting lines
) +
geom_vline(data = chr_boundaries, aes(xintercept = x), color = "grey70", linetype = "dashed") +
# scale_color_manual(values = c("Amplification" = "red", "Deletion" = "blue", "Normal" = "black")) +
scale_x_continuous(breaks = x_breaks, labels = x_labels) +
scale_color_manual(values = c("SeSAMe" = "red", "MethylMaster" = "blue",
"Conumee" = "green", "SNP" = "black", "Gene" = "orange")) +
labs(
x = "Genomic Position (across chromosomes)",
y = "Segment Mean (log2 ratio)",
title = "CNV Segments Across Genome"
) + geom_hline(yintercept = -0.2, linetype = "dotted", color = "black") +
geom_hline(yintercept = 0.2, linetype = "dotted", color = "black") +
scale_y_continuous(breaks = c(-0.75, -0.5, -0.25, 0, 0.25,0.5,0.75)) +
theme_minimal() +
theme(
panel.grid.major.y = element_line(color = "grey90"),
panel.grid.major.x = element_blank(),
legend.position = "bottom"
)
return(p)
}The above code plots the Manhattan plots I have been showing off. It takes a dataframe preprocessed by the above functions, and then it sorts it , calculates the median positions to place every chromosome upon, finds the upper and lower bounds, and then plots everything on the plot I have shown before.
geneGen <- function(Gene, db = NULL){
entrez_idsDB <- mapIds(org.Hs.eg.db,
keys=Gene,
column="ENTREZID",
keytype="SYMBOL",
multiVals="first")
chr_locations <- AnnotationDbi::select(org.Hs.eg.db,
keys = entrez_idsDB,
columns = c("CHR", "CHRLOC", "CHRLOCEND"),
keytype = "ENTREZID")
txdb <- TxDb.Hsapiens.UCSC.hg19.knownGene
gene_ranges <- genes(txdb)
target_genes_ranges <- gene_ranges[gene_ranges$gene_id %in% entrez_idsDB]
coords_df <- as.data.frame(target_genes_ranges)
coords_df$entrez_id <- target_genes_ranges$gene_id
coords_final <- coords_df[, c("entrez_id", "seqnames", "start", "end",
"strand", "width")] %>%
dplyr::mutate(chrom=seqnames) %>%
dplyr::mutate(chrom = as.numeric(gsub("chr","",chrom)),
Gene = rownames(.)) %>%
dplyr::select(-c(seqnames))
rownames(coords_final) <- Gene
if(!is.null(db)){
print("is here")
dt <- db %>% dplyr::filter((Gene == "0")) %>%
dplyr::mutate(Gene = NA)
gcoords <- coords_final %>%
dplyr::mutate(loc.start = as.numeric(start), loc.end = as.numeric(end)) %>%
dplyr::mutate(seg.mean = 0, CNVStatus = "Normal", type = "Gene") %>%
dplyr::mutate(Gene = Gene) %>%
dplyr::select(-c("strand", "width", "entrez_id", "start", "end"))
grC <- makeGRangesFromDataFrame(gcoords,
start.field = "loc.start",
end.field = "loc.end",
keep.extra.columns = TRUE)
grDt <- makeGRangesFromDataFrame(dt,
start.field = "loc.start",
end.field = "loc.end",
keep.extra.columns = TRUE)
overlaps <- findOverlaps(grDt, grC)
overlapping_regions <- pintersect(grDt[queryHits(overlaps)], grC[subjectHits(overlaps)])
overlapping_regions <- as.data.frame(overlapping_regions) %>%
dplyr::select(-c("strand", "width", "hit", "Gene")) %>%
dplyr::rename(loc.start = start, loc.end = end) %>%
dplyr::mutate(chrom = as.numeric(seqnames)) %>%
dplyr::select(-c("seqnames"))
overlapping_regions <- dplyr::left_join(overlapping_regions, coords_final,
by=c("chrom"="chrom",
"loc.start" = "start",
"loc.end" = "end")) %>%
dplyr::select(-c("entrez_id", "strand", "width"))
overlapping_regions <- unique(overlapping_regions[c(6, 1, 2, 3, 4, 5, 7)])
overlapping_regions$type <- ifelse(
overlapping_regions$type == "Conumee", "Gene_Conumee",
ifelse(overlapping_regions$type == "SeSAMe", "Gene_SeSAMe",
ifelse(overlapping_regions$type == "MethylMaster", "Gene_MMasteR",
ifelse(overlapping_regions$type == "SNP", "Gene_SNP", "Unknown")))
)
overlapping_regions <- overlapping_regions %>% drop_na()
print(overlapping_regions)
# Developing visualization
mat <- matrix(NA, nrow = 4, ncol = length(unique(overlapping_regions$Gene)))
overlapping_regions <- overlapping_regions %>% drop_na()
print(unique(overlapping_regions$type))
colnames(mat) <- unique(overlapping_regions$Gene)
rownames(mat) <- unique(overlapping_regions$type)
for (i in 1:nrow(overlapping_regions)) {
row_index <- match(overlapping_regions$type[i], rownames(mat))
col_index <- match(overlapping_regions$Gene[i], colnames(mat))
mat[row_index, col_index] <- as.numeric(overlapping_regions$seg.mean[i])
}
mat[is.na(mat)] <- 0
print(mat)
colors <- rev(brewer.pal(n = 7, name = "RdBu"))
labels_matrix <- matrix(sprintf("%.3f", mat),
nrow = nrow(mat),
ncol = ncol(mat))
ph <- pheatmap(
mat,
color = colors,
scale = "row", # Scales the values in each row/column/none to a z-score
cluster_rows = FALSE,
cluster_cols = FALSE,
show_rownames = TRUE, # Set to TRUE if you have few genes
display_numbers = labels_matrix,
main = "Gene Expression Heatmap (Log2 Ratio / Z-score)"
)
list(ph, overlapping_regions)
} else {
coords_final
}
}This above code is basically identical to the preprocessor in the gene-level analysis. It is merely that this includes some post-processing into a matrix to make a heatmap, and create the heatmap itself using a pheatmap.
geneAnno <- function(Gene, db = NULL) {
reference <- geneGen(Gene = Gene, db = db)
print(reference[[1]])
pheatmap_ggplot <- as.ggplot(reference[[1]]$gtable)
reference2 <- reference[[2]]
db <- unique(rbind(db, reference2))
img2 <- plot_cnv_segments(db)
return(list((img2 + pheatmap_ggplot + plot_layout(widths = unit(c(20,
8), c("null", "null")))), db))
}This combines the two, the gene heatmap and the Manhattan plot, into one singular plot.
A Run-through
Talking about code feels very abstract, so below is a little runthrough of ALL the code, taking through how a typical set of samples would be analyzed. Some of the driver code is dropped because it muddles understanding, but can be explained if needed.
Let’s take the code to be analysing case STT 9202, an LMS case, at 10000 basepair bins.
df <- rbind(labLMSProc(9202, "MethylMaster", 10000), labLMSProc(9202,
"Sesame", 10000), labLMSProc(9202, "Conumee", 10000)) # This creates the full database of data for that case at that basepair bin.
print(df)## seg.mean loc.start loc.end chrom type CNVStatus Gene
## 1 -0.3777818159 747994 28115000 1 MethylMaster Deletion 0
## 2 -0.7534818159 28185000 28505000 1 MethylMaster Deletion 0
## 3 -0.4224818159 28530000 38525000 1 MethylMaster Deletion 0
## 4 0.1562181841 38690000 186405000 1 MethylMaster Normal 0
## 5 0.3858181841 186560000 199570000 1 MethylMaster Amplification 0
## 6 0.1513181841 199885000 208295000 1 MethylMaster Normal 0
## 7 -0.3127818159 208480000 248923211 1 MethylMaster Deletion 0
## 8 -0.5230000000 754192 39046130 1 SNP Deletion 0
## 9 0.3290000000 39053684 71837405 1 SNP Amplification 0
## 10 0.5860000000 71858457 72654730 1 SNP Amplification 0
## 11 0.3720000000 72662685 76640953 1 SNP Amplification 0
## 12 -0.0230000000 76658494 77726109 1 SNP Normal 0
## 13 0.3400000000 77737217 93047956 1 SNP Amplification 0
## 14 0.0030000000 93073228 98750052 1 SNP Normal 0
## 15 0.3250000000 98766448 100543962 1 SNP Amplification 0
## 16 -0.0280000000 100549400 110221639 1 SNP Normal 0
## 17 0.2600000000 110222219 111181086 1 SNP Amplification 0
## 18 -0.0210000000 111193595 152411090 1 SNP Normal 0
## 19 0.3470000000 152411813 208551533 1 SNP Amplification 0
## 20 -0.5640000000 208569475 249212878 1 SNP Deletion 0
## 21 -0.3056818159 110000 46830000 2 MethylMaster Deletion 0
## 22 -1.3103818159 46880000 49160000 2 MethylMaster Deletion 0
## 23 -0.3053818159 49835000 200815000 2 MethylMaster Deletion 0
## 24 -0.5376818159 200840000 201305000 2 MethylMaster Deletion 0
## 25 -0.3142818159 201405000 242111765 2 MethylMaster Deletion 0
## 26 -0.5260000000 21494 47051551 2 SNP Deletion 0
## 27 -1.6880000000 47067057 49997218 2 SNP Deletion 0
## 28 -0.5610000000 50007748 243052331 2 SNP Deletion 0
## 29 0.0185181841 115000 198097780 3 MethylMaster Normal 0
## 30 -0.0690000000 63411 197852564 3 SNP Normal 0
## 31 0.0581181841 110000 190066561 4 MethylMaster Normal 0
## 32 -0.5940000000 69404 334213 4 SNP Deletion 0
## 33 -0.0470000000 360026 180023290 4 SNP Normal 0
## 34 -0.4110000000 180040368 180365623 4 SNP Deletion 0
## 35 -0.0540000000 180392930 190915650 4 SNP Normal 0
## 36 0.0446181841 50000 181369130 5 MethylMaster Normal 0
## 37 -0.0080000000 38139 392863 5 SNP Normal 0
## 38 0.2300000000 412226 788914 5 SNP Amplification 0
## 39 -0.0070000000 804103 180698312 5 SNP Normal 0
## 40 -0.0131818159 140000 170662990 6 MethylMaster Normal 0
## 41 -0.0320000000 204909 170913051 6 SNP Normal 0
## 42 -0.3608818159 50000 159247987 7 MethylMaster Deletion 0
## 43 -0.5470000000 41421 159118443 7 SNP Deletion 0
## 44 0.0127181841 195000 145039318 8 MethylMaster Normal 0
## 45 -0.0200000000 172417 39194984 8 SNP Normal 0
## 46 -1.6230000000 39217074 39460780 8 SNP Deletion 0
## 47 -0.0250000000 39480366 146292734 8 SNP Normal 0
## 48 -0.0264818159 215000 138187359 9 MethylMaster Normal 0
## 49 -0.0240000000 204738 5021738 9 SNP Normal 0
## 50 -0.2510000000 5023689 5069837 9 SNP Deletion 0
## 51 -0.0480000000 5071049 129580187 9 SNP Normal 0
## 52 -0.2400000000 129582563 129844541 9 SNP Deletion 0
## 53 0.0000000000 129854773 141054761 9 SNP Normal 0
## 54 0.0141181841 125000 74415000 10 MethylMaster Normal 0
## 55 -0.3479818159 74595000 133625233 10 MethylMaster Deletion 0
## 56 -0.0340000000 126070 76263261 10 SNP Normal 0
## 57 -0.5810000000 76287336 135434303 10 SNP Deletion 0
## 58 -0.0006818159 145000 62735000 11 MethylMaster Normal 0
## 59 -0.3424818159 62760000 62840000 11 MethylMaster Deletion 0
## 60 -0.0074818159 62865000 134993311 11 MethylMaster Normal 0
## 61 -0.0150000000 192764 134938847 11 SNP Normal 0
## 62 0.0027181841 70000 133222655 12 MethylMaster Normal 0
## 63 -0.0310000000 189400 133818115 12 SNP Normal 0
## 64 0.0403181841 18679053 47270000 13 MethylMaster Normal 0
## 65 -0.3266818159 47630000 61950000 13 MethylMaster Deletion 0
## 66 0.0940181841 63095000 114332164 13 MethylMaster Normal 0
## 67 -0.0190000000 19084823 48054661 13 SNP Normal 0
## 68 -0.5470000000 48058244 63661960 13 SNP Deletion 0
## 69 0.0190000000 63685149 115103150 13 SNP Normal 0
## 70 0.0220181841 19770857 71035000 14 MethylMaster Normal 0
## 71 -0.3619818159 71155000 90290000 14 MethylMaster Deletion 0
## 72 -0.0233818159 90360000 106751859 14 MethylMaster Normal 0
## 73 -0.0220000000 20219083 71568215 14 SNP Normal 0
## 74 -0.6010000000 71580778 90801109 14 SNP Deletion 0
## 75 0.0170000000 90815342 106836445 14 SNP Normal 0
## 76 -0.2410000000 106839840 106931347 14 SNP Deletion 0
## 77 -0.0370000000 106931821 107282024 14 SNP Normal 0
## 78 -0.0141818159 20232279 101850595 15 MethylMaster Normal 0
## 79 -0.0180000000 20161372 44502266 15 SNP Normal 0
## 80 0.2050000000 44514571 44777942 15 SNP Amplification 0
## 81 -0.0040000000 44788617 102397317 15 SNP Normal 0
## 82 -0.0895818159 40000 48010000 16 MethylMaster Normal 0
## 83 -0.3532818159 