check for sc

marine.py

@@ -243,7 +243,7 @@ def generate_depths(output_folder, bam_filepaths, paired_end=False, barcode_tag=
                                 '{}/final_edit_info_no_coverage.tsv'.format(output_folder),
                             '{}/depths_source_cells.txt'.format(output_folder), 
                             '{}/final_edit_info.tsv'.format(output_folder), 
-                                header_columns, paired_end=paired_end)
+                                header_columns, barcode_tag=barcode_tag)
 
     coverage_total_time = time.perf_counter() - coverage_start_time
 

src/utils.py

@@ -652,14 +652,14 @@ def concat_and_write_bams_wrapper(params):
     concat_and_write_bams(contig, df_dict, header_string, split_bams_folder, barcode_tag=barcode_tag, number_of_expected_bams=number_of_expected_bams, verbose=verbose)
 
 
-def generate_and_run_bash_merge(output_folder, file1_path, file2_path, output_file_path, header_columns, paired_end=False):
+def generate_and_run_bash_merge(output_folder, file1_path, file2_path, output_file_path, header_columns, barcode_tag=None):
     # Convert header list into a tab-separated string
     header = "\t".join(header_columns)
 
-    position_adjustment = '1'
-    if paired_end:
-        position_adjustment = '0' 
-    print(f"position adjustment is {position_adjustment} (paired_end is {paired_end})")
+    position_adjustment = '1' # for samtools view
+    if not barcode_tag:
+        position_adjustment = '0'  # for samtools depth
+    print(f"position adjustment is {position_adjustment} (barcode_tag is {barcode_tag})")
 
     # Generate the Bash command for processing
     bash_command = f"""#!/bin/bash

tests/integration_tests.ipynb

@@ -2889,7 +2889,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "id": "f5c3ed3e-13dd-4399-924e-3d1ac17ce387",
    "metadata": {},
    "outputs": [
@@ -3012,6 +3012,7 @@
       "\t >>> long_read_sc_test passed! <<<\n",
       "\n",
       "Checking that analyzing a single-cell dataset in 'bulk' mode (i.e. not specificying the 'CB' barcode) yields the exact same positions and base changes, but with counts and coverages aggregated rather than at a single-cell resolution\n",
+      "grouped_sc_rows: 62, bulk_rows: 26\n",
       "Exception: \n",
       "\n",
       "\t ~~~ single cell vs bulk modes on sc dataset equivalency test FAILED! ~~~\n",
@@ -3359,6 +3360,7 @@
     "    bulk_rows.append((r['contig'], r['position'], r['strand_conversion']))\n",
     "\n",
     "try:\n",
+    "    print(\"grouped_sc_rows: {}, bulk_rows: {}\".format(len(grouped_sc_rows), len(bulk_rows)))\n",
     "    assert(grouped_sc_rows == bulk_rows)\n",
     "    for bulk_item, grouped_sc_item in zip(bulk_rows, grouped_sc_rows):\n",
     "        assert(bulk_item == grouped_sc_item)\n",