library(MungeSumstats)MungeSumstats now offers high throughput query and import functionality to data from the MRC IEU Open GWAS Project.
#### Search for datasets ####
metagwas <- MungeSumstats::find_sumstats(traits = c("parkinson","alzheimer"),
min_sample_size = 1000)
head(metagwas,3)
ids <- (dplyr::arrange(metagwas, nsnp))$id ## id trait group_name year author
## 1 ieu-a-298 Alzheimer's disease public 2013 Lambert
## 2 ieu-b-2 Alzheimer's disease public 2019 Kunkle BW
## 3 ieu-a-297 Alzheimer's disease public 2013 Lambert
## consortium
## 1 IGAP
## 2 Alzheimer Disease Genetics Consortium (ADGC), European Alzheimer's Disease Initiative (EADI), Cohorts for Heart and Aging Research in Genomic Epidemiology Consortium (CHARGE), Genetic and Environmental Risk in AD/Defining Genetic, Polygenic and Environmental Risk for Alzheimer's Disease Consortium (GERAD/PERADES),
## 3 IGAP
## sex population unit nsnp sample_size build
## 1 Males and Females European log odds 11633 74046 HG19/GRCh37
## 2 Males and Females European NA 10528610 63926 HG19/GRCh37
## 3 Males and Females European log odds 7055882 54162 HG19/GRCh37
## category subcategory ontology mr priority pmid sd
## 1 Disease Psychiatric / neurological NA 1 1 24162737 NA
## 2 Binary Psychiatric / neurological NA 1 0 30820047 NA
## 3 Disease Psychiatric / neurological NA 1 2 24162737 NA
## note ncase
## 1 Exposure only; Effect allele frequencies are missing; forward(+) strand 25580
## 2 NA 21982
## 3 Effect allele frequencies are missing; forward(+) strand 17008
## ncontrol N
## 1 48466 74046
## 2 41944 63926
## 3 37154 54162You can supply import_sumstats() with a list of as many OpenGWAS IDs as you
want, but we’ll just give one to save time.
datasets <- MungeSumstats::import_sumstats(ids = "ieu-a-298",
ref_genome = "GRCH37")By default, import_sumstats results a named list where the names are the Open
GWAS dataset IDs and the items are the respective paths to the formatted summary
statistics.
print(datasets)## $`ieu-a-298`
## [1] "/tmp/RtmpJM70ZV/ieu-a-298.tsv.gz"You can easily turn this into a data.frame as well.
results_df <- data.frame(id=names(datasets),
path=unlist(datasets))
print(results_df)## id path
## ieu-a-298 ieu-a-298 /tmp/RtmpJM70ZV/ieu-a-298.tsv.gzOptional: Speed up with multi-threaded download via axel.
datasets <- MungeSumstats::import_sumstats(ids = ids,
vcf_download = TRUE,
download_method = "axel",
nThread = max(2,future::availableCores()-2))See the Getting started vignette for more information on how to use MungeSumstats and its functionality.
utils::sessionInfo()## R Under development (unstable) (2024-10-21 r87258)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 24.04.1 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.21-bioc/R/lib/libRblas.so
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.12.0
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_GB LC_COLLATE=C
## [5] LC_MONETARY=en_US.UTF-8 LC_MESSAGES=en_US.UTF-8
## [7] LC_PAPER=en_US.UTF-8 LC_NAME=C
## [9] LC_ADDRESS=C LC_TELEPHONE=C
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C
##
## time zone: America/New_York
## tzcode source: system (glibc)
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] MungeSumstats_1.15.2 BiocStyle_2.35.0
##
## loaded via a namespace (and not attached):
## [1] tidyselect_1.2.1
## [2] dplyr_1.1.4
## [3] blob_1.2.4
## [4] R.utils_2.12.3
## [5] Biostrings_2.75.0
## [6] bitops_1.0-9
## [7] fastmap_1.2.0
## [8] RCurl_1.98-1.16
## [9] VariantAnnotation_1.53.0
## [10] GenomicAlignments_1.43.0
## [11] XML_3.99-0.17
## [12] digest_0.6.37
## [13] lifecycle_1.0.4
## [14] KEGGREST_1.47.0
## [15] RSQLite_2.3.7
## [16] magrittr_2.0.3
## [17] googleAuthR_2.0.2
## [18] compiler_4.5.0
## [19] rlang_1.1.4
## [20] sass_0.4.9
## [21] tools_4.5.0
## [22] utf8_1.2.4
## [23] yaml_2.3.10
## [24] data.table_1.16.2
## [25] rtracklayer_1.67.0
## [26] knitr_1.48
## [27] S4Arrays_1.7.1
## [28] bit_4.5.0
## [29] curl_5.2.3
## [30] DelayedArray_0.33.1
## [31] abind_1.4-8
## [32] BiocParallel_1.41.0
## [33] BiocGenerics_0.53.0
## [34] R.oo_1.26.0
## [35] grid_4.5.0
## [36] stats4_4.5.0
## [37] fansi_1.0.6
## [38] SummarizedExperiment_1.37.0
## [39] cli_3.6.3
## [40] rmarkdown_2.28
## [41] crayon_1.5.3
## [42] generics_0.1.3
## [43] BSgenome.Hsapiens.1000genomes.hs37d5_0.99.1
## [44] httr_1.4.7
## [45] rjson_0.2.23
## [46] DBI_1.2.3
## [47] cachem_1.1.0
## [48] stringr_1.5.1
## [49] zlibbioc_1.53.0
## [50] assertthat_0.2.1
## [51] parallel_4.5.0
## [52] AnnotationDbi_1.69.0
## [53] BiocManager_1.30.25
## [54] XVector_0.47.0
## [55] restfulr_0.0.15
## [56] matrixStats_1.4.1
## [57] vctrs_0.6.5
## [58] Matrix_1.7-1
## [59] jsonlite_1.8.9
## [60] bookdown_0.41
## [61] IRanges_2.41.0
## [62] S4Vectors_0.45.0
## [63] bit64_4.5.2
## [64] GenomicFiles_1.43.0
## [65] GenomicFeatures_1.59.0
## [66] jquerylib_0.1.4
## [67] glue_1.8.0
## [68] codetools_0.2-20
## [69] stringi_1.8.4
## [70] GenomeInfoDb_1.43.0
## [71] BiocIO_1.17.0
## [72] GenomicRanges_1.59.0
## [73] UCSC.utils_1.3.0
## [74] tibble_3.2.1
## [75] pillar_1.9.0
## [76] SNPlocs.Hsapiens.dbSNP155.GRCh37_0.99.24
## [77] htmltools_0.5.8.1
## [78] GenomeInfoDbData_1.2.13
## [79] BSgenome_1.75.0
## [80] R6_2.5.1
## [81] evaluate_1.0.1
## [82] lattice_0.22-6
## [83] Biobase_2.67.0
## [84] R.methodsS3_1.8.2
## [85] png_0.1-8
## [86] Rsamtools_2.23.0
## [87] gargle_1.5.2
## [88] memoise_2.0.1
## [89] bslib_0.8.0
## [90] SparseArray_1.7.0
## [91] xfun_0.48
## [92] fs_1.6.5
## [93] MatrixGenerics_1.19.0
## [94] pkgconfig_2.0.3