48160000 54995000 16 MethylMaster Deletion 0
## 84 -0.0350818159 55185000 55785000 16 MethylMaster Normal 0
## 85 -0.3510818159 55925000 56730000 16 MethylMaster Deletion 0
## 86 -0.0746818159 56820000 57925000 16 MethylMaster Normal 0
## 87 -0.3635818159 57995000 90149173 16 MethylMaster Deletion 0
## 88 0.0300000000 83887 48175235 16 SNP Normal 0
## 89 -0.5670000000 48185960 55137655 16 SNP Deletion 0
## 90 0.0520000000 55156505 55879117 16 SNP Normal 0
## 91 -0.5860000000 55889730 56698268 16 SNP Deletion 0
## 92 0.0290000000 56724810 57983711 16 SNP Normal 0
## 93 -0.5640000000 58011450 90158005 16 SNP Deletion 0
## 94 -0.0707818159 130000 68480000 17 MethylMaster Normal 0
## 95 0.1569181841 68530000 72070000 17 MethylMaster Normal 0
## 96 -0.0682818159 72115000 83168721 17 MethylMaster Normal 0
## 97 0.0000000000 400959 80263427 17 SNP Normal 0
## 98 0.0574181841 135000 80206643 18 MethylMaster Normal 0
## 99 0.0010000000 12842 78007784 18 SNP Normal 0
## 100 -0.1467818159 175000 29890000 19 MethylMaster Normal 0
## 101 0.0527181841 29975000 32370000 19 MethylMaster Normal 0
## 102 -0.1348818159 32490000 34390000 19 MethylMaster Normal 0
## 103 -0.4709818159 34455000 58588808 19 MethylMaster Deletion 0
## 104 0.0100000000 247232 20170214 19 SNP Normal 0
## 105 -0.3030000000 20179614 20462595 19 SNP Deletion 0
## 106 -0.0540000000 20473553 34916011 19 SNP Normal 0
## 107 -0.5750000000 34931904 59093239 19 SNP Deletion 0
## 108 -0.0246818159 178168 64292084 20 MethylMaster Normal 0
## 109 -0.0130000000 69094 62912463 20 SNP Normal 0
## 110 0.0343181841 10569444 46679992 21 MethylMaster Normal 0
## 111 0.0440000000 9648315 48097610 21 SNP Normal 0
## 112 -0.0662818159 16567005 50769234 22 MethylMaster Normal 0
## 113 0.0300000000 16054713 24341388 22 SNP Normal 0
## 114 0.6420000000 24346428 24390318 22 SNP Amplification 0
## 115 0.0210000000 24394088 51213826 22 SNP Normal 0
## 116 -0.3008000000 677994 16510000 1 SeSAMe Deletion 0
## 117 0.0215000000 16570000 16779582 1 SeSAMe Normal 0
## 118 -0.3448000000 16869582 28185000 1 SeSAMe Deletion 0
## 119 -0.6069000000 28275000 28695000 1 SeSAMe Deletion 0
## 120 -0.3593000000 28795000 38525000 1 SeSAMe Deletion 0
## 121 0.2126000000 38690000 186405000 1 SeSAMe Normal 0
## 122 0.4444000000 186560000 199570000 1 SeSAMe Amplification 0
## 123 0.2130000000 199885000 208295000 1 SeSAMe Normal 0
## 124 -0.2521000000 208480000 248923211 1 SeSAMe Normal 0
## 125 -0.5230000000 754192 39046130 1 SNP Deletion 0
## 126 0.3290000000 39053684 71837405 1 SNP Amplification 0
## 127 0.5860000000 71858457 72654730 1 SNP Amplification 0
## 128 0.3720000000 72662685 76640953 1 SNP Amplification 0
## 129 -0.0230000000 76658494 77726109 1 SNP Normal 0
## 130 0.3400000000 77737217 93047956 1 SNP Amplification 0
## 131 0.0030000000 93073228 98750052 1 SNP Normal 0
## 132 0.3250000000 98766448 100543962 1 SNP Amplification 0
## 133 -0.0280000000 100549400 110221639 1 SNP Normal 0
## 134 0.2600000000 110222219 111181086 1 SNP Amplification 0
## 135 -0.0210000000 111193595 152411090 1 SNP Normal 0
## 136 0.3470000000 152411813 208551533 1 SNP Amplification 0
## 137 -0.5640000000 208569475 249212878 1 SNP Deletion 0
## 138 -0.2467000000 110000 46830000 2 SeSAMe Normal 0
## 139 -1.2535000000 46880000 49160000 2 SeSAMe Deletion 0
## 140 -0.2428000000 49835000 200815000 2 SeSAMe Normal 0
## 141 -0.4734000000 200840000 201305000 2 SeSAMe Deletion 0
## 142 -0.2557000000 201405000 242111765 2 SeSAMe Normal 0
## 143 -0.5260000000 21494 47051551 2 SNP Deletion 0
## 144 -1.6880000000 47067057 49997218 2 SNP Deletion 0
## 145 -0.5610000000 50007748 243052331 2 SNP Deletion 0
## 146 0.0762000000 115000 198172780 3 SeSAMe Normal 0
## 147 -0.0690000000 63411 197852564 3 SNP Normal 0
## 148 0.1150000000 65000 190066561 4 SeSAMe Normal 0
## 149 -0.5940000000 69404 334213 4 SNP Deletion 0
## 150 -0.0470000000 360026 180023290 4 SNP Normal 0
## 151 -0.4110000000 180040368 180365623 4 SNP Deletion 0
## 152 -0.0540000000 180392930 190915650 4 SNP Normal 0
## 153 0.1023000000 50000 181369130 5 SeSAMe Normal 0
## 154 -0.0080000000 38139 392863 5 SNP Normal 0
## 155 0.2300000000 412226 788914 5 SNP Amplification 0
## 156 -0.0070000000 804103 180698312 5 SNP Normal 0
## 157 0.0438000000 140000 170662990 6 SeSAMe Normal 0
## 158 -0.0320000000 204909 170913051 6 SNP Normal 0
## 159 -0.3015000000 50000 159247987 7 SeSAMe Deletion 0
## 160 -0.5470000000 41421 159118443 7 SNP Deletion 0
## 161 0.0701000000 160000 145039318 8 SeSAMe Normal 0
## 162 -0.0200000000 172417 39194984 8 SNP Normal 0
## 163 -1.6230000000 39217074 39460780 8 SNP Deletion 0
## 164 -0.0250000000 39480366 146292734 8 SNP Normal 0
## 165 0.0336000000 110000 138227359 9 SeSAMe Normal 0
## 166 -0.0240000000 204738 5021738 9 SNP Normal 0
## 167 -0.2510000000 5023689 5069837 9 SNP Deletion 0
## 168 -0.0480000000 5071049 129580187 9 SNP Normal 0
## 169 -0.2400000000 129582563 129844541 9 SNP Deletion 0
## 170 0.0000000000 129854773 141054761 9 SNP Normal 0
## 171 0.0729000000 70000 74415000 10 SeSAMe Normal 0
## 172 -0.2900000000 74595000 133625233 10 SeSAMe Normal 0
## 173 -0.0340000000 126070 76263261 10 SNP Normal 0
## 174 -0.5810000000 76287336 135434303 10 SNP Deletion 0
## 175 0.0508000000 130000 135013311 11 SeSAMe Normal 0
## 176 -0.0150000000 192764 134938847 11 SNP Normal 0
## 177 0.0600000000 55000 133222655 12 SeSAMe Normal 0
## 178 -0.0310000000 189400 133818115 12 SNP Normal 0
## 179 0.1000000000 18639053 47270000 13 SeSAMe Normal 0
## 180 -0.2705000000 47630000 62140000 13 SeSAMe Normal 0
## 181 0.1508000000 63120000 114332164 13 SeSAMe Normal 0
## 182 -0.0190000000 19084823 48054661 13 SNP Normal 0
## 183 -0.5470000000 48058244 63661960 13 SNP Deletion 0
## 184 0.0190000000 63685149 115103150 13 SNP Normal 0
## 185 0.0794000000 19187179 71035000 14 SeSAMe Normal 0
## 186 -0.3041000000 71155000 90290000 14 SeSAMe Deletion 0
## 187 0.0322000000 90360000 106796859 14 SeSAMe Normal 0
## 188 -0.0220000000 20219083 71568215 14 SNP Normal 0
## 189 -0.6010000000 71580778 90801109 14 SNP Deletion 0
## 190 0.0170000000 90815342 106836445 14 SNP Normal 0
## 191 -0.2410000000 106839840 106931347 14 SNP Deletion 0
## 192 -0.0370000000 106931821 107282024 14 SNP Normal 0
## 193 -0.3009000000 20062627 22068372 15 SeSAMe Deletion 0
## 194 0.0452000000 22569121 101875595 15 SeSAMe Normal 0
## 195 -0.0180000000 20161372 44502266 15 SNP Normal 0
## 196 0.2050000000 44514571 44777942 15 SNP Amplification 0
## 197 -0.0040000000 44788617 102397317 15 SNP Normal 0
## 198 -0.0305000000 40000 48010000 16 SeSAMe Normal 0
## 199 -0.2948000000 48160000 54995000 16 SeSAMe Normal 0
## 200 0.0270000000 55185000 55785000 16 SeSAMe Normal 0
## 201 -0.2897000000 55925000 56730000 16 SeSAMe Normal 0
## 202 -0.0154000000 56820000 57925000 16 SeSAMe Normal 0
## 203 -0.2987000000 57995000 90159173 16 SeSAMe Normal 0
## 204 0.0300000000 83887 48175235 16 SNP Normal 0
## 205 -0.5670000000 48185960 55137655 16 SNP Deletion 0
## 206 0.0520000000 55156505 55879117 16 SNP Normal 0
## 207 -0.5860000000 55889730 56698268 16 SNP Deletion 0
## 208 0.0290000000 56724810 57983711 16 SNP Normal 0
## 209 -0.5640000000 58011450 90158005 16 SNP Deletion 0
## 210 -0.0107000000 120000 68480000 17 SeSAMe Normal 0
## 211 0.2163000000 68530000 72070000 17 SeSAMe Normal 0
## 212 -0.0098000000 72115000 83168721 17 SeSAMe Normal 0
## 213 0.0000000000 400959 80263427 17 SNP Normal 0
## 214 0.1163000000 80000 80206643 18 SeSAMe Normal 0
## 215 0.0010000000 12842 78007784 18 SNP Normal 0
## 216 -0.0894000000 175000 29890000 19 SeSAMe Normal 0
## 217 0.1090000000 29975000 32370000 19 SeSAMe Normal 0
## 218 -0.0719000000 32490000 34390000 19 SeSAMe Normal 0
## 219 -0.4152000000 34455000 53560000 19 SeSAMe Deletion 0
## 220 -0.7416000000 53605000 53765000 19 SeSAMe Deletion 0
## 221 -0.3768000000 53820000 58588808 19 SeSAMe Deletion 0
## 222 0.0100000000 247232 20170214 19 SNP Normal 0
## 223 -0.3030000000 20179614 20462595 19 SNP Deletion 0
## 224 -0.0540000000 20473553 34916011 19 SNP Normal 0
## 225 -0.5750000000 34931904 59093239 19 SNP Deletion 0
## 226 0.0340000000 178168 64292084 20 SeSAMe Normal 0
## 227 -0.0130000000 69094 62912463 20 SNP Normal 0
## 228 0.0914000000 5055000 46679992 21 SeSAMe Normal 0
## 229 0.0440000000 9648315 48097610 21 SNP Normal 0
## 230 -0.0092000000 15422159 50769234 22 SeSAMe Normal 0
## 231 0.0300000000 16054713 24341388 22 SNP Normal 0
## 232 0.6420000000 24346428 24390318 22 SNP Amplification 0
## 233 0.0210000000 24394088 51213826 22 SNP Normal 0
## 234 -0.3180000000 93709 39040000 1 Conumee Deletion 0
## 235 0.1910000000 39115000 93105000 1 Conumee Normal 0
## 236 0.0430000000 93270000 98515000 1 Conumee Normal 0
## 237 0.2900000000 98685000 100545000 1 Conumee Amplification 0
## 238 0.0330000000 100595000 110285000 1 Conumee Normal 0
## 239 0.1820000000 110300000 111505000 1 Conumee Normal 0
## 240 0.0110000000 111595000 152240000 1 Conumee Normal 0
## 241 0.1900000000 152315000 185705000 1 Conumee Normal 0
## 242 0.3630000000 185820000 199735000 1 Conumee Amplification 0
## 243 0.1580000000 199910000 208510000 1 Conumee Normal 0
## 244 -0.2790000000 208690000 249220311 1 Conumee Deletion 0
## 245 -0.5230000000 754192 39046130 1 SNP Deletion 0
## 246 0.3290000000 39053684 71837405 1 SNP Amplification 0
## 247 0.5860000000 71858457 72654730 1 SNP Amplification 0
## 248 0.3720000000 72662685 76640953 1 SNP Amplification 0
## 249 -0.0230000000 76658494 77726109 1 SNP Normal 0
## 250 0.3400000000 77737217 93047956 1 SNP Amplification 0
## 251 0.0030000000 93073228 98750052 1 SNP Normal 0
## 252 0.3250000000 98766448 100543962 1 SNP Amplification 0
## 253 -0.0280000000 100549400 110221639 1 SNP Normal 0
## 254 0.2600000000 110222219 111181086 1 SNP Amplification 0
## 255 -0.0210000000 111193595 152411090 1 SNP Normal 0
## 256 0.3470000000 152411813 208551533 1 SNP Amplification 0
## 257 -0.5640000000 208569475 249212878 1 SNP Deletion 0
## 258 -0.2890000000 30000 47050000 2 Conumee Deletion 0
## 259 -1.2360000000 47095000 49795000 2 Conumee Deletion 0
## 260 -0.2900000000 50395000 243046238 2 Conumee Deletion 0
## 261 -0.5260000000 21494 47051551 2 SNP Deletion 0
## 262 -1.6880000000 47067057 49997218 2 SNP Deletion 0
## 263 -0.5610000000 50007748 243052331 2 SNP Deletion 0
## 264 0.0200000000 150000 197881215 3 Conumee Normal 0
## 265 -0.0690000000 63411 197852564 3 SNP Normal 0
## 266 0.0500000000 35000 190992138 4 Conumee Normal 0
## 267 -0.5940000000 69404 334213 4 SNP Deletion 0
## 268 -0.0470000000 360026 180023290 4 SNP Normal 0
## 269 -0.4110000000 180040368 180365623 4 SNP Deletion 0
## 270 -0.0540000000 180392930 190915650 4 SNP Normal 0
## 271 0.0460000000 35000 180797630 