Name	Modified	Size
	..	Jan 3, 2025 02:44 AM
	Lec9TB.pdf	Jan 3, 2025 02:43 AM	1.4 MB
	TB-Bio_Info_11.pdf	Jan 3, 2025 02:43 AM	1.0 MB
	Lec8TB.pdf	Jan 3, 2025 02:43 AM	977.8 KB
	Lec10TB.pdf	Jan 3, 2025 02:43 AM	492.4 KB
	Exam-MidEX1.R	Jan 3, 2025 02:44 AM	6.7 KB
	Bio-Lab2.R	Jan 3, 2025 02:44 AM	2.2 KB
	Exam-mid.R	Jan 3, 2025 02:44 AM	1.7 KB
	Lab-Last.R	Jan 3, 2025 02:44 AM	1.6 KB
	Bio-Lab3.R	Jan 3, 2025 02:44 AM	1.1 KB
	Bio-Lab5.R	Jan 3, 2025 02:44 AM	867 B
	Bio-Lab4.R	Jan 3, 2025 02:44 AM	686 B
	Bio_Pr1.R	Jan 3, 2025 02:44 AM	645 B
	Bio-Lab.R	Jan 3, 2025 02:44 AM	517 B

	  library(HardyWeinberg)
library(genetics)
#############################3
#Genotype frequencies for 70 SNPs related to Alzheimer's disease

data(Alzheimer)
View(Alzheimer)

HWQqplot(X=as.matrix(Alzheimer[,1:3]),logplot=TRUE,pvaluetype="selome",main="Q-Q Plot for HWE")

HWTernaryPlot(X=as.matrix(Alzheimer[,1:3]))

HWGenotypePlot(X=as.matrix(Alzheimer[,1:3]))

data(HapMapCHBChr1)
View(HapMapCHBChr1)

#Biallelic polymorphisms sampled from chromosome
#22 of the CEU population of the 1000 Genomes project.

data(CEUchr22)
View(CEUchr22)

###########################################
data1<-HWData(nm=1000,n=100)
HWAlltests(data1[1,])
HWTernaryPlot(data1)
HWQqplot(X=data1,logplot=TRUE,pvaluetype="selome",main="Q-Q
Plot for HWE")
HWGenotypePlot(data1)
#######################################
geno1<-c("A/A","A/T","T/A","T/T")
nsnp1<-5;nsample<-100

geneA<-matrix(0,nsample,nsnp1)
for(i in 1:nsnp1){   
  geneA[,i]<-sample(geno1,nsample,replace=TRUE)
}

data<-makeGenotypes(data.frame(geneA))
af<-c()
for(i in 1:ncol(data)){ 
  af[i]<-max(unname(summary(data[,i])$allele.freq[,2]))
}

phwe<-c()
for(i in 1:ncol(data)){ 
  phwe[i]<-HWE.test(data[,i])$test$p.value
}
phwe

plot(af,phwe,pch=16,type="b")

#####################################################3
p<-seq(0,1,0.01)

plot(p, (1-p)^2, ylab ="genotype frequency",  main="Under HWE",type="l",
     col="blue")

lines(p, 2*p*(1-p),col="green")
lines(p, p^2, col="grey")

legend(0.5,0.95,"genotype =0",lty = 1, col ="blue", bty="n")
legend(0.5,0.85,"genotype =1",lty = 1, col ="green", bty = "n")
legend(0.5,0.75,"genotype =2",lty = 1, col ="grey", bty = "n")

abline(v = 0.5, lty=2)
	  

	  
	  
	  library(genetics)
library(combinat)
library(LDheatmap)

snp <- 10
sample <- 100

geno <- c( "A/A", "A/T", "T/A", "T/T")  # ,"C/G", "C/C", "G/C", "G/G"
APCO3_gene <- matrix(0,sample,snp)  #ROW,COL
APCO3_gene      #Only Matrix Created

for(i in 1:snp){     # Col - wise Fill
  APCO3_gene[,i]<- sample(geno,sample,replace=TRUE)   
}

APCO3_gene
summary(APCO3_gene)

APCO3 <- makeGenotypes(data.frame(APCO3_gene))   # Matrix to Genetype 
APCO3
r1 <- summary(APCO3)
r1

LDheatmap(APCO3)
LDheatmap(APCO3,color=heat.colors(10),flip=TRUE)

ldt <- LD(APCO3)
LDtable(ldt)

r2 <- ldt$`R^2`
r2

#het <- ldt$



af<- matrix(0,ncol(APCO3),2)
for(i in 1:ncol(APCO3)){
  af[i,]<- unname(summary(APCO3[,i])$allele.freq[,2] )
}
af

gf<- list()
for(i in 1:ncol(APCO3)){
  gf[i]<- unname(summary(APCO3[,i])$genotype.freq[,2] )
}
gf

	  

Assing...

