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/RtmpZU6bK9/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/RtmpZU6bK9/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 version 4.4.0 beta (2024-04-15 r86425)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 22.04.4 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.19-bioc/R/lib/libRblas.so
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.10.0
##
## 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_1.11.10 BiocStyle_2.31.0
##
## 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_2.71.6
## [6] bitops_1.0-7
## [7] fastmap_1.1.1
## [8] RCurl_1.98-1.14
## [9] VariantAnnotation_1.49.7
## [10] GenomicAlignments_1.39.5
## [11] XML_3.99-0.16.1
## [12] digest_0.6.35
## [13] lifecycle_1.0.4
## [14] KEGGREST_1.43.0
## [15] RSQLite_2.3.6
## [16] magrittr_2.0.3
## [17] googleAuthR_2.0.1
## [18] compiler_4.4.0
## [19] rlang_1.1.3
## [20] sass_0.4.9
## [21] tools_4.4.0
## [22] utf8_1.2.4
## [23] yaml_2.3.8
## [24] data.table_1.15.4
## [25] rtracklayer_1.63.2
## [26] knitr_1.46
## [27] S4Arrays_1.3.7
## [28] bit_4.0.5
## [29] curl_5.2.1
## [30] DelayedArray_0.29.9
## [31] abind_1.4-5
## [32] BiocParallel_1.37.1
## [33] BiocGenerics_0.49.1
## [34] R.oo_1.26.0
## [35] grid_4.4.0
## [36] stats4_4.4.0
## [37] fansi_1.0.6
## [38] SummarizedExperiment_1.33.3
## [39] cli_3.6.2
## [40] rmarkdown_2.26
## [41] crayon_1.5.2
## [42] generics_0.1.3
## [43] BSgenome.Hsapiens.1000genomes.hs37d5_0.99.1
## [44] httr_1.4.7
## [45] rjson_0.2.21
## [46] DBI_1.2.2
## [47] cachem_1.0.8
## [48] stringr_1.5.1
## [49] zlibbioc_1.49.3
## [50] assertthat_0.2.1
## [51] parallel_4.4.0
## [52] AnnotationDbi_1.65.2
## [53] BiocManager_1.30.22
## [54] XVector_0.43.1
## [55] restfulr_0.0.15
## [56] matrixStats_1.3.0
## [57] vctrs_0.6.5
## [58] Matrix_1.7-0
## [59] jsonlite_1.8.8
## [60] bookdown_0.39
## [61] IRanges_2.37.1
## [62] S4Vectors_0.41.7
## [63] bit64_4.0.5
## [64] GenomicFiles_1.39.0
## [65] GenomicFeatures_1.55.4
## [66] jquerylib_0.1.4
## [67] glue_1.7.0
## [68] codetools_0.2-20
## [69] stringi_1.8.3
## [70] GenomeInfoDb_1.39.14
## [71] BiocIO_1.13.0
## [72] GenomicRanges_1.55.4
## [73] UCSC.utils_0.99.7
## [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_1.2.12
## [79] BSgenome_1.71.4
## [80] R6_2.5.1
## [81] evaluate_0.23
## [82] lattice_0.22-6
## [83] Biobase_2.63.1
## [84] R.methodsS3_1.8.2
## [85] png_0.1-8
## [86] Rsamtools_2.19.4
## [87] gargle_1.5.2
## [88] memoise_2.0.1
## [89] bslib_0.7.0
## [90] SparseArray_1.3.5
## [91] xfun_0.43
## [92] fs_1.6.3
## [93] MatrixGenerics_1.15.1
## [94] pkgconfig_2.0.3