temporary code pieces for MPNST analysis

Author: ymahlich

manuscript/figure4ExVivoResults.Rmd

@@ -16,7 +16,7 @@ library(tidyverse)
 library(ggplot2)
 library(arrow)
 library(dplyr)
-
+library(gridExtra)
 source('coderdataResultsFunctions.R')
 ```
 
@@ -63,6 +63,47 @@ print(plot)
 ## Create funtion to dive in
 
 
+```{r}
+tgt = 'ccle'
+
+all_preds <- do.call(
+  rbind,
+  lapply(
+    models,
+    function(mdl) getModelPredictionData(dset = mdl) |>
+      dplyr::filter(target == tgt & source != tgt & source != 'beataml' & source != 'mpnst') |>
+      collect()
+    )
+  )
+```
+```{r}
+plot_panel <- function(data, title){
+  data <- sample_n(data, 10000)
+  plot <- (
+    ggplot(data, aes(x=auc_pred, y=auc_true))
+    + geom_point()
+    + geom_smooth(method=lm)
+    + facet_grid(source ~ model)
+    + ggtitle(title)
+    # + xlim(0, 1)
+    # + ylim(0, 1.25)
+  )
+}
+```
+```{r}
+all_preds <- all_preds |> mutate(auc_ranges = cut(auc_true, c(-Inf, 0.2, 0.8, Inf), labels = c('auc_true <= 0.2', '0.2 < auc_true <= 0.8', 'auc_true > 0.8')))
+
+```
+```{r}
+ranges <- list('auc_true <= 0.2', '0.2 < auc_true <= 0.8', 'auc_true > 0.8')
+plots <- lapply(ranges, function(auc_range){
+  data <- all_preds |> filter(auc_ranges == auc_range) |> collect()
+  plot_panel(data, auc_range)
+})
+plot <- arrangeGrob(grobs = plots, ncol = 3)
+ggsave('ccle_auc_plot.pdf', plot, dpi=300, width=30, height=10)
+```
+
 Full model predictions are stored on synapse as parquet files. Individual
 datasets can be downloaded via `getModelPredictionData` in
 `coderdataResultsFunctions.R` (sources during the setup process).
@@ -78,17 +119,51 @@ all_preds <- do.call(
   lapply(
     models,
     function(mdl) getModelPredictionData(dset = mdl) |>
-      dplyr::filter(target == tgt) |>
+      dplyr::filter(target == tgt & source != tgt & source != 'beataml') |>
       collect()
     )
   )
 
 ```
 
+We want to group results by drugs i.e. create a panel per drug. To that end we 
+extract the drugs and determine the "grid layout" by size of target drugs.
+```{r}
 
+drugs <- unique(all_preds$improve_chem_id)
+grid_ncol = 4
+grid_nrow = ceiling(length(drugs) / grid_ncol)
+```
+
+Defining the plot function for the individual "panels"
 ```{r}
-plot <- ggplot(all_preds, aes(x=auc_true, y=auc_pred)) + geom_point() + geom_smooth(method=lm) + facet_grid(source ~ model)
-print(plot)
-ggsave('mpnst_auc_plot.pdf', plot, dpi=300, width=20, height=20)
+plot_panel <- function(data, title){
+  plot <- (
+    ggplot(data, aes(x=auc_true, y=auc_pred))
+    + geom_point()
+    + geom_smooth(method=lm)
+    + facet_grid(source ~ model)
+    + ggtitle(title)
+    + xlim(0, 1)
+    + ylim(0, 1.25)
+  )
+}
+
 ```
 
+```{r}
+plots <- lapply(drugs, function(drug_id){
+  data <- all_preds |> filter(improve_chem_id == drug_id) |> collect()
+  plot_panel(data, drug_id)
+})
+```
+
+```{r}
+plot <- arrangeGrob(grobs = plots, ncol = grid_ncol, nrow = grid_nrow)
+```
+
+
+```{r}
+# print(plot)
+ggsave('mpnst_auc_plot.pdf', plot, dpi=300, width=40, height=60, limitsize = FALSE)
+```