Add q30 check when calculating sample reads (#3680)

### Added

- Check for q30 when calculating Sample.reads
- Tests for when the q30 of a lane is below the threshold for the sequencer type

cg/services/illumina/post_processing/post_processing_service.py

@@ -134,7 +134,9 @@ def update_samples_for_metrics(
     ) -> None:
         unique_samples_on_run: list[str] = self.get_unique_samples_from_run(sample_metrics)
         for sample_id in unique_samples_on_run:
-            self.status_db.update_sample_reads_illumina(internal_id=sample_id)
+            self.status_db.update_sample_reads_illumina(
+                internal_id=sample_id, sequencer_type=sequencing_run.sequencer_type
+            )
             self.status_db.update_sample_sequenced_at(
                 sample_id, date=sequencing_run.sequencing_completed_at
             )

cg/store/crud/update.py

@@ -6,6 +6,8 @@
 
 from cg.constants import SequencingRunDataAvailability
 from cg.constants.constants import SequencingQCStatus
+from cg.constants.sequencing import Sequencers
+from cg.services.illumina.post_processing.utils import get_q30_threshold
 from cg.store.base import BaseHandler
 from cg.store.models import (
     Case,
@@ -58,12 +60,17 @@ def update_sequencing_qc_status(self, case: Case, status: SequencingQCStatus) ->
         case.aggregated_sequencing_qc = status
         self.session.commit()
 
-    def update_sample_reads_illumina(self, internal_id: str):
+    def update_sample_reads_illumina(self, internal_id: str, sequencer_type: Sequencers):
         sample: Sample = self.get_sample_by_internal_id(internal_id)
         total_reads_for_sample: int = 0
         sample_metrics: list[IlluminaSampleSequencingMetrics] = sample.sample_run_metrics
+
+        q30_threshold: int = get_q30_threshold(sequencer_type)
+
         for sample_metric in sample_metrics:
-            total_reads_for_sample += sample_metric.total_reads_in_lane
+            if sample_metric.base_passing_q30_percent >= q30_threshold:
+                total_reads_for_sample += sample_metric.total_reads_in_lane
+
         sample.reads = total_reads_for_sample
         self.session.commit()
 

tests/store/crud/update/test_update.py

@@ -1,7 +1,8 @@
 from datetime import datetime
 
 from cg.constants import SequencingRunDataAvailability
-from cg.store.models import IlluminaSequencingRun, Sample
+from cg.constants.sequencing import Sequencers
+from cg.store.models import IlluminaSequencingRun, Sample, IlluminaSampleSequencingMetrics
 from cg.store.store import Store
 
 
@@ -50,7 +51,7 @@ def test_update_sample_reads_illumina(
 
     # WHEN updating the sample reads for a sequencing run
     store_with_illumina_sequencing_data.update_sample_reads_illumina(
-        internal_id=selected_novaseq_x_sample_ids[0]
+        internal_id=selected_novaseq_x_sample_ids[0], sequencer_type=Sequencers.NOVASEQX
     )
 
     # THEN the total reads for the sample is updated
@@ -61,6 +62,26 @@ def test_update_sample_reads_illumina(
     assert sample.reads == total_reads_for_sample
 
 
+def test_update_sample_reads_illumina_fail_q30(
+    store_with_illumina_sequencing_data: Store, selected_novaseq_x_sample_ids: list[str]
+):
+    # GIVEN a store with Illumina Sequencing Runs and a sample id
+    sample: Sample = store_with_illumina_sequencing_data.get_sample_by_internal_id(
+        selected_novaseq_x_sample_ids[0]
+    )
+    assert sample.reads == 0
+    # GIVEN that the q30 for the lane is below the threshold for the sequencer type
+    sample.sample_run_metrics[0].base_passing_q30_percent = 30
+
+    # WHEN updating the sample reads for a sequencing run
+    store_with_illumina_sequencing_data.update_sample_reads_illumina(
+        internal_id=selected_novaseq_x_sample_ids[0], sequencer_type=Sequencers.NOVASEQX
+    )
+
+    # THEN the total reads for the sample is updated
+    assert sample.reads == 0
+
+
 def test_update_sample_last_sequenced_at(
     store_with_illumina_sequencing_data: Store,
     selected_novaseq_x_sample_ids: list[str],