Creating files for MOVA function input

Create the necessary files for the MOVA function.

Usage

Edit_final_variant_file(input_file_name, export_file_name)

Arguments

input_file_name

export_file_name2 output by Edit_polyphen_data

export_file_name

File name to be exported

Details

This function adds ref, Pos, alt, and change columns to the export_file_name2 output by Edit_polyphen_data.

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$ref <- substr(x$HGVSp_VEP_split, 3, 5)
    x$Pos <- substr(x$HGVSp_VEP_split, 6, nchar(x$HGVSp_VEP_split) - 
        3)
    x$alt <- substr(x$HGVSp_VEP_split, nchar(x$HGVSp_VEP_split) - 
        2, nchar(x$HGVSp_VEP_split))
    for (i in 1:nrow(x)) {
        x$change[i] <- paste(amino_code1[x$ref[i]], x$Pos[i], 
            amino_code1[x$alt[i]], sep = "")
    }
    fwrite(x, export_file_name)
  }
#> function (input_file_name, export_file_name) 
#> {
#>     amino_code1 <- c("A", "R", "N", "D", "C", "Q", "E", "G", 
#>         "I", "L", "K", "M", "F", "P", "S", "T", "W", "Y", "V", 
#>         "H")
#>     amino_code3 = c("Ala", "Arg", "Asn", "Asp", "Cys", "Gln", 
#>         "Glu", "Gly", "Ile", "Leu", "Lys", "Met", "Phe", "Pro", 
#>         "Ser", "Thr", "Trp", "Tyr", "Val", "His")
#>     names(amino_code1) <- amino_code3
#>     x <- fread(input_file_name)
#>     colnames(x)[10] <- "Protein_Consequence"
#>     x$ref <- substr(x$HGVSp_VEP_split, 3, 5)
#>     x$Pos <- substr(x$HGVSp_VEP_split, 6, nchar(x$HGVSp_VEP_split) - 
#>         3)
#>     x$alt <- substr(x$HGVSp_VEP_split, nchar(x$HGVSp_VEP_split) - 
#>         2, nchar(x$HGVSp_VEP_split))
#>     for (i in 1:nrow(x)) {
#>         x$change[i] <- paste(amino_code1[x$ref[i]], x$Pos[i], 
#>             amino_code1[x$alt[i]], sep = "")
#>     }
#>     fwrite(x, export_file_name)
#>   }
#> <environment: 0x0000011a8824a338>