Package 'gwid'

Title: Genome-Wide Identity-by-Descent
Description: Methods and tools for the analysis of Genome Wide Identity-by-Descent ('gwid') mapping data, focusing on testing whether there is a higher occurrence of Identity-By-Descent (IBD) segments around potential causal variants in cases compared to controls, which is crucial for identifying rare variants. To enhance its analytical power, 'gwid' incorporates a Sliding Window Approach, allowing for the detection and analysis of signals from multiple Single Nucleotide Polymorphisms (SNPs).
Authors: Soroush Mahmoudiandehkordi [aut, cre], Steven J Schrodi [aut], Mehdi Maadooliat [aut]
Maintainer: Soroush Mahmoudiandehkordi <[email protected]>
License: MIT + file LICENSE
Version: 0.3.0
Built: 2025-02-06 05:27:49 UTC
Source: https://github.com/soroushmdg/gwid

Help Index

Open a SNP GDS file and extract information.

Description

Open a SNP GDS file and extract information.

Usage

build_gwas(gds_data = "name.gds", caco = "name.Rda", gwas_generator = TRUE)

Arguments

gds_data

File name
caco

An object of class caco. Output of case_control function.
gwas_generator

logical; if TRUE an object of class result_snps will be saved inside output list.

Value

a list of seven objects; including smp.id, snp.id, snp.pos, smp.indx, smp.snp (a matrix with samples in rows and snp in columns), caco, snps(column sum of smp.snp for each case control)

Open a ibd file and extract information.

Description

Open a ibd file and extract information.

Usage

build_gwid(
  ibd_data = "name.ibd",
  gwas = "object of class gwas",
  gwid_generator = TRUE
)

Arguments

ibd_data

a file name for output of Refined IBD
gwas

object of class gwas
gwid_generator

logical; if TRUE an object of class result_snps will be saved inside output list.

Value

the output will be a object(list) of class gwid contains profile object, IBD object and result_snps object.

Read .vcf structured text format files and reduce the size of file.

Description

Read .vcf structured text format files and reduce the size of file.

Usage

build_phase(phased_vcf = "name.vcf", caco)

Arguments

phased_vcf

A file name for a variant call format (vcf) file.
caco

An object of class caco. Output of case_control function.

Value

the output will be a a list of class phase contains two sparse matrix for each haplotype.

Reload saved case-control list file

Description

Reload saved case-control list file

Usage

case_control(case_control_rda, ...)

Arguments

case_control_rda

A character string giving the name of the case-control file to load. The file is a list of character vectors including subject names in each case-control groups or csv file including subject name for a disease.
...

name of a column (disease name) of csv file.

Value

The output will be a list of character vectors include subject names and groups. The class of returned object is caco.

Extract information from SNP GDS file.

Description

Extract information from SNP GDS file.

Usage

extract(obj, ...)

Arguments

obj

an object of class gwas
...

other arguments

Value

extract object instants

extract component of an object

Description

extract component of an object

Usage

extract_window(obj, ...)

Arguments

obj

obj
...

other variables

Value

the output will be a result_snps (data.table) object including 3 columns including, “snp_pos”, “case_control”, and “value”

Extract information from ibd data in a moving window

Description

Extract information from ibd data in a moving window

Usage

## S3 method for class 'gwid'
extract_window(obj, w = 10, snp_start, snp_end, ...)

Arguments

obj

object of class gwid(output of function build_gwid)
w

window size
snp_start

select starting position of snp, which we want to aggregate.
snp_end

select ending position of snp, which we want to aggregate.
...

other variables

Value

the output will be a result_snps (data.table) object including 3 columns including, “snp_pos”, “case_control”, and “value”

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)
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)

Extract information from SNP GDS file.

Description

Extract information from SNP GDS file.

Usage

## S3 method for class 'gwas'
extract(obj, type = c("snps", "snp2", "nas"), snp_start, snp_end, ...)

Arguments

obj

object of class gwas.
type

indicate type of aggregation on sample-snp data and must be one of snps, snp2, or nas
snp_start

select starting position of snp, which we want to aggregate.
snp_end

select ending position of snp, which we want to aggregate.
...

other arguments

Value

the output will be a result_snps (data.table) object including 3 columns including, snp_pos, case_control, and value

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)
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)

Extract information from ibd data.

Description

Extract information from ibd data.