5 Conumee Normal 0
## 272 -0.0080000000 38139 392863 5 SNP Normal 0
## 273 0.2300000000 412226 788914 5 SNP Amplification 0
## 274 -0.0070000000 804103 180698312 5 SNP Normal 0
## 275 0.0250000000 130000 170977534 6 Conumee Normal 0
## 276 -0.0320000000 204909 170913051 6 SNP Normal 0
## 277 -0.3160000000 40000 159044332 7 Conumee Deletion 0
## 278 -0.5470000000 41421 159118443 7 SNP Deletion 0
## 279 0.0260000000 95000 146267011 8 Conumee Normal 0
## 280 -0.0200000000 172417 39194984 8 SNP Normal 0
## 281 -1.6230000000 39217074 39460780 8 SNP Deletion 0
## 282 -0.0250000000 39480366 146292734 8 SNP Normal 0
## 283 -0.0160000000 110000 141081716 9 Conumee Normal 0
## 284 -0.0240000000 204738 5021738 9 SNP Normal 0
## 285 -0.2510000000 5023689 5069837 9 SNP Deletion 0
## 286 -0.0480000000 5071049 129580187 9 SNP Normal 0
## 287 -0.2400000000 129582563 129844541 9 SNP Deletion 0
## 288 0.0000000000 129854773 141054761 9 SNP Normal 0
## 289 0.0060000000 80000 76205000 10 Conumee Normal 0
## 290 -0.3020000000 76310000 135482374 10 Conumee Deletion 0
## 291 -0.0340000000 126070 76263261 10 SNP Normal 0
## 292 -0.5810000000 76287336 135434303 10 SNP Deletion 0
## 293 0.0090000000 130000 134893258 11 Conumee Normal 0
## 294 -0.0150000000 192764 134938847 11 SNP Normal 0
## 295 0.0020000000 182870 133795948 12 Conumee Normal 0
## 296 -0.0310000000 189400 133818115 12 SNP Normal 0
## 297 0.0290000000 19100000 47985000 13 Conumee Normal 0
## 298 -0.2610000000 48350000 63100000 13 Conumee Deletion 0
## 299 0.0660000000 63860000 115094939 13 Conumee Normal 0
## 300 -0.0190000000 19084823 48054661 13 SNP Normal 0
## 301 -0.5470000000 48058244 63661960 13 SNP Deletion 0
## 302 0.0190000000 63685149 115103150 13 SNP Normal 0
## 303 0.0330000000 19210000 71515000 14 Conumee Normal 0
## 304 -0.3240000000 71610000 73705000 14 Conumee Deletion 0
## 305 -0.5770000000 73715000 74150000 14 Conumee Deletion 0
## 306 -0.3150000000 74185000 90760000 14 Conumee Deletion 0
## 307 -0.0080000000 90795000 107254770 14 Conumee Normal 0
## 308 -0.0220000000 20219083 71568215 14 SNP Normal 0
## 309 -0.6010000000 71580778 90801109 14 SNP Deletion 0
## 310 0.0170000000 90815342 106836445 14 SNP Normal 0
## 311 -0.2410000000 106839840 106931347 14 SNP Deletion 0
## 312 -0.0370000000 106931821 107282024 14 SNP Normal 0
## 313 0.0030000000 20185000 102430696 15 Conumee Normal 0
## 314 -0.0180000000 20161372 44502266 15 SNP Normal 0
## 315 0.2050000000 44514571 44777942 15 SNP Amplification 0
## 316 -0.0040000000 44788617 102397317 15 SNP Normal 0
## 317 -0.0810000000 80000 48165000 16 Conumee Normal 0
## 318 -0.3090000000 48215000 55040000 16 Conumee Deletion 0
## 319 0.0300000000 55225000 55885000 16 Conumee Normal 0
## 320 -0.3250000000 55970000 56715000 16 Conumee Deletion 0
## 321 -0.0410000000 56745000 57995000 16 Conumee Normal 0
## 322 -0.3390000000 58020000 90222377 16 Conumee Deletion 0
## 323 0.0300000000 83887 48175235 16 SNP Normal 0
## 324 -0.5670000000 48185960 55137655 16 SNP Deletion 0
## 325 0.0520000000 55156505 55879117 16 SNP Normal 0
## 326 -0.5860000000 55889730 56698268 16 SNP Deletion 0
## 327 0.0290000000 56724810 57983711 16 SNP Normal 0
## 328 -0.5640000000 58011450 90158005 16 SNP Deletion 0
## 329 -0.0470000000 15000 81122605 17 Conumee Normal 0
## 330 0.0000000000 400959 80263427 17 SNP Normal 0
## 331 0.0330000000 45000 78008624 18 Conumee Normal 0
## 332 0.0010000000 12842 78007784 18 SNP Normal 0
## 333 -0.1290000000 175000 34880000 19 Conumee Normal 0
## 334 -0.4130000000 34910000 59099492 19 Conumee Deletion 0
## 335 0.0100000000 247232 20170214 19 SNP Normal 0
## 336 -0.3030000000 20179614 20462595 19 SNP Deletion 0
## 337 -0.0540000000 20473553 34916011 19 SNP Normal 0
## 338 -0.5750000000 34931904 59093239 19 SNP Deletion 0
## 339 -0.0220000000 100000 62927760 20 Conumee Normal 0
## 340 -0.0130000000 69094 62912463 20 SNP Normal 0
## 341 0.0070000000 10843948 48099948 21 Conumee Normal 0
## 342 0.0440000000 9648315 48097610 21 SNP Normal 0
## 343 -0.0470000000 16165000 51212283 22 Conumee Normal 0
## 344 0.0300000000 16054713 24341388 22 SNP Normal 0
## 345 0.6420000000 24346428 24390318 22 SNP Amplification 0
## 346 0.0210000000 24394088 51213826 22 SNP Normal 0A reasonable contest would be that this data has a lot of duplications. Further processing actually eliminates this in the analytical functions, as they all contain unique filter functions to ENSURE this doesn’t happen.
GenomeModified(df) # We calculate how much of the genome is modified.## [1] 54.11321GenomicIndex(df, T) # Calculates the GI for the selected dataframe## [1] 240.1# An inherent limitation of this function is that it does
# one case at a time, else the # statistics break
suppressWarnings({
print("MethylMasteR")
print(fpCheck(labLMSProc(9202, "MethylMaster", 10000)))
print("SeSAMe")
print(fpCheck(labLMSProc(9202, "Sesame", 10000)))
print("Conumee")
print(fpCheck(labLMSProc(9202, "Conumee", 10000)))
})## [1] "MethylMasteR"## [[1]]
## Chromosome Genome_bp TP_bp FP_bp FN_bp CNV_bp TN_bp Accuracy
## 1 1 249250621 148673726 0 98364708 247038434 2212187 0.6053582
## 2 2 243199373 241125736 0 0 241125736 2073637 1.0000000
## 3 3 198022430 197737565 0 0 197737565 284865 1.0000000
## 4 4 191154276 189336897 0 549470 189886367 1267909 0.9971255
## 5 5 180915260 180237074 0 376689 180613763 301497 0.9979179
## 6 6 171115067 170458082 0 0 170458082 656985 1.0000000
## 7 7 159138663 159068444 0 0 159068444 70219 1.0000000
## 8 8 146364022 144558938 0 243707 144802645 1561377 0.9983349
## 9 9 141213431 137648465 0 308128 137956593 3256838 0.9978180
## 10 10 135534747 131626829 1668262 0 133295091 2239656 0.9876913
## 11 11 135006516 134616085 80001 0 134696086 310430 0.9994074
## 12 12 133851895 133033256 0 0 133033256 818639 1.0000000
## 13 13 115169878 92723951 424662 566961 93715574 21454304 0.9913899
## 14 14 107349540 85461659 413216 441110 86315985 21033555 0.9920416
## 15 15 102531392 81331967 0 263372 81595339 20936053 0.9974313
## 16 16 90354753 89351150 20427 0 89371577 983176 0.9997739
## 17 17 81195210 79767471 0 0 79767471 1427739 1.0000000
## 18 18 78077248 77872785 0 0 77872785 204463 1.0000000
## 19 19 59128983 57291338 461012 282982 58035332 1093651 0.9874174
## 20 20 63025520 62734296 0 0 62734296 291224 1.0000000
## 21 21 48129895 36110549 0 0 36110549 12019346 1.0000000
## 22 22 51304566 34149531 0 43891 34193422 17111144 0.9991445
## CNV_Only_Accuracy
## 1 0.6018243
## 2 1.0000000
## 3 1.0000000
## 4 0.9971063
## 5 0.9979144
## 6 1.0000000
## 7 1.0000000
## 8 0.9983170
## 9 0.9977665
## 10 0.9874844
## 11 0.9994061
## 12 1.0000000
## 13 0.9894188
## 14 0.9901023
## 15 0.9967722
## 16 0.9997714
## 17 1.0000000
## 18 1.0000000
## 19 0.9871803
## 20 1.0000000
## 21 1.0000000
## 22 0.9987164
##
## [[2]]
## [1] 0.9795842
##
## [1] "SeSAMe"## [[1]]
## Chromosome Genome_bp TP_bp FP_bp FN_bp CNV_bp TN_bp
## 1 1 249250621 107865408 0 138999562 246864970 2385651
## 2 2 243199373 2729497 0 238396239 241125736 2073637
## 3 3 198022430 197737565 0 0 197737565 284865
## 4 4 191154276 189336897 0 590066 189926963 1227313
## 5 5 180915260 180237074 0 376689 180613763 301497
## 6 6 171115067 170458082 0 0 170458082 656985
## 7 7 159138663 159068444 0 0 159068444 70219
## 8 8 146364022 144581521 0 243707 144825228 1538794
## 9 9 141213431 137698727 0 308128 138006855 3206576
## 10 10 135534747 75957193 0 57337898 133295091 2239656
## 11 11 135006516 134746084 0 0 134746084 260432
## 12 12 133851895 133033256 0 0 133033256 818639
## 13 13 115169878 79256856 0 14623718 93880574 21289304
## 14 14 107349540 85506659 413216 441110 86360985 20988555
## 15 15 102531392 79020125 1907001 263372 81190498 21340894
## 16 16 90354753 49651543 0 39728866 89380409 974344
## 17 17 81195210 79767471 0 0 79767471 1427739
## 18 18 78077248 77927785 0 0 77927785 149463
## 19 19 59128983 57191340 461012 282982 57935334 1193649
## 20 20 63025520 62734296 0 0 62734296 291224
## 21 21 48129895 37031678 0 0 37031678 11098217
## 22 22 51304566 34661823 0 43891 34705714 16598852
## Accuracy CNV_Only_Accuracy
## 1 0.44233013 0.43694092
## 2 0.01974978 0.01131981
## 3 1.00000000 1.00000000
## 4 0.99691314 0.99689320
## 5 0.99791787 0.99791439
## 6 1.00000000 1.00000000
## 7 1.00000000 1.00000000
## 8 0.99833493 0.99831723
## 9 0.99781800 0.99776730
## 10 0.57695057 0.56984239
## 11 1.00000000 1.00000000
## 12 1.00000000 1.00000000
## 13 0.87302480 0.84423063
## 14 0.99204164 0.99010750
## 15 0.97883211 0.97326814
## 16 0.56030132 0.55550812
## 17 1.00000000 1.00000000
## 18 1.00000000 1.00000000
## 19 0.98741744 0.98715820
## 20 1.00000000 1.00000000
## 21 1.00000000 1.00000000
## 22 0.99914450 0.99873534
##
## [[2]]
## [1] 0.8827626
##
## [1] "Conumee"## [[1]]
## Chromosome Genome_bp TP_bp FP_bp FN_bp CNV_bp TN_bp Accuracy
## 1 1 249250621 151524732 65053 95644747 247234532 2016089 0.6160098
## 2 2 243199373 242371241 0 0 242371241 828132 1.0000000
## 3 3 198022430 197702565 0 0 197702565 319865 1.0000000
## 4 4 191154276 190185986 0 590066 190776052 378224 0.9969131
## 5 5 180915260 180248935 0 376689 180625624 289636 0.9979179
## 6 6 171115067 170708143 0 0 170708143 406924 1.0000000
## 7 7 159138663 159002912 0 0 159002912 135751 1.0000000
## 8 8 146364022 145809214 0 243707 146052921 311101 0.9983349
## 9 9 141213431 140526129 0 308128 140834257 379174 0.9978180
## 10 10 135534747 135203235 0 0 135203235 331512 1.0000000
## 11 11 135006516 134700495 0 0 134700495 306021 1.0000000
## 12 12 133851895 133606549 0 0 133606549 245346 1.0000000
## 13 13 115169878 94869942 0 0 94869942 20299936 1.0000000
## 14 14 107349540 86744975 0 97618 86842593 20506947 0.9990907
## 15 15 102531392 81925968 0 263372 82189340 20342052 0.9974313
## 16 16 90354753 89665220 0 0 89665220 689533 1.0000000
## 17 17 81195210 79862469 0 0 79862469 1332741 1.0000000
## 18 18 78077248 77962785 0 0 77962785 114463 1.0000000
## 19 19 59128983 58490767 6012 282982 58779761 349222 0.9951125
## 20 20 63025520 62812464 0 0 62812464 213056 1.0000000
## 21 21 48129895 37253663 0 0 37253663 10876232 1.0000000
## 22 22 51304566 34994585 0 43891 35038476 16266090 0.9991445
## CNV_Only_Accuracy
## 1 0.6128785
## 2 1.0000000
## 3 1.0000000
## 4 0.9969070
## 5 0.9979145
## 6 1.0000000
## 7 1.0000000
## 8 0.9983314
## 9 0.9978121
## 10 1.0000000
## 11 1.0000000
## 12 1.0000000
## 13 1.0000000
## 14 0.9988759
## 15 0.9967955
## 16 1.0000000
## 17 1.0000000
## 18 1.0000000
## 19 0.9950834
## 20 1.0000000
## 21 1.0000000
## 22 0.9987473
##
## [[2]]
## [1] 0.9817169I am not running the full processing again as it is clearly visible how large the system is. Also, it works more like a black-box, so the graph kinda pops out of the code.
