v1.9.0 to develop

clarity_epp/__init__.py

@@ -38,8 +38,8 @@ def get_sample_artifacts_from_pool(lims, pool_artifact):
                 # Check if sample_artifact with 2 samples are from the same person
                 if len(sample_artifact.samples) == 2:
                     if (
-                        'Dx Persoons ID' in sample_artifact.samples[0].udf or
-                        'Dx Persoons ID' in sample_artifact.samples[1].udf or
+                        'Dx Persoons ID' in sample_artifact.samples[0].udf and
+                        'Dx Persoons ID' in sample_artifact.samples[1].udf and
                         sample_artifact.samples[0].udf['Dx Persoons ID'] == sample_artifact.samples[1].udf['Dx Persoons ID']
                     ):
                         sample_artifacts.append(sample_artifact)

clarity_epp/export/illumina.py

@@ -231,14 +231,16 @@ def create_samplesheet(lims, process_id, output_file):
     process = Process(lims, id=process_id)
     sequencer_conversion_settings = config.sequencer_conversion_settings[process.type.name]
 
+    # Get output container assume one flowcell per sequencing run
+    output_container = process.output_containers()[0]
+
     # Get samples samples per lane
-    samplesheet_samples = []
-    for lane in process.analytes()[0]:
-        sample_artifacts = get_sample_artifacts_from_pool(lims, process.analytes()[0][0])
-        samplesheet_samples.append(
-            get_samplesheet_samples(
-                sample_artifacts, process, sequencer_conversion_settings['index_2_conversion_orientation']
-            )
+    samplesheet_samples = {}
+    for lane_idx, lane_artifact in output_container.get_placements().items():
+        lane_idx = lane_idx.split(':')[0]
+        sample_artifacts = get_sample_artifacts_from_pool(lims, lane_artifact)
+        samplesheet_samples[lane_idx] = get_samplesheet_samples(
+            sample_artifacts, process, sequencer_conversion_settings['index_2_conversion_orientation']
         )
 
     # Create SampleSheet
@@ -264,6 +266,7 @@ def create_samplesheet(lims, process_id, output_file):
         "FindAdaptersWithIndels,TRUE",
         "BarcodeMismatchesIndex1,0",
         "BarcodeMismatchesIndex2,0",
+        "TrimUMI,TRUE",
         # BCLConvert_Data
         "[BCLConvert_Data]"
     ]
@@ -278,17 +281,17 @@ def create_samplesheet(lims, process_id, output_file):
     sample_sheet.append(bcl_convert_data_header)
 
     # Add samples to SampleSheet
-    for lane, lane_samples in enumerate(samplesheet_samples):
+    for lane, lane_samples in sorted(samplesheet_samples.items()):
         for sample in lane_samples:
             bcl_convert_data_row = "{sample_name},{index_1},{index_2},{override_cycles},{project}".format(
                     sample_name=sample,
-                    index_1=samplesheet_samples[lane][sample]['index_1'],
-                    index_2=samplesheet_samples[lane][sample]['index_2'],
-                    override_cycles=samplesheet_samples[lane][sample]['override_cycles'],
-                    project=samplesheet_samples[lane][sample]['project']
+                    index_1=lane_samples[sample]['index_1'],
+                    index_2=lane_samples[sample]['index_2'],
+                    override_cycles=lane_samples[sample]['override_cycles'],
+                    project=lane_samples[sample]['project']
                 )
             if multiple_lanes:  # Add lane number to row if multiple lanes conversion
-                bcl_convert_data_row = f"{lane+1},{bcl_convert_data_row}"
+                bcl_convert_data_row = f"{lane},{bcl_convert_data_row}"
             sample_sheet.append(bcl_convert_data_row)
 
