MOVA with only 3D coordinates as explanatory variable
MOVA_only_3d_coordinates.RdRandom forest is performed with 3D coordinates as the only explanatory variable and the pathogenicity of the variants as the objective variable.
Usage
MOVA_only_3d_coordinates(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_only_3d_coordinates 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
Draw ROC curve for MOVA_only_3d_coordinates (green). MOVA_only_3d_coordinates is evaluated using the Stratified 5-fold cross validation method, and the model is repeated five more times. The average of the predicted values is added to the "only_3d_coordinates_predict" column of the MOVA_predict_file. The final MOVA_only_3d_coordinates predicted value are added to the "only_3d_coordinates_predict" column in MOVA_final_predict_file. "protein/gene name_Target or Pathogenic_result_only_3d_coordinates.csv" contains the Cutoff value (Youden index) for each fold (Column: Cutoff), the number of positive variants for each gene used in the analysis (Column: positive_variant_num), number of negative variants (Column: negative_variant_num), AUC for each fold of MOVA_only_3d_coordinates (Column: AUC), cvAUC for MOVA_only_3d_coordinates (Column: cvauc). The file required for redrawing with the MOVA_redraw function of MOVA_only_3d_coordinates is output in "protein/gene name_Target or Pathogenic_predict_orig_only_3d_coordinates.csv".
Value
A data.frame containing the Cutoff value (Youden index) for each fold (Column: Cutoff), the number of positive variants for each gene used in the analysis (Column: positive_variant_num), number of negative variants (Column: negative_variant_num), AUC for each fold of MOVA_only_3d_coordinates (Column: AUC), cvAUC for MOVA_only_3d_coordinates (Column: cvauc). The same data is output to "protein/gene name_Target or Pathogenic_result_only_3d_coordinates.csv".
Examples
##---- Should be DIRECTLY executable !! ----
##-- ==> Define data, use random,
##-- or do help(data=index) for the standard data sets.
## The function is currently defined as
function (protein_name, MOVA_final_predict_file, MOVA_predict_file,
phenotype = "Target")
{
D <- fread(MOVA_predict_file)
D$only_3d_coordinates_predict <- 0
D[, c("only_3d_coordinates_predict")] <- list(NULL)
if (phenotype == "Target") {
D <- D[(D$Type == "Target") | (D$Type == "Ctrl"), ]
}
fpredict <- data.frame(matrix(rep(NA, 3), nrow = 1))[numeric(0),
]
colnames(fpredict) <- c("change", "predict", "n")
final_data <- fread(MOVA_final_predict_file)
final_data$only_3d_coordinates_predict <- 0
final_data[, c("only_3d_coordinates_predict")] <- list(NULL)
df <- data.frame(matrix(rep(NA, 6), nrow = 1))[numeric(0),
]
colnames(df) <- c("ID", "result", "predict", "change", "iter1",
"iter2")
D$id2 <- 0
D[, c("id2")] <- list(NULL)
if (phenotype == "Target") {
D$result <- D$Type2
}
else {
D$result <- D$Type3
}
oldw <- getOption("warn")
options(warn = -1)
D <- rowid_to_column(D, var = "id2")
for (i2 in 1:5) {
D$id3 <- D$id2
j <- 5
dat1 <- D %>% stratified(., group = "result", size = 1/j)
dat1$iter <- 1
datzan <- D[-dat1$id2, ]
for (i in 2:j) {
datzan[, c("id2")] <- list(NULL)
datzan <- rowid_to_column(datzan, var = "id2")
if (i != j) {
dat2 <- datzan %>% stratified(., group = "result",
size = 1/(j - i + 1))
}
else {
dat2 <- datzan
}
dat2$iter <- i
datzan <- datzan[-dat2$id2, ]
