getCloudData Download the pregenerated curated data sets from ReUseData cloud bucket

Usage

getCloudData(datahub, outdir = character())

Arguments

datahub: The dataHub object returned from dataSearch() with 1 data record available on ReUseData cloud bucket.
outdir: The output directory for the data (and concomitant annotation files) to be downloaded. It is recommended to use a new folder under a shared folder for a new to-be-downloaded data.

Value

Data and concomitant annotation files will be downloaded to the user-specified folder that is locally searchable with dataSearch().

Examples

outdir <- file.path(tempdir(), "gcpData")
dh <- dataSearch(c("ensembl", "GRCh38"))
dh <- dh[grep("http", dataPaths(dh))]

## download data from google bucket
getCloudData(dh[1], outdir = outdir)
#> Data is downloaded: 
#> /tmp/Rtmp7Lq2kA/gcpData/GRCh37_to_GRCh38.chain

## Update local data caching
dataUpdate(outdir)  ## no "cloud=TRUE" here, only showing local data cache
#> 
#> Updating data record...
#> GRCh37_to_GRCh38.chain added
#> dataHub with 145 records
#> cache path:  /home/qhu/.cache/R/ReUseData 
#> # dataUpdate() to update the local data cache
#> # dataSearch() to query a specific dataset
#> # Additional information can be retrieved using: 
#> # dataNames(), dataParams(), dataNotes(), dataPaths(), dataTag() or mcols()
#> 
#>             name                   
#>   BFC899  | GRCh37_to_GRCh38.chain 
#>   BFC1927 | GRCm38_to_NCBIM36.chain
#>   BFC2825 | GRCh37_to_GRCh38.chain 
#>   BFC2826 | outfile.txt            
#>   BFC2955 | outfile.txt            
#>   ...       ...                    
#>   BFC4627 | knownGene_mm39.sql     
#>   BFC4628 | knownGene_mm39.txt     
#>   BFC4629 | refGene_mm39.sql       
#>   BFC4630 | refGene_mm39.txt       
#>   BFC4631 | GRCh37_to_GRCh38.chain 
#>           Path                                                               
#>   BFC899  /tmp/RtmpMZs31N/gcpData/GRCh37_to_GRCh38.chain                     
#>   BFC1927 /tmp/Rtmp4dXPOh/gcpData/GRCm38_to_NCBIM36.chain                    
#>   BFC2825 /tmp/Rtmp4dXPOh/gcpData/GRCh37_to_GRCh38.chain                     
#>   BFC2826 /tmp/RtmpkdDQm8/working_dir/RtmpjAGUWK/test_SharedData/outfile.txt 
#>   BFC2955 /tmp/RtmpRwEJgD/working_dir/Rtmpilpixw/test_SharedData/outfile.txt 
#>   ...     ...                                                                
#>   BFC4627 https://storage.googleapis.com/reusedata/ucsc_database/knownGene...
#>   BFC4628 https://storage.googleapis.com/reusedata/ucsc_database/knownGene...
#>   BFC4629 https://storage.googleapis.com/reusedata/ucsc_database/refGene_m...
#>   BFC4630 https://storage.googleapis.com/reusedata/ucsc_database/refGene_m...
#>   BFC4631 /tmp/Rtmp7Lq2kA/gcpData/GRCh37_to_GRCh38.chain                     

## Now the data is available to use locally 
dataSearch(c("ensembl", "GRCh38"))
#> dataHub with 21 records
#> cache path:  /home/qhu/.cache/R/ReUseData 
#> # dataUpdate() to update the local data cache
#> # dataSearch() to query a specific dataset
#> # Additional information can be retrieved using: 
#> # dataNames(), dataParams(), dataNotes(), dataPaths(), dataTag() or mcols()
#> 
#>             name                  
#>   BFC899  | GRCh37_to_GRCh38.chain
#>   BFC2825 | GRCh37_to_GRCh38.chain
#>   BFC3341 | GRCh37_to_GRCh38.chain
#>   BFC3470 | GRCh37_to_GRCh38.chain
#>   BFC3599 | GRCh37_to_GRCh38.chain
#>   ...       ...                   
#>   BFC4517 | GRCh38_to_NCBI36.chain
#>   BFC4519 | NCBI34_to_GRCh38.chain
#>   BFC4521 | NCBI35_to_GRCh38.chain
#>   BFC4523 | NCBI36_to_GRCh38.chain
#>   BFC4631 | GRCh37_to_GRCh38.chain
#>           Path                                                               
#>   BFC899  /tmp/RtmpMZs31N/gcpData/GRCh37_to_GRCh38.chain                     
#>   BFC2825 /tmp/Rtmp4dXPOh/gcpData/GRCh37_to_GRCh38.chain                     
#>   BFC3341 /tmp/RtmpMF39J6/gcpData/GRCh37_to_GRCh38.chain                     
#>   BFC3470 /tmp/Rtmp8mVqnL/gcpData/GRCh37_to_GRCh38.chain                     
#>   BFC3599 /tmp/RtmpKEpli0/gcpData/GRCh37_to_GRCh38.chain                     
#>   ...     ...                                                                
#>   BFC4517 https://storage.googleapis.com/reusedata/ensembl_liftover/GRCh38...
#>   BFC4519 https://storage.googleapis.com/reusedata/ensembl_liftover/NCBI34...
#>   BFC4521 https://storage.googleapis.com/reusedata/ensembl_liftover/NCBI35...
#>   BFC4523 https://storage.googleapis.com/reusedata/ensembl_liftover/NCBI36...
#>   BFC4631 /tmp/Rtmp7Lq2kA/gcpData/GRCh37_to_GRCh38.chain