     # Write SampleSheet to file

clarity_epp/export/merge.py

@@ -7,7 +7,17 @@
 def create_file(lims, process_id, output_file):
     """Create mege file."""
     process = Process(lims, id=process_id)
-    sample_artifacts = get_sample_artifacts_from_pool(lims, process.analytes()[0][0])
+
+    # Get output container assume one flowcell per sequencing run
+    output_container = process.output_containers()[0]
+
+    # Get unique sample artifacts in run
+    # TODO: This is a copy of the code from ped.py. It should be refactored to a common function.
+    sample_artifacts = []
+    for lane_artifact in output_container.get_placements().values():
+        for sample_artifact in get_sample_artifacts_from_pool(lims, lane_artifact):
+            if sample_artifact not in sample_artifacts:
+                sample_artifacts.append(sample_artifact)
 
     output_file.write('Sample\tMerge 1 Sample\tMerge 1 Sequencing Run\tMerge 2 Sample\tMerge 2 Sequencing Run\n')
 

clarity_epp/export/ped.py

@@ -7,7 +7,18 @@
 def create_file(lims, process_id, output_file):
     """Create ped file."""
     process = Process(lims, id=process_id)
-    sample_artifacts = get_sample_artifacts_from_pool(lims, process.analytes()[0][0])
+
+    # Get output container assume one flowcell per sequencing run
+    output_container = process.output_containers()[0]
+
+    # Get unique sample artifacts in run
+    # TODO: This is a copy of the code from merge.py. It should be refactored to a common function.
+    sample_artifacts = []
+    for lane_artifact in output_container.get_placements().values():
+        for sample_artifact in get_sample_artifacts_from_pool(lims, lane_artifact):
+            if sample_artifact not in sample_artifacts:
+                sample_artifacts.append(sample_artifact)
+
     ped_families = {}
 
     for sample_artifact in sample_artifacts:

clarity_epp/placement/artifact.py

@@ -3,6 +3,7 @@
 from genologics.entities import Process, Workflow
 
 from .. import get_sequence_name
+from clarity_epp.export.utils import sort_artifact_list
 import config
 
 
@@ -17,19 +18,23 @@ def set_sequence_name(lims, process_id):
 def set_runid_name(lims, process_id):
     """Change artifact name to run id."""
     process = Process(lims, id=process_id)
-    analyte = process.analytes()[0][0]
     input_artifact = process.all_inputs()[0]
 
-    container_name = analyte.container.name
+    # Fix for NovaSeqXPlus workflow configuration
+    # TODO: Set NovaSeqXPlus step to 'Analysis' type.
+    if 'NovaSeqXPlus' in input_artifact.parent_process.type.name:
+        input_artifact = input_artifact.parent_process.all_inputs()[0]
 
     # Find sequencing process
     # Assume one sequence process per input artifact
     for sequence_process_type in config.sequence_process_types:
         sequence_processes = lims.get_processes(type=sequence_process_type, inputartifactlimsid=input_artifact.id)
         for sequence_process in sequence_processes:
-            if sequence_process.analytes()[0][0].container.name == container_name:
-                analyte.name = sequence_process.udf['Run ID']
-                analyte.put()
+            sequence_process_lanes = sorted(sequence_process.analytes()[0], key=sort_artifact_list)
+            for lane_idx, lane in enumerate(sorted(process.analytes()[0], key=sort_artifact_list)):
+                if sequence_process_lanes[lane_idx].container.name == lane.container.name:
+                    lane.name = sequence_process.udf['Run ID']
+                    lane.put()
 
 
 def route_to_workflow(lims, process_id, workflow):

clarity_epp/placement/pool.py

@@ -14,6 +14,11 @@ def unpooling(lims, process_id):
         pool_artifact = process.all_inputs()[0]
         pool_artifact_parent_process = pool_artifact.parent_process
 
+        # Fix for NovaSeqXPlus workflow configuration
+        # TODO: Set NovaSeqXPlus step to 'Analysis' type.
+        if 'laden' not in pool_artifact_parent_process.type.name.lower():
+            pool_artifact_parent_process = pool_artifact_parent_process.all_inputs()[0].parent_process
+
         run_id = pool_artifact.name  # Assume run id is set as pool name using placement/artifact/set_runid_name
         sample_artifacts = []  # sample artifacts before pooling
         sample_projects = {}
@@ -35,22 +40,22 @@ def unpooling(lims, process_id):
                         sample_projects[data[sample_index]] = data[project_index]
 
