Fix bug in threshold.txt file checking

R/config.R

@@ -20,7 +20,7 @@ AUTHORIZED_STROMA_VALUES <<- c('DAPI', 'stroma', 'other')
 AUTHORIZED_TUMOR_VALUES  <<- c('CK', 'tumor')
 AUTHORIZED_MARKERS       <<- c('CAL', 'CD3', 'CD4', 'CD8', 'CD11c', 'CD15', 'CD20', 'CD56', 'CD68',
                                'CD103', 'CD163', 'CD206', 'FOXP3', 'GB', 'gH2AX', 'gH2AXN', 'IDO',
-                               'IL10R', 'Keratin', 'Ki67', 'PD1', 'PDL1', 'PERFORIN', 'SOX10',
+                               'IL10R', 'Keratin', 'KI67', 'PD1', 'PDL1', 'PERFORIN', 'SOX10',
                                'WT1', 'CK', 'VISTA')
 IGNORED_PHENOTYPES       <<- c('DAPIp', 'MISSING')
 NO_PHENOTYPE             <<- 'MISSING'

R/input_check.R

@@ -144,6 +144,15 @@ standardize_and_split_cell_data <- function(input_file,
                                file_name        = input_file)
 
 
+    # Remove any duplicated rows in the input data. Note that for computing speed reasons, we
+    # first check on a subset of the input table whether there are potentially any duplicates,
+    # before expanding the search to the entire data. Since duplicates are rare, this will save
+    # time in most cases.
+    if(any(duplicated(input_table[,c('cell_id', 'cell_x_position', 'cell_y_position')]))){
+        input_table = input_table[!duplicated(input_table),]
+    }
+
+
     # Extract sample names and filter to keep only rows matching samples names present in the
     # input parameters.
     sample_names = extract_sample_name(input_table[,'sample_name'], input_file=input_file)
@@ -259,6 +268,9 @@ standardize_and_split_tissue_data <- function(input_file,
                                actual_columns   = colnames(input_table),
                                file_name        = input_file)
 
+    # Remove any duplicated rows in the input data.
+    if(any(duplicated(input_table))) input_table = input_table[!duplicated(input_table),]
+
 
     # Extract sample name and "image ID" values.
     # *****************************************

R/load_data.R

@@ -279,7 +279,7 @@ load_thresholds_file <- function(input_file,
     if(col_names[1] != 'sample_name') raise_error(
         msg  = "The first column of the threshold file must be 'sample_name'.",
         file = input_file)
-    if('tissue_type' %in% col_names & col_names[2] != 'sample_name') raise_error(
+    if('tissue_type' %in% col_names & col_names[2] != 'tissue_type') raise_error(
         msg  = "If present, the 'tissue_type' column must be the second column of the file.",
         file = input_file)