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/RtmpF89jhr/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/RtmpF89jhr/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 4.3.0 RC (2023-04-13 r84269)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 22.04.2 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.17-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_1.8.0 BiocStyle_2.28.0
##
## loaded via a namespace (and not attached):
## [1] tidyselect_1.2.0
## [2] dplyr_1.1.2
## [3] blob_1.2.4
## [4] filelock_1.0.2
## [5] R.utils_2.12.2
## [6] Biostrings_2.68.0
## [7] bitops_1.0-7
## [8] fastmap_1.1.1
## [9] RCurl_1.98-1.12
## [10] BiocFileCache_2.8.0
## [11] VariantAnnotation_1.46.0
## [12] GenomicAlignments_1.36.0
## [13] XML_3.99-0.14
## [14] digest_0.6.31
## [15] lifecycle_1.0.3
## [16] KEGGREST_1.40.0
## [17] RSQLite_2.3.1
## [18] googleAuthR_2.0.1
## [19] magrittr_2.0.3
## [20] compiler_4.3.0
## [21] rlang_1.1.0
## [22] sass_0.4.5
## [23] progress_1.2.2
## [24] tools_4.3.0
## [25] utf8_1.2.3
## [26] yaml_2.3.7
## [27] data.table_1.14.8
## [28] rtracklayer_1.60.0
## [29] knitr_1.42
## [30] prettyunits_1.1.1
## [31] bit_4.0.5
## [32] curl_5.0.0
## [33] DelayedArray_0.26.0
## [34] xml2_1.3.3
## [35] BiocParallel_1.34.0
## [36] BiocGenerics_0.46.0
## [37] R.oo_1.25.0
## [38] grid_4.3.0
## [39] stats4_4.3.0
## [40] fansi_1.0.4
## [41] biomaRt_2.56.0
## [42] SummarizedExperiment_1.30.0
## [43] cli_3.6.1
## [44] rmarkdown_2.21
## [45] crayon_1.5.2
## [46] generics_0.1.3
## [47] BSgenome.Hsapiens.1000genomes.hs37d5_0.99.1
## [48] httr_1.4.5
## [49] rjson_0.2.21
## [50] DBI_1.1.3
## [51] cachem_1.0.7
## [52] stringr_1.5.0
## [53] zlibbioc_1.46.0
## [54] assertthat_0.2.1
## [55] parallel_4.3.0
## [56] AnnotationDbi_1.62.0
## [57] BiocManager_1.30.20
## [58] XVector_0.40.0
## [59] restfulr_0.0.15
## [60] matrixStats_0.63.0
## [61] vctrs_0.6.2
## [62] Matrix_1.5-4
## [63] jsonlite_1.8.4
## [64] bookdown_0.33
## [65] IRanges_2.34.0
## [66] hms_1.1.3
## [67] S4Vectors_0.38.0
## [68] bit64_4.0.5
## [69] GenomicFiles_1.36.0
## [70] GenomicFeatures_1.52.0
## [71] jquerylib_0.1.4
## [72] glue_1.6.2
## [73] codetools_0.2-19
## [74] stringi_1.7.12
## [75] GenomeInfoDb_1.36.0
## [76] BiocIO_1.10.0
## [77] GenomicRanges_1.52.0
## [78] tibble_3.2.1
## [79] pillar_1.9.0
## [80] SNPlocs.Hsapiens.dbSNP155.GRCh37_0.99.24
## [81] rappdirs_0.3.3
## [82] htmltools_0.5.5
## [83] GenomeInfoDbData_1.2.10
## [84] BSgenome_1.68.0
## [85] R6_2.5.1
## [86] dbplyr_2.3.2
## [87] evaluate_0.20
## [88] lattice_0.21-8
## [89] Biobase_2.60.0
## [90] R.methodsS3_1.8.2
## [91] png_0.1-8
## [92] Rsamtools_2.16.0
## [93] gargle_1.4.0
## [94] memoise_2.0.1
## [95] bslib_0.4.2
## [96] xfun_0.39
## [97] fs_1.6.2
## [98] MatrixGenerics_1.12.0
## [99] pkgconfig_2.0.3