Usage

## S3 method for class 'gwid'
extract(obj = "object of class gwid", snp_start, snp_end, ...)

Arguments

obj

object of class gwid(output of function build_gwid)
snp_start

select starting position of snp, which we want to aggregate.
snp_end

select ending position of snp, which we want to aggregate.
...

other objects

Value

the output will be a result_snps (data.table) object including 3 columns including, “snp_pos”, “case_control”, and “value”

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)
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)

Fisher test

Description

Fisher test

Usage

fisher_test(obj, ...)

Arguments

obj

an object
...

other variables

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.

Fisher's Exact Test for gwas count data

Description

Fisher's Exact Test for gwas count data

Usage

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

Arguments

obj

object of class gwas
reference

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

select starting position of snps.
snp_end

select ending position of snp.
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)
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)

Fisher's Exact Test for gwid count data

Description

Fisher's Exact Test for gwid count data

Usage

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

Arguments

obj

An object of class gwid. Output of build_gwid function
caco

An object of class caco. Output of case_control function.
snp_start

select starting position of snps.
snp_end

select ending position of snp.
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)
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)

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)

perform gtest

Description

perform gtest

Usage

gtest(haplotype_structure, ...)

Arguments

haplotype_structure

object of a class
...

other variables

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.

Perform G-test on haplotype structures extracted from haplotype_structure function

Description

Perform G-test on haplotype structures extracted from haplotype_structure function

Usage

## S3 method for class 'haplotype_structure'
gtest(haplotype_structure, reference, ...)

Arguments

haplotype_structure

An object of class haplotype_structure. Output of haplotype_structure function.
reference

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

other variables

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.

haplotype frequency

Description

haplotype frequency

Usage

haplotype_frequency(haplotype_structure, ...)

Arguments

haplotype_structure

object of class haplotype structure
...

other variables

Value

An object of class haplotype_frequency contains of two objects. first one is object of haplotype_structure_frequency (data.table) and second one is object of class result_snps(data.table)

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)
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)

haplotype frequency in sliding windows

Description

haplotype frequency in sliding windows

Usage

## S3 method for class 'haplotype_structure'
haplotype_frequency(haplotype_structure, ...)

Arguments

haplotype_structure

An object of class haplotype_structure. Output of haplotype_structure function.
...

other variables

Value

An object of class haplotype_frequency contains of two objects. first one is object of haplotype_structure_frequency (data.table) and second one is object of class result_snps(data.table)

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)
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)

haplotype structures in a window

Description

haplotype structures in a window

Usage

haplotype_structure(obj, ...)

Arguments

obj

object
...

other variables

Value

The output will be an object of class haplotype_structure (data.table) that has information about subjects haplotype structures in a a window.

extract haplotype structures of individuals in a window

Description

extract haplotype structures of individuals in a window

Usage

## S3 method for class 'gwas'
haplotype_structure(obj, phase, w = 10, snp_start, snp_end, ...)

Arguments

obj

object of class gwas
phase

An object of class phase. Output of build_phase function
w

window size
snp_start

select starting position of snps.
snp_end

select ending position of snps.
...

other variables

Value

The output will be an object of class haplotype_structure (data.table) that has information about subjects haplotype structures in a a window.

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)
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)

extract haplotype structures of pairwise ibd samples in a window

Description

extract haplotype structures of pairwise ibd samples in a window

Usage

## S3 method for class 'gwid'
haplotype_structure(obj, phase, w = 10, snp_start, snp_end, ...)

Arguments

obj

An object of class gwid. Output of build_gwid function.
phase

An object of class phase. Output of build_phase function.
w

window size
snp_start

select starting position of snps.
snp_end

select ending position of snps.
...

other variables

Value

The output will be an object of class haplotype_structure (data.table) that has information about subjects haplotype structures in a a window.

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)
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)

laucnh a shiny app

Description

laucnh a shiny app

Usage

launch_app(data_folder_address, ...)

Arguments

data_folder_address

address of the folder that your data folders are. for example if you have two sets of data such as data1 and data2 and they are in mydata folder then your data_folder_address should be "./mydata"
...

other variables

Value

open a shiny app

mcnemar test

Description

mcnemar test

Usage

mcnemar_test(roh, ...)

Arguments

roh

roh as class result_snp
...

other variables

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.

mcnemar permutation

Description

mcnemar permutation

Usage

mcnemar_test_permut(mcnemar, ...)