# Looking for concordance
genes <- names(ap)
bins <- c("50000", "10000", "1e+05", "1e+06")
states <- c("Conumee – default bin size", "Conumee – 10kb",
"Conumee – 100kb", "Conumee – 1Mb", "Sesame – default bin size",
"Sesame – 10kb", "Sesame – 100kb", "Sesame – 1Mb",
"MethylMasteR – default bin size", "MethylMasteR – 10kb",
"MethylMasteR – 100kb", "MethylMasteR – 1Mb")
CCNE1 <- c(1:length(states))
CDKN2A <- c(1:length(states))
MYC <- c(1:length(states))
MYOCD <- c(1:length(states))
PTEN <- c(1:length(states))
RB1 <- c(1:length(states))
TP53 <- c(1:length(states))
output.df <- data.frame(states, CCNE1, CDKN2A, MYC, MYOCD, PTEN,
RB1, TP53)
for (i in seq_along(ap)) {
for (j in bins) {
print(genes[i])
print(j)
Methyl <- ap[[i]][[j]] %>%
dplyr::filter(type == "Gene_MMasteR") %>%
dplyr::mutate(seg.mean = as.numeric(seg.mean))
Ses <- ap[[i]][[j]] %>%
dplyr::filter(type == "Gene_SeSAMe") %>%
dplyr::mutate(seg.mean = as.numeric(seg.mean))
Con <- ap[[i]][[j]] %>%
dplyr::filter(type == "Gene_Conumee") %>%
dplyr::mutate(seg.mean = as.numeric(seg.mean))
Snp <- ap[[i]][[j]] %>%
dplyr::filter(type == "Gene_SNP") %>%
dplyr::mutate(seg.mean = as.numeric(seg.mean))
Snp <- Snp %>%
group_by(case) %>%
summarize(log2ratio = mean(seg.mean))
mCorr <- cor(Methyl$seg.mean, Snp$log2ratio)
sCorr <- cor(Ses$seg.mean, Snp$log2ratio)
cCorr <- cor(Con$seg.mean, Snp$log2ratio)
print(paste0(mCorr, " ", sCorr, " ", cCorr))
tag <- 0
if (j == "50000") {
tag <- 1
}
if (j == "10000") {
tag <- 2
}
if (j == "1e+05") {
tag <- 3
}
if (j == "1e+06") {
tag <- 4
}
output.df[tag, i + 1] <- mCorr
output.df[tag + 4, i + 1] <- sCorr
output.df[tag + 8, i + 1] <- cCorr
}
}## [1] "CCNE1"
## [1] "50000"
## [1] "0.826417880352618 0.813440323796319 0.845943210618849"
## [1] "CCNE1"
## [1] "10000"
## [1] "0.849134403884159 0.836896340412142 0.844368393910045"
## [1] "CCNE1"
## [1] "1e+05"
## [1] "0.843005346823355 0.829474876393488 0.831894387147325"
## [1] "CCNE1"
## [1] "1e+06"
## [1] "0.79489252657153 0.805152583360047 0.845781813166039"
## [1] "CDKN2A"
## [1] "50000"
## [1] "0.770286775383964 0.824711869003358 0.820810622368492"
## [1] "CDKN2A"
## [1] "10000"
## [1] "0.784476652907735 0.842870595760608 0.837815008814301"
## [1] "CDKN2A"
## [1] "1e+05"
## [1] "0.828431908549295 0.863729216325694 0.814386084893461"
## [1] "CDKN2A"
## [1] "1e+06"
## [1] "0.776951840796653 0.809258743289404 0.843185857302898"
## [1] "MYC"
## [1] "50000"
## [1] "0.550119920847339 0.533111942514943 0.623517986495779"
## [1] "MYC"
## [1] "10000"
## [1] "0.594882099031743 0.513851869692022 0.379050348014905"
## [1] "MYC"
## [1] "1e+05"
## [1] "0.728429963922226 0.590602707782826 0.616991728990406"
## [1] "MYC"
## [1] "1e+06"
## [1] "0.599560636492384 0.493157855491004 0.613060168297233"
## [1] "MYOCD"
## [1] "50000"
## [1] "0.703082777869045 0.737155429945174 0.757266803619211"
## [1] "MYOCD"
## [1] "10000"
## [1] "0.759241487110125 0.721856082001065 0.743062822010953"
## [1] "MYOCD"
## [1] "1e+05"
## [1] "0.788779978335249 0.738024751153176 0.744233670582984"
## [1] "MYOCD"
## [1] "1e+06"
## [1] "0.737604178197128 0.736457605970674 0.755436379247107"
## [1] "PTEN"
## [1] "50000"
## [1] "0.173994453322823 0.201614441620541 0.158087271330171"
## [1] "PTEN"
## [1] "10000"
## [1] "0.183646163979431 0.212871187889706 0.0466493488085179"
## [1] "PTEN"
## [1] "1e+05"
## [1] "0.156183661438954 0.212959236115107 0.174572305471204"
## [1] "PTEN"
## [1] "1e+06"
## [1] "-0.00562029336073261 0.0525883803472474 0.00346858286312494"
## [1] "RB1"
## [1] "50000"
## [1] "0.284964544161419 -0.103117646873573 0.55669826414135"
## [1] "RB1"
## [1] "10000"
## [1] "0.273210786726921 0.0727401864100489 0.409547861912897"
## [1] "RB1"
## [1] "1e+05"
## [1] "0.444760905459316 -0.022745446473997 0.34792966700185"
## [1] "RB1"
## [1] "1e+06"
## [1] "0.395649026750018 0.328853019174688 0.689928235069948"
## [1] "TP53"
## [1] "50000"
## [1] "0.92032642794316 0.895923294419126 0.889208352500564"
## [1] "TP53"
## [1] "10000"
## [1] "0.91015423233901 0.887451563223858 0.831874713823817"
## [1] "TP53"
## [1] "1e+05"
## [1] "0.925389940484122 0.898103823567314 0.894178403267808"
## [1] "TP53"
## [1] "1e+06"
## [1] "0.838169101292533 0.911586067526427 0.898609062298142"# Melt to long format
df_long <- melt(output.df, id.vars = "states", variable.name = "gene",
value.name = "correlation")
# Keep row order
df_long$states <- factor(df_long$states, levels = rev(output.df$states))
# Plot
p <- ggplot(df_long, aes(x = gene, y = states, fill = correlation)) +
geom_tile(color = "black", linewidth = 0.5) + geom_text(aes(label = sprintf("%.2f",
correlation)), size = 3, color = "black") + scale_fill_gradient2(low = "#2166ac",
mid = "#f7f7f7", high = "#50C878", midpoint = 0.5, limits = c(min(df_long$correlation),
1), name = "Correlation") + labs(title = "CNV Method Comparison by Gene",
x = "Gene", y = "Method & Bin Size") + theme_minimal(base_size = 12) +
theme(plot.title = element_text(hjust = 0.5, face = "bold",
size = 14), axis.text.x = element_text(angle = 30, hjust = 1,
face = "bold"), axis.text.y = element_text(size = 9),
panel.grid = element_blank(), legend.position = "right")
p
I just ran the visualizer, as that is the meat of the code.
Finally, we need to plot the final dataset for the case.
Gene <- c("MYC", "MYOCD", "CCNE1", "CDKN2A", "PTEN", "RB1", "TP53")
geneAnno(Gene = Gene, db = df)## [1] "is here"## chrom loc.start loc.end seg.mean type CNVStatus Gene
