Merge pull request #306 from kedhammar/fix-anglerfish-udf-error

In Anglerfish parsing, only assign barcode-specific UDFs to barcoded samples
NationalGenomicsInfrastructure · Feb 9, 2024 · bb41d7a · bb41d7a
2 parents 631c48a + 9d3cfdc
commit bb41d7a
Show file tree

Hide file tree

Showing 2 changed files with 17 additions and 9 deletions.
diff --git a/VERSIONLOG.md b/VERSIONLOG.md
@@ -1,5 +1,9 @@
 # Scilifelab_epps Version Log
 
+## 20240208.1
+
+In Anglerfish parsing, only try to assign barcode-specific UDFs for barcoded samples.
+
 ## 20240130.1
 
 Handle Anglerfish result parsing for runs W/O ONT barcodes

diff --git a/scripts/parse_anglerfish_results.py b/scripts/parse_anglerfish_results.py
@@ -114,15 +114,6 @@ def ont_barcode_well2name(barcode_well: str) -> str:
 
 
 def fill_udfs(currentStep: Process, df: pd.DataFrame):
-    # Dictate which LIMS UDF corresponds to which column in the dataframe
-    udfs_to_cols = {
-        "# Reads": "num_reads",
-        "Avg. Read Length": "mean_read_len",
-        "Std. Read Length": "std_read_len",
-        "Representation Within Run (%)": "repr_total_pc",
-        "Representation Within Barcode (%)": "repr_within_barcode_pc",
-    }
-
     # Get Illumina pools
     illumina_pools = [
         input_art
@@ -160,12 +151,25 @@ def fill_udfs(currentStep: Process, df: pd.DataFrame):
                         ]
 
                     else:
+                        # Subset df to the current Illumina sample
                         df_sample = df[df["sample_name"] == illumina_sample.name]
 
                     assert (
                         len(df_sample) == 1
                     ), f"Multiple entries matching both Illumina sample name {illumina_sample.name} and ONT barcode {barcode_name} was found in the dataframe."
 
+                    # Determine which UDFs to assign
+                    udfs_to_cols = {
+                        "# Reads": "num_reads",
+                        "Avg. Read Length": "mean_read_len",
+                        "Std. Read Length": "std_read_len",
+                        "Representation Within Run (%)": "repr_total_pc",
+                    }
+                    if barcode_well:
+                        udfs_to_cols[
+                            "Representation Within Barcode (%)"
+                        ] = "repr_within_barcode_pc"
+
                     # Start putting UDFs
                     for udf, col in udfs_to_cols.items():
                         try: