Merge pull request #6 from UMCUGenetics/develop

v1.1.2

clarity_epp.py

@@ -64,14 +64,20 @@ def export_manual_pipetting(args):
     elif args.type == 'multiplex_sequence_pool':
         clarity_epp.export.manual_pipetting.samplesheet_multiplex_sequence_pool(lims, args.process_id, args.output_file)
 
+
 def export_ped_file(args):
     """Export ped file."""
     clarity_epp.export.ped.create_file(lims, args.process_id, args.output_file)
 
 
-def export_samplelist(args):
-    """Generate samplelist."""
-    clarity_epp.export.samplelist.removed_samples(lims, args.output_file)
+def export_merge_file(args):
+    """Export merge file."""
+    clarity_epp.export.merge.create_file(lims, args.process_id, args.output_file)
+
+
+def export_removed_samples(args):
+    """Export removed sampels table."""
+    clarity_epp.export.sample.removed_samples(lims, args.output_file)
 
 
 def export_tapestation(args):
@@ -208,6 +214,10 @@ def placement_complete_step(args):
     parser_export_ped.add_argument('process_id', help='Clarity lims process id')
     parser_export_ped.set_defaults(func=export_ped_file)
 
+    parser_export_ped = subparser_export.add_parser('merge', help='Export merge file.', parents=[output_parser])
+    parser_export_ped.add_argument('process_id', help='Clarity lims process id')
+    parser_export_ped.set_defaults(func=export_merge_file)
+
     parser_export_workflow = subparser_export.add_parser('workflow', help='Export workflow result file.', parents=[output_parser])
     parser_export_workflow.add_argument('type', choices=['lab', 'data_analysis'], help='Workflow type')
     parser_export_workflow.add_argument('process_id', help='Clarity lims process id')
@@ -218,8 +228,8 @@ def placement_complete_step(args):
     parser_export_illumina.add_argument('artifact_id', help='Clarity lims samplesheet artifact id')
     parser_export_illumina.set_defaults(func=export_illumina)
 
-    parser_export_samplelist = subparser_export.add_parser('samplelist', help='Export samplelist.', parents=[output_parser])
-    parser_export_samplelist.set_defaults(func=export_samplelist)
+    parser_export_removed_samples = subparser_export.add_parser('removed_samples', help='Export removed sampels table.', parents=[output_parser])
+    parser_export_removed_samples.set_defaults(func=export_removed_samples)
 
     # Sample upload
     parser_upload = subparser.add_parser('upload', help='Upload samples or results to clarity lims')

clarity_epp/__init__.py

@@ -27,13 +27,15 @@ def get_sequence_name(sample):
     except KeyError:  # None DX sample, use sample.name as sequence name.
         sequence_name = sample.name
     else:
-        sequence_name = '{familienummer}{fam_status}{sex}{monsternummer}'.format(
-            familienummer=sample.udf['Dx Familienummer'],
-            fam_status=fam_status,
-            sex=sex,
-            monsternummer=sample.udf['Dx Monsternummer']
-        )
-
+        if not sample.name.startswith(sample.udf['Dx Familienummer']):
+            sequence_name = '{familienummer}{fam_status}{sex}{monsternummer}'.format(
+                familienummer=sample.udf['Dx Familienummer'],
+                fam_status=fam_status,
+                sex=sex,
+                monsternummer=sample.udf['Dx Monsternummer']
+            )
+        else:
+            sequence_name = sample.name
     return sequence_name
 
 

clarity_epp/export/__init__.py

@@ -6,8 +6,9 @@
 import illumina
 import labels
 import manual_pipetting
+import merge
 import ped
-import samplelist
+import sample
 import tapestation
 import tecan
 import workflow

clarity_epp/export/illumina.py

@@ -1,9 +1,9 @@
 """Illumina export functions."""
-import re
-
 from genologics.entities import Process, Artifact
 
 from .. import get_sequence_name
+import utils
+import config
 
 
 def update_samplesheet(lims, process_id, artifact_id, output_file):
@@ -22,16 +22,24 @@ def update_samplesheet(lims, process_id, artifact_id, output_file):
                     families[family] = {'samples': [], 'NICU': False, 'project_type': 'unknown_project', 'split_project_type': False}
 
