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/Rtmp6LvvmQ/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/Rtmp6LvvmQ/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 4.2.0 (2022-04-22)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.4 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.15-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.15-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_1.4.5 BiocStyle_2.24.0
##
## 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_1.4.3
## [8] googleAuthR_2.0.0
## [9] GenomeInfoDb_1.32.2
## [10] tools_4.2.0
## [11] bslib_0.3.1
## [12] utf8_1.2.2
## [13] R6_2.5.1
## [14] DBI_1.1.2
## [15] BiocGenerics_0.42.0
## [16] tidyselect_1.1.2
## [17] prettyunits_1.1.1
## [18] bit_4.0.4
## [19] curl_4.3.2
## [20] compiler_4.2.0
## [21] cli_3.3.0
## [22] Biobase_2.56.0
## [23] xml2_1.3.3
## [24] DelayedArray_0.22.0
## [25] rtracklayer_1.56.0
## [26] bookdown_0.26
## [27] sass_0.4.1
## [28] rappdirs_0.3.3
## [29] stringr_1.4.0
## [30] digest_0.6.29
## [31] Rsamtools_2.12.0
## [32] rmarkdown_2.14
## [33] R.utils_2.11.0
## [34] XVector_0.36.0
## [35] BSgenome.Hsapiens.1000genomes.hs37d5_0.99.1
## [36] pkgconfig_2.0.3
## [37] htmltools_0.5.2
## [38] MatrixGenerics_1.8.0
## [39] highr_0.9
## [40] dbplyr_2.2.0
## [41] fastmap_1.1.0
## [42] BSgenome_1.64.0
## [43] rlang_1.0.2
## [44] RSQLite_2.2.14
## [45] jquerylib_0.1.4
## [46] BiocIO_1.6.0
## [47] generics_0.1.2
## [48] jsonlite_1.8.0
## [49] BiocParallel_1.30.3
## [50] dplyr_1.0.9
## [51] R.oo_1.24.0
## [52] VariantAnnotation_1.42.1
## [53] RCurl_1.98-1.7
## [54] magrittr_2.0.3
## [55] GenomeInfoDbData_1.2.8
## [56] Matrix_1.4-1
## [57] Rcpp_1.0.8.3
## [58] S4Vectors_0.34.0
## [59] fansi_1.0.3
## [60] lifecycle_1.0.1
## [61] R.methodsS3_1.8.1
## [62] stringi_1.7.6
## [63] yaml_2.3.5
## [64] SummarizedExperiment_1.26.1
## [65] zlibbioc_1.42.0
## [66] BiocFileCache_2.4.0
## [67] grid_4.2.0
## [68] blob_1.2.3
## [69] parallel_4.2.0
## [70] crayon_1.5.1
## [71] lattice_0.20-45
## [72] Biostrings_2.64.0
## [73] GenomicFeatures_1.48.3
## [74] hms_1.1.1
## [75] KEGGREST_1.36.2
## [76] seqminer_8.4
## [77] knitr_1.39
## [78] pillar_1.7.0
## [79] GenomicRanges_1.48.0
## [80] rjson_0.2.21
## [81] codetools_0.2-18
## [82] biomaRt_2.52.0
## [83] stats4_4.2.0
## [84] XML_3.99-0.9
## [85] glue_1.6.2
## [86] evaluate_0.15
## [87] SNPlocs.Hsapiens.dbSNP144.GRCh37_0.99.20
## [88] data.table_1.14.2
## [89] BiocManager_1.30.18
## [90] png_0.1-7
## [91] vctrs_0.4.1
## [92] purrr_0.3.4
## [93] assertthat_0.2.1
## [94] cachem_1.0.6
## [95] xfun_0.31
## [96] restfulr_0.0.14
## [97] gargle_1.2.0
## [98] tibble_3.1.7
## [99] GenomicAlignments_1.32.0
## [100] AnnotationDbi_1.58.0
## [101] memoise_2.0.1
## [102] IRanges_2.30.0
## [103] ellipsis_0.3.2