Genomes
In misha: Toolkit for Analysis of Genomic Data

knitr::opts_chunk$set(
    collapse = TRUE,
    comment = "#>"
)

library(misha)

Create a `misha` database from UCSC

The easiest way to create a misha database is to use the gdb.create_genome function:

gdb.create_genome("hg19") # creates a database for the hg19 genome
gdb.create_genome("hg38") # creates a database for the hg38 genome
gdb.create_genome("mm10") # creates a database for the mm10 genome
gdb.create_genome("mm9") # creates a database for the mm9 genome
gdb.create_genome("mm39") # creates a database for the mm39 genome

However, if you need to create a database for a genome that is not supported by gdb.create_genome, or if you want to make sure that the database is created from the latest version of the genome in ucsc, you can create it manually using the commands below.

hg19

In order to create a misha database for hg19 genome, run the following commands (assuming "hg19" is your new data base path):

ftp <- "ftp://hgdownload.soe.ucsc.edu/goldenPath/hg19"
gdb.create(
    "hg19",
    paste(ftp, "chromosomes", paste0("chr", c(1:22, "X", "Y", "M"), ".fa.gz"), sep = "/"),
    paste(ftp, "database/knownGene.txt.gz", sep = "/"),
    paste(ftp, "database/kgXref.txt.gz", sep = "/"),
    c(
        "kgID", "mRNA", "spID", "spDisplayID", "geneSymbol",
        "refseq", "protAcc", "description", "rfamAcc",
        "tRnaName"
    )
)
gdb.init("hg19")

hg38

In order to create a misha database for hg38 genome, run the following commands (assuming "hg38" is your new data base path):

ftp <- "ftp://hgdownload.soe.ucsc.edu/goldenPath/hg38"
gdb.create(
    "hg38",
    paste(ftp, "chromosomes", paste0("chr", c(1:22, "X", "Y", "M"), ".fa.gz"), sep = "/"),
    paste(ftp, "database/knownGene.txt.gz", sep = "/"),
    paste(ftp, "database/kgXref.txt.gz", sep = "/"),
    c(
        "kgID", "mRNA", "spID", "spDisplayID", "geneSymbol",
        "refseq", "protAcc", "description", "rfamAcc",
        "tRnaName"
    )
)
gdb.init("hg38")

mm9

In order to create a misha database for mm9 genome, run the following commands (assuming "mm9" is your new data base path):

ftp <- "ftp://hgdownload.soe.ucsc.edu/goldenPath/mm9"
gdb.create(
    "mm9",
    paste(ftp, "chromosomes", paste0("chr", c(1:19, "X", "Y", "M"), ".fa.gz"), sep = "/"),
    paste(ftp, "database/knownGene.txt.gz", sep = "/"),
    paste(ftp, "database/kgXref.txt.gz", sep = "/"),
    c(
        "kgID", "mRNA", "spID", "spDisplayID", "geneSymbol",
        "refseq", "protAcc", "description"
    )
)
gdb.init("mm9")

mm10

In order to create a misha database for mm10 genome, run the following commands (assuming "mm10" is your new data base path):

ftp <- "ftp://hgdownload.soe.ucsc.edu/goldenPath/mm10"
gdb.create(
    "mm10",
    paste(ftp, "chromosomes", paste0("chr", c(1:19, "X", "Y", "M"), ".fa.gz"), sep = "/"),
    paste(ftp, "database/knownGene.txt.gz", sep = "/"),
    paste(ftp, "database/kgXref.txt.gz", sep = "/"),
    c(
        "kgID", "mRNA", "spID", "spDisplayID", "geneSymbol",
        "refseq", "protAcc", "description", "rfamAcc",
        "tRnaName"
    )
)
gdb.init("mm10")

mm39

In order to create a misha database for mm39 genome, run the following commands (assuming "mm39" is your new data base path):

ftp <- "ftp://hgdownload.soe.ucsc.edu/goldenPath/mm39"
gdb.create(
    "mm39",
    paste(ftp, "chromosomes", paste0("chr", c(1:19, "X", "Y", "M"), ".fa.gz"), sep = "/"),
    paste(ftp, "database/knownGene.txt.gz", sep = "/"),
    paste(ftp, "database/kgXref.txt.gz", sep = "/"),
    c(
        "kgID", "mRNA", "spID", "spDisplayID", "geneSymbol",
        "refseq", "protAcc", "description", "rfamAcc",
        "tRnaName"
    )
)
gdb.init("mm39")