Revert "move to new IGO_ID column for kickoff"

This reverts commit 80ad2f7.

python_tools/constants.py

@@ -98,15 +98,13 @@
 TITLE_FILE__SAMPLE_CLASS_COLUMN = "Class"
 TITLE_FILE__BARCODE_INDEX_1_COLUMN = "Barcode_index_1"
 TITLE_FILE__BARCODE_INDEX_2_COLUMN = "Barcode_index_2"
-TITLE_FILE__RUN_ID_COLUMN = "Run_ID"
 TITLE_FILE__LANE_COLUMN = "Lane"
 
 # Columns inferred from other columns defined above
 TITLE_FILE__SAMPLE_TYPE_COLUMN = "Sample_type"
 TITLE_FILE__BAIT_VERSION_COLUMN = "Bait_version"
 
 # Columns defined as constants
-TITLE_FILE__IGO_ID_COLUMN = "IGO_ID"
 TITLE_FILE__COLLAB_ID_COLUMN = "Collab_ID"
 
 # Columns inteferred from samplesheet metadata/operator column
@@ -202,7 +200,6 @@
     TITLE_FILE__BARCODE_ID_COLUMN,
     TITLE_FILE__POOL_COLUMN,
     TITLE_FILE__SAMPLE_ID_COLUMN,
-    TITLE_FILE__IGO_ID_COLUMN,
     TITLE_FILE__COLLAB_ID_COLUMN,
     TITLE_FILE__PATIENT_ID_COLUMN,
     TITLE_FILE__SAMPLE_CLASS_COLUMN,
@@ -214,7 +211,6 @@
     TITLE_FILE__ACCESSION_COLUMN,
     TITLE_FILE__BARCODE_INDEX_1_COLUMN,
     TITLE_FILE__BARCODE_INDEX_2_COLUMN,
-    TITLE_FILE__RUN_ID_COLUMN,
     TITLE_FILE__LANE_COLUMN,
 ]
 

python_tools/legacy_constants.py

@@ -132,7 +132,6 @@
 TITLE_FILE__BARCODE_ID_COLUMN               = 'Barcode'
 TITLE_FILE__POOL_COLUMN                     = 'Pool'
 TITLE_FILE__SAMPLE_ID_COLUMN                = 'Sample'
-TITLE_FILE__IGO_ID_COLUMN                   = 'IGO_ID'
 TITLE_FILE__COLLAB_ID_COLUMN                = 'Collab_ID'
 TITLE_FILE__PATIENT_ID_COLUMN               = 'Patient_ID'
 TITLE_FILE__CLASS_COLUMN                    = 'Class'
@@ -144,9 +143,8 @@
 TITLE_FILE__SEX_COLUMN                      = 'Sex'
 TITLE_FILE__BARCODE_INDEX_1_COLUMN          = 'Barcode_index_1'
 TITLE_FILE__BARCODE_INDEX_2_COLUMN          = 'Barcode_index_2'
-TITLE_FILE__RUN_ID_COLUMN                   = 'Run_ID'
 TITLE_FILE__LANE_COLUMN                     = 'Lane'
-TITLE_FILE__STUDY_ID_COLUMN                 = 'Study_ID'
+TITLE_FILE__STUDY_ID_COLUMN                 = 'Study ID'
 
 
 ##########################

python_tools/pipeline_kickoff/create_inputs_from_title_file.py

@@ -139,8 +139,8 @@ def remove_missing_samples_from_title_file(title_file, fastq1, title_file_path):
 
     # Todo: Should we instead raise an error and not continue?
     """
-    found_boolv = np.array([any([sample in f['path'] for f in fastq1]) for sample in title_file[TITLE_FILE__IGO_ID_COLUMN]])
-    samples_not_found = title_file.loc[~found_boolv, TITLE_FILE__IGO_ID_COLUMN]
+    found_boolv = np.array([any([sample in f['path'] for f in fastq1]) for sample in title_file[TITLE_FILE__COLLAB_ID_COLUMN]])
+    samples_not_found = title_file.loc[~found_boolv, TITLE_FILE__COLLAB_ID_COLUMN]
 
     if samples_not_found.shape[0] > 0:
         print(DELIMITER + 'Error: The following samples were missing either a read 1 fastq, read 2 fastq, or sample sheet. ' +
@@ -160,9 +160,9 @@ def remove_missing_fastq_samples(fastq1, fastq2, sample_sheet, title_file):
 
     Todo: For the SampleSheet files, this relies on the parent folder containing the sample name
     """
-    fastq1 = filter(lambda f: any([sid in f['path'] for sid in title_file[TITLE_FILE__IGO_ID_COLUMN]]), fastq1)
-    fastq2 = filter(lambda f: any([sid in f['path'] for sid in title_file[TITLE_FILE__IGO_ID_COLUMN]]), fastq2)
-    sample_sheet = filter(lambda s: any([sid in s['path'] for sid in title_file[TITLE_FILE__IGO_ID_COLUMN]]), sample_sheet)
+    fastq1 = filter(lambda f: any([sid in f['path'] for sid in title_file[TITLE_FILE__COLLAB_ID_COLUMN]]), fastq1)
+    fastq2 = filter(lambda f: any([sid in f['path'] for sid in title_file[TITLE_FILE__COLLAB_ID_COLUMN]]), fastq2)
+    sample_sheet = filter(lambda s: any([sid in s['path'] for sid in title_file[TITLE_FILE__COLLAB_ID_COLUMN]]), sample_sheet)
 
     return fastq1, fastq2, sample_sheet
 
@@ -472,14 +472,17 @@ def perform_validation(title_file, title_file_path, project_name):
     1. Sample IDs / Collab IDs must be unique
     2. Barcodes must be unique within each lane
     3. Sample_type is in ['Plasma', 'Buffy Coat']
-    4. Sample Class is in ['Tumor', 'Normal']   
+    4. Sample Class is in ['Tumor', 'Normal']
     """
     if not project_name in title_file_path:
         print('WARNING: project ID not found in title file path. Are you sure you are using the correct title file?')
 
     if np.sum(title_file[TITLE_FILE__SAMPLE_ID_COLUMN].duplicated()) > 0:
         raise Exception(DELIMITER + 'Duplicate sample IDs. Exiting.')
 
+    #if set([TITLE_FILE__COLLAB_ID_COLUMN]).issubset(title_file.columns) and np.sum(title_file[TITLE_FILE__COLLAB_ID_COLUMN].duplicated()) > 0:
+    #    raise Exception(DELIMITER + 'Duplicate investigator sample IDs. Exiting.')
+
     if np.sum(title_file[TITLE_FILE__SAMPLE_CLASS_COLUMN].isin(ALLOWED_SAMPLE_DESCRIPTION)) < len(title_file):
         raise Exception(DELIMITER + 'Not all sample classes are in {}'.format(",".join(ALLOWED_SAMPLE_DESCRIPTION)))
 

python_tools/util.py

@@ -376,7 +376,7 @@ def contained_in(sample_id, fastq):
             return 0
 
     if use_cmo_sample_id:
-        boolv = title_file[TITLE_FILE__IGO_ID_COLUMN].apply(contained_in, fastq=sample_object)
+        boolv = title_file[MANIFEST__CMO_SAMPLE_ID_COLUMN].apply(contained_in, fastq=sample_object)
     else:
         # Samples from IGO will use the COLLAB_ID
         boolv = title_file[TITLE_FILE__COLLAB_ID_COLUMN].apply(contained_in, fastq=sample_object)