         # Parse sequencing run samples and move Dx samples to post sequencing workflow
-        for sample_artifact in get_sample_artifacts_from_pool(lims, pool_artifact):
-            sample = sample_artifact.samples[0]   # Asume all samples metadata is identical.
-
-            # Set sample sequencing run and project
-            sample_artifact.udf['Dx Sequencing Run ID'] = run_id
-            # Use sample.name for external (clarity_portal) samples
-            if 'Sample Type' in sample.udf and 'library' in sample.udf['Sample Type']:
-                sample_artifact.udf['Dx Sequencing Run Project'] = sample_projects[sample.name]
-            else:  # Use sample_artifact.name for Dx samples (upload via Helix)
-                sample_artifact.udf['Dx Sequencing Run Project'] = sample_projects[sample_artifact.name]
-            sample_artifact.put()
-
-            # Only move DX production samples to post sequencing workflow
-            if sample.project and sample.project.udf['Application'] == 'DX':
-                sample_artifacts.append(sample_artifact)
-
+        for lane in process.all_inputs():
+            for sample_artifact in get_sample_artifacts_from_pool(lims, lane):
+                sample = sample_artifact.samples[0]   # Asume all samples metadata is identical.
+
+                # Set sample sequencing run and project
+                sample_artifact.udf['Dx Sequencing Run ID'] = run_id
+                # Use sample.name for external (clarity_portal) samples
+                if 'Sample Type' in sample.udf and 'library' in sample.udf['Sample Type']:
+                    sample_artifact.udf['Dx Sequencing Run Project'] = sample_projects[sample.name]
+                else:  # Use sample_artifact.name for Dx samples (upload via Helix)
+                    sample_artifact.udf['Dx Sequencing Run Project'] = sample_projects[sample_artifact.name]
+                sample_artifact.put()
+
+                # Only move DX production samples to post sequencing workflow
+                if sample_artifact not in sample_artifacts and sample.project and sample.project.udf['Application'] == 'DX':
+                    sample_artifacts.append(sample_artifact)
         lims.route_artifacts(sample_artifacts, workflow_uri=Workflow(lims, id=config.post_sequencing_workflow).uri)
 
 

clarity_epp/qc/qubit.py

@@ -9,7 +9,7 @@ def set_qc_flag(lims, process_id, cutoff=10):
     """Set qubit qc flags based on Dx Concentratie fluorescentie (ng/ul) values."""
     process = Process(lims, id=process_id)
     artifacts = process.result_files()
-    concentration_range = map(float, re.findall('[\d\.]+', process.udf['Concentratiebereik (ng/ul)']))
+    concentration_range = list(map(float, re.findall('[\d\.]+', process.udf['Concentratiebereik (ng/ul)'])))
     samples_measurements = {}
 
     for artifact in artifacts:

clarity_epp/upload/tecan.py

@@ -10,7 +10,7 @@
 def results_qc(lims, process_id):
     """Upload tecan results to artifacts."""
     process = Process(lims, id=process_id)
-    concentration_range = map(float, re.findall('[\d\.]+', process.udf['Concentratiebereik (ng/ul)']))
+    concentration_range = list(map(float, re.findall('[\d\.]+', process.udf['Concentratiebereik (ng/ul)'])))
 
     # Parse output file
     for output in process.all_outputs(unique=True):
@@ -21,7 +21,7 @@ def results_qc(lims, process_id):
 
             measurements = {}
             sample_measurements = {}
-            for line in lims.get_file_contents(tecan_result_file.id).data.split('\n'):
+            for line in lims.get_file_contents(tecan_result_file.id).data.decode('utf-8').split('\n'):
                 if not line.startswith('<>'):
                     data = line.rstrip().split('\t')
                     for index, value in enumerate(data[1:]):

config.py

@@ -88,6 +88,7 @@
     'Dx NextSeq Run v1.0', 'Dx NextSeq Run v1.1',
     'Dx Automated NovaSeq Run (standaard) v1.0', 'Dx Automated NovaSeq Run (standaard) v1.1',
     'AUTOMATED - NovaSeq Run (NovaSeq 6000 v3.1)',
+    'Dx NovaSeqXPlus Run v1.0'
 ]
 
 # BCLConvert conversion settings