Merge pull request #295 from chuan-wang/master

Change the way how samples are sorted

Author: ssjunnebo

taca/illumina/HiSeqX_Runs.py

@@ -374,8 +374,8 @@ def _generate_clean_samplesheet(ssparser, indexfile, fields_to_remove=None, rena
             sample['index2'] = index_dict_smartseq[smartseq_index][x][1]
 
     # Sort to get the added indicies from 10x in the right place
-    # Python 3 doesn't support sorting a list of dicts implicitly. Sort by lane and then index
-    ssparser.data.sort(key=lambda item: (item.get('Lane'), item.get('index')))
+    # Python 3 doesn't support sorting a list of dicts implicitly. Sort by lane and then Sample_ID
+    ssparser.data.sort(key=lambda item: (item.get('Lane'), item.get('Sample_ID')))
 
     if not fields_to_remove:
         fields_to_remove = []

tests/data/2014/FCIDXX.csv

@@ -6,7 +6,7 @@ Experiment Name,CIDXX
 151
 151
 [Data]
-Lane,SampleID,SampleName,SamplePlate,SampleWell,index,index2,Project,Description
+Lane,Sample_ID,Sample_Name,Sample_Plate,Sample_Well,index,index2,Project,Description
 1,Sample_P10000_1001,P10000_1001,CIDXX,1:1,SI-GA-A1,,A_Test_18_01,
 2,Sample_P10000_1005,P10000_1005,CIDXX,2:1,AGGTACC,,A_Test_18_01,
 3,Sample_P10000_1006,P10000_1006,CIDXX,3:1,SMARTSEQ-1A,,A_Test_18_01,

tests/test_illumina.py

@@ -731,16 +731,16 @@ def test_generate_clean_samplesheet(self):
 Experiment Name,CIDXX
 Investigator Name,Test
 [Data]
-Lane,SampleID,SampleName,SamplePlate,SampleWell,index,index2,Project,Description
+Lane,Sample_ID,Sample_Name,Sample_Plate,Sample_Well,index,index2,Project,Description
 1,Sample_P10000_1001,P10000_1001,CIDXX,1:1,AACCGTAA,,A_Test_18_01,
-1,Sample_P10000_1001,P10000_1001,CIDXX,1:1,CTAAACGG,,A_Test_18_01,
 1,Sample_P10000_1001,P10000_1001,CIDXX,1:1,GGTTTACT,,A_Test_18_01,
+1,Sample_P10000_1001,P10000_1001,CIDXX,1:1,CTAAACGG,,A_Test_18_01,
 1,Sample_P10000_1001,P10000_1001,CIDXX,1:1,TCGGCGTC,,A_Test_18_01,
 2,Sample_P10000_1005,P10000_1005,CIDXX,2:1,AGGTACC,,A_Test_18_01,
+3,Sample_P10000_1006,P10000_1006,CIDXX,3:1,TGTATCCGAA,CACAGGTGAA,A_Test_18_01,
 3,Sample_P10000_1006,P10000_1006,CIDXX,3:1,GAGCGCCTAT,TTGGTACGCG,A_Test_18_01,
-3,Sample_P10000_1006,P10000_1006,CIDXX,3:1,GCTAGGTCAA,CACAGGTGAA,A_Test_18_01,
 3,Sample_P10000_1006,P10000_1006,CIDXX,3:1,TAAGACGGTG,TTGGTACGCG,A_Test_18_01,
-3,Sample_P10000_1006,P10000_1006,CIDXX,3:1,TGTATCCGAA,CACAGGTGAA,A_Test_18_01,
+3,Sample_P10000_1006,P10000_1006,CIDXX,3:1,GCTAGGTCAA,CACAGGTGAA,A_Test_18_01,
 4,Sample_P10000_1007,P10000_1007,CIDXX,4:1,GTAACATGCG,AGTGTTACCT,A_Test_18_01,
 '''
         got_samplesheet = _generate_clean_samplesheet(ssparser, indexfile, rename_samples=True, rename_qPCR_suffix = True, fields_qPCR=[ssparser.dfield_snm])
@@ -893,7 +893,7 @@ def test_generate_samplesheet_subset(self):
 Experiment Name,CIDXX
 Investigator Name,Test
 [Data]
-Lane,SampleID,SampleName,SamplePlate,SampleWell,index,index2,Project,Description
+Lane,Sample_ID,Sample_Name,Sample_Plate,Sample_Well,index,index2,Project,Description
 1,Sample_P10000_1001,P10000_1001,CIDXX,1:1,SI-GA-A1,,A_Test_18_01,
 '''
         self.assertEqual(got_data, expected_data)