1. Bhuiyan, M. S. A., Lee, D. H., Kim, H. J., Lee, S. H., Cho, S. H., Yang, B. S., Kim, S. D., & Lee, S. H. 2018. Estimates of genetic parameters for fatty acid compositions in the longissimus dorsi muscle of Hanwoo cattle. Animal, 12(5), 675-683.
2. B. Park / 2013 / National Genetic Evaluation (System) of Hanwoo (Korean Native Cattle) / Animal Bioscience / 26 (2) : 151 ~ 2
3. Geay Y, Bauchart D, Hocquette J, Culioli J. 2001. Effect of nutritional factors on biochemical, structural and metabolic factors on of muscles in ruminant, consequences on dietic value and sensorial qualities of meat. Reprod. Nutr. Dev. 41: 1-26.
4. Tatum J, Smith C, Carpenter Z. 1982. Interrelationships between marbling, subcutaneous fat thickness, and cooked beef palatability. J. Anim. Sci. 43: 777-784.
5. Hocquette J, Richardson I, Prachardson I, Prache S, Medale F, Duffy G, Scollan, N. 2005. The future trends for research on quality and safety of animal product. Italian J. Anim. Sci. 4: 49-72.
6. Kim KH, Lee JH, Oh YG, Kang SW, Lee SC, Park WY, Ko YD. 2005.The Optimal TDN Levels of Concentrates and Slaughter Age in Hanwoo Steers. J Anim Sci & Technol (Kor.). 47: 731-744
7. Lee SH, Park EW, Cho YM et al. 2006. Lipogenesis gene expression profiling on the early and late fattening stage of Hanwoo muscle. J. Anim. Sci & Technol(kor). 48: 913-920.
8. Zhang S, Knight T, Reecy J, Beitz D. 2008. DNA polymorphisms in bovine fatty acid synthase are associated with beef fatty acid composition. Anim. Genet. 39: 62-70.

# 데이터 로드
data <- read.table(“data-snp.txt”, header = TRUE)

# 데이터 요약
summary(data)
str(data)

# Box Plot 그리기
library(ggplot2)

# rs799031002와 형질 간의 Box Plot
p1=ggplot(data, aes(x = rs799031002, y = MS)) +
geom_boxplot() + labs(title = “Box Plot of MS by rs799031002”, x = “rs799031002”, y = “MS”)

p2=ggplot(data, aes(x = rs799031002, y = D_IMF)) +
geom_boxplot() + labs(title = “Box Plot of D_IMF by rs799031002”, x = “rs799031002”, y = “D_IMF”)

p3=ggplot(data, aes(x = rs799031002, y = S_IMF)) + geom_boxplot() + labs(title = “Box Plot of S_IMF by rs799031002”, x = “rs799031002”, y = “S_IMF”)

grid.arrange(p1,p2,p3, ncol=3) # 3개의 그림을 하나의 파일로 통합

# rs209494671와 형질 간의 Box Plot
p1=ggplot(data, aes(x = rs209494671, y = MS)) +
geom_boxplot() +
labs(title = “Box Plot of MS by rs209494671”, x = “rs209494671”, y = “MS”)

p2=ggplot(data, aes(x = rs209494671, y = D_IMF)) +
geom_boxplot() +
labs(title = “Box Plot of D_IMF by rs209494671”, x = “rs209494671”, y = “D_IMF”)

p3=ggplot(data, aes(x = rs209494671, y = S_IMF)) +
geom_boxplot() +
labs(title = “Box Plot of S_IMF by rs209494671”, x = “rs209494671”, y = “S_IMF”)
grid.arrange(p1,p2,p3, ncol=3)

# rs210204777와 형질 간의 Box Plot
p1=ggplot(data, aes(x = rs210204777, y = MS)) +
geom_boxplot() +
labs(title = “Box Plot of MS by rs210204777”, x = “rs210204777”, y = “MS”)

p2=ggplot(data, aes(x = rs210204777, y = D_IMF)) +
geom_boxplot() +
labs(title = “Box Plot of D_IMF by rs210204777”, x = “rs210204777”, y = “D_IMF”)

p3=ggplot(data, aes(x = rs210204777, y = S_IMF)) +
geom_boxplot() +
labs(title = “Box Plot of S_IMF by rs210204777”, x = “rs210204777”, y = “S_IMF”)
grid.arrange(p1,p2,p3, ncol=3)