                 # Update family information
-                if sample.udf['Dx NICU Spoed']:
-                    families[family]['NICU'] = True
-                    project_type = 'NICU_{0}'.format(sample.udf['Dx Familienummer'])
-                    families[family]['project_type'] = project_type
-                    families[family]['split_project_type'] = False
-
-                elif 'elidS30409818' in sample.udf['Dx Protocolomschrijving'] and not families[family]['NICU']:
-                    project_type = 'CREv2'
-                    families[family]['project_type'] = project_type
-                    families[family]['split_project_type'] = True
+                if sample.udf['Dx Onderzoeksreden'] == 'Research':  # Dx research sample
+                    for onderzoeksindicatie in config.research_onderzoeksindicatie_project:
+                        if sample.udf['Dx Onderzoeksindicatie'] == onderzoeksindicatie:
+                            project_type = config.research_onderzoeksindicatie_project[onderzoeksindicatie]
+                            families[family]['project_type'] = project_type
+                            families[family]['split_project_type'] = False
+                            break
+
+                else:  # Dx clinic sample
+                    if sample.udf['Dx NICU Spoed']:
+                        families[family]['NICU'] = True
+                        project_type = 'NICU_{0}'.format(sample.udf['Dx Familienummer'])
+                        families[family]['project_type'] = project_type
+                        families[family]['split_project_type'] = False
+                    elif 'elidS30409818' in sample.udf['Dx Protocolomschrijving'] and not families[family]['NICU']:
+                        project_type = 'CREv2'
+                        families[family]['project_type'] = project_type
+                        families[family]['split_project_type'] = True
 
             else:
                 family = sample.project.name
@@ -72,21 +80,46 @@ def update_samplesheet(lims, process_id, artifact_id, output_file):
         else:
             family_project_type['index'] += 1
 
+    # Check sequencer type -> NextSeq runs need to reverse complement 'index2' for dual barcodes and 'index' for single barcodes.
+    if 'nextseq' in process.type.name.lower():
+        nextseq_run = True
+    else:
+        nextseq_run = False
+
     # Edit clarity samplesheet
-    header = ''  # empty until [data] section
+    sample_header = ''  # empty until [data] section
+    settings_section = False
     samplesheet_artifact = Artifact(lims, id=artifact_id)
     file_id = samplesheet_artifact.files[0].id
 
     for line in lims.get_file_contents(id=file_id).rstrip().split('\n'):
-        if line.startswith('Sample_ID'):  # Samples header line
-            header = line.rstrip().split(',')
+        if line.startswith('[Settings]'):
+            output_file.write('{line}\n'.format(line=line))
+            output_file.write('Read1EndWithCycle,{value}\n'.format(value=process.udf['Read 1 Cycles']-1))
+            output_file.write('Read2EndWithCycle,{value}\n'.format(value=process.udf['Read 2 Cycles']-1))
+            settings_section = True
+
+        elif line.startswith('[Data]') and not settings_section:
+            output_file.write('[Settings]\n')
+            output_file.write('Read1EndWithCycle,{value}\n'.format(value=process.udf['Read 1 Cycles']-1))
+            output_file.write('Read2EndWithCycle,{value}\n'.format(value=process.udf['Read 2 Cycles']-1))
+            output_file.write('{line}\n'.format(line=line))
+
+        elif line.startswith('Sample_ID'):  # Samples header line
+            sample_header = line.rstrip().split(',')
+            sample_id_index = sample_header.index('Sample_ID')
+            sample_name_index = sample_header.index('Sample_Name')
+            sample_project_index = sample_header.index('Sample_Project')
+
+            if 'index2' in sample_header:
+                index_index = sample_header.index('index2')
+            else:
+                index_index = sample_header.index('index')
+
             output_file.write('{line}\n'.format(line=line))
 
-        elif header:  # Samples header seen, so continue with samples.
+        elif sample_header:  # Samples header seen, so continue with samples.
             data = line.rstrip().split(',')
-            sample_id_index = header.index('Sample_ID')
-            sample_name_index = header.index('Sample_Name')
-            sample_project_index = header.index('Sample_Project')
 
             # Set Sample_Project
             try:
@@ -97,6 +130,10 @@ def update_samplesheet(lims, process_id, artifact_id, output_file):
             # Overwrite Sample_ID with Sample_name to get correct conversion output folder structure
             data[sample_id_index] = data[sample_name_index]
 
+            # Reverse complement index for NextSeq runs
+            if nextseq_run:
+                data[index_index] = utils.reverse_complement(data[index_index])
+
             output_file.write('{line}\n'.format(line=','.join(data)))
         else:  # Leave other lines untouched.
             output_file.write('{line}\n'.format(line=line))