## 1 8 128747765 128753680 0.01271818 Gene_MMasteR Normal 4609
## 2 8 128747765 128753680 -0.02500000 Gene_SNP Normal 4609
## 3 9 21967751 21994490 -0.02648182 Gene_MMasteR Normal 1029
## 4 9 21967751 21994490 -0.04800000 Gene_SNP Normal 1029
## 5 10 89623195 89728532 -0.34798182 Gene_MMasteR Deletion 5728
## 6 10 89623195 89728532 -0.58100000 Gene_SNP Deletion 5728
## 7 13 48877883 49056026 -0.32668182 Gene_MMasteR Deletion 5925
## 8 13 48877883 49056026 -0.54700000 Gene_SNP Deletion 5925
## 9 17 7565097 7590868 -0.07078182 Gene_MMasteR Normal 7157
## 10 17 12569207 12670651 -0.07078182 Gene_MMasteR Normal 93649
## 11 17 7565097 7590868 0.00000000 Gene_SNP Normal 7157
## 12 17 12569207 12670651 0.00000000 Gene_SNP Normal 93649
## 13 19 30302901 30315215 0.05271818 Gene_MMasteR Normal 898
## 14 19 30302901 30315215 -0.05400000 Gene_SNP Normal 898
## 15 8 128747765 128753680 0.07010000 Gene_SeSAMe Normal 4609
## 16 9 21967751 21994490 0.03360000 Gene_SeSAMe Normal 1029
## 17 10 89623195 89728532 -0.29000000 Gene_SeSAMe Normal 5728
## 18 13 48877883 49056026 -0.27050000 Gene_SeSAMe Normal 5925
## 19 17 7565097 7590868 -0.01070000 Gene_SeSAMe Normal 7157
## 20 17 12569207 12670651 -0.01070000 Gene_SeSAMe Normal 93649
## 21 19 30302901 30315215 0.10900000 Gene_SeSAMe Normal 898
## 22 8 128747765 128753680 0.02600000 Gene_Conumee Normal 4609
## 23 9 21967751 21994490 -0.01600000 Gene_Conumee Normal 1029
## 24 10 89623195 89728532 -0.30200000 Gene_Conumee Deletion 5728
## 25 13 48877883 49056026 -0.26100000 Gene_Conumee Deletion 5925
## 26 17 7565097 7590868 -0.04700000 Gene_Conumee Normal 7157
## 27 17 12569207 12670651 -0.04700000 Gene_Conumee Normal 93649
## 28 19 30302901 30315215 -0.12900000 Gene_Conumee Normal 898
## [1] "Gene_MMasteR" "Gene_SNP" "Gene_SeSAMe" "Gene_Conumee"
## 4609 1029 5728 5925 7157
## Gene_MMasteR 0.01271818 -0.02648182 -0.3479818 -0.3266818 -0.07078182
## Gene_SNP -0.02500000 -0.04800000 -0.5810000 -0.5470000 0.00000000
## Gene_SeSAMe 0.07010000 0.03360000 -0.2900000 -0.2705000 -0.01070000
## Gene_Conumee 0.02600000 -0.01600000 -0.3020000 -0.2610000 -0.04700000
## 93649 898
## Gene_MMasteR -0.07078182 0.05271818
## Gene_SNP 0.00000000 -0.05400000
## Gene_SeSAMe -0.01070000 0.10900000
## Gene_Conumee -0.04700000 -0.12900000
## # A tibble: 22 × 4
## chrom chr_len chr_start chr_mid
## <dbl> <dbl> <dbl> <dbl>
## 1 1 249220311 0 124610156.
## 2 2 243052331 249220311 370746476.
## 3 3 198172780 492272642 591359032
## 4 4 190992138 690445422 785941491
## 5 5 181369130 881437560 972122125
## 6 6 170977534 1062806690 1148295457
## 7 7 159247987 1233784224 1313408218.
## 8 8 146292734 1393032211 1466178578
## 9 9 141081716 1539324945 1609865803
## 10 10 135482374 1680406661 1748147848
## # ℹ 12 more rows
## [1] "chr1" "chr2" "chr3" "chr4" "chr5" "chr6" "chr7" "chr8" "chr9"
## [10] "chr10" "chr11" "chr12" "chr13" "chr14" "chr15" "chr16" "chr17" "chr18"
## [19] "chr19" "chr20" "chr21" "chr22"
## seg.mean loc.start loc.end chrom type CNVStatus Gene
## 1 -0.3180000000 93709 39040000 1 Conumee Deletion 0
## 2 -0.3008000000 677994 16510000 1 SeSAMe Deletion 0
## 3 -0.3777818159 747994 28115000 1 MethylMaster Deletion 0
## 4 -0.5230000000 754192 39046130 1 SNP Deletion 0
## 5 0.0215000000 16570000 16779582 1 SeSAMe Normal 0
## 6 -0.3448000000 16869582 28185000 1 SeSAMe Deletion 0
## 7 -0.7534818159 28185000 28505000 1 MethylMaster Deletion 0
## 8 -0.6069000000 28275000 28695000 1 SeSAMe Deletion 0
## 9 -0.4224818159 28530000 38525000 1 MethylMaster Deletion 0
## 10 -0.3593000000 28795000 38525000 1 SeSAMe Deletion 0
## 11 0.1562181841 38690000 186405000 1 MethylMaster Normal 0
## 12 0.2126000000 38690000 186405000 1 SeSAMe Normal 0
## 13 0.3290000000 39053684 71837405 1 SNP Amplification 0
## 14 0.1910000000 39115000 93105000 1 Conumee Normal 0
## 15 0.5860000000 71858457 72654730 1 SNP Amplification 0
## 16 0.3720000000 72662685 76640953 1 SNP Amplification 0
## 17 -0.0230000000 76658494 77726109 1 SNP Normal 0
## 18 0.3400000000 77737217 93047956 1 SNP Amplification 0
## 19 0.0030000000 93073228 98750052 1 SNP Normal 0
## 20 0.0430000000 93270000 98515000 1 Conumee Normal 0
## 21 0.2900000000 98685000 100545000 1 Conumee Amplification 0
## 22 0.3250000000 98766448 100543962 1 SNP Amplification 0
## 23 -0.0280000000 100549400 110221639 1 SNP Normal 0
## 24 0.0330000000 100595000 110285000 1 Conumee Normal 0
## 25 0.2600000000 110222219 111181086 1 SNP Amplification 0
## 26 0.1820000000 110300000 111505000 1 Conumee Normal 0
## 27 -0.0210000000 111193595 152411090 1 SNP Normal 0
## 28 0.0110000000 111595000 152240000 1 Conumee Normal 0
## 29 0.1900000000 152315000 185705000 1 Conumee Normal 0
## 30 0.3470000000 152411813 208551533 1 SNP Amplification 0
## 31 0.3630000000 185820000 199735000 1 Conumee Amplification 0
## 32 0.3858181841 186560000 199570000 1 MethylMaster Amplification 0
## 33 0.4444000000 186560000 199570000 1 SeSAMe Amplification 0
## 34 0.1513181841 199885000 208295000 1 MethylMaster Normal 0
## 35 0.2130000000 199885000 208295000 1 SeSAMe Normal 0
## 36 0.1580000000 199910000 208510000 1 Conumee Normal 0
## 37 -0.3127818159 208480000 248923211 1 MethylMaster Deletion 0
## 38 -0.2521000000 208480000 248923211 1 SeSAMe Normal 0
## 39 -0.5640000000 208569475 249212878 1 SNP Deletion 0
## 40 -0.2790000000 208690000 249220311 1 Conumee Deletion 0
## 41 -0.5260000000 21494 47051551 2 SNP Deletion 0
## 42 -0.2890000000 30000 47050000 2 Conumee Deletion 0
## 43 -0.3056818159 110000 46830000 2 MethylMaster Deletion 0
## 44 -0.2467000000 110000 46830000 2 SeSAMe Normal 0
## 45 -1.3103818159 46880000 49160000 2 MethylMaster Deletion 0
## 46 -1.2535000000 46880000 49160000 2 SeSAMe Deletion 0
## 47 -1.6880000000 47067057 49997218 2 SNP Deletion 0
## 48 -1.2360000000 47095000 49795000 2 Conumee Deletion 0
## 49 -0.3053818159 49835000 200815000 2 MethylMaster Deletion 0
## 50 -0.2428000000 49835000 200815000 2 SeSAMe Normal 0
## 51 -0.5610000000 50007748 243052331 2 SNP Deletion 0
## 52 -0.2900000000 50395000 243046238 2 Conumee Deletion 0
## 53 -0.5376818159 200840000 201305000 2 MethylMaster Deletion 0
## 54 -0.4734000000 200840000 201305000 2 SeSAMe Deletion 0
## 55 -0.3142818159 201405000 242111765 2 MethylMaster Deletion 0
## 56 -0.2557000000 201405000 242111765 2 SeSAMe Normal 0
## 57 -0.0690000000 63411 197852564 3 SNP Normal 0
## 58 0.0185181841 115000 198097780 3 MethylMaster Normal 0
## 59 0.0762000000 115000 198172780 3 SeSAMe Normal 0
## 60 0.0200000000 150000 197881215 3 Conumee Normal 0
## 61 0.0500000000 35000 190992138 4 Conumee Normal 0
## 62 0.1150000000 65000 190066561 4 SeSAMe Normal 0
## 63 -0.5940000000 69404 334213 4 SNP Deletion 0
## 64 0.0581181841 110000 190066561 4 MethylMaster Normal 0
## 65 -0.0470000000 360026 180023290 4 SNP Normal 0
## 66 -0.4110000000 180040368 180365623 4 SNP Deletion 0
## 67 -0.0540000000 180392930 190915650 4 SNP Normal 0
## 68 0.0460000000 35000 180797630 5 Conumee Normal 0
## 69 -0.0080000000 38139 392863 5 SNP Normal 0
## 70 0.0446181841 50000 181369130 5 MethylMaster Normal 0
## 71 0.1023000000 50000 181369130 5 SeSAMe Normal 0
## 72 0.2300000000 412226 788914 5 SNP Amplification 0
## 73 -0.0070000000 804103 180698312 5 SNP Normal 0
## 74 0.0250000000 130000 170977534 6 Conumee Normal 0
## 75 -0.0131818159 140000 170662990 6 MethylMaster Normal 0
## 76 0.0438000000 140000 170662990 6 SeSAMe Normal 0
## 77 -0.0320000000 204909 170913051 6 SNP Normal 0
## 78 -0.3160000000 40000 159044332 7 Conumee Deletion 0
## 79 -0.5470000000 41421 159118443 7 SNP Deletion 0
## 80 -0.3608818159 50000 159247987 7 MethylMaster Deletion 0
## 81 -0.3015000000 50000 159247987 7 SeSAMe Deletion 0
## 82 0.0260000000 95000 146267011 8 Conumee Normal 0
## 83 0.0701000000 160000 145039318 8 SeSAMe Normal 0
## 84 -0.0200000000 172417 39194984 8 SNP Normal 0
## 85 0.0127181841 195000 145039318 8 MethylMaster Normal 0
## 86 -1.6230000000 39217074 39460780 8 SNP Deletion 0
## 87 -0.0250000000 39480366 146292734 8 SNP Normal 0
## 88 0.0127181841 128747765 128753680 8 Gene_MMasteR Normal 4609
## 89 -0.0250000000 128747765 128753680 8 Gene_SNP Normal 4609
## 90 0.0701000000 128747765 128753680 8 Gene_SeSAMe Normal 4609
## 91 0.0260000000 128747765 128753680 8 Gene_Conumee Normal 4609
## 92 0.0336000000 110000 138227359 9 SeSAMe Normal 0
## 93 -0.0160000000 110000 141081716 9 Conumee Normal 0
## 94 -0.0240000000 204738 5021738 9 SNP Normal 0
## 95 -0.0264818159 215000 138187359 9 MethylMaster Normal 0
## 96 -0.2510000000 5023689 5069837 9 SNP Deletion 0
## 97 -0.0480000000 5071049 129580187 9 SNP Normal 0
## 98 -0.0264818159 21967751 21994490 9 Gene_MMasteR Normal 1029
## 99 -0.0480000000 21967751 21994490 9 Gene_SNP Normal 1029
## 100 0.0336000000 21967751 21994490 9 Gene_SeSAMe Normal 1029
## 101 -0.0160000000 21967751 21994490 9 Gene_Conumee Normal 1029
## 102 -0.2400000000 129582563 129844541 9 SNP Deletion 0
## 103 0.0000000000 129854773 141054761 9 SNP Normal 0
## 104 0.0729000000 70000 74415000 10 SeSAMe Normal 0
## 105 0.0060000000 80000 76205000 10 Conumee Normal 0
## 106 0.0141181841 125000 74415000 10 MethylMaster Normal 0
## 107 -0.0340000000 126070 76263261 10 SNP Normal 0
## 108 -0.3479818159 74595000 133625233 10 MethylMaster Deletion 0
## 109 -0.2900000000 74595000 133625233 10 SeSAMe Normal 0
## 110 -0.5810000000 76287336 135434303 10 SNP Deletion 0
## 111 -0.3020000000 76310000 135482374 10 Conumee Deletion 0
## 112 -0.3479818159 89623195 89728532 10 Gene_MMasteR Deletion 5728
## 113 -0.5810000000 89623195 89728532 10 Gene_SNP Deletion 5728
## 114 -0.2900000000 89623195 89728532 10 Gene_SeSAMe Normal 5728
## 115 -0.3020000000 89623195 89728532 10 Gene_Conumee Deletion 5728
## 116 0.0508000000 130000 135013311 11 SeSAMe Normal 0
## 117 0.0090000000 130000 134893258 11 Conumee Normal 0
## 118 -0.0006818159 145000 62735000 11 MethylMaster Normal 0
## 119 -0.0150000000 192764 134938847 11 SNP Normal 0
## 120 -0.3424818159 62760000 62840000 11 MethylMaster Deletion 0
## 121 -0.0074818159 62865000 134993311 11 MethylMaster Normal 0
## 122 0.0600000000 55000 133222655 12 SeSAMe Normal 0
## 123 0.0027181841 70000 133222655 12 MethylMaster Normal 0
## 124 0.0020000000 182870 133795948 12 Conumee Normal 0
## 125 -0.0310000000 189400 133818115 12 SNP Normal 0
## 126 0.1000000000 18639053 47270000 13 SeSAMe Normal 0
## 127 0.0403181841 18679053 47270000 13 MethylMaster Normal 0
## 128 -0.0190000000 19084823 48054661 13 SNP Normal 0
## 129 0.0290000000 19100000 47985000 13 Conumee Normal 0
## 130 -0.3266818159 47630000 61950000 13 MethylMaster Deletion 0
## 131 -0.2705000000 47630000 62140000 13 SeSAMe Normal 0
## 132 -0.5470000000 48058244 63661960 13 SNP Deletion 0
## 133 -0.2610000000 48350000 63100000 13 Conumee Deletion 0
## 134 -0.3266818159 48877883 49056026 13 Gene_MMasteR Deletion 5925
## 135 -0.5470000000 48877883 49056026 13 Gene_SNP Deletion 5925
## 136 -0.2705000000 48877883 49056026 13 Gene_SeSAMe Normal 5925
## 137 -0.2610000000 48877883 49056026 13 Gene_Conumee Deletion 5925
## 138 0.0940181841 63095000 114332164 13 MethylMaster Normal 0
## 139 0.1508000000 63120000 114332164 13 SeSAMe Normal 0
## 140 0.0190000000 63685149 115103150 13 SNP Normal 0
## 141 0.0660000000 63860000 115094939 13 Conumee Normal 0
## 142 0.0794000000 19187179 71035000 14 SeSAMe Normal 0
## 143 0.0330000000 19210000 71515000 14 Conumee Normal 0
## 144 0.0220181841 19770857 71035000 14 MethylMaster Normal 0
## 145 -0.0220000000 20219083 71568215 14 SNP Normal 0
## 146 -0.3619818159 71155000 90290000 14 MethylMaster Deletion 0
## 147 -0.3041000000 71155000 90290000 14 SeSAMe Deletion 0
## 148 -0.6010000000 71580778 90801109 14 SNP Deletion 0
## 149 -0.3240000000 71610000 73705000 14 Conumee Deletion 0
## 150 -0.5770000000 73715000 74150000 14 Conumee Deletion 0
## 151 -0.3150000000 74185000 90760000 14 Conumee Deletion 0
## 152 -0.0233818159 90360000 106751859 14 