add back option for new output directory

ark/phenotyping/pixel_consensus_cluster.R

@@ -19,17 +19,19 @@ library(foreach)
 library(parallel)
 
 # helper function to map a FOV to its consensus labels
-mapConsensusLabels <- function(fov, pixelMatDir, som_to_meta_map) {
+mapConsensusLabels <- function(fov, pixelMatDir, som_to_meta_map, pixelOutDir) {
     # read in pixel data, we'll need the cluster column for mapping
     fileName <- file.path(fov, "feather", fsep=".")
     matPath <- file.path(pixelMatDir, fileName)
+    matOutPath <- file.path(pixelOutDir, fileName)
+
     fovPixelData <- arrow::read_feather(matPath)
 
     # assign hierarchical cluster labels
     fovPixelData$pixel_meta_cluster <- som_to_meta_map[as.character(fovPixelData$pixel_som_cluster)]
 
     # write data with consensus labels
-    arrow::write_feather(as.data.table(fovPixelData), matPath)
+    arrow::write_feather(as.data.table(fovPixelData), matOutPath)
 }
 
 # get the number of cores
@@ -66,6 +68,8 @@ batchSize <- strtoi(args[8])
 seed <- strtoi(args[9])
 set.seed(seed)
 
+pixelOutDir <- args[10]
+
 # read cluster averaged data
 print("Reading cluster averaged data")
 clusterAvgs <- as.data.frame(read.csv(clusterAvgPath, check.names=FALSE))
@@ -104,7 +108,7 @@ for (batchStart in seq(1, length(fovs), batchSize)) {
         i=batchStart:batchEnd,
         .combine='c'
     ) %dopar% {
-        mapConsensusLabels(fovs[i], pixelMatDir, som_to_meta_map)
+        mapConsensusLabels(fovs[i], pixelMatDir, som_to_meta_map, pixelOutDir)
     }
 
     # unregister the parallel cluster

ark/phenotyping/run_pixel_som.R

@@ -15,9 +15,10 @@ library(foreach)
 library(parallel)
 
 # helper function to map a FOV to its SOM labels
-mapSOMLabels <- function(fov, somWeights, pixelMatDir) {
+mapSOMLabels <- function(fov, somWeights, pixelMatDir, pixelOutDir) {
     fileName <- paste0(fov, ".feather")
     matPath <- file.path(pixelMatDir, fileName)
+    matOutPath <- file.path(pixelOutDir, fileName)
     fovPixelData_all <- data.table(arrow::read_feather(matPath))
 
     # 99.9% normalization
@@ -35,7 +36,7 @@ mapSOMLabels <- function(fov, somWeights, pixelMatDir) {
     fovPixelData$pixel_som_cluster <- as.integer(clusters[,1])
 
     # write to feather
-    arrow::write_feather(as.data.table(fovPixelData),  matPath)
+    arrow::write_feather(as.data.table(fovPixelData), matOutPath)
 }
 
 # get the number of cores
@@ -59,6 +60,9 @@ pixelWeightsPath <- args[4]
 # retrieve the batch size to determine number of threads to run in parallel
 batchSize <- strtoi(args[5])
 
+# get new output directory
+pixelOutDir <- args[6]
+
 # read the weights
 somWeights <- as.matrix(arrow::read_feather(pixelWeightsPath))
 
@@ -91,7 +95,7 @@ for (batchStart in seq(1, length(fovs), batchSize)) {
         i=batchStart:batchEnd,
         .combine='c'
     ) %dopar% {
-        mapSOMLabels(fovs[i], somWeights, pixelMatDir)
+        mapSOMLabels(fovs[i], somWeights, pixelMatDir, pixelOutDir)
     }
 
     # unregister the parallel cluster

ark/phenotyping/som_utils.py

@@ -1210,7 +1210,7 @@ def cluster_pixels(fovs, channels, base_dir, data_dir='pixel_mat_data',
 
     # run the trained SOM on the dataset, assigning clusters
     process_args = ['Rscript', '/run_pixel_som.R', ','.join(fovs),
-                    data_path, norm_vals_path, weights_path, str(batch_size)]
+                    data_path, norm_vals_path, weights_path, str(batch_size), out_path]
 
     process = subprocess.Popen(process_args, stdout=subprocess.PIPE, stderr=subprocess.STDOUT)