Authors: Koki Tsuyuzaki [aut, cre], Manabu Ishii [aut], Itoshi Nikaido [aut]
Last modified: 2022-04-12 12:05:43
Compiled: Tue Apr 12 15:52:47 2022

1 Installation

To install this package, start R (>= 4.1.0) and enter:

if(!requireNamespace("BiocManager", quietly = TRUE))
    install.packages("BiocManager")
BiocManager::install("AHPubMedDbs")

2 Fetch PubMed tibble datasets from AnnotationHub

The AHPubMedDbs package provides the metadata for all PubMed datasets , which is preprocessed as tibble format and saved in AnnotationHub. First we load/update the AnnotationHub resource.

library(AnnotationHub)
ah <- AnnotationHub()

Next we list all PubMed entries from AnnotationHub.

query(ah, "PubMed")
## AnnotationHub with 63 records
## # snapshotDate(): 2022-04-12
## # $dataprovider: NCBI
## # $species: NA
## # $rdataclass: data.table, Tibble, SQLiteFile
## # additional mcols(): taxonomyid, genome, description,
## #   coordinate_1_based, maintainer, rdatadateadded, preparerclass, tags,
## #   rdatapath, sourceurl, sourcetype 
## # retrieve records with, e.g., 'object[["AH91771"]]' 
## 
##              title                                   
##   AH91771  | SQLite for PubMed ID                    
##   AH91772  | SQLite for PubMed Abstract              
##   AH91773  | SQLite for PubMed Author Information    
##   AH91774  | SQLite for PMC                          
##   AH91775  | SQLite for MeSH (Descriptor)            
##   ...        ...                                     
##   AH100394 | Data.table for PubMed Author Information
##   AH100395 | Data.table for PMC                      
##   AH100396 | Data.table for MeSH (Descriptor)        
##   AH100397 | Data.table for MeSH (Qualifier)         
##   AH100398 | Data.table for MeSH (SCR)

We can confirm the metadata in AnnotationHub in Bioconductor S3 bucket with mcols().

mcols(query(ah, "PubMed"))
## DataFrame with 63 rows and 15 columns
##                           title dataprovider     species taxonomyid      genome
##                     <character>  <character> <character>  <integer> <character>
## AH91771    SQLite for PubMed ID         NCBI          NA         NA          NA
## AH91772  SQLite for PubMed Ab..         NCBI          NA         NA          NA
## AH91773  SQLite for PubMed Au..         NCBI          NA         NA          NA
## AH91774          SQLite for PMC         NCBI          NA         NA          NA
## AH91775  SQLite for MeSH (Des..         NCBI          NA         NA          NA
## ...                         ...          ...         ...        ...         ...
## AH100394 Data.table for PubMe..         NCBI          NA         NA          NA
## AH100395     Data.table for PMC         NCBI          NA         NA          NA
## AH100396 Data.table for MeSH ..         NCBI          NA         NA          NA
## AH100397 Data.table for MeSH ..         NCBI          NA         NA          NA
## AH100398 Data.table for MeSH ..         NCBI          NA         NA          NA
##                     description coordinate_1_based             maintainer
##                     <character>          <integer>            <character>
## AH91771                    PMID                  1 Koki Tsuyuzaki <k.t...
## AH91772  Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH91773  Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH91774  Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH91775  Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## ...                         ...                ...                    ...
## AH100394 Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH100395 Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH100396 Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH100397 Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH100398 Correspondence table..                  1 Koki Tsuyuzaki <k.t...
##          rdatadateadded preparerclass                           tags
##             <character>   <character>                         <AsIs>
## AH91771      2021-04-19   AHPubMedDbs         NCBI,PubMed,SQLite,...
## AH91772      2021-04-19   AHPubMedDbs         NCBI,PubMed,SQLite,...
## AH91773      2021-04-19   AHPubMedDbs         NCBI,PubMed,SQLite,...
## AH91774      2021-04-19   AHPubMedDbs            NCBI,PMC,SQLite,...
## AH91775      2021-04-19   AHPubMedDbs       Descriptor,MeSH,NCBI,...
## ...                 ...           ...                            ...
## AH100394     2022-04-12   AHPubMedDbs     data.table,NCBI,PubMed,...
## AH100395     2022-04-12   AHPubMedDbs        data.table,NCBI,PMC,...
## AH100396     2022-04-12   AHPubMedDbs data.table,Descriptor,MeSH,...
## AH100397     2022-04-12   AHPubMedDbs       data.table,MeSH,NCBI,...
## AH100398     2022-04-12   AHPubMedDbs       data.table,MeSH,NCBI,...
##           rdataclass              rdatapath              sourceurl  sourcetype
##          <character>            <character>            <character> <character>
## AH91771   SQLiteFile AHPubMedDbs/v001/pub.. https://github.com/r..         XML
## AH91772   SQLiteFile AHPubMedDbs/v001/abs.. https://github.com/r..         XML
## AH91773   SQLiteFile AHPubMedDbs/v001/aut.. https://github.com/r..         XML
## AH91774   SQLiteFile AHPubMedDbs/v001/pmc.. https://github.com/r..         XML
## AH91775   SQLiteFile AHPubMedDbs/v001/des.. https://github.com/r..         XML
## ...              ...                    ...                    ...         ...
## AH100394  data.table AHPubMedDbs/v003/aut.. https://github.com/r..         XML
## AH100395  data.table AHPubMedDbs/v003/pmc.. https://github.com/r..         XML
## AH100396  data.table AHPubMedDbs/v003/des.. https://github.com/r..         XML
## AH100397  data.table AHPubMedDbs/v003/qua.. https://github.com/r..         XML
## AH100398  data.table AHPubMedDbs/v003/scr.. https://github.com/r..         XML

