Skip to contents

Function to retrieve the required information from the downloaded gnomAD file

Edit_gnomAD_file.Rd

Function to retrieve the required information from the downloaded gnomAD file. Before applying this function, be sure to check the contents of the file yourself and delete all but the missense mutations.

Usage

Edit_gnomAD_file(input_file_name, export_file_name)

Arguments

input_file_name

The name of downloaded gnomAD file

export_file_name

Output file name

Details

Value

References

Author

Yuya Hatano

Note

See also

Examples

Hgmd_divide("./source/TARDBP.csv")
Edit_gnomAD_file("./source/gnomAD_v3.1.2_ENST00000240185_2023_02_14_13_23_48.csv", "./source/TARDBP_gnomAD.csv")
Edit_variant_data("../CADD_REVEL/AlphScore_final.tsv", "./source/TARDBP.csv", "./source/TARDBP_gnomAD.csv", "Q13148", "TARDBP", "./source/TARDBPvariantdata.csv")
Edit_polyphen_data("../dbNSFP/dbNSFP4.3a/dbNSFP4.3a_variant.chr1","./source/TARDBPvariantdata.csv", "TARDBP_alph.csv",  "Q13148",  11012654, 11025492 ,"./source/TARDBPvariantdatapol.csv", "./source/TARDBP_alphpol.csv")
Edit_final_variant_file("./source/TARDBP_alphpol.csv","./source/TARDBP_alphpol2.csv")
MOVA("./source/Q13148.fa", "TARDBP", "./source/AF-Q13148-F1-model_v2.pdb","./source/TARDBP_alphpol2.csv", "./source/TARDBPvariantdatapol.csv")

## The function is currently defined as
function (input_file_name, export_file_name) 
{
    amino_code1 <- c("A", "R", "N", "D", "C", "Q", "E", "G", 
        "I", "L", "K", "M", "F", "P", "S", "T", "W", "Y", "V", 
        "H")
    amino_code3 = c("Ala", "Arg", "Asn", "Asp", "Cys", "Gln", 
        "Glu", "Gly", "Ile", "Leu", "Lys", "Met", "Phe", "Pro", 
        "Ser", "Thr", "Trp", "Tyr", "Val", "His")
    names(amino_code1) <- amino_code3
    x <- fread(input_file_name)
    colnames(x)[10] <- "Protein_Consequence"
    x$ref <- substr(x$Protein_Consequence, 3, 5)
    x$Pos <- substr(x$Protein_Consequence, 6, nchar(x$Protein_Consequence) - 
        3)
    x$alt <- substr(x$Protein_Consequence, nchar(x$Protein_Consequence) - 
        2, nchar(x$Protein_Consequence))
    for (i in 1:nrow(x)) {
        x$change[i] <- paste(amino_code1[x$ref[i]], x$Pos[i], 
            amino_code1[x$alt[i]], sep = "")
    }
    y <- data.frame(Chromosome = x$Chromosome, Position = x$Position, 
        Reference = x$Reference, Alternate = x$Alternate, change = x$change)
    fwrite(y, export_file_name)
  }
#> function (input_file_name, export_file_name) 
#> {
#>     amino_code1 <- c("A", "R", "N", "D", "C", "Q", "E", "G", 
#>         "I", "L", "K", "M", "F", "P", "S", "T", "W", "Y", "V", 
#>         "H")
#>     amino_code3 = c("Ala", "Arg", "Asn", "Asp", "Cys", "Gln", 
#>         "Glu", "Gly", "Ile", "Leu", "Lys", "Met", "Phe", "Pro", 
#>         "Ser", "Thr", "Trp", "Tyr", "Val", "His")
#>     names(amino_code1) <- amino_code3
#>     x <- fread(input_file_name)
#>     colnames(x)[10] <- "Protein_Consequence"
#>     x$ref <- substr(x$Protein_Consequence, 3, 5)
#>     x$Pos <- substr(x$Protein_Consequence, 6, nchar(x$Protein_Consequence) - 
#>         3)
#>     x$alt <- substr(x$Protein_Consequence, nchar(x$Protein_Consequence) - 
#>         2, nchar(x$Protein_Consequence))
#>     for (i in 1:nrow(x)) {
#>         x$change[i] <- paste(amino_code1[x$ref[i]], x$Pos[i], 
#>             amino_code1[x$alt[i]], sep = "")
#>     }
#>     y <- data.frame(Chromosome = x$Chromosome, Position = x$Position, 
#>         Reference = x$Reference, Alternate = x$Alternate, change = x$change)
#>     fwrite(y, export_file_name)
#>   }
#> <environment: 0x0000011a8b40ada0>