corehunter (version 3.0.1)

genotypes: Create Core Hunter genotype data from data frame, matrix or file.

Description

Specify either a data frame or matrix, or a file from which to read the genotypes. See www.corehunter.org for documentation and examples of the genotype data file format used by Core Hunter.

Usage

genotypes(data, alleles, file, format = c("default", "biparental", "frequency"))

Arguments

data

Data frame or matrix containing the genotypes (individuals x markers) depending on the chosen format:

In case a data frame is provided, an optional first column NAME may be included to specify item names. The remaining columns should follow the format of the matrix or data frame described above. See www.corehunter.org for more details about the supported genotype formats.

alleles

Allele names per marker (character vector). Optional and ignored for all formats except frequency. Allele names should be ordered in correspondence with the data columns.

file

File containing the genotype data.

format

Genotype data format, one of default, biparental or frequency.

Value

Genotype data of class chdist with elements

Examples

# create from data frame or matrix

# default format
geno.data <- data.frame(
 NAME = c("Alice", "Bob", "Carol", "Dave", "Eve"),
 M1.1 = c(1,2,1,2,1),
 M1.2 = c(3,2,2,3,1),
 M2.1 = c("B","C","D","B",NA),
 M2.2 = c("B","A","D","B",NA),
 M3.1 = c("a1","a1","a2","a2","a1"),
 M3.2 = c("a1","a2","a2","a1","a1"),
 M4.1 = c(NA,"+","+","+","-"),
 M4.2 = c(NA,"-","+","-","-"),
 row.names = paste("g", 1:5, sep = "-")
)
geno <- genotypes(geno.data)

# biparental
geno.data <- matrix(
 sample(c(0,1,2), replace = TRUE, size = 1000),
 nrow = 10, ncol = 100
)
rownames(geno.data) <- paste("g", 1:10, sep = "-")
colnames(geno.data) <- paste("m", 1:100, sep = "-")
geno <- genotypes(geno.data, format = "biparental")

# frequencies
geno.data <- matrix(
 c(0.0, 0.3, 0.7, 0.5, 0.5, 0.0, 1.0,
   0.4, 0.0, 0.6, 0.1, 0.9, 0.0, 1.0,
   0.3, 0.3, 0.4, 1.0, 0.0, 0.6, 0.4),
 byrow = TRUE, nrow = 3, ncol = 7
)
rownames(geno.data) <- paste("g", 1:3, sep = "-")
colnames(geno.data) <- c("M1", "M1", "M1", "M2", "M2", "M3", "M3")
alleles <- c("M1-a", "M1-b", "M1-c", "M2-a", "M2-b", "M3-a", "M3-b")
geno <- genotypes(geno.data, alleles, format = "frequency")

# read from file

# default format
geno.file <- system.file("extdata", "genotypes.csv", package = "corehunter")
geno <- genotypes(file = geno.file)

# biparental
geno.file <- system.file("extdata", "genotypes-biparental.csv", package = "corehunter")
geno <- genotypes(file = geno.file, format = "biparental")

# frequencies
geno.file <- system.file("extdata", "genotypes-frequency.csv", package = "corehunter")
geno <- genotypes(file = geno.file, format = "frequency")