Some bug fixes

Author: CodingBash

crispr-ambiguous-mapping/crispr_ambiguous_mapping/processing/crispr_guide_counting.py

@@ -26,7 +26,7 @@
 from .crispr_count_processing import get_counterseries_all_results
 from ..quality_control.crispr_mapping_quality_control import perform_counts_quality_control
 from ..models.mapping_models import GeneralGuideCountType, GeneralMappingInferenceDict
-from ..models.mapping_models import AllMatchSetWhitelistReporterCounterSeriesResults, WhitelistReporterCountsResult, SampleWhitelistReporterCountsResult, InferenceResult, CountInput
+from ..models.mapping_models import AllMatchSetWhitelistReporterCounterSeriesResults, WhitelistReporterCountsResult, SampleWhitelistReporterCountsResult, InferenceResult, CountInput, QualityControlResult
 
 
 # TODO: There will probably be some type errors with the DefaultDict when testing on non UMI (since it requires CounterType), so make sure to test with different variations of inputs
@@ -164,7 +164,7 @@ def pad_series(series):
     # Some organization: Map the inferred result of each observed sequence to a dict with the inferred result and correspoding count
 
     if contains_sample_barcode:
-        observed_guide_reporter_umi_counts_inferred_all_samples: DefaultDict[str, GeneralMappingInferenceDict] = defaultdict(GeneralMappingInferenceDict)
+        observed_guide_reporter_umi_counts_inferred_all_samples: DefaultDict[str, GeneralMappingInferenceDict] = defaultdict(lambda: defaultdict(dict))
         # Add all cell_barcodes
         for observed_guide_reporter_key_index, observed_guide_reporter_key in enumerate(observed_guide_reporter_list): # Iterate through each observed guide key
             observed_guide_reporter_cell_counts = observed_guide_reporter_umi_counts[observed_guide_reporter_key]
@@ -184,17 +184,20 @@ def pad_series(series):
 
         # GET THE MAPPED COUNT SERIES BASED ON THE INFERENCE RESULTS
         print("Prepare the processed count series ")
-        all_cell_barcodes: List[str] = observed_guide_reporter_umi_counts_inferred_all_samples.keys()
-        all_match_set_whitelist_reporter_counter_series_results_all_samples: DefaultDict[str, AllMatchSetWhitelistReporterCounterSeriesResults]
-        quality_control_result_all_samples: DefaultDict[str, GeneralMappingInferenceDict]
-        for cell_barcode in all_cell_barcodes:
+        all_cell_barcodes: List[str] = list(observed_guide_reporter_umi_counts_inferred_all_samples.keys())
+        all_match_set_whitelist_reporter_counter_series_results_all_samples: DefaultDict[str, AllMatchSetWhitelistReporterCounterSeriesResults] = defaultdict(AllMatchSetWhitelistReporterCounterSeriesResults)
+        quality_control_result_all_samples: DefaultDict[str, QualityControlResult] = defaultdict(QualityControlResult)
+        for cell_barcode_i, cell_barcode in enumerate(all_cell_barcodes):
             observed_guide_reporter_umi_counts_inferred_per_sample = observed_guide_reporter_umi_counts_inferred_all_samples[cell_barcode]
             all_match_set_whitelist_reporter_counter_series_results_per_sample = get_counterseries_all_results(observed_guide_reporter_umi_counts_inferred_per_sample, whitelist_guide_reporter_df, contains_guide_barcode, contains_guide_surrogate, contains_guide_umi)
-            quality_control_result_per_sample = perform_counts_quality_control(observed_guide_reporter_umi_counts_inferred_per_sample, contains_guide_umi, contains_guide_surrogate, contains_guide_barcode)
+            quality_control_result_per_sample: QualityControlResult = perform_counts_quality_control(observed_guide_reporter_umi_counts_inferred_per_sample, contains_guide_umi, contains_guide_surrogate, contains_guide_barcode)
 
             all_match_set_whitelist_reporter_counter_series_results_all_samples[cell_barcode] = all_match_set_whitelist_reporter_counter_series_results_per_sample
             quality_control_result_all_samples[cell_barcode] = quality_control_result_per_sample
 
+            if cell_barcode_i % 2500 == 0:
+                print(f"- Processed cell_barcode {cell_barcode_i} out of {len(all_cell_barcodes)}")
+
 
         count_input= CountInput(whitelist_guide_reporter_df=whitelist_guide_reporter_df,
             contains_surrogate=contains_guide_surrogate,
@@ -232,7 +235,7 @@ def pad_series(series):
         print(f"{(after_counterseries_time-after_inference_processing_time).seconds} seconds for counter series generation")
 
         print("Preparing quality control")
-        quality_control_result = perform_counts_quality_control(observed_guide_reporter_umi_counts_inferred, contains_guide_umi, contains_guide_surrogate, contains_guide_barcode)
+        quality_control_result: QualityControlResult = perform_counts_quality_control(observed_guide_reporter_umi_counts_inferred, contains_guide_umi, contains_guide_surrogate, contains_guide_barcode)
 
         after_qualitycontrol_time = datetime.now()
         print(f"{(after_qualitycontrol_time-after_counterseries_time).seconds} seconds for quality control")