library(genetics)
library(combinat)
library(LDheatmap)
library(ggplot2)

num_snps <- 100
sample <- 1000

geno <- c( "A/A", "T/A", "T/T" ) 

APCO3_gene <- matrix(0,sample,num_snps) 
#APCO3_gene    

set.seed(1234)
for(i in 1:num_snps){   
  APCO3_gene[,i]<- sample(geno,sample,replace=TRUE, prob = c(0.97, 0.025, 0.005))   
}

#Show Matrix gene Data
#APCO3_gene

#summary(APCO3_gene)

APCO3 <- makeGenotypes(data.frame(APCO3_gene))   # Matrix to Genetype 
#APCO3

# Calculation of Allele Frequencies

maf <- matrix(0, ncol(APCO3), 1)

for (i in 1:ncol(APCO3)) {
  allele_freq <- unname(summary(APCO3[, i])$allele.freq[, 2])
  maf[i] <- min(allele_freq)
}

#Show MAF Values
maf


#MAF plot  
maf_plot <- data.frame(SNP = 1:length(maf), MAF = maf)

ggplot(maf_plot, aes(x = SNP, y = MAF)) +
  geom_bar(stat = "identity", fill = "#32d1bf", color = "black") +  # Bar plot
  geom_hline(yintercept = 0.02, color = "red", linetype = "dashed", linewidth = 1) +  # Horizontal line
  labs(title = "Minor Allele Frequency (MAF) Bar Plot", 
       x = "Number of SNPs", 
       y = "Minor Allele Frequency (MAF)")  + theme_minimal() + theme(plot.title = element_text(hjust = 0.5))


# Heterozygosity (HET) and PIC

het <- numeric(ncol(APCO3))
pic <- numeric(ncol(APCO3))
for (i in 1:ncol(APCO3)) {
  het[i] <- unname(summary(APCO3[, i])$Hu)
  pic[i] <- unname(summary(APCO3[, i])$pic)
}

#PLOT 

# Create data frames for plotting
het_plot <- data.frame(SNP = 1:length(het), HET = het)
pic_plot <- data.frame(SNP = 1:length(pic), PIC = pic)

# Plot HET values
ggplot(het_plot, aes(x = SNP, y = HET)) +
  geom_bar(stat = "identity", fill = "skyblue", color = "black") +
  labs(title = "Heterozygosity (HET) Bar Plot", x = "Number of SNPs", y = "Heterozygosity (HET)") +
  theme_minimal() + theme(plot.title = element_text(hjust = 0.5))


# Plot PIC values
ggplot(pic_plot, aes(x = SNP, y = PIC)) +
  geom_bar(stat = "identity", fill = "lightgreen", color = "black") +
  labs(title = "Polymorphic Information Content (PIC) Bar Plot", x = "Number of SNPs", y = "PIC") +
  theme_minimal() + theme(plot.title = element_text(hjust = 0.5))


#LD Measures:

ld_result <- LD(APCO3)
ld_r2 <- ld_result$`R^2`
ld_d_prime <- ld_result$`D'`
ld_result

#Plot LD Measures

ld_plot <- data.frame(SNP1 = rep(1:nsnp, nsnp), SNP2 = rep(1:nsnp, each = nsnp), R2 = as.vector(ld_r2))
ggplot(ld_plot, aes(x = SNP1, y = SNP2, fill = R2)) +
  geom_tile() +
  labs(title = "Pairwise LD (R2)", x = "SNP 1", y = "SNP 2") +
  theme_minimal() + theme(plot.title = element_text(hjust = 0.5)) +
  scale_fill_gradient(low = "white", high = "red")

LDheatmap(data,color=heat.colors(20),flip=TRUE)

#part c (QC Results and Marker Reduction:)


maf_threshold <- 0.02
selected_snps <- which(maf >= maf_threshold)
filtered_snps <- which(maf < maf_threshold)  # SNPs to eliminate

# Display results
cat("Total SNPs:", nsnp, "\n")
cat("SNPs passing QC (MAF >= 0.02):", length(selected_snps), "\n")
cat("SNPs eliminated (MAF < 0.02):", length(filtered_snps), "\n")

	

		5--
	
	library(genetics)
library(combinat)
library(LDheatmap)

n <- 100
sample <- 1000

geno <- c( "A/A", "A/T",  "T/T") #  c( "A/A", "A/T", "T/A", "T/T") 

set.seed(100)
snp1<- sample(geno,n,replace=TRUE)
snp1
table(snp1)

set.seed(100)
snp2<- sample(geno,n,replace=TRUE)


phenotype <- c("case","control")
phe<-sample(phenotype,n,replace=TRUE,prob=c(0.5,0.5))
table(phe)


data<-data.frame(phe,snp1,snp2)
tab <- table(data$snp1)
chisq.test(tab)$p.value

tab <- table(data$snp2)
chisq.test(tab)$p.value