MethylMaster Normal 0
## 153 0.0322000000 90360000 106796859 14 SeSAMe Normal 0
## 154 -0.0080000000 90795000 107254770 14 Conumee Normal 0
## 155 0.0170000000 90815342 106836445 14 SNP Normal 0
## 156 -0.2410000000 106839840 106931347 14 SNP Deletion 0
## 157 -0.0370000000 106931821 107282024 14 SNP Normal 0
## 158 -0.3009000000 20062627 22068372 15 SeSAMe Deletion 0
## 159 -0.0180000000 20161372 44502266 15 SNP Normal 0
## 160 0.0030000000 20185000 102430696 15 Conumee Normal 0
## 161 -0.0141818159 20232279 101850595 15 MethylMaster Normal 0
## 162 0.0452000000 22569121 101875595 15 SeSAMe Normal 0
## 163 0.2050000000 44514571 44777942 15 SNP Amplification 0
## 164 -0.0040000000 44788617 102397317 15 SNP Normal 0
## 165 -0.0895818159 40000 48010000 16 MethylMaster Normal 0
## 166 -0.0305000000 40000 48010000 16 SeSAMe Normal 0
## 167 -0.0810000000 80000 48165000 16 Conumee Normal 0
## 168 0.0300000000 83887 48175235 16 SNP Normal 0
## 169 -0.3532818159 48160000 54995000 16 MethylMaster Deletion 0
## 170 -0.2948000000 48160000 54995000 16 SeSAMe Normal 0
## 171 -0.5670000000 48185960 55137655 16 SNP Deletion 0
## 172 -0.3090000000 48215000 55040000 16 Conumee Deletion 0
## 173 0.0520000000 55156505 55879117 16 SNP Normal 0
## 174 -0.0350818159 55185000 55785000 16 MethylMaster Normal 0
## 175 0.0270000000 55185000 55785000 16 SeSAMe Normal 0
## 176 0.0300000000 55225000 55885000 16 Conumee Normal 0
## 177 -0.5860000000 55889730 56698268 16 SNP Deletion 0
## 178 -0.3510818159 55925000 56730000 16 MethylMaster Deletion 0
## 179 -0.2897000000 55925000 56730000 16 SeSAMe Normal 0
## 180 -0.3250000000 55970000 56715000 16 Conumee Deletion 0
## 181 0.0290000000 56724810 57983711 16 SNP Normal 0
## 182 -0.0410000000 56745000 57995000 16 Conumee Normal 0
## 183 -0.0746818159 56820000 57925000 16 MethylMaster Normal 0
## 184 -0.0154000000 56820000 57925000 16 SeSAMe Normal 0
## 185 -0.3635818159 57995000 90149173 16 MethylMaster Deletion 0
## 186 -0.2987000000 57995000 90159173 16 SeSAMe Normal 0
## 187 -0.5640000000 58011450 90158005 16 SNP Deletion 0
## 188 -0.3390000000 58020000 90222377 16 Conumee Deletion 0
## 189 -0.0470000000 15000 81122605 17 Conumee Normal 0
## 190 -0.0107000000 120000 68480000 17 SeSAMe Normal 0
## 191 -0.0707818159 130000 68480000 17 MethylMaster Normal 0
## 192 0.0000000000 400959 80263427 17 SNP Normal 0
## 193 -0.0707818159 7565097 7590868 17 Gene_MMasteR Normal 7157
## 194 0.0000000000 7565097 7590868 17 Gene_SNP Normal 7157
## 195 -0.0107000000 7565097 7590868 17 Gene_SeSAMe Normal 7157
## 196 -0.0470000000 7565097 7590868 17 Gene_Conumee Normal 7157
## 197 -0.0707818159 12569207 12670651 17 Gene_MMasteR Normal 93649
## 198 0.0000000000 12569207 12670651 17 Gene_SNP Normal 93649
## 199 -0.0107000000 12569207 12670651 17 Gene_SeSAMe Normal 93649
## 200 -0.0470000000 12569207 12670651 17 Gene_Conumee Normal 93649
## 201 0.1569181841 68530000 72070000 17 MethylMaster Normal 0
## 202 0.2163000000 68530000 72070000 17 SeSAMe Normal 0
## 203 -0.0682818159 72115000 83168721 17 MethylMaster Normal 0
## 204 -0.0098000000 72115000 83168721 17 SeSAMe Normal 0
## 205 0.0010000000 12842 78007784 18 SNP Normal 0
## 206 0.0330000000 45000 78008624 18 Conumee Normal 0
## 207 0.1163000000 80000 80206643 18 SeSAMe Normal 0
## 208 0.0574181841 135000 80206643 18 MethylMaster Normal 0
## 209 -0.1467818159 175000 29890000 19 MethylMaster Normal 0
## 210 -0.0894000000 175000 29890000 19 SeSAMe Normal 0
## 211 -0.1290000000 175000 34880000 19 Conumee Normal 0
## 212 0.0100000000 247232 20170214 19 SNP Normal 0
## 213 -0.3030000000 20179614 20462595 19 SNP Deletion 0
## 214 -0.0540000000 20473553 34916011 19 SNP Normal 0
## 215 0.0527181841 29975000 32370000 19 MethylMaster Normal 0
## 216 0.1090000000 29975000 32370000 19 SeSAMe Normal 0
## 217 0.0527181841 30302901 30315215 19 Gene_MMasteR Normal 898
## 218 -0.0540000000 30302901 30315215 19 Gene_SNP Normal 898
## 219 0.1090000000 30302901 30315215 19 Gene_SeSAMe Normal 898
## 220 -0.1290000000 30302901 30315215 19 Gene_Conumee Normal 898
## 221 -0.1348818159 32490000 34390000 19 MethylMaster Normal 0
## 222 -0.0719000000 32490000 34390000 19 SeSAMe Normal 0
## 223 -0.4709818159 34455000 58588808 19 MethylMaster Deletion 0
## 224 -0.4152000000 34455000 53560000 19 SeSAMe Deletion 0
## 225 -0.4130000000 34910000 59099492 19 Conumee Deletion 0
## 226 -0.5750000000 34931904 59093239 19 SNP Deletion 0
## 227 -0.7416000000 53605000 53765000 19 SeSAMe Deletion 0
## 228 -0.3768000000 53820000 58588808 19 SeSAMe Deletion 0
## 229 -0.0130000000 69094 62912463 20 SNP Normal 0
## 230 -0.0220000000 100000 62927760 20 Conumee Normal 0
## 231 -0.0246818159 178168 64292084 20 MethylMaster Normal 0
## 232 0.0340000000 178168 64292084 20 SeSAMe Normal 0
## 233 0.0914000000 5055000 46679992 21 SeSAMe Normal 0
## 234 0.0440000000 9648315 48097610 21 SNP Normal 0
## 235 0.0343181841 10569444 46679992 21 MethylMaster Normal 0
## 236 0.0070000000 10843948 48099948 21 Conumee Normal 0
## 237 -0.0092000000 15422159 50769234 22 SeSAMe Normal 0
## 238 0.0300000000 16054713 24341388 22 SNP Normal 0
## 239 -0.0470000000 16165000 51212283 22 Conumee Normal 0
## 240 -0.0662818159 16567005 50769234 22 MethylMaster Normal 0
## 241 0.6420000000 24346428 24390318 22 SNP Amplification 0
## 242 0.0210000000 24394088 51213826 22 SNP Normal 0
## type_group chr_len chr_start chr_mid start_cum end_cum
## 1 non-SNP 249220311 0 124610156 93709 39040000
## 2 non-SNP 249220311 0 124610156 677994 16510000
## 3 non-SNP 249220311 0 124610156 747994 28115000
## 4 SNP 249220311 0 124610156 754192 39046130
## 5 non-SNP 249220311 0 124610156 16570000 16779582
## 6 non-SNP 249220311 0 124610156 16869582 28185000
## 7 non-SNP 249220311 0 124610156 28185000 28505000
## 8 non-SNP 249220311 0 124610156 28275000 28695000
## 9 non-SNP 249220311 0 124610156 28530000 38525000
## 10 non-SNP 249220311 0 124610156 28795000 38525000
## 11 non-SNP 249220311 0 124610156 38690000 186405000
## 12 non-SNP 249220311 0 124610156 38690000 186405000
## 13 SNP 249220311 0 124610156 39053684 71837405
## 14 non-SNP 249220311 0 124610156 39115000 93105000
## 15 SNP 249220311 0 124610156 71858457 72654730
## 16 SNP 249220311 0 124610156 72662685 76640953
## 17 SNP 249220311 0 124610156 76658494 77726109
## 18 SNP 249220311 0 124610156 77737217 93047956
## 19 SNP 249220311 0 124610156 93073228 98750052
## 20 non-SNP 249220311 0 124610156 93270000 98515000
## 21 non-SNP 249220311 0 124610156 98685000 100545000
## 22 SNP 249220311 0 124610156 98766448 100543962
## 23 SNP 249220311 0 124610156 100549400 110221639
## 24 non-SNP 249220311 0 124610156 100595000 110285000
## 25 SNP 249220311 0 124610156 110222219 111181086
## 26 non-SNP 249220311 0 124610156 110300000 111505000
## 27 SNP 249220311 0 124610156 111193595 152411090
## 28 non-SNP 249220311 0 124610156 111595000 152240000
## 29 non-SNP 249220311 0 124610156 152315000 185705000
## 30 SNP 249220311 0 124610156 152411813 208551533
## 31 non-SNP 249220311 0 124610156 185820000 199735000
## 32 non-SNP 249220311 0 124610156 186560000 199570000
## 33 non-SNP 249220311 0 124610156 186560000 199570000
## 34 non-SNP 249220311 0 124610156 199885000 208295000
## 35 non-SNP 249220311 0 124610156 199885000 208295000
## 36 non-SNP 249220311 0 124610156 199910000 208510000
## 37 non-SNP 249220311 0 124610156 208480000 248923211
## 38 non-SNP 249220311 0 124610156 208480000 248923211
## 39 SNP 249220311 0 124610156 208569475 249212878
## 40 non-SNP 249220311 0 124610156 208690000 249220311
## 41 SNP 243052331 249220311 370746476 249241805 296271862
## 42 non-SNP 243052331 249220311 370746476 249250311 296270311
## 43 non-SNP 243052331 249220311 370746476 249330311 296050311
## 44 non-SNP 243052331 249220311 370746476 249330311 296050311
## 45 non-SNP 243052331 249220311 370746476 296100311 298380311
## 46 non-SNP 243052331 249220311 370746476 296100311 298380311
## 47 SNP 243052331 249220311 370746476 296287368 299217529
## 48 non-SNP 243052331 249220311 370746476 296315311 299015311
## 49 non-SNP 243052331 249220311 370746476 299055311 450035311
## 50 non-SNP 243052331 249220311 370746476 299055311 450035311
## 51 SNP 243052331 249220311 370746476 299228059 492272642
## 52 non-SNP 243052331 249220311 370746476 299615311 492266549
## 53 non-SNP 243052331 249220311 370746476 450060311 450525311
## 54 non-SNP 243052331 249220311 370746476 450060311 450525311
## 55 non-SNP 243052331 249220311 370746476 450625311 491332076
## 56 non-SNP 243052331 249220311 370746476 450625311 491332076
## 57 SNP 198172780 492272642 591359032 492336053 690125206
## 58 non-SNP 198172780 492272642 591359032 492387642 690370422
## 59 non-SNP 198172780 492272642 591359032 492387642 690445422
## 60 non-SNP 198172780 492272642 591359032 492422642 690153857
## 61 non-SNP 190992138 690445422 785941491 690480422 881437560
## 62 non-SNP 190992138 690445422 785941491 690510422 880511983
## 63 SNP 190992138 690445422 785941491 690514826 690779635
## 64 non-SNP 190992138 690445422 785941491 690555422 880511983
## 65 SNP 190992138 690445422 785941491 690805448 870468712
## 66 SNP 190992138 690445422 785941491 870485790 870811045
## 67 SNP 190992138 690445422 785941491 870838352 881361072
## 68 non-SNP 181369130 881437560 972122125 881472560 1062235190
## 69 SNP 181369130 881437560 972122125 881475699 881830423
## 70 non-SNP 181369130 881437560 972122125 881487560 1062806690
## 71 non-SNP 181369130 881437560 972122125 881487560 1062806690
## 72 SNP 181369130 881437560 972122125 881849786 882226474
## 73 SNP 181369130 881437560 972122125 882241663 1062135872
## 74 non-SNP 170977534 1062806690 1148295457 1062936690 1233784224
## 75 non-SNP 170977534 1062806690 1148295457 1062946690 1233469680
## 76 non-SNP 170977534 1062806690 1148295457 1062946690 1233469680
## 77 SNP 170977534 1062806690 1148295457 1063011599 1233719741
## 78 non-SNP 159247987 1233784224 1313408218 1233824224 1392828556
## 79 SNP 159247987 1233784224 1313408218 1233825645 1392902667
## 80 non-SNP 159247987 1233784224 1313408218 1233834224 1393032211
## 81 non-SNP 159247987 1233784224 1313408218 1233834224 1393032211
## 82 non-SNP 146292734 1393032211 1466178578 1393127211 1539299222
## 83 non-SNP 146292734 1393032211 1466178578 1393192211 1538071529
## 84 SNP 146292734 1393032211 1466178578 1393204628 1432227195
## 85 non-SNP 146292734 1393032211 1466178578 1393227211 1538071529
## 86 SNP 146292734 1393032211 1466178578 1432249285 1432492991
## 87 SNP 146292734 1393032211 1466178578 1432512577 1539324945
## 88 non-SNP 146292734 1393032211 1466178578 1521779976 1521785891
## 89 non-SNP 146292734 1393032211 1466178578 1521779976 1521785891
## 90 non-SNP 146292734 1393032211 1466178578 1521779976 1521785891
## 91 non-SNP 146292734 1393032211 1466178578 1521779976 1521785891
## 92 non-SNP 141081716 1539324945 1609865803 1539434945 1677552304
## 93 non-SNP 141081716 1539324945 1609865803 1539434945 1680406661
## 94 SNP 141081716 1539324945 1609865803 1539529683 1544346683
## 95 non-SNP 141081716 1539324945 1609865803 1539539945 1677512304
## 96 SNP 141081716 1539324945 1609865803 1544348634 1544394782
## 97 SNP 141081716 1539324945 1609865803 1544395994 1668905132
## 98 non-SNP 141081716 1539324945 1609865803 1561292696 1561319435
## 99 non-SNP 141081716 1539324945 1609865803 1561292696 1561319435
## 100 non-SNP 141081716 1539324945 1609865803 1561292696 1561319435
## 101 non-SNP 141081716 1539324945 1609865803 1561292696 1561319435
## 102 SNP 141081716 1539324945 1609865803 1668907508 1669169486
## 103 SNP 141081716 1539324945 1609865803 1669179718 1680379706
## 104 non-SNP 135482374 1680406661 1748147848 1680476661 1754821661
## 105 non-SNP 135482374 1680406661 1748147848 1680486661 1756611661
## 106 non-SNP 135482374 1680406661 1748147848 1680531661 1754821661
## 107 SNP 135482374 1680406661 1748147848 1680532731 1756669922
## 108 non-SNP 