SRAdb-package: Query NCBI SRA metadata within R or from a local SQLite...

In zhujack/SRAdb: A compilation of metadata from NCBI SRA and tools

Query NCBI SRA metadata within R or from a local SQLite database

Description

The Sequence Read Archive (SRA) represents largest public repository of sequencing data from the next generation of sequencing platforms including Roche 454 GS System, Illumina Genome Analyzer, Applied Biosystems SOLiD System, Helicos Heliscope, and others. However, finding data of interest can be challenging using current tools. SRAdb is an attempt to make access to the metadata associated with submission, study, sample, experiment and run much more feasible. This is accomplished by parsing all the NCBI SRA metadata into a SQLite database that can be stored and queried locally. SRAdb is simply a thin wrapper around the SQLite database along with associated tools and documentation. Fulltext search in the package make querying metadata very flexible and powerful. SRA data files (sra or sra-lite) can be downloaded for doing alignment locally. Available BAM files in local or in the Meltzerlab sraDB can be loaded into IGV for visualization easily. The SQLite database is updated regularly as new data is added to SRA and can be downloaded at will for the most up-to-date metadata.

Details

Package:	SRAdb
Type:	Package
Date of creation:	2012-02-13
License:	What license is it under?
LazyLoad:	yes

Author(s)

Jack Zhu and Sean Davis

Maintainer: Jack Zhu <[e-mail]>

References

https://s3.amazonaws.com/starbuck1/sradb/SRAmetadb.sqlite.gz https://gbnci-abcc.ncifcrf.gov/backup/SRAmetadb.sqlite.gz

Examples

## Using the SRAmetadb demo database
  
    library(SRAdb)
	sra_dbname <- file.path(system.file('extdata', package='SRAdb'), 'SRAmetadb_demo.sqlite')	
    sra_con <- dbConnect(dbDriver("SQLite"), sra_dbname)
  
    ## Get column descriptions
    a <- colDescriptions(sra_con=sra_con)[1:5,]
  
    ## Convert SRA experiment accessions to other types
    b <- sraConvert( in_acc=c(" SRR000137", "SRR000138 "), out_type=c('sample'), sra_con=sra_con )
  
    ## Fulltext search SRA meta data using SQLite fts3 module
    rs <- getSRA (search_terms ='breas* NEAR/2 can*', out_types=c('run','study'), sra_con=sra_con)
    rs <- getSRA (search_terms ='breast', out_types=c('run','study'), sra_con=sra_con)
    rs <- getSRA (search_terms ='"breas* can*"', out_types=c('study'), sra_con=sra_con) 
    rs <- getSRA (search_terms ='MCF7 OR "MCF-7"', out_types=c('sample'), sra_con=sra_con) 
    rs <- getSRA (search_terms ='study_title: brea* can*', out_types=c('run','study'), sra_con=sra_con)  
    rs <- getSRA (search_terms ='study_title: brea* can*', out_types=c('run','study'), sra_con=sra_con, acc_only=TRUE) 

    ## List fastq file ftp or fasp addresses associated with "SRX000122"
    listSRAfile (in_acc = c("SRX000122"), sra_con = sra_con, fileType = 'sra')
    listSRAfile (in_acc = c("SRX000122"), sra_con = sra_con, fileType = 'sra', srcType='fasp')
  
    ## Get file size and date from NCBI ftp site for available fastq files associated with "SRS012041","SRS000290" 
    ## Not run:   
    getSRAinfo (in_acc=c("SRS012041","SRS000290"), sra_con=sra_con, sraType='sra')
    
## End(Not run)

    ## Download sra files from NCBI SRA using ftp protocol:
    ## Not run: 
    getSRAfile( in_acc = c("SRR000648","SRR000657"), sra_con = sra_con, destDir = getwd(), fileType = 'sra' )
    ## Download fastq files from EBI using ftp protocol:
    getSRAfile( in_acc, sra_con, destDir = getwd(), fileType = 'fastq', srcType = 'ftp', makeDirectory = FALSE, method = 'curl', ascpCMD = NULL )
    
## End(Not run)
    
    ## Download fastq files from EBI  ftp siteusing fasp protocol:
    ## Not run: 
    ascpCMD <-  'ascp -QT -l 300m -i /usr/local/aspera/connect/etc/asperaweb_id_dsa.putty'
    getSRAfile( in_acc, sra_con,  fileType = 'fastq', srcType = 'fasp',  ascpCMD = ascpCMD )
## End(Not run)
   
    ## Start IGV from R if no IGV running
    ## Not run: startIGV(memory='mm')

    ## load BAM files to IGV
    ## Not run: 
    exampleBams = file.path(system.file('extdata',package='SRAdb'), dir(system.file('extdata',package='SRAdb'),pattern='bam$'))
    sock <- IGVsocket()
    IGVload(sock,exampleBams)
    
## End(Not run)
    ## Change the IGV genome
    ## Not run: 
    IGVgenome(sock,genome='hg18')
    
## End(Not run)
    ## Go to a specified region in IGV
    ## Not run: 
    IGVgoto(sock,'chr1:1-10000')
    IGVgoto(sock,'TP53')
    
## End(Not run)

    ## Make a snapshot of the current IGV window
    ## Not run:   
    IGVsnapshot(sock)
    dir()
    
## End(Not run)
  
    ## create a graphNEL object from SRA accessions, which are full text search results of terms 'primary thyroid cell line'
    g <- sraGraph('MCF7 OR "MCF-7"', sra_con)
  
    ## Not run: 
    library(Rgraphviz)
    attrs <- getDefaultAttrs(list(node=list(fillcolor='lightblue', shape='ellipse')))
    plot(g, attrs=attrs)
    
## End(Not run)
    dbDisconnect(sra_con) 

## The actual SRAmetadb sqlite database can be downloaded using function: getSRAdbFile. Warning: the actual SRAmetadb sqlite database is pretty large (> 35GB as of May, 2018) after uncompression. So, downloading and uncompressing of the actual SRAmetadb sqlite could take quite a few minutes depending on your network bandwidth.  Direct links for downloading the SRAmetadb sqlite database:  https://s3.amazonaws.com/starbuck1/sradb/SRAmetadb.sqlite.gz https://gbnci-abcc.ncifcrf.gov/backup/SRAmetadb.sqlite.gz

zhujack/SRAdb documentation built on Dec. 6, 2024, 2:15 a.m.