fisher_test.result_snps {gwid}

fisher exact test for result_snps count data

Description

fisher exact test for result_snps count data

Usage

## S3 method for class 'result_snps'
fisher_test(
  obj,
  caco,
  reference,
  alternative = c("two.sided", "greater", "less"),
  ...
)

Arguments

obj

An object of class result_snps

caco

An object of class caco. Output of case_control function.

reference

reference group of subjects in which we want to perform fisher test.

alternative

indicates the alternative hypothesis and must be one of "two.sided", "greater" or "less". You can specify just the initial letter. Only used in the 2 by 2 case

...

optional arguments to fisher.test

Value

the output will be a test_snps (data.table) object including 3 columns: “snp_pos”, “case_control”, and “value” which is a p-values.

Examples

piggyback::pb_download(repo = "soroushmdg/gwid",tag = "v0.0.1",dest = tempdir())
ibd_data_file <- paste0(tempdir(),"//chr3.ibd")
genome_data_file <- paste0(tempdir(),"//chr3.gds")
phase_data_file <- paste0(tempdir(),"//chr3.vcf")
case_control_data_file <- paste0(tempdir(),"//case-cont-RA.withmap.Rda")
# case-control data
case_control <- gwid::case_control(case_control_rda = case_control_data_file)
names(case_control) #cases and controls group
summary(case_control) # in here, we only consider cases,cont1,cont2,cont3 groups in the study
case_control$cases[1:3] # first three subject names of cases group
# read SNP data (use SNPRelate to convert it to gds) and count number of minor alleles
snp_data_gds <- gwid::build_gwas(gds_data = genome_data_file,
caco = case_control,gwas_generator = TRUE)
class(snp_data_gds)
names(snp_data_gds)
head(snp_data_gds$snps) # it has information about counts of minor alleles in each location.
# read haplotype data (output of beagle)
haplotype_data <- gwid::build_phase(phased_vcf = phase_data_file,caco = case_control)
class(haplotype_data)
names(haplotype_data)
dim(haplotype_data$Hap.1) #22302 SNP and 1911 subjects
# read IBD data (output of Refined-IBD)
ibd_data <- gwid::build_gwid(ibd_data = ibd_data_file,gwas = snp_data_gds)
class(ibd_data)
ibd_data$ibd # refined IBD output
ibd_data$res # count number of IBD for each SNP location
# plot count of IBD in chromosome 3
plot(ibd_data,y = c("cases","cont1"),ly = FALSE)
# Further investigate location between 117M and 122M
# significant number of IBD's in group cases, compare to cont1, cont2 and cont3.
plot(ibd_data,y = c("cases","cont1"),snp_start = 119026294,snp_end = 120613594,ly = FALSE)
model_fisher <- gwid::fisher_test(ibd_data,case_control,reference = "cases",
snp_start = 119026294,snp_end = 120613594)
model_permutation <- permutation_test(ibd_data,snp_data_gds,
snp_start = 119026294,snp_end = 120613594,nperm=20,reference = "cases")
class(model_fisher)
plot(model_fisher, y = c("cases","cont1"),ly = FALSE)
hap_str <- gwid::haplotype_structure(ibd_data,phase = haplotype_data,w = 10,
snp_start = 119026294,snp_end = 120613594)
haplo_freq <- gwid::haplotype_frequency(hap_str)
plot(haplo_freq,y = c("cases", "cont1"),plot_type = "haplotype_structure_frequency",
nwin = 1, type = "version1",ly = FALSE)