fix barcode reading (fix does not affect any results in practice)

Author: andrewprzh

misc/assess_barcode_quality.py

@@ -132,7 +132,7 @@ def assess_single_barcode_mode(
     # Process input file
     with open(input_file) as f:
         for line in f:
-            if line.startswith('#'):
+            if line.startswith('#') or line.startswith('read_id\t'):
                 continue
 
             cols = line.strip().split('\t')
@@ -237,7 +237,7 @@ def assess_split_barcode_mode(
 
     with open(input_file) as f:
         for line in f:
-            if line.startswith('#'):
+            if line.startswith('#') or line.startswith('read_id\t'):
                 continue
 
             cols = line.strip().split('\t')

misc/inject_bam_tags.py

@@ -28,7 +28,7 @@ def load_barcoded_reads(barcoded_reads_path: str) -> dict[str, tuple[str, str]]:
     barcode_dict: dict[str, tuple[str, str]] = {}
     with open(barcoded_reads_path) as f:
         for line in f:
-            if line.startswith("#"):
+            if line.startswith("#") or line.startswith("read_id\t"):
                 continue
             tokens = line.strip().split("\t")
             if len(tokens) < 3:

src/parallel_workers.py

@@ -99,7 +99,7 @@ def load_barcode_dict(sample, chr_id):
         if os.path.exists(barcode_file):
             logger.debug(f"Loading barcodes from {barcode_file}")
             for line in open(barcode_file):
-                if line.startswith("#"):
+                if line.startswith("#") or line.startswith("read_id\t"):
                     continue
                 parts = line.strip().split('\t')
                 if len(parts) >= 3:

src/string_pools.py

@@ -305,7 +305,7 @@ def load_barcode_pool(self, barcode_file: str):
         umis = set()
         with open(barcode_file, 'r') as f:
             for line in f:
-                if line.startswith('#'):
+                if line.startswith('#') or line.startswith('read_id\t'):
                     continue
                 parts = line.strip().split('\t')
                 if len(parts) >= 2 and parts[1]:

src/table_splitter.py

@@ -179,7 +179,7 @@ def process_table_for_chromosomes(worker_id, input_tsvs, my_chromosomes, bam_fil
 
             try:
                 for line in file_handle:
-                    if line.startswith("#") or not line.strip():
+                    if line.startswith("#") or line.startswith("read_id\t") or not line.strip():
                         continue
 
                     total_reads_processed += 1