Authors: Koki Tsuyuzaki [aut, cre], Manabu Ishii [aut], Itoshi Nikaido [aut]
Last modified: 2023-03-28 14:09:11.268674
Compiled: Tue Mar 28 14:11:34 2023

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 105 records
## # snapshotDate(): 2023-03-28
## # $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)            
##   ...        ...                                     
##   AH111548 | Data.table for PubMed Author Information
##   AH111549 | Data.table for PMC                      
##   AH111550 | Data.table for MeSH (Descriptor)        
##   AH111551 | Data.table for MeSH (Qualifier)         
##   AH111552 | Data.table for MeSH (SCR)

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

mcols(query(ah, "PubMed"))
## DataFrame with 105 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
## ...                         ...          ...         ...        ...         ...
## AH111548 Data.table for PubMe..         NCBI          NA         NA          NA
## AH111549     Data.table for PMC         NCBI          NA         NA          NA
## AH111550 Data.table for MeSH ..         NCBI          NA         NA          NA
## AH111551 Data.table for MeSH ..         NCBI          NA         NA          NA
## AH111552 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...
## ...                         ...                ...                    ...
## AH111548 Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH111549 Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH111550 Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH111551 Correspondence table..                  1 Koki Tsuyuzaki <k.t...
## AH111552 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,...
## ...                 ...           ...                            ...
## AH111548     2023-03-28   AHPubMedDbs     data.table,NCBI,PubMed,...
## AH111549     2023-03-28   AHPubMedDbs        data.table,NCBI,PMC,...
## AH111550     2023-03-28   AHPubMedDbs data.table,Descriptor,MeSH,...
## AH111551     2023-03-28   AHPubMedDbs       data.table,MeSH,NCBI,...
## AH111552     2023-03-28   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
## ...              ...                    ...                    ...         ...
## AH111548  data.table AHPubMedDbs/v005/aut.. https://github.com/r..         XML
## AH111549  data.table AHPubMedDbs/v005/pmc.. https://github.com/r..         XML
## AH111550  data.table AHPubMedDbs/v005/des.. https://github.com/r..         XML
## AH111551  data.table AHPubMedDbs/v005/qua.. https://github.com/r..         XML
## AH111552  data.table AHPubMedDbs/v005/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) (2023-01-05 r83566)
## Platform: x86_64-apple-darwin21.6.0 (64-bit)
## Running under: macOS Monterey 12.6.2
## 
## Matrix products: default
## BLAS:   /Users/ka36530/R-stuff/bin/R-devel/lib/libRblas.dylib 
## LAPACK: /Users/ka36530/R-stuff/bin/R-devel/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: system (macOS)
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
## [1] AnnotationHub_3.7.1 BiocFileCache_2.7.1 dbplyr_2.3.0       
## [4] BiocGenerics_0.45.0 BiocStyle_2.27.1   
## 
## loaded via a namespace (and not attached):
##  [1] KEGGREST_1.39.0               xfun_0.37                    
##  [3] bslib_0.4.2                   Biobase_2.59.0               
##  [5] bitops_1.0-7                  vctrs_0.5.2                  
##  [7] tools_4.3.0                   generics_0.1.3               
##  [9] stats4_4.3.0                  curl_5.0.0                   
## [11] tibble_3.1.8                  fansi_1.0.4                  
## [13] AnnotationDbi_1.61.0          RSQLite_2.2.20               
## [15] blob_1.2.3                    pkgconfig_2.0.3              
## [17] S4Vectors_0.37.3              assertthat_0.2.1             
## [19] GenomeInfoDbData_1.2.9        lifecycle_1.0.3              
## [21] compiler_4.3.0                Biostrings_2.67.0            
## [23] GenomeInfoDb_1.35.15          httpuv_1.6.9                 
## [25] htmltools_0.5.4               sass_0.4.5                   
## [27] RCurl_1.98-1.10               yaml_2.3.7                   
## [29] interactiveDisplayBase_1.37.0 pillar_1.8.1                 
## [31] later_1.3.0                   crayon_1.5.2                 
## [33] jquerylib_0.1.4               ellipsis_0.3.2               
## [35] cachem_1.0.6                  mime_0.12                    
## [37] tidyselect_1.2.0              digest_0.6.31                
## [39] purrr_1.0.1                   dplyr_1.1.0                  
## [41] bookdown_0.32                 BiocVersion_3.17.1           
## [43] fastmap_1.1.0                 cli_3.6.0                    
## [45] magrittr_2.0.3                utf8_1.2.3                   
## [47] withr_2.5.0                   filelock_1.0.2               
## [49] promises_1.2.0.1              rappdirs_0.3.3               
## [51] bit64_4.0.5                   rmarkdown_2.20               
## [53] XVector_0.39.0                httr_1.4.4                   
## [55] bit_4.0.5                     png_0.1-8                    
## [57] memoise_2.0.1                 shiny_1.7.4                  
## [59] evaluate_0.20                 knitr_1.42                   
## [61] IRanges_2.33.0                rlang_1.0.6                  
## [63] Rcpp_1.0.10                   xtable_1.8-4                 
## [65] glue_1.6.2                    DBI_1.1.3                    
## [67] BiocManager_1.30.19           jsonlite_1.8.4               
## [69] R6_2.5.1                      zlibbioc_1.45.0