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 54162
You 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/RtmpB9qXKP/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/RtmpB9qXKP/ieu-a-298.tsv.gz
Optional: 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 r84257)
## Platform: x86_64-apple-darwin20 (64-bit)
## Running under: macOS Monterey 12.6.4
##
## Matrix products: default
## BLAS: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRblas.0.dylib
## LAPACK: /Library/Frameworks/R.framework/Versions/4.3-x86_64/Resources/lib/libRlapack.dylib; LAPACK version 3.11.0
##
## locale:
## [1] C/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
##
## time zone: America/New_York
## tzcode source: internal
##
## 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_1.1.1
## [22] sass_0.4.6
## [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] S4Arrays_1.0.4
## [32] bit_4.0.5
## [33] curl_5.0.0
## [34] DelayedArray_0.26.2
## [35] xml2_1.3.4
## [36] BiocParallel_1.34.1
## [37] BiocGenerics_0.46.0
## [38] R.oo_1.25.0
## [39] grid_4.3.0
## [40] stats4_4.3.0
## [41] fansi_1.0.4
## [42] biomaRt_2.56.0
## [43] SummarizedExperiment_1.30.1
## [44] cli_3.6.1
## [45] rmarkdown_2.21
## [46] crayon_1.5.2
## [47] generics_0.1.3
## [48] BSgenome.Hsapiens.1000genomes.hs37d5_0.99.1
## [49] httr_1.4.6
## [50] rjson_0.2.21
## [51] DBI_1.1.3
## [52] cachem_1.0.8
## [53] stringr_1.5.0
## [54] zlibbioc_1.46.0
## [55] assertthat_0.2.1
## [56] parallel_4.3.0
## [57] AnnotationDbi_1.62.1
## [58] BiocManager_1.30.20
## [59] XVector_0.40.0
## [60] restfulr_0.0.15
## [61] matrixStats_0.63.0
## [62] vctrs_0.6.2
## [63] Matrix_1.5-4
## [64] jsonlite_1.8.4
## [65] bookdown_0.34
## [66] IRanges_2.34.0
## [67] hms_1.1.3
## [68] S4Vectors_0.38.1
## [69] bit64_4.0.5
## [70] GenomicFiles_1.36.0
## [71] GenomicFeatures_1.52.0
## [72] jquerylib_0.1.4
## [73] glue_1.6.2
## [74] codetools_0.2-19
## [75] stringi_1.7.12
## [76] GenomeInfoDb_1.36.0
## [77] BiocIO_1.10.0
## [78] GenomicRanges_1.52.0
## [79] tibble_3.2.1
## [80] pillar_1.9.0
## [81] SNPlocs.Hsapiens.dbSNP155.GRCh37_0.99.24
## [82] rappdirs_0.3.3
## [83] htmltools_0.5.5
## [84] GenomeInfoDbData_1.2.10
## [85] BSgenome_1.68.0
## [86] R6_2.5.1
## [87] dbplyr_2.3.2
## [88] evaluate_0.21
## [89] lattice_0.21-8
## [90] Biobase_2.60.0
## [91] R.methodsS3_1.8.2
## [92] png_0.1-8
## [93] Rsamtools_2.16.0
## [94] gargle_1.4.0
## [95] memoise_2.0.1
## [96] bslib_0.4.2
## [97] xfun_0.39
## [98] fs_1.6.2
## [99] MatrixGenerics_1.12.0
## [100] pkgconfig_2.0.3