Convert geneids into GRanges

Convert geneids into GRanges

genes_to_granges(geneids, txdb, complement = TRUE, plot = TRUE, verbose = TRUE)

genefile_to_granges(file, txdb, complement = TRUE, plot = TRUE)

Arguments

geneids	Gene identifier vector
txdb	TxDb-class or EnsDb-class
complement	TRUE (default) or FALSE: add complementary strand?
plot	TRUE (default) or FALSE
verbose	TRUE (default) or FALSE
file	Gene identifier file (one per row)

Value

GRanges-class

See also

char_to_granges, bed_to_granges

Examples

# Entrez
#-------
    genefile <- system.file('extdata/SRF.entrez', package='multicrispr')
    geneids  <- as.character(read.table(genefile)[[1]])
    txdb     <- getFromNamespace('TxDb.Mmusculus.UCSC.mm10.knownGene',
                             'TxDb.Mmusculus.UCSC.mm10.knownGene')
    (gr <- genes_to_granges(geneids, txdb))
#>   66 genes were dropped because they have exons located on both strands
#>   of the same reference sequence or on more than one reference sequence,
#>   so cannot be represented by a single genomic range.
#>   Use 'single.strand.genes.only=FALSE' to get all the genes in a
#>   GRangesList object, or use suppressMessages() to suppress this message.
#> 		Convert 10 genes to 10 GRanges
#> 	Retain 20 unique target ranges after adding inverse strands
#> GRanges object with 20 ranges and 4 metadata columns:
#>               seqnames              ranges strand |     gene_id  targetname
#>                  <Rle>           <IRanges>  <Rle> | <character> <character>
#>       27392_r     chr1 105518422-105663677      - |       27392     27392_r
#>       27392_f     chr1 105518422-105663677      + |       27392     27392_f
#>   100043424_r     chr2 128178319-128502765      - |   100043424 100043424_r
#>   100043424_f     chr2 128178319-128502765      + |   100043424 100043424_f
#>      622434_f     chr3   62338344-62462221      + |      622434    622434_f
#>           ...      ...                 ...    ... .         ...         ...
#>       71918_f    chr14   25711642-25769039      + |       71918     71918_f
#>       13653_f    chr18   34859823-34864984      + |       13653     13653_f
#>       13653_r    chr18   34859823-34864984      - |       13653     13653_r
#>       52662_f    chr18   67933257-68268630      + |       52662     52662_f
#>       52662_r    chr18   67933257-68268630      - |       52662     52662_r
#>               targetstart targetend
#>                 <integer> <integer>
#>       27392_r   105518422 105663677
#>       27392_f   105518422 105663677
#>   100043424_r   128178319 128502765
#>   100043424_f   128178319 128502765
#>      622434_f    62338344  62462221
#>           ...         ...       ...
#>       71918_f    25711642  25769039
#>       13653_f    34859823  34864984
#>       13653_r    34859823  34864984
#>       52662_f    67933257  68268630
#>       52662_r    67933257  68268630
#>   -------
#>   seqinfo: 66 sequences (1 circular) from mm10 genome
    (gr <- genefile_to_granges(genefile, txdb))
#>   66 genes were dropped because they have exons located on both strands
#>   of the same reference sequence or on more than one reference sequence,
#>   so cannot be represented by a single genomic range.
#>   Use 'single.strand.genes.only=FALSE' to get all the genes in a
#>   GRangesList object, or use suppressMessages() to suppress this message.
#> 		Convert 10 genes to 10 GRanges
#> 	Retain 20 unique target ranges after adding inverse strands
#> GRanges object with 20 ranges and 4 metadata columns:
#>               seqnames              ranges strand |     gene_id  targetname
#>                  <Rle>           <IRanges>  <Rle> | <character> <character>
#>       27392_r     chr1 105518422-105663677      - |       27392     27392_r
#>       27392_f     chr1 105518422-105663677      + |       27392     27392_f
#>   100043424_r     chr2 128178319-128502765      - |   100043424 100043424_r
#>   100043424_f     chr2 128178319-128502765      + |   100043424 100043424_f
#>      622434_f     chr3   62338344-62462221      + |      622434    622434_f
#>           ...      ...                 ...    ... .         ...         ...
#>       71918_f    chr14   25711642-25769039      + |       71918     71918_f
#>       13653_f    chr18   34859823-34864984      + |       13653     13653_f
#>       13653_r    chr18   34859823-34864984      - |       13653     13653_r
#>       52662_f    chr18   67933257-68268630      + |       52662     52662_f
#>       52662_r    chr18   67933257-68268630      - |       52662     52662_r
#>               targetstart targetend
#>                 <integer> <integer>
#>       27392_r   105518422 105663677
#>       27392_f   105518422 105663677
#>   100043424_r   128178319 128502765
#>   100043424_f   128178319 128502765
#>      622434_f    62338344  62462221
#>           ...         ...       ...
#>       71918_f    25711642  25769039
#>       13653_f    34859823  34864984
#>       13653_r    34859823  34864984
#>       52662_f    67933257  68268630
#>       52662_r    67933257  68268630
#>   -------
#>   seqinfo: 66 sequences (1 circular) from mm10 genome

# Ensembl
#--------
    # txdb <- AnnotationHub::AnnotationHub()[["AH75036"]]
    # genefile <- system.file('extdata/SRF.ensembl', package='multicrispr')
    # geneids <- as.character(read.table(genefile)[[1]])
    # (gr <- genes_to_granges(geneids, txdb))
    # (gr <- genefile_to_granges(genefile, txdb))