Download and process GWAS summary statistics for ingestion into existing GACT database

Introduction

This tutorial is designed for incorporating new genetic association data into an existing gact database. The example below is for the UK Biobank 2021 Glycated Hemoglobin (HbA1c) GWAS data for European ancestry.

# Load libraries
library(qgg)
library(gact)
library(data.table)


# Load GAlist with information on gact database
GAlist <- readRDS(file="C:/Users/gact/hsa.0.0.1/GAlist_hsa.0.0.1.rds")


################################################################################
# UK Biobank 2021 HbA1c GWAS: European ancestry
################################################################################
# link: https://t2d.hugeamp.org/dinspector.html?dataset=SinnottArmstrong2021_HBA1C_EU

# Load GWAS data
fname_stat <- "C:/Users/gact/hsa.0.0.1/download/Glycated_haemoglobin_HbA1c.imp.gz"
stat <- fread(fname_stat, data.table = FALSE)
head(stat)

# Modify columns according to required format


# Subset and rename columns according to required format
stat <- stat[, c("MarkerName", "#CHROM", "POS", "ALT", "REF", "Effect", "StdErr", "P-value")]
colnames(stat) <- c("marker", "chr", "pos", "ea", "nea", "b", "seb", "p")


# Update database
GAlist <- updateStatDB(GAlist = GAlist,
                       stat = stat,
                       source = "Glycated_haemoglobin_HbA1c.imp",
                       trait = "HbA1C",
                       type = "quantitative",
                       gender = "both",
                       ancestry = "EUR",
                       build = "GRCh37",
                       reference = "PMID:33462484",
                       n = 318779,
                       ncase = 0,
                       ncontrol = 0,
                       comments = "Just UK biobank",
                       writeStatDB = TRUE)

# Save updated database
saveRDS(GAlist, file="C:/Users/gact/hsa.0.0.1/GAlist_hsa.0.0.1.rds", compress = FALSE)