dat1 <- rbind(dat1, dat2)
}
dat1[, c("id2")] <- list(NULL)
dat1 <- rowid_to_column(dat1, var = "id2")
for (i in 1:j) {
val <- dat1[dat1$iter == i, ]
train.data <- dat1[-val$id2, ]
rf <- randomForest(result ~ x + y + z, train.data,
importance = TRUE)
f <- data.frame(ID = val$ID, result = val$result,
predict = predict(rf, val), change = val$change,
iter1 = i, iter2 = i2)
df <- rbind(df, f)
}
}
for (i in 1:30) {
rf <- randomForest(result ~ x + y + z, D)
f <- data.frame(ID = final_data$ID, predict = predict(rf,
final_data), n = i)
fpredict <- rbind(fpredict, f)
}
options(warn = oldw)
fpredictb <- fpredict %>% group_by(ID) %>% summarise(only_3d_coordinates_predict = mean(predict))
ID <- str_split(fpredictb$ID, pattern = ":", simplify = TRUE)
for (i in 1:nrow(fpredictb)) {
if (ID[i, 5] == ID[i, 7]) {
fpredictb$predict[i] = 0
}
}
final_data <- merge(fpredictb, final_data)
fwrite(final_data, MOVA_final_predict_file)
df$iter3 <- df$iter1 + (df$iter2 * 5)
out <- cvAUC(df$predict, df$result, label.ordering = NULL,
folds = df$iter3)
plot(out$perf, col = "green", avg = "vertical", add = TRUE)
cvauc <- out$cvAUC
YI2 <- data.frame(matrix(rep(NA, 5), nrow = 1))[numeric(0),
]
colnames(YI2) <- c("Cutoff", "positive_variant_num", "negative_variant_num",
"AUC", "cvauc")
for (i in 6:30) {
pred <- prediction(df[df$iter3 == i, ]$predict, df[df$iter3 ==
i, ]$result)
auc.tmp <- performance(pred, "auc")
auc <- as.numeric(auc.tmp@y.values)
tab <- data.frame(Cutoff = unlist(pred@cutoffs), TP = unlist(pred@tp),
FP = unlist(pred@fp), FN = unlist(pred@fn), TN = unlist(pred@tn),
Sensitivity = unlist(pred@tp)/(unlist(pred@tp) +
unlist(pred@fn)), Specificity = unlist(pred@tn)/(unlist(pred@fp) +
unlist(pred@tn)), Accuracy = ((unlist(pred@tp) +
unlist(pred@tn))/nrow(df)), Precision = (unlist(pred@tp)/(unlist(pred@tp) +
unlist(pred@fp))))
tab$Youden <- tab$Sensitivity + tab$Specificity - 1
YI <- tab[order(tab$Youden, decreasing = T), ]
YI <- data.frame(Cutoff = YI$Cutoff[1], positive_variant_num = c(nrow(df[(df$result ==
1) & (df$iter2 == 1), ])), negative_variant_num = c(nrow(df[(df$result ==
0) & (df$iter2 == 1), ])), AUC = c(auc), cvauc = c(cvauc))
YI2 <- rbind(YI2, YI)
}
fwrite(YI2, paste(protein_name, phenotype, "result_only_3d_coordinates.csv",
sep = "_"))
df2 <- df %>% group_by(ID) %>% summarise(only_3d_coordinates_predict = mean(predict))
D[, c("result")] <- list(NULL)
fwrite(merge(D, df2), MOVA_predict_file)
fwrite(df, paste(protein_name, phenotype, "predict_orig_only_3d_coordinates.csv",
sep = "_"))
return(YI2)
}
#> function (protein_name, MOVA_final_predict_file, MOVA_predict_file,
#> phenotype = "Target")
#> {
#> D <- fread(MOVA_predict_file)
#> D$only_3d_coordinates_predict <- 0
#> D[, c("only_3d_coordinates_predict")] <- list(NULL)
#> if (phenotype == "Target") {
#> D <- D[(D$Type == "Target") | (D$Type == "Ctrl"), ]
#> }
#> fpredict <- data.frame(matrix(rep(NA, 3), nrow = 1))[numeric(0),
#> ]
#> colnames(fpredict) <- c("change", "predict", "n")
#> final_data <- fread(MOVA_final_predict_file)
#> final_data$only_3d_coordinates_predict <- 0
#> final_data[, c("only_3d_coordinates_predict")] <- list(NULL)
#> df <- data.frame(matrix(rep(NA, 6), nrow = 1))[numeric(0),
#> ]
#> colnames(df) <- c("ID", "result", "predict", "change", "iter1",
#> "iter2")
#> D$id2 <- 0
#> D[, c("id2")] <- list(NULL)
#> if (phenotype == "Target") {
#> D$result <- D$Type2
