Merge pull request #187 from dule1322/CTX-6635

CTX-6635: Fix metadata entry with sample file matching
coretex-ai · Aug 20, 2024 · 299549b · 299549b
2 parents f1202a9 + a8699d0
commit 299549b
Show file tree

Hide file tree

Showing 2 changed files with 25 additions and 7 deletions.
diff --git a/tasks/r-alpha-beta-diversity/main.r b/tasks/r-alpha-beta-diversity/main.r
@@ -176,7 +176,6 @@ perpareSampleData <- function(phyloseqObject, targetColumn) {
 subset_samples_custom <- function(pseq, targetColumnValue) {
     metadata <- data.frame(sample_data(pseq))
     if (!targetColumnValue %in% unique(metadata$target)) {
-        print(paste("Could not find", targetColumnValue, "among the samples"))
         return(NULL)
     }
 
@@ -210,10 +209,13 @@ validateTargetValues <- function(sampleDataFrame, targetValues) {
 }
 
 genusAbundancePlot <- function(pseq_bac, target_column_value, output_path, taskRun) {
-    print(sprintf("Creating abundance plot for %s", target_column_value))
+    sa <- subset_samples_custom(pseq_bac, target_column_value)
+    if (is.null(sa)) {
+        return()
+    }
 
+    print(sprintf("Creating abundance plot for %s", target_column_value))
     genus_col_index <- which(rank_names(pseq_bac) == "genus")
-    sa <- subset_samples_custom(pseq_bac, target_column_value)
 
     genus_sum = tapply(taxa_sums(sa), tax_table(sa)[, "genus"], sum, na.rm = FALSE)
     topgenera = names(sort(genus_sum, TRUE))[1:30]
@@ -269,7 +271,7 @@ validatePhyoseq <- function(phyloseqObject) {
         sampleName <- rownames(metadata)[counter + 1]
         if (asvCount == 0) {
             sample_data(phyloseqObject) <- subset(metadata, metadata$sampleId != sampleName)
-            print(paste0("Sample ", sampleName, " has 0 ASVs in the OTU table!"))
+            print(paste0("Sample ", sampleName, " has 0 ASVs in the OTU table! This sample will be skipped during processing!"))
         }
         counter <- counter + 1
     }

diff --git a/tasks/r-dada2/main.r b/tasks/r-dada2/main.r
@@ -328,9 +328,15 @@ tryFilterAndTrim <- function(
 }
 
 getSampleName <- function(forward_path, metadata) {
+    forward_name <- basename(forward_path)
+
     for (sampleId in metadata$sampleId) {
-        if (startsWith(basename(forward_path), sampleId)) {
-            return(sampleId)
+        sample_length <- nchar(sampleId)
+        if (substr(forward_name, 1, sample_length) == sampleId) {
+            next_char <- substr(forward_name, sample_length + 1, sample_length + 1)
+            if (!grepl("[[:alnum:]]", next_char)) {
+                return(sampleId)
+            }
         }
     }
 
@@ -454,17 +460,27 @@ main <- function(taskRun) {
     )
 
     for (path in filtered_forward_read_paths) {
-        taskRun$createArtifact(
+        print(paste0("Uploading filtered_reads/", basename(path), " to artifacts..."))
+        artifact <- taskRun$createArtifact(
             path,
             file.path("filtered_reads", basename(path))
         )
+
+        if (is.null(artifact)) {
+            print(paste0("Failed to upload filtered_reads/", basename(path), " to artifacts"))
+        }
     }
 
     for (path in filtered_reverse_read_paths) {
+        print(paste0("Uploading filtered_reads/", basename(path), " to artifacts..."))
         taskRun$createArtifact(
             path,
             file.path("filtered_reads", basename(path))
         )
+
+        if (is.null(artifact)) {
+            print(paste0("Failed to upload filtered_reads/", basename(path), " to artifacts"))
+        }
     }
 
     filtering_results_path <- file.path(output_path, "filtering_results.csv")