135482374 1680406661 1748147848 1755001661 1814031894
## 109 non-SNP 135482374 1680406661 1748147848 1755001661 1814031894
## 110 SNP 135482374 1680406661 1748147848 1756693997 1815840964
## 111 non-SNP 135482374 1680406661 1748147848 1756716661 1815889035
## 112 non-SNP 135482374 1680406661 1748147848 1770029856 1770135193
## 113 non-SNP 135482374 1680406661 1748147848 1770029856 1770135193
## 114 non-SNP 135482374 1680406661 1748147848 1770029856 1770135193
## 115 non-SNP 135482374 1680406661 1748147848 1770029856 1770135193
## 116 non-SNP 135013311 1815889035 1883395690 1816019035 1950902346
## 117 non-SNP 135013311 1815889035 1883395690 1816019035 1950782293
## 118 non-SNP 135013311 1815889035 1883395690 1816034035 1878624035
## 119 SNP 135013311 1815889035 1883395690 1816081799 1950827882
## 120 non-SNP 135013311 1815889035 1883395690 1878649035 1878729035
## 121 non-SNP 135013311 1815889035 1883395690 1878754035 1950882346
## 122 non-SNP 133818115 1950902346 2017811404 1950957346 2084125001
## 123 non-SNP 133818115 1950902346 2017811404 1950972346 2084125001
## 124 non-SNP 133818115 1950902346 2017811404 1951085216 2084698294
## 125 SNP 133818115 1950902346 2017811404 1951091746 2084720461
## 126 non-SNP 115103150 2084720461 2142272036 2103359514 2131990461
## 127 non-SNP 115103150 2084720461 2142272036 2103399514 2131990461
## 128 SNP 115103150 2084720461 2142272036 2103805284 2132775122
## 129 non-SNP 115103150 2084720461 2142272036 2103820461 2132705461
## 130 non-SNP 115103150 2084720461 2142272036 2132350461 2146670461
## 131 non-SNP 115103150 2084720461 2142272036 2132350461 2146860461
## 132 SNP 115103150 2084720461 2142272036 2132778705 2148382421
## 133 non-SNP 115103150 2084720461 2142272036 2133070461 2147820461
## 134 non-SNP 115103150 2084720461 2142272036 2133598344 2133776487
## 135 non-SNP 115103150 2084720461 2142272036 2133598344 2133776487
## 136 non-SNP 115103150 2084720461 2142272036 2133598344 2133776487
## 137 non-SNP 115103150 2084720461 2142272036 2133598344 2133776487
## 138 non-SNP 115103150 2084720461 2142272036 2147815461 2199052625
## 139 non-SNP 115103150 2084720461 2142272036 2147840461 2199052625
## 140 SNP 115103150 2084720461 2142272036 2148405610 2199823611
## 141 non-SNP 115103150 2084720461 2142272036 2148580461 2199815400
## 142 non-SNP 107282024 2199823611 2253464623 2219010790 2270858611
## 143 non-SNP 107282024 2199823611 2253464623 2219033611 2271338611
## 144 non-SNP 107282024 2199823611 2253464623 2219594468 2270858611
## 145 SNP 107282024 2199823611 2253464623 2220042694 2271391826
## 146 non-SNP 107282024 2199823611 2253464623 2270978611 2290113611
## 147 non-SNP 107282024 2199823611 2253464623 2270978611 2290113611
## 148 SNP 107282024 2199823611 2253464623 2271404389 2290624720
## 149 non-SNP 107282024 2199823611 2253464623 2271433611 2273528611
## 150 non-SNP 107282024 2199823611 2253464623 2273538611 2273973611
## 151 non-SNP 107282024 2199823611 2253464623 2274008611 2290583611
## 152 non-SNP 107282024 2199823611 2253464623 2290183611 2306575470
## 153 non-SNP 107282024 2199823611 2253464623 2290183611 2306620470
## 154 non-SNP 107282024 2199823611 2253464623 2290618611 2307078381
## 155 SNP 107282024 2199823611 2253464623 2290638953 2306660056
## 156 SNP 107282024 2199823611 2253464623 2306663451 2306754958
## 157 SNP 107282024 2199823611 2253464623 2306755432 2307105635
## 158 non-SNP 102430696 2307105635 2358320983 2327168262 2329174007
## 159 SNP 102430696 2307105635 2358320983 2327267007 2351607901
## 160 non-SNP 102430696 2307105635 2358320983 2327290635 2409536331
## 161 non-SNP 102430696 2307105635 2358320983 2327337914 2408956230
## 162 non-SNP 102430696 2307105635 2358320983 2329674756 2408981230
## 163 SNP 102430696 2307105635 2358320983 2351620206 2351883577
## 164 SNP 102430696 2307105635 2358320983 2351894252 2409502952
## 165 non-SNP 90222377 2409536331 2454647520 2409576331 2457546331
## 166 non-SNP 90222377 2409536331 2454647520 2409576331 2457546331
## 167 non-SNP 90222377 2409536331 2454647520 2409616331 2457701331
## 168 SNP 90222377 2409536331 2454647520 2409620218 2457711566
## 169 non-SNP 90222377 2409536331 2454647520 2457696331 2464531331
## 170 non-SNP 90222377 2409536331 2454647520 2457696331 2464531331
## 171 SNP 90222377 2409536331 2454647520 2457722291 2464673986
## 172 non-SNP 90222377 2409536331 2454647520 2457751331 2464576331
## 173 SNP 90222377 2409536331 2454647520 2464692836 2465415448
## 174 non-SNP 90222377 2409536331 2454647520 2464721331 2465321331
## 175 non-SNP 90222377 2409536331 2454647520 2464721331 2465321331
## 176 non-SNP 90222377 2409536331 2454647520 2464761331 2465421331
## 177 SNP 90222377 2409536331 2454647520 2465426061 2466234599
## 178 non-SNP 90222377 2409536331 2454647520 2465461331 2466266331
## 179 non-SNP 90222377 2409536331 2454647520 2465461331 2466266331
## 180 non-SNP 90222377 2409536331 2454647520 2465506331 2466251331
## 181 SNP 90222377 2409536331 2454647520 2466261141 2467520042
## 182 non-SNP 90222377 2409536331 2454647520 2466281331 2467531331
## 183 non-SNP 90222377 2409536331 2454647520 2466356331 2467461331
## 184 non-SNP 90222377 2409536331 2454647520 2466356331 2467461331
## 185 non-SNP 90222377 2409536331 2454647520 2467531331 2499685504
## 186 non-SNP 90222377 2409536331 2454647520 2467531331 2499695504
## 187 SNP 90222377 2409536331 2454647520 2467547781 2499694336
## 188 non-SNP 90222377 2409536331 2454647520 2467556331 2499758708
## 189 non-SNP 83168721 2499758708 2541343068 2499773708 2580881313
## 190 non-SNP 83168721 2499758708 2541343068 2499878708 2568238708
## 191 non-SNP 83168721 2499758708 2541343068 2499888708 2568238708
## 192 SNP 83168721 2499758708 2541343068 2500159667 2580022135
## 193 non-SNP 83168721 2499758708 2541343068 2507323805 2507349576
## 194 non-SNP 83168721 2499758708 2541343068 2507323805 2507349576
## 195 non-SNP 83168721 2499758708 2541343068 2507323805 2507349576
## 196 non-SNP 83168721 2499758708 2541343068 2507323805 2507349576
## 197 non-SNP 83168721 2499758708 2541343068 2512327915 2512429359
## 198 non-SNP 83168721 2499758708 2541343068 2512327915 2512429359
## 199 non-SNP 83168721 2499758708 2541343068 2512327915 2512429359
## 200 non-SNP 83168721 2499758708 2541343068 2512327915 2512429359
## 201 non-SNP 83168721 2499758708 2541343068 2568288708 2571828708
## 202 non-SNP 83168721 2499758708 2541343068 2568288708 2571828708
## 203 non-SNP 83168721 2499758708 2541343068 2571873708 2582927429
## 204 non-SNP 83168721 2499758708 2541343068 2571873708 2582927429
## 205 SNP 80206643 2582927429 2623030750 2582940271 2660935213
## 206 non-SNP 80206643 2582927429 2623030750 2582972429 2660936053
## 207 non-SNP 80206643 2582927429 2623030750 2583007429 2663134072
## 208 non-SNP 80206643 2582927429 2623030750 2583062429 2663134072
## 209 non-SNP 59099492 2663134072 2692683818 2663309072 2693024072
## 210 non-SNP 59099492 2663134072 2692683818 2663309072 2693024072
## 211 non-SNP 59099492 2663134072 2692683818 2663309072 2698014072
## 212 SNP 59099492 2663134072 2692683818 2663381304 2683304286
## 213 SNP 59099492 2663134072 2692683818 2683313686 2683596667
## 214 SNP 59099492 2663134072 2692683818 2683607625 2698050083
## 215 non-SNP 59099492 2663134072 2692683818 2693109072 2695504072
## 216 non-SNP 59099492 2663134072 2692683818 2693109072 2695504072
## 217 non-SNP 59099492 2663134072 2692683818 2693436973 2693449287
## 218 non-SNP 59099492 2663134072 2692683818 2693436973 2693449287
## 219 non-SNP 59099492 2663134072 2692683818 2693436973 2693449287
## 220 non-SNP 59099492 2663134072 2692683818 2693436973 2693449287
## 221 non-SNP 59099492 2663134072 2692683818 2695624072 2697524072
## 222 non-SNP 59099492 2663134072 2692683818 2695624072 2697524072
## 223 non-SNP 59099492 2663134072 2692683818 2697589072 2721722880
## 224 non-SNP 59099492 2663134072 2692683818 2697589072 2716694072
## 225 non-SNP 59099492 2663134072 2692683818 2698044072 2722233564
## 226 SNP 59099492 2663134072 2692683818 2698065976 2722227311
## 227 non-SNP 59099492 2663134072 2692683818 2716739072 2716899072
## 228 non-SNP 59099492 2663134072 2692683818 2716954072 2721722880
## 229 SNP 64292084 2722233564 2754379606 2722302658 2785146027
## 230 non-SNP 64292084 2722233564 2754379606 2722333564 2785161324
## 231 non-SNP 64292084 2722233564 2754379606 2722411732 2786525648
## 232 non-SNP 64292084 2722233564 2754379606 2722411732 2786525648
## 233 non-SNP 48099948 2786525648 2810575622 2791580648 2833205640
## 234 SNP 48099948 2786525648 2810575622 2796173963 2834623258
## 235 non-SNP 48099948 2786525648 2810575622 2797095092 2833205640
## 236 non-SNP 48099948 2786525648 2810575622 2797369596 2834625596
## 237 non-SNP 51213826 2834625596 2860232509 2850047755 2885394830
## 238 SNP 51213826 2834625596 2860232509 2850680309 2858966984
## 239 non-SNP 51213826 2834625596 2860232509 2850790596 2885837879
## 240 non-SNP 51213826 2834625596 2860232509 2851192601 2885394830
## 241 SNP 51213826 2834625596 2860232509 2858972024 2859015914
## 242 SNP 51213826 2834625596 2860232509 2859019684 2885839422## [[1]]
##
## [[2]]
## seg.mean loc.start loc.end chrom type CNVStatus Gene
## 1 -0.3777818159 747994 28115000 1 MethylMaster Deletion 0
## 2 -0.7534818159 28185000 28505000 1 MethylMaster Deletion 0
## 3 -0.4224818159 28530000 38525000 1 MethylMaster Deletion 0
## 4 0.1562181841 38690000 186405000 1 MethylMaster Normal 0
## 5 0.3858181841 186560000 199570000 1 MethylMaster Amplification 0
## 6 0.1513181841 199885000 208295000 1 MethylMaster Normal 0
## 7 -0.3127818159 208480000 248923211 1 MethylMaster Deletion 0
## 8 -0.5230000000 754192 39046130 1 SNP Deletion 0
## 9 0.3290000000 39053684 71837405 1 SNP Amplification 0
## 10 0.5860000000 71858457 72654730 1 SNP Amplification 0
## 11 0.3720000000 72662685 76640953 1 SNP Amplification 0
## 12 -0.0230000000 76658494 77726109 1 SNP Normal 0
## 13 0.3400000000 77737217 93047956 1 SNP Amplification 0
## 14 0.0030000000 93073228 98750052 1 SNP Normal 0
## 15 0.3250000000 98766448 100543962 1 SNP Amplification 0
## 16 -0.0280000000 100549400 110221639 1 SNP Normal 0
## 17 0.2600000000 110222219 111181086 1 SNP Amplification 0
## 18 -0.0210000000 111193595 152411090 1 SNP Normal 0
## 19 0.3470000000 152411813 208551533 1 SNP Amplification 0
## 20 -0.5640000000 208569475 249212878 1 SNP Deletion 0
## 21 -0.3056818159 110000 46830000 2 MethylMaster Deletion 0
## 22 -1.3103818159 46880000 49160000 2 MethylMaster Deletion 0
## 23 -0.3053818159 49835000 200815000 2 MethylMaster Deletion 0
## 24 -0.5376818159 200840000 201305000 2 MethylMaster Deletion 0
## 25 -0.3142818159 201405000 242111765 2 MethylMaster Deletion 0
## 26 -0.5260000000 21494 47051551 2 SNP Deletion 0
## 27 -1.6880000000 47067057 49997218 2 SNP Deletion 0
## 28 -0.5610000000 50007748 243052331 2 SNP Deletion 0
## 29 0.0185181841 115000 198097780 3 MethylMaster Normal 0
## 30 -0.0690000000 63411 197852564 3 SNP Normal 0
## 31 0.0581181841 110000 190066561 4 MethylMaster Normal 0
## 32 -0.5940000000 69404 334213 4 SNP Deletion 0
## 33 -0.0470000000 360026 180023290 4 SNP Normal 0
## 34 -0.4110000000 180040368 180365623 4 SNP Deletion 0
## 35 -0.0540000000 180392930 190915650 4 SNP Normal 0
## 36 0.0446181841 50000 181369130 5 MethylMaster Normal 0
## 37 -0.0080000000 38139 392863 5 SNP Normal 0
## 38 0.2300000000 412226 788914 5 SNP Amplification 0
## 39 -0.0070000000 804103 180698312 5 SNP Normal 0
## 40 -0.0131818159 140000 170662990 6 MethylMaster Normal 0
## 41 -0.0320000000 204909 170913051 6 SNP Normal 0
## 42 -0.3608818159 50000 159247987 7 MethylMaster Deletion 0
## 43 -0.5470000000 41421 159118443 7 SNP Deletion 0
## 44 0.0127181841 195000 145039318 8 MethylMaster Normal 0
## 45 -0.0200000000 172417 39194984 8 SNP Normal 0
## 46 -1.6230000000 39217074 39460780 8 SNP Deletion 0
## 47 -0.0250000000 39480366 146292734 8 SNP Normal 0
## 48 -0.0264818159 215000 