Arguments

mcnemar

macnemar test output
...

other variables

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.

mcnemar permutation test

Description

mcnemar permutation test

Usage

## S3 method for class 'result_snps'
mcnemar_test_permut(
  mcnemar = "object of class result_snps (output of function mcnemar_test with fun=sum)",
  roh_mat = "output of roh function when roh_mat = TRUE",
  gwas = "object of class gwas",
  nperm = 1000,
  reference = "cases",
  w,
  ...
)

Arguments

mcnemar

macnemar test output
roh_mat

roh matrix
gwas

gwas
nperm

number of permutation
reference

reference group
w

window
...

other variables

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.

mcnemar test

Description

mcnemar test

Usage

## S3 method for class 'result_snps'
mcnemar_test(
  roh = "object of class result_snps (output of function roh with fun=sum)",
  reference,
  w = 10,
  ...
)

Arguments

roh

An object of class result_snps (output of function roh with fun=sum)
reference

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

window size
...

other variables

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.

permutation test

Description

permutation test

Usage

permutation_test(obj, ...)

Arguments

obj

object
...

other variables

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.

Permutation test for gwas object

Description

Permutation test for gwas object

Usage

## S3 method for class 'gwas'
permutation_test(
  obj,
  snp_start,
  snp_end,
  nperm = 1000,
  reference = "cases",
  ...
)

Arguments

obj

object of class gwas
snp_start

elect starting position of snps.
snp_end

select ending position of snp.
nperm

Number of permutations.
reference

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

other variables

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)

permutation test for gwid count data

Description

permutation test for gwid count data

Usage

## S3 method for class 'gwid'
permutation_test(
  obj,
  gwas,
  snp_start,
  snp_end,
  nperm = 100,
  reference = "cases",
  ...
)

Arguments

obj

An object of class gwid. Output of build_gwid function
gwas

object of class gwas
snp_start

select starting position of snps.
snp_end

select ending position of snp.
nperm

Number of permutations.
reference

reference group
...

other variables

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)

Permutation test for 'haplotype_structure' object

Description

Permutation test for 'haplotype_structure' object

Usage

## S3 method for class 'haplotype_structure'
permutation_test(obj, nperm, reference, ...)

Arguments

obj

object of class 'haplotype_structure'
nperm

Number of permutations.
reference

reference group of subjects in which we want to perform 'gtest'
...

other variables

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)

Line plot of gwas objects

Description

Line plot of gwas objects

Usage

## S3 method for class 'gwas'
plot(x, y = NA, title = "number of snps", ...)

Arguments

x

object of class gwas.
y

default value is NA, if specified it should be a vector of names of subject groups i.e. y = c("case","control")
title

title of the plot.
...

optional argument of plot

Value

an interactive line plot of gwas objects for each case control subjects.

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)
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)

Line plot of gwid objects

Description

Line plot of gwid objects

Usage

## S3 method for class 'gwid'
plot(
  x,
  y = NA,
  title = "number of IBD in each snp",
  plot_type = c("result_snps", "profile"),
  reference,
  ...
)

Arguments

x

An object of class gwid. Output of build_gwid function.
y

default value is NA, if specified it should be a vector of names of subject groups i.e. y = c("case","control")
title

title of the plot.
plot_type

either “result_snps” or “profile”.
reference

reference group of subjects in which we want to have profile plot.
...

if plot_type is “result_snps” it is optional argument of plot. if plot_type is “profile” we can subset plot based on snp_start and snp_end locations.

Value

if plot_type is “result_snps” an interactive line plot of result_snps for each case control subjects. if plot_type is “profile” an interactive profile plot of identity by descent subjects in subset of locations.

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)
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)

Line plot of haplotype_frequency object

Description

Line plot of haplotype_frequency object

Usage

## S3 method for class 'haplotype_frequency'
plot(
  x,
  y = NA,
  plot_type = c("haplotype_structure_frequency", "result_snps"),
  type = c("version1", "version2"),
  ly = TRUE,
  nwin,
  title,
  line_size = 0.6,
  ...
)

Arguments

x

an object of class haplotype_frequency
y

default value is 'NA', if specified it should be a vector of names of subject groups i.e. 'y = c("case","control")'
plot_type

either “result_snps” or “"haplotype_structure_frequency"”
type

either “version1” or “version2” when plot_type is “"haplotype_structure_frequency"”
ly

if TRUE, we have a plotly object and if it is false plot is going to be a ggplot object.
nwin

window number
title

title of the plot.
line_size

geom_line size
...

optional argument of plot

Value

an interactive line plot of haplotype_frequency objects for each case control subjects.

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)
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)
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)

Two type of line plots for haplotype_structure_frequency objects .

Description

Two type of line plots for haplotype_structure_frequency objects .

