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/RtmpXyoUgm/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/RtmpXyoUgm/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 4.2.1 (2022-06-23)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.5 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.16-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.16-bioc/R/lib/libRlapack.so
##
## 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
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] MungeSumstats_1.6.0 BiocStyle_2.26.0
##
## loaded via a namespace (and not attached):
## [1] fs_1.5.2
## [2] bitops_1.0-7
## [3] matrixStats_0.62.0
## [4] bit64_4.0.5
## [5] filelock_1.0.2
## [6] progress_1.2.2
## [7] httr_1.4.4
## [8] GenomeInfoDb_1.34.0
## [9] googleAuthR_2.0.0
## [10] GenomicFiles_1.34.0
## [11] tools_4.2.1
## [12] bslib_0.4.0
## [13] utf8_1.2.2
## [14] R6_2.5.1
## [15] DBI_1.1.3
## [16] BiocGenerics_0.44.0
## [17] tidyselect_1.2.0
## [18] prettyunits_1.1.1
## [19] bit_4.0.4
## [20] curl_4.3.3
## [21] compiler_4.2.1
## [22] cli_3.4.1
## [23] Biobase_2.58.0
## [24] xml2_1.3.3
## [25] DelayedArray_0.24.0
## [26] rtracklayer_1.58.0
## [27] bookdown_0.29
## [28] sass_0.4.2
## [29] rappdirs_0.3.3
## [30] stringr_1.4.1
## [31] digest_0.6.30
## [32] Rsamtools_2.14.0
## [33] rmarkdown_2.17
## [34] R.utils_2.12.1
## [35] XVector_0.38.0
## [36] BSgenome.Hsapiens.1000genomes.hs37d5_0.99.1
## [37] pkgconfig_2.0.3
## [38] htmltools_0.5.3
## [39] MatrixGenerics_1.10.0
## [40] highr_0.9
## [41] dbplyr_2.2.1
## [42] fastmap_1.1.0
## [43] BSgenome_1.66.0
## [44] rlang_1.0.6
## [45] RSQLite_2.2.18
## [46] jquerylib_0.1.4
## [47] BiocIO_1.8.0
## [48] generics_0.1.3
## [49] jsonlite_1.8.3
## [50] BiocParallel_1.32.0
## [51] dplyr_1.0.10
## [52] R.oo_1.25.0
## [53] VariantAnnotation_1.44.0
## [54] RCurl_1.98-1.9
## [55] magrittr_2.0.3
## [56] GenomeInfoDbData_1.2.9
## [57] Matrix_1.5-1
## [58] Rcpp_1.0.9
## [59] S4Vectors_0.36.0
## [60] fansi_1.0.3
## [61] lifecycle_1.0.3
## [62] R.methodsS3_1.8.2
## [63] stringi_1.7.8
## [64] yaml_2.3.6
## [65] SummarizedExperiment_1.28.0
## [66] zlibbioc_1.44.0
## [67] BiocFileCache_2.6.0
## [68] grid_4.2.1
## [69] blob_1.2.3
## [70] parallel_4.2.1
## [71] crayon_1.5.2
## [72] lattice_0.20-45
## [73] Biostrings_2.66.0
## [74] GenomicFeatures_1.50.0
## [75] hms_1.1.2
## [76] KEGGREST_1.38.0
## [77] knitr_1.40
## [78] pillar_1.8.1
## [79] GenomicRanges_1.50.0
## [80] rjson_0.2.21
## [81] SNPlocs.Hsapiens.dbSNP155.GRCh37_0.99.22
## [82] codetools_0.2-18
## [83] biomaRt_2.54.0
## [84] stats4_4.2.1
## [85] XML_3.99-0.12
## [86] glue_1.6.2
## [87] evaluate_0.17
## [88] data.table_1.14.4
## [89] BiocManager_1.30.19
## [90] png_0.1-7
## [91] vctrs_0.5.0
## [92] assertthat_0.2.1
## [93] cachem_1.0.6
## [94] xfun_0.34
## [95] restfulr_0.0.15
## [96] gargle_1.2.1
## [97] tibble_3.1.8
## [98] GenomicAlignments_1.34.0
## [99] AnnotationDbi_1.60.0
## [100] memoise_2.0.1
## [101] IRanges_2.32.0
## [102] ellipsis_0.3.2