#> }
#> else {
#> D$result <- D$Type3
#> }
#> oldw <- getOption("warn")
#> options(warn = -1)
#> D <- rowid_to_column(D, var = "id2")
#> for (i2 in 1:5) {
#> D$id3 <- D$id2
#> j <- 5
#> dat1 <- D %>% stratified(., group = "result", size = 1/j)
#> dat1$iter <- 1
#> datzan <- D[-dat1$id2, ]
#> for (i in 2:j) {
#> datzan[, c("id2")] <- list(NULL)
#> datzan <- rowid_to_column(datzan, var = "id2")
#> if (i != j) {
#> dat2 <- datzan %>% stratified(., group = "result",
#> size = 1/(j - i + 1))
#> }
#> else {
#> dat2 <- datzan
#> }
#> dat2$iter <- i
#> datzan <- datzan[-dat2$id2, ]
#> dat1 <- rbind(dat1, dat2)
#> }
#> dat1[, c("id2")] <- list(NULL)
#> dat1 <- rowid_to_column(dat1, var = "id2")
#> for (i in 1:j) {
#> val <- dat1[dat1$iter == i, ]
#> train.data <- dat1[-val$id2, ]
#> rf <- randomForest(result ~ x + y + z, train.data,
#> importance = TRUE)
#> f <- data.frame(ID = val$ID, result = val$result,
#> predict = predict(rf, val), change = val$change,
#> iter1 = i, iter2 = i2)
#> df <- rbind(df, f)
#> }
#> }
#> for (i in 1:30) {
#> rf <- randomForest(result ~ x + y + z, D)
#> f <- data.frame(ID = final_data$ID, predict = predict(rf,
#> final_data), n = i)
#> fpredict <- rbind(fpredict, f)
#> }
#> options(warn = oldw)
#> fpredictb <- fpredict %>% group_by(ID) %>% summarise(only_3d_coordinates_predict = mean(predict))
#> ID <- str_split(fpredictb$ID, pattern = ":", simplify = TRUE)
#> for (i in 1:nrow(fpredictb)) {
#> if (ID[i, 5] == ID[i, 7]) {
#> fpredictb$predict[i] = 0
#> }
#> }
#> final_data <- merge(fpredictb, final_data)
#> fwrite(final_data, MOVA_final_predict_file)
#> df$iter3 <- df$iter1 + (df$iter2 * 5)
#> out <- cvAUC(df$predict, df$result, label.ordering = NULL,
#> folds = df$iter3)
#> plot(out$perf, col = "green", avg = "vertical", add = TRUE)
#> cvauc <- out$cvAUC
#> YI2 <- data.frame(matrix(rep(NA, 5), nrow = 1))[numeric(0),
#> ]
#> colnames(YI2) <- c("Cutoff", "positive_variant_num", "negative_variant_num",
#> "AUC", "cvauc")
#> for (i in 6:30) {
#> pred <- prediction(df[df$iter3 == i, ]$predict, df[df$iter3 ==
#> i, ]$result)
#> auc.tmp <- performance(pred, "auc")
#> auc <- as.numeric(auc.tmp@y.values)
#> tab <- data.frame(Cutoff = unlist(pred@cutoffs), TP = unlist(pred@tp),
#> FP = unlist(pred@fp), FN = unlist(pred@fn), TN = unlist(pred@tn),
#> Sensitivity = unlist(pred@tp)/(unlist(pred@tp) +
#> unlist(pred@fn)), Specificity = unlist(pred@tn)/(unlist(pred@fp) +
#> unlist(pred@tn)), Accuracy = ((unlist(pred@tp) +
#> unlist(pred@tn))/nrow(df)), Precision = (unlist(pred@tp)/(unlist(pred@tp) +
#> unlist(pred@fp))))
#> tab$Youden <- tab$Sensitivity + tab$Specificity - 1
#> YI <- tab[order(tab$Youden, decreasing = T), ]
#> YI <- data.frame(Cutoff = YI$Cutoff[1], positive_variant_num = c(nrow(df[(df$result ==
#> 1) & (df$iter2 == 1), ])), negative_variant_num = c(nrow(df[(df$result ==
#> 0) & (df$iter2 == 1), ])), AUC = c(auc), cvauc = c(cvauc))
#> YI2 <- rbind(YI2, YI)
#> }
#> fwrite(YI2, paste(protein_name, phenotype, "result_only_3d_coordinates.csv",
#> sep = "_"))
#> df2 <- df %>% group_by(ID) %>% summarise(only_3d_coordinates_predict = mean(predict))
#> D[, c("result")] <- list(NULL)
#> fwrite(merge(D, df2), MOVA_predict_file)
#> fwrite(df, paste(protein_name, phenotype, "predict_orig_only_3d_coordinates.csv",
#> sep = "_"))
#> return(YI2)
#> }
#> <environment: 0x0000011a8478b868>