513 lines
19 KiB
R
513 lines
19 KiB
R
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1,2,3)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.breaks[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.breaks[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
#g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.breaks <- g.hist$breaks # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.breaks[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean)/kmin)
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
alpha.LM
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean/kmin))
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1, lwd=5)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean/kmin))
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1, lwd=3)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean/kmin))
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4)
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1, lwd=3)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2, lwd=3)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
#plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3, lwd=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean/kmin))
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4, lwd=3)
|
|
plot(yeast)
|
|
hist(yeast)
|
|
hist(g.vec)
|
|
g.pois
|
|
g.mean
|
|
alpha.LM
|
|
alpha.ML
|
|
degree(g)
|
|
sort(degree(g))
|
|
sort(degree(g),decreasing=FALSE)
|
|
sort(degree(g),decreasing=F)
|
|
sort(degree(g),decreasing=false)
|
|
sort(degree(g), decreasing = TRUE)
|
|
head(sort(degree(g), decreasing = TRUE))
|
|
stddev(degree(g))
|
|
sd(degree(g))
|
|
tail(sort(degree(g), decreasing = TRUE))
|
|
plot(log(g.breaks.clean), log(g.probs.clean))
|
|
# Homework 4 for the University of Tulsa' s CS-7863 Network Theory Course
|
|
# Degree Distribution
|
|
# Professor: Dr. McKinney, Spring 2022
|
|
# Noah Schrick - 1492657
|
|
library(igraph)
|
|
library(igraphdata)
|
|
data(yeast)
|
|
g <- yeast
|
|
g.netname <- "Yeast"
|
|
################# Set up Work #################
|
|
g.vec <- degree(g)
|
|
g.hist <- hist(g.vec, freq=FALSE, main=paste("Histogram of the", g.netname,
|
|
" Network"))
|
|
legend("topright", c("Guess", "Poisson", "Least-Squares Fit",
|
|
"Max Log-Likelihood"), lty=c(1,2,3,4), col=c("#40B0A6",
|
|
"#006CD1", "#E66100", "#D35FB7"))
|
|
g.mean <- mean(g.vec)
|
|
g.seq <- 0:max(g.vec) # x-axis
|
|
################# Guessing Alpha #################
|
|
alpha.guess <- 1.5
|
|
lines(g.seq, g.seq^(-alpha.guess), col="#40B0A6", lty=1, lwd=3)
|
|
################# Poisson #################
|
|
g.pois <- dpois(g.seq, g.mean, log=F)
|
|
lines(g.seq, g.pois, col="#006CD1", lty=2, lwd=3)
|
|
################# Linear model: Least-Squares Fit #################
|
|
g.breaks <- g.hist$breaks[-c(1)] # remove 0
|
|
g.probs <- g.hist$density[-1] # make lengths match
|
|
# Need to clean up probabilities that are 0
|
|
nz.probs.mask <- g.probs!=0
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.fit <- lm(log(g.probs.clean)~log(g.breaks.clean))
|
|
summary(g.fit)
|
|
alpha.LM <- coef(g.fit)[2]
|
|
lines(g.seq, g.seq^(-alpha.LM), col="#E66100", lty=3, lwd=3)
|
|
################# Max-Log-Likelihood #################
|
|
n <- length(g.breaks.clean)
|
|
kmin <- g.breaks.clean[1]
|
|
alpha.ML <- 1 + n/sum(log(g.breaks.clean/kmin))
|
|
alpha.ML
|
|
lines(g.seq, g.seq^(-alpha.ML), col="#D35FB7", lty=4, lwd=3)
|
|
plot(log(g.breaks.clean), log(g.probs.clean))
|
|
g.breaks.clean <- g.breaks[nz.probs.mask]
|
|
g.probs.clean <- g.probs[nz.probs.mask]
|
|
plot(log(g.breaks.clean), log(g.probs.clean))
|
|
## Set Working Directory to file directory - RStudio approach
|
|
setwd(dirname(rstudioapi::getActiveDocumentContext()$path))
|
|
#### Part A: GenBank sequences and a multiple fasta file
|
|
if (!require("ape")) install.packages("ape")
|
|
library(ape) # needed for read.GenBank
|
|
# fetch the mtDNA sequences
|
