Creation of Hgmd files
Hgmd_divide.RdCreate a positive variant file from the Hgmd data.
Details
Based on HGMD data, list amino acid changes (column: HGVSprotein), VCF (column: VCF), DM if DM in HGMD, DMp if DM? (column: possible), Pathogenic if pathogenic but not a target phenotype, and Target if target phenotype(column: Type) for each variant and save it. This is processed by Hgmd_divide and can be processed by Edit_variant_data.
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 (hgmd_file_name)
{
x <- fread(hgmd_file_name)
x <- x %>% separate(VCF, c("buf1", "buf2"), sep = ":")
x <- x %>% separate(buf2, c("buf3", "Alternate"), sep = "/")
x$Chromosome <- str_sub(x$buf1, 4, -1)
x$Position <- str_sub(x$buf3, 1, -2)
x$Reference <- str_sub(x$buf3, -1, -1)
x[, `:=`(buf1, NULL)]
x[, `:=`(buf3, NULL)]
fwrite(x, hgmd_file_name)
}
#> function (hgmd_file_name)
#> {
#> x <- fread(hgmd_file_name)
#> x <- x %>% separate(VCF, c("buf1", "buf2"), sep = ":")
#> x <- x %>% separate(buf2, c("buf3", "Alternate"), sep = "/")
#> x$Chromosome <- str_sub(x$buf1, 4, -1)
#> x$Position <- str_sub(x$buf3, 1, -2)
#> x$Reference <- str_sub(x$buf3, -1, -1)
#> x[, `:=`(buf1, NULL)]
#> x[, `:=`(buf3, NULL)]
#> fwrite(x, hgmd_file_name)
#> }
#> <environment: 0x0000011a816a0900>