Calculate the 'distance to the known pathogenic variant' for each variant in MOVA_final_predict_file.

Calculate the 'distance to the known pathogenic variant' for each variant in MOVA_final_predict_file. This function should be done in advance of the machine learning function with 'distance to the known pathogenic variant' as a feature.

Usage

MOVA_predistance(protein_name, MOVA_final_predict_file, MOVA_predict_file, phenotype = "Target")

Arguments

protein_name: Name of target protein/gene. Used to name the file to be exported.
MOVA_final_predict_file: The "gene name_Target or Pathogenic_finalpredict.csv" file output by the MOVA function. The final MOVA_3d_distance predicted values will be in this file.
MOVA_predict_file: The "gene name_Target or Pathogenic_predict.csv" file output by the MOVA function.
phenotype: Specify "Target" if you want the positive variant to be the Target variant only, or "Pathogenic" if you want to include the Pathogenic variant as well. The default is "Target".

Details

This function must be performed before the following functions are performed. *MOVA_3d_distance *MOVA_3d_distance_log *MOVA_LOPOV *MOVA_plus_3d_distance *MOVA_plus_3d_distance_SVM *MOVA_plus_3d_distance_xgboost

Value

References

Author

Yuya Hatano

Note

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")
MOVA_predistance("TARDBP", "TARDBP_Target_finalpredict.csv","TARDBP_Target_predict.csv")
MOVA_plus_3d_distance("TARDBP", "TARDBP_Target_finalpredict.csv","TARDBP_Target_predict.csv")

## The function is currently defined as
function (protein_name, MOVA_final_predict_file, MOVA_predict_file, 
    phenotype = "Target") 
{
    D <- fread(MOVA_predict_file)
    if (phenotype == "Target") {
        D <- D[(D$Type == "Target") | (D$Type == "Ctrl"), ]
    }
    final_data <- fread(MOVA_final_predict_file)
    if (phenotype == "Target") {
        x <- D[Type2 == 1, ]$x
        y <- D[Type2 == 1, ]$y
        z <- D[Type2 == 1, ]$z
        D$t_distance <- 0
        final_data$t_distance <- 0
        for (i3 in 1:nrow(final_data)) {
            t_distance <- sqrt((x - final_data[i3]$x) * (x - 
                final_data[i3]$x) + (y - final_data[i3]$y) * 
                (y - final_data[i3]$y) + (z - final_data[i3]$z) * 
                (z - final_data[i3]$z))
            t_distance <- sort(t_distance, decreasing = F)
            final_data[i3]$t_distance <- t_distance[1]
        }
    }
    else {
        x <- D[Type3 == 1, ]$x
        y <- D[Type3 == 1, ]$y
        z <- D[Type3 == 1, ]$z
        D$t_distance <- 0
        final_data$t_distance <- 0
        for (i3 in 1:nrow(final_data)) {
            t_distance <- sqrt((x - final_data[i3]$x) * (x - 
                final_data[i3]$x) + (y - final_data[i3]$y) * 
                (y - final_data[i3]$y) + (z - final_data[i3]$z) * 
                (z - final_data[i3]$z))
            t_distance <- sort(t_distance, decreasing = F)
            final_data[i3]$t_distance <- t_distance[1]
        }
    }
    fwrite(final_data, MOVA_final_predict_file)
  }
#> function (protein_name, MOVA_final_predict_file, MOVA_predict_file, 
#>     phenotype = "Target") 
#> {
#>     D <- fread(MOVA_predict_file)
#>     if (phenotype == "Target") {
#>         D <- D[(D$Type == "Target") | (D$Type == "Ctrl"), ]
#>     }
#>     final_data <- fread(MOVA_final_predict_file)
#>     if (phenotype == "Target") {
#>         x <- D[Type2 == 1, ]$x
#>         y <- D[Type2 == 1, ]$y
#>         z <- D[Type2 == 1, ]$z
#>         D$t_distance <- 0
#>         final_data$t_distance <- 0
#>         for (i3 in 1:nrow(final_data)) {
#>             t_distance <- sqrt((x - final_data[i3]$x) * (x - 
#>                 final_data[i3]$x) + (y - final_data[i3]$y) * 
#>                 (y - final_data[i3]$y) + (z - final_data[i3]$z) * 
#>                 (z - final_data[i3]$z))
#>             t_distance <- sort(t_distance, decreasing = F)
#>             final_data[i3]$t_distance <- t_distance[1]
#>         }
#>     }
#>     else {
#>         x <- D[Type3 == 1, ]$x
#>         y <- D[Type3 == 1, ]$y
#>         z <- D[Type3 == 1, ]$z
#>         D$t_distance <- 0
#>         final_data$t_distance <- 0
#>         for (i3 in 1:nrow(final_data)) {
#>             t_distance <- sqrt((x - final_data[i3]$x) * (x - 
#>                 final_data[i3]$x) + (y - final_data[i3]$y) * 
#>                 (y - final_data[i3]$y) + (z - final_data[i3]$z) * 
#>                 (z - final_data[i3]$z))
#>             t_distance <- sort(t_distance, decreasing = F)
#>             final_data[i3]$t_distance <- t_distance[1]
#>         }
#>     }
#>     fwrite(final_data, MOVA_final_predict_file)
#>   }
#> <environment: 0x0000011a810326a8>