We can retrieve only the PubMedDb tibble files as follows.

qr <- query(ah, c("PubMedDb"))
# pubmed_tibble <- qr[[1]]

Session information

## R Under development (unstable) (2022-03-10 r81873)
## Platform: x86_64-apple-darwin19.6.0 (64-bit)
## Running under: macOS Catalina 10.15.7
## 
## Matrix products: default
## BLAS:   /Users/ka36530_ca/R-stuff/bin/R-devel/lib/libRblas.dylib
## LAPACK: /Users/ka36530_ca/R-stuff/bin/R-devel/lib/libRlapack.dylib
## 
## locale:
## [1] C/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
## [1] AnnotationHub_3.3.9 BiocFileCache_2.3.4 dbplyr_2.1.1       
## [4] BiocGenerics_0.41.2 BiocStyle_2.23.1   
## 
## loaded via a namespace (and not attached):
##  [1] Rcpp_1.0.8.3                  png_0.1-7                    
##  [3] Biostrings_2.63.3             assertthat_0.2.1             
##  [5] digest_0.6.29                 utf8_1.2.2                   
##  [7] mime_0.12                     R6_2.5.1                     
##  [9] GenomeInfoDb_1.31.7           stats4_4.2.0                 
## [11] RSQLite_2.2.12                evaluate_0.15                
## [13] httr_1.4.2                    pillar_1.7.0                 
## [15] zlibbioc_1.41.0               rlang_1.0.2                  
## [17] curl_4.3.2                    jquerylib_0.1.4              
## [19] blob_1.2.2                    S4Vectors_0.33.16            
## [21] rmarkdown_2.13                stringr_1.4.0                
## [23] RCurl_1.98-1.6                bit_4.0.4                    
## [25] shiny_1.7.1                   compiler_4.2.0               
## [27] httpuv_1.6.5                  xfun_0.30                    
## [29] pkgconfig_2.0.3               htmltools_0.5.2              
## [31] tidyselect_1.1.2              KEGGREST_1.35.0              
## [33] GenomeInfoDbData_1.2.7        tibble_3.1.6                 
## [35] interactiveDisplayBase_1.33.0 bookdown_0.25                
## [37] IRanges_2.29.1                fansi_1.0.3                  
## [39] crayon_1.5.1                  dplyr_1.0.8                  
## [41] later_1.3.0                   bitops_1.0-7                 
## [43] rappdirs_0.3.3                jsonlite_1.8.0               
## [45] xtable_1.8-4                  lifecycle_1.0.1              
## [47] DBI_1.1.2                     magrittr_2.0.3               
## [49] cli_3.2.0                     stringi_1.7.6                
## [51] cachem_1.0.6                  XVector_0.35.0               
## [53] promises_1.2.0.1              bslib_0.3.1                  
## [55] ellipsis_0.3.2                filelock_1.0.2               
## [57] generics_0.1.2                vctrs_0.4.0                  
## [59] tools_4.2.0                   bit64_4.0.5                  
## [61] Biobase_2.55.1                glue_1.6.2                   
## [63] purrr_0.3.4                   BiocVersion_3.15.2           
## [65] fastmap_1.1.0                 yaml_2.3.5                   
## [67] AnnotationDbi_1.57.1          BiocManager_1.30.16          
## [69] memoise_2.0.1                 knitr_1.38                   
## [71] sass_0.4.1