Usage

## S3 method for class 'haplotype_structure_frequency'
plot(
  x,
  y = NA,
  type = c("version1", "version2"),
  nwin,
  ly = TRUE,
  line_size = 0.6,
  ...
)

Arguments

x

an object of class haplotype_structure_frequency
y

default value is NA, if specified it should be a vector of names of subject groups i.e. y = c("case","control")
type

either “version1” or “version2”
nwin

window number
ly

if 'TRUE', we have a 'plotly' object and if it is 'FALSE' plot is going to be a 'ggplot' object.
line_size

geom_line size
...

other variables

Value

an interactive line plot of haplotype_structure_frequency objects for each case control subjects.

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)
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)

Line plot of result_snps objects

Description

Line plot of result_snps objects

Usage

## S3 method for class 'result_snps'
plot(x, y = NA, title, snp_start, snp_end, ly = TRUE, line_size = 0.6, ...)

Arguments

x

An object of class result_snps.
y

default value is NA, if specified it should be a vector of names of subject groups i.e. y = c("case","control")
title

title of the plot.
snp_start

select starting position of snps.
snp_end

select ending position of snps.
ly

if TRUE, we have a plotly object and if it is false plot is going to be a ggplot object.
line_size

geom_line size
...

other variables

Value

an interactive line plot of result_snps for each case control subjects.

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)
# 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)
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)

Line plot of test_snps objects

Description

Line plot of test_snps objects

Usage

## S3 method for class 'test_snps'
plot(
  x,
  y = NA,
  title,
  snp_start,
  snp_end,
  ly = TRUE,
  line_size = 0.6,
  log_transformation = TRUE,
  QQplot = FALSE,
  ...
)

Arguments

x

an object of class test_snps.
y

default value is NA, if specified it should be a vector of names of subject groups i.e. y = c("case","control")
title

title of the plot.
snp_start

select starting position of snps.
snp_end

select ending position of snps.
ly

if 'TRUE', we have a 'plotly' object and if it is 'FALSE' plot is going to be a 'ggplot' object.
line_size

geom_line size
log_transformation

if 'TRUE' plot -log10 transformation of p_values.
QQplot

if TRUE, plot QQplot of P-values
...

other variables

Value

an interactive line plot of test_snps objects for each case control subjects.

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)
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)

print

Description

print

Usage

print(x, ...)

Arguments

x

an object
...

other objects

Value

print an object

print gwas instants

Description

print gwas instants

Usage

## S3 method for class 'gwas'
print(x, ...)

Arguments

x

object gwas
...

other objects

Value

print number of subjects and number of SNPs of a GWAS object

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$cases[1:3] # first three subject names of cases group
# read SNP data (use SNPRelate to convert it to gds) and count number of minor alleles
snp_data_gds <- gwid::build_gwas(gds_data = genome_data_file,
caco = case_control,gwas_generator = TRUE)
print(snp_data_gds)
class(snp_data_gds)
names(snp_data_gds)
head(snp_data_gds$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)
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)

runs of homozygosity

Description

runs of homozygosity

Usage

roh(phase, ...)

Arguments

phase

object of phase
...

other variables

Value

runs of homozygosity data table or matrix

runs of homozygosity

Description

runs of homozygosity

Usage

## S3 method for class 'phase'
roh(
  phase,
  gwas,
  w = 10,
  fun = c("sum", "mean"),
  snp_start,
  snp_end,
  roh_mat = FALSE,
  ...
)

Arguments

phase

An object of class phase. Output of build_phase function
gwas

object of class gwas
w

window size
fun

an aggregate function. either “sum” or “mean”
snp_start

select starting position of snps.
snp_end

select ending position of snps.
roh_mat

return roh as matrix
...

other variables

Value

the output will be a result_snps (data.table) object including 3 columns including, “snp_pos”, “case_control”, and “value”

subset an object

Description

subset an object

Usage

subset(obj, ...)

Arguments

obj

object
...

other variables

Value

the output will be a object(list) of class gwid contains profile object and result_snps object.

subset gwid object based on snp position

Description

subset gwid object based on snp position

Usage

## S3 method for class 'gwid'
subset(obj, snp_start, snp_end, ...)

Arguments

obj

object of class gwid(output of function build_gwid)
snp_start

select starting position of snp, which we want to aggregate.
snp_end

select ending position of snp, which we want to aggregate.
...

other variables

Value

the output will be a object(list) of class gwid contains profile object and result_snps object.

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)
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)