# rs799031002와 MS 간 분산분석: 본문 내용과 무관하게 표현형과 유전자형(범주형)간의 분산분석 모델
anova_ms <- aov(MS ~ rs799031002, data = data)
summary(anova_ms)

# rs799031002와 D_IMF 간 분산분석
anova_d_imf <- aov(D_IMF ~ rs799031002, data = data)
summary(anova_d_imf)

# rs799031002와 S_IMF 간 분산분석
anova_s_imf <- aov(S_IMF ~ rs799031002, data = data)
summary(anova_s_imf)

# 형질별 요약 통계량 기초통계량을 위한 계산
summary(data$MS)
summary(data$D_IMF)
summary(data$S_IMF)

# SNP별 데이터 분포 요약 유전자형 분포
table(data$rs799031002)
table(data$rs209494671)
table(data$rs210204777)

# 데이터 로드
data <- read.table(“data_snp.txt”, header = TRUE)

# 대립유전자 빈도 계산 함수
calculate_allele_frequency <- function(snp_column) {
# SNP 데이터를 문자로 변환
alleles <- unlist(strsplit(as.character(snp_column), “”))

# 대립유전자별 빈도 계산
freq_table <- table(alleles)
freq_percentage <- prop.table(freq_table) * 100

# 결과 출력
list(allele_counts = freq_table, allele_frequencies = freq_percentage)
}

# rs799031002 대립유전자 빈도 계산(각 유전변이에 대한 빈도계산후 연구자가 직접 표를 작성해야합니다.
rs799031002_freq <- calculate_allele_frequency(data$rs799031002)
cat(“rs799031002 대립유전자 빈도:\n”)
print(rs799031002_freq)

rs209494671_freq <- calculate_allele_frequency(data$rs209494671)
cat(“rs209494671 대립유전자 빈도:\n”)
print(rs209494671_freq)

rs210204777_freq <- calculate_allele_frequency(data$rs210204777)
cat(“rs210204777 대립유전자 빈도:\n”)
print(rs210204777_freq)

# 유전자형 변환 함수: 현재 파일에서는 유전자형이 범주형으로 되어 있어서, 이를 수치형(0,1,2)로 변환하여 회귀분석을 진행해야 해서, 유전자형의 수치형 변환

convert_genotype <- function(genotype_column) {
# 대립유전자 빈도 계산
alleles <- unlist(strsplit(as.character(genotype_column), “”))
allele_freq <- table(alleles)

# Minor allele 확인
minor_allele <- names(allele_freq)[which.min(allele_freq)]

# 유전자형을 숫자로 변환
sapply(genotype_column, function(genotype) {
  if (genotype == paste0(minor_allele, minor_allele)) {
    return(2) # Minor homozygote
  } else if (grepl(minor_allele, genotype)) {
    return(1) # Heterozygote
  } else {
    return(0) # Major homozygote
  }
})
}

# 모든 유전자형 열에 변환 적용
genotype_columns <- colnames(data)[5:ncol(data)]
for (col in genotype_columns) {
data[[col]] <- convert_genotype(data[[col]])
}

# 결과 출력
print(data)
# 변환된 수치형자료를 이용하여 회귀분석 수행.
# Regression analysis: rs799031002와 MS 간
R1 <- lm(MS ~ rs799031002, data = data)
summary(R1)

R2 <- lm(D_IMF ~ rs799031002, data = data)
summary(R2)

R3 <- lm(S_IMF ~ rs799031002, data = data)
summary(R3)

R4 <- lm(MS ~ rs209494671, data = data)
summary(R4)

R5 <- lm(D_IMF ~ rs209494671, data = data)
summary(R5)

R6 <- lm(S_IMF ~ rs209494671, data = data)
summary(R6)

R7 <- lm(MS ~ rs210204777, data = data)
summary(R7)

R8 <- lm(D_IMF ~ rs210204777, data = data)
summary(R8)

R9 <- lm(S_IMF ~ rs210204777, data = data)
summary(R9)