138187359 9 MethylMaster Normal 0
## 49 -0.0240000000 204738 5021738 9 SNP Normal 0
## 50 -0.2510000000 5023689 5069837 9 SNP Deletion 0
## 51 -0.0480000000 5071049 129580187 9 SNP Normal 0
## 52 -0.2400000000 129582563 129844541 9 SNP Deletion 0
## 53 0.0000000000 129854773 141054761 9 SNP Normal 0
## 54 0.0141181841 125000 74415000 10 MethylMaster Normal 0
## 55 -0.3479818159 74595000 133625233 10 MethylMaster Deletion 0
## 56 -0.0340000000 126070 76263261 10 SNP Normal 0
## 57 -0.5810000000 76287336 135434303 10 SNP Deletion 0
## 58 -0.0006818159 145000 62735000 11 MethylMaster Normal 0
## 59 -0.3424818159 62760000 62840000 11 MethylMaster Deletion 0
## 60 -0.0074818159 62865000 134993311 11 MethylMaster Normal 0
## 61 -0.0150000000 192764 134938847 11 SNP Normal 0
## 62 0.0027181841 70000 133222655 12 MethylMaster Normal 0
## 63 -0.0310000000 189400 133818115 12 SNP Normal 0
## 64 0.0403181841 18679053 47270000 13 MethylMaster Normal 0
## 65 -0.3266818159 47630000 61950000 13 MethylMaster Deletion 0
## 66 0.0940181841 63095000 114332164 13 MethylMaster Normal 0
## 67 -0.0190000000 19084823 48054661 13 SNP Normal 0
## 68 -0.5470000000 48058244 63661960 13 SNP Deletion 0
## 69 0.0190000000 63685149 115103150 13 SNP Normal 0
## 70 0.0220181841 19770857 71035000 14 MethylMaster Normal 0
## 71 -0.3619818159 71155000 90290000 14 MethylMaster Deletion 0
## 72 -0.0233818159 90360000 106751859 14 MethylMaster Normal 0
## 73 -0.0220000000 20219083 71568215 14 SNP Normal 0
## 74 -0.6010000000 71580778 90801109 14 SNP Deletion 0
## 75 0.0170000000 90815342 106836445 14 SNP Normal 0
## 76 -0.2410000000 106839840 106931347 14 SNP Deletion 0
## 77 -0.0370000000 106931821 107282024 14 SNP Normal 0
## 78 -0.0141818159 20232279 101850595 15 MethylMaster Normal 0
## 79 -0.0180000000 20161372 44502266 15 SNP Normal 0
## 80 0.2050000000 44514571 44777942 15 SNP Amplification 0
## 81 -0.0040000000 44788617 102397317 15 SNP Normal 0
## 82 -0.0895818159 40000 48010000 16 MethylMaster Normal 0
## 83 -0.3532818159 48160000 54995000 16 MethylMaster Deletion 0
## 84 -0.0350818159 55185000 55785000 16 MethylMaster Normal 0
## 85 -0.3510818159 55925000 56730000 16 MethylMaster Deletion 0
## 86 -0.0746818159 56820000 57925000 16 MethylMaster Normal 0
## 87 -0.3635818159 57995000 90149173 16 MethylMaster Deletion 0
## 88 0.0300000000 83887 48175235 16 SNP Normal 0
## 89 -0.5670000000 48185960 55137655 16 SNP Deletion 0
## 90 0.0520000000 55156505 55879117 16 SNP Normal 0
## 91 -0.5860000000 55889730 56698268 16 SNP Deletion 0
## 92 0.0290000000 56724810 57983711 16 SNP Normal 0
## 93 -0.5640000000 58011450 90158005 16 SNP Deletion 0
## 94 -0.0707818159 130000 68480000 17 MethylMaster Normal 0
## 95 0.1569181841 68530000 72070000 17 MethylMaster Normal 0
## 96 -0.0682818159 72115000 83168721 17 MethylMaster Normal 0
## 97 0.0000000000 400959 80263427 17 SNP Normal 0
## 98 0.0574181841 135000 80206643 18 MethylMaster Normal 0
## 99 0.0010000000 12842 78007784 18 SNP Normal 0
## 100 -0.1467818159 175000 29890000 19 MethylMaster Normal 0
## 101 0.0527181841 29975000 32370000 19 MethylMaster Normal 0
## 102 -0.1348818159 32490000 34390000 19 MethylMaster Normal 0
## 103 -0.4709818159 34455000 58588808 19 MethylMaster Deletion 0
## 104 0.0100000000 247232 20170214 19 SNP Normal 0
## 105 -0.3030000000 20179614 20462595 19 SNP Deletion 0
## 106 -0.0540000000 20473553 34916011 19 SNP Normal 0
## 107 -0.5750000000 34931904 59093239 19 SNP Deletion 0
## 108 -0.0246818159 178168 64292084 20 MethylMaster Normal 0
## 109 -0.0130000000 69094 62912463 20 SNP Normal 0
## 110 0.0343181841 10569444 46679992 21 MethylMaster Normal 0
## 111 0.0440000000 9648315 48097610 21 SNP Normal 0
## 112 -0.0662818159 16567005 50769234 22 MethylMaster Normal 0
## 113 0.0300000000 16054713 24341388 22 SNP Normal 0
## 114 0.6420000000 24346428 24390318 22 SNP Amplification 0
## 115 0.0210000000 24394088 51213826 22 SNP Normal 0
## 116 -0.3008000000 677994 16510000 1 SeSAMe Deletion 0
## 117 0.0215000000 16570000 16779582 1 SeSAMe Normal 0
## 118 -0.3448000000 16869582 28185000 1 SeSAMe Deletion 0
## 119 -0.6069000000 28275000 28695000 1 SeSAMe Deletion 0
## 120 -0.3593000000 28795000 38525000 1 SeSAMe Deletion 0
## 121 0.2126000000 38690000 186405000 1 SeSAMe Normal 0
## 122 0.4444000000 186560000 199570000 1 SeSAMe Amplification 0
## 123 0.2130000000 199885000 208295000 1 SeSAMe Normal 0
## 124 -0.2521000000 208480000 248923211 1 SeSAMe Normal 0
## 138 -0.2467000000 110000 46830000 2 SeSAMe Normal 0
## 139 -1.2535000000 46880000 49160000 2 SeSAMe Deletion 0
## 140 -0.2428000000 49835000 200815000 2 SeSAMe Normal 0
## 141 -0.4734000000 200840000 201305000 2 SeSAMe Deletion 0
## 142 -0.2557000000 201405000 242111765 2 SeSAMe Normal 0
## 146 0.0762000000 115000 198172780 3 SeSAMe Normal 0
## 148 0.1150000000 65000 190066561 4 SeSAMe Normal 0
## 153 0.1023000000 50000 181369130 5 SeSAMe Normal 0
## 157 0.0438000000 140000 170662990 6 SeSAMe Normal 0
## 159 -0.3015000000 50000 159247987 7 SeSAMe Deletion 0
## 161 0.0701000000 160000 145039318 8 SeSAMe Normal 0
## 165 0.0336000000 110000 138227359 9 SeSAMe Normal 0
## 171 0.0729000000 70000 74415000 10 SeSAMe Normal 0
## 172 -0.2900000000 74595000 133625233 10 SeSAMe Normal 0
## 175 0.0508000000 130000 135013311 11 SeSAMe Normal 0
## 177 0.0600000000 55000 133222655 12 SeSAMe Normal 0
## 179 0.1000000000 18639053 47270000 13 SeSAMe Normal 0
## 180 -0.2705000000 47630000 62140000 13 SeSAMe Normal 0
## 181 0.1508000000 63120000 114332164 13 SeSAMe Normal 0
## 185 0.0794000000 19187179 71035000 14 SeSAMe Normal 0
## 186 -0.3041000000 71155000 90290000 14 SeSAMe Deletion 0
## 187 0.0322000000 90360000 106796859 14 SeSAMe Normal 0
## 193 -0.3009000000 20062627 22068372 15 SeSAMe Deletion 0
## 194 0.0452000000 22569121 101875595 15 SeSAMe Normal 0
## 198 -0.0305000000 40000 48010000 16 SeSAMe Normal 0
## 199 -0.2948000000 48160000 54995000 16 SeSAMe Normal 0
## 200 0.0270000000 55185000 55785000 16 SeSAMe Normal 0
## 201 -0.2897000000 55925000 56730000 16 SeSAMe Normal 0
## 202 -0.0154000000 56820000 57925000 16 SeSAMe Normal 0
## 203 -0.2987000000 57995000 90159173 16 SeSAMe Normal 0
## 210 -0.0107000000 120000 68480000 17 SeSAMe Normal 0
## 211 0.2163000000 68530000 72070000 17 SeSAMe Normal 0
## 212 -0.0098000000 72115000 83168721 17 SeSAMe Normal 0
## 214 0.1163000000 80000 80206643 18 SeSAMe Normal 0
## 216 -0.0894000000 175000 29890000 19 SeSAMe Normal 0
## 217 0.1090000000 29975000 32370000 19 SeSAMe Normal 0
## 218 -0.0719000000 32490000 34390000 19 SeSAMe Normal 0
## 219 -0.4152000000 34455000 53560000 19 SeSAMe Deletion 0
## 220 -0.7416000000 53605000 53765000 19 SeSAMe Deletion 0
## 221 -0.3768000000 53820000 58588808 19 SeSAMe Deletion 0
## 226 0.0340000000 178168 64292084 20 SeSAMe Normal 0
## 228 0.0914000000 5055000 46679992 21 SeSAMe Normal 0
## 230 -0.0092000000 15422159 50769234 22 SeSAMe Normal 0
## 234 -0.3180000000 93709 39040000 1 Conumee Deletion 0
## 235 0.1910000000 39115000 93105000 1 Conumee Normal 0
## 236 0.0430000000 93270000 98515000 1 Conumee Normal 0
## 237 0.2900000000 98685000 100545000 1 Conumee Amplification 0
## 238 0.0330000000 100595000 110285000 1 Conumee Normal 0
## 239 0.1820000000 110300000 111505000 1 Conumee Normal 0
## 240 0.0110000000 111595000 152240000 1 Conumee Normal 0
## 241 0.1900000000 152315000 185705000 1 Conumee Normal 0
## 242 0.3630000000 185820000 199735000 1 Conumee Amplification 0
## 243 0.1580000000 199910000 208510000 1 Conumee Normal 0
## 244 -0.2790000000 208690000 249220311 1 Conumee Deletion 0
## 258 -0.2890000000 30000 47050000 2 Conumee Deletion 0
## 259 -1.2360000000 47095000 49795000 2 Conumee Deletion 0
## 260 -0.2900000000 50395000 243046238 2 Conumee Deletion 0
## 264 0.0200000000 150000 197881215 3 Conumee Normal 0
## 266 0.0500000000 35000 190992138 4 Conumee Normal 0
## 271 0.0460000000 35000 180797630 5 Conumee Normal 0
## 275 0.0250000000 130000 170977534 6 Conumee Normal 0
## 277 -0.3160000000 40000 159044332 7 Conumee Deletion 0
## 279 0.0260000000 95000 146267011 8 Conumee Normal 0
## 283 -0.0160000000 110000 141081716 9 Conumee Normal 0
## 289 0.0060000000 80000 76205000 10 Conumee Normal 0
## 290 -0.3020000000 76310000 135482374 10 Conumee Deletion 0
## 293 0.0090000000 130000 134893258 11 Conumee Normal 0
## 295 0.0020000000 182870 133795948 12 Conumee Normal 0
## 297 0.0290000000 19100000 47985000 13 Conumee Normal 0
## 298 -0.2610000000 48350000 63100000 13 Conumee Deletion 0
## 299 0.0660000000 63860000 115094939 13 Conumee Normal 0
## 303 0.0330000000 19210000 71515000 14 Conumee Normal 0
## 304 -0.3240000000 71610000 73705000 14 Conumee Deletion 0
## 305 -0.5770000000 73715000 74150000 14 Conumee Deletion 0
## 306 -0.3150000000 74185000 90760000 14 Conumee Deletion 0
## 307 -0.0080000000 90795000 107254770 14 Conumee Normal 0
## 313 0.0030000000 20185000 102430696 15 Conumee Normal 0
## 317 -0.0810000000 80000 48165000 16 Conumee Normal 0
## 318 -0.3090000000 48215000 55040000 16 Conumee Deletion 0
## 319 0.0300000000 55225000 55885000 16 Conumee Normal 0
## 320 -0.3250000000 55970000 56715000 16 Conumee Deletion 0
## 321 -0.0410000000 56745000 57995000 16 Conumee Normal 0
## 322 -0.3390000000 58020000 90222377 16 Conumee Deletion 0
## 329 -0.0470000000 15000 81122605 17 Conumee Normal 0
## 331 0.0330000000 45000 78008624 18 Conumee Normal 0
## 333 -0.1290000000 175000 34880000 19 Conumee Normal 0
## 334 -0.4130000000 34910000 59099492 19 Conumee Deletion 0
## 339 -0.0220000000 100000 62927760 20 Conumee Normal 0
## 341 0.0070000000 10843948 48099948 21 Conumee Normal 0
## 343 -0.0470000000 16165000 51212283 22 Conumee Normal 0
## 347 0.0127181841 128747765 128753680 8 Gene_MMasteR Normal 4609
## 348 -0.0250000000 128747765 128753680 8 Gene_SNP Normal 4609
## 349 -0.0264818159 21967751 21994490 9 Gene_MMasteR Normal 1029
## 350 -0.0480000000 21967751 21994490 9 Gene_SNP Normal 1029
## 351 -0.3479818159 89623195 89728532 10 Gene_MMasteR Deletion 5728
## 352 -0.5810000000 89623195 89728532 10 Gene_SNP Deletion 5728
## 353 -0.3266818159 48877883 49056026 13 Gene_MMasteR Deletion 5925
## 354 -0.5470000000 48877883 49056026 13 Gene_SNP Deletion 5925
## 355 -0.0707818159 7565097 7590868 17 Gene_MMasteR Normal 7157
## 356 -0.0707818159 12569207 12670651 17 Gene_MMasteR Normal 93649
## 357 0.0000000000 7565097 7590868 17 Gene_SNP Normal 7157
## 358 0.0000000000 12569207 12670651 17 Gene_SNP Normal 93649
## 359 0.0527181841 30302901 30315215 19 Gene_MMasteR Normal 898
## 360 -0.0540000000 30302901 30315215 19 Gene_SNP Normal 898
## 361 0.0701000000 128747765 128753680 8 Gene_SeSAMe Normal 4609
## 362 0.0336000000 21967751 21994490 9 Gene_SeSAMe Normal 1029
## 363 -0.2900000000 89623195 89728532 10 Gene_SeSAMe Normal 5728
## 364 -0.2705000000 48877883 49056026 13 Gene_SeSAMe Normal 5925
## 365 -0.0107000000 7565097 7590868 17 Gene_SeSAMe Normal 7157
## 366 -0.0107000000 12569207 12670651 17 Gene_SeSAMe Normal 93649
## 367 0.1090000000 30302901 30315215 19 Gene_SeSAMe Normal 898
## 368 0.0260000000 128747765 128753680 8 Gene_Conumee Normal 4609
## 369 -0.0160000000 21967751 21994490 9 Gene_Conumee Normal 1029
## 370 -0.3020000000 89623195 89728532 10 Gene_Conumee Deletion 5728
## 371 -0.2610000000 48877883 49056026 13 Gene_Conumee Deletion 5925
## 372 -0.0470000000 7565097 7590868 17 Gene_Conumee Normal 7157
## 373 -0.0470000000 12569207 12670651 17 Gene_Conumee Normal 93649
## 374 -0.1290000000 30302901 30315215 19 Gene_Conumee Normal 898It looks terribly compressed, but this is honestly just due to the limits of this RMD file. Saving it with the proper parameters make it look more like this:
A lot more elegant!
Conclusion
That’s about it! This whole pipeline gives an elegant flow, from preprocessing the data into a common readable format, to the different forms of analysis, all the way down to the visualizations, step by step.