|
mtDNA.MultiSeqs.list<-read.GenBank(c("AF011222","AF254446","X90314","AF089820",
|
|
"AF176766","AF451972", "AY079510",
|
|
"AF050738","AF176722","AF315498",
|
|
"AF176731","AF451964"), as.character=TRUE)
|
|
# look at species names
|
|
mtDNA.Species<-attr(mtDNA.MultiSeqs.list,"species")
|
|
# use species as name instead of genbank id
|
|
names(mtDNA.MultiSeqs.list)<-mtDNA.Species
|
|
names(mtDNA.MultiSeqs.list)
|
|
# need to fix some names
|
|
names(mtDNA.MultiSeqs.list)[1] <- paste("German_Neanderthal",sep="")
|
|
names(mtDNA.MultiSeqs.list)[2] <- paste("Russian_Neanderthal",sep="")
|
|
names(mtDNA.MultiSeqs.list)[3] <- paste("Human")
|
|
names(mtDNA.MultiSeqs.list)[6] <- paste("Puti_Orangutan",sep="")
|
|
names(mtDNA.MultiSeqs.list)[12] <- paste("Jari_Orangutan",sep="")
|
|
names(mtDNA.MultiSeqs.list)
|
|
# look at one of the sequences using $
|
|
mtDNA.MultiSeqs.list$Human
|
|
length(mtDNA.MultiSeqs.list$Human)
|
|
## Convert to Biostrings object for the sequences
|
|
if (!require("BiocManager")) install.packages("BiocManager")
|
|
library(BiocManager)
|
|
if (!require("Biostrings")) BiocManager::install("Biostrings")
|
|
library(Biostrings)
|
|
# loop through the list to create vector of strings for Biostrings input
|
|
Names.vec <- c() # initialize speices names string vector
|
|
Seqs.vec <- c() # initialize sequence string vector
|
|
for (mtDNA.name in names(mtDNA.MultiSeqs.list))
|
|
{
|
|
Names.vec <- c(Names.vec,mtDNA.name) # concatenate vector
|
|
Seqs.vec <-c(Seqs.vec,paste(mtDNA.MultiSeqs.list[[mtDNA.name]],collapse=""))
|
|
}
|
|
mtDNA.multSeqs.bstr <- DNAStringSet(Seqs.vec) # convert to Biostring
|
|
# name the Biostring sequences and compute stats
|
|
names(mtDNA.multSeqs.bstr) <- Names.vec # count nucs and sequence lengths
|
|
num.nts <- alphabetFrequency(mtDNA.multSeqs.bstr)[,1:4]
|
|
mtDNA.lengths <- rowSums(num.nts)
|
|
proportion.nts <- num.nts/mtDNA.lengths
|
|
num.nts
|
|
names(mtDA.multSeqs.bstr)
|
|
names(mtDNA.multSeqs.bstr)
|
|
mtDNA.multSeqs.bstr
|
|
mtDNA.multSeqs.bstr
|
|
mtDNA.multSeqs.bstr
|
|
mtDNA.multSeqs.bstr --help
|
|
print(mtDNA.multSeqs.bstr)
|
|
print(mtDNA.multSeqs.bstr, -n40)
|
|
print(mtDNA.multSeqs.bstr, -n 40)
|
|
print(mtDNA.multSeqs.bstr, n=20)
|
|
class(mtDNA.multSeqs.bstr)
|
|
print(mtDNA.multSeqs.bstr)
|
|
?print()
|
|
?print
|
|
table(mtDNA.multSeqs.bstr)
|
|
mtDNA.multSeqs.bstr
|
|
mtDNA.multSeqs.bstr$width
|
|
mtDNA.multSeqs.bstr[,1]$width
|
|
mtDNA.multSeqs.bstr[1,]$width
|
|
mtDNA.multSeqs.bstr[1]$width
|
|
mtDNA.multSeqs.bstr[1]
|
|
mtDNA.multSeqs.bstr[1]$seq
|
|
mtDNA.multSeqs.bstr[1]$width
|
|
mtDNA.multSeqs.bstr[1]$names
|
|
mtDNA.multSeqs.bstr$names
|
|
# name the Biostring sequences and compute stats
|
|
names(mtDNA.multSeqs.bstr) <- Names.vec # count nucs and sequence lengths
|
|
mtDNA.multSeqs.bstr$names
|
|
mtDNA.multSeqs.bstr$Names
|
|
mtDNA.lengths
|
|
table(mtDNA.lengths, Names.vec)
|
|
cbind(mtDNA.lengths, Names.vec)
|
|
sort(cbind(mtDNA.lengths, Names.vec))
|
|
cbind(mtDNA.lengths, Names.vec)
|
|
cbind(mtDNA.lengths, Names.vec)
|
|
table(cbind(mtDNA.lengths, Names.vec))
|
|
rbind(cbind(mtDNA.lengths, Names.vec))
|
|
sort(rbind(cbind(mtDNA.lengths, Names.vec)))
|
|
rbind(mtDNA.lengths, Names.vec)
|
|
cbind(mtDNA.lengths, Names.vec)
|
|
max(cbind(mtDNA.lengths, Names.vec))
|
|
max(cbind(mtDNA.lengths, Names.vec))[,1]
|
|
max(cbind(mtDNA.lengths, Names.vec)[,1])
|
|
max(cbind(mtDNA.lengths, Names.vec)[1,])
|
|
max(cbind(mtDNA.lengths, Names.vec)[,1])
|
|
max(cbind(mtDNA.lengths, Names.vec))
|
|
cbind(mtDNA.lengths, Names.vec)
|
|
nlengthnames <- cbind(mtDNA.lengths, Names.vec)
|
|
max(nlengthnames[,1])
|
|
nlengthnames <- cbind(mtDNA.lengths, Names.vec)
|
|
nlengthnames[which.max(nlengthnames[,1])]
|
|
idx <- which.max(nlengthnames[,1])
|
|
idx
|
|
nlengthnames[idx, idx]
|
|
nlengthnames[idx]
|
|
nlengthnames
|
|
nlengthnames[idx,]
|
|
proportion.nts <- num.nts/mtDNA.lengths
|
|
proportion.nts
|