kl-metapool beta.zip (#141)

antgonza · AmandaBirmingham · web-flow · commit 7cef79326efe · 2025-08-30T15:01:13.000-06:00
* kl-metapool beta.zip

* 100 -&gt; 90

* illumina/good_sheet1.csv 100 -&gt; 90

* good-sample-sheet_w_context.csv

* good_sheet_w_replicates.csv

* good_sheet1.csv

* duplicate_sample-sample-sheet.csv

* metatranscriptomic

* 100-&gt;0

* fix errors

* fix TestPipeline.test_generate_sample_information_files_multiple_preps_w_context

* kl-metapool main

* scipy

* sklearn

* sklearn -&gt; scikit-learn

* rm changes to conda install

* Remove contains_replicates column in bioinformatics table

* Change sheet type to standard_metat for metatv0

* Put back sheet type as standard_metag

* add Library Well

---------

Co-authored-by: Amanda Birmingham &lt;AmandaBirmingham@users.noreply.github.com&gt;
diff --git a/src/qp_klp/StandardMetagenomicWorkflow.py b/src/qp_klp/StandardMetagenomicWorkflow.py
@@ -221,6 +221,7 @@ def __init__(self, **kwargs):
                 'Project Plate': '',
                 'Project Name': project_name,
                 'Well': '',
+                'Library Well': '',
                 '# Reads': f'{_d.reads.sum()}',
                 'Lane': '1'}
             data.append(sample)
diff --git a/tests/data/bad-sample-sheet-bool-test.csv b/tests/data/bad-sample-sheet-bool-test.csv
diff --git a/tests/data/bad-sample-sheet-metagenomics.csv b/tests/data/bad-sample-sheet-metagenomics.csv
@@ -1,7 +1,7 @@
 [Header],,,,,,,,,,,
 IEMFileVersion,4,,,,,,,,,,
 SheetType,standard_metag,,,,,,,,,,
-SheetVersion,100,,,,,,,,,,
+SheetVersion,90,,,,,,,,,,
 Investigator Name,Knight,,,,,,,,,,
 Experiment Name,RKL0042,,,,,,,,,,
 Date,2020-02-26,,,,,,,,,,
@@ -19,7 +19,7 @@ Chemistry,Default,,,,,,,,,,
 ReverseComplement,0,,,,,,,,,,
 ,,,,,,,,,,,
 [Data],,,,,,,,,,,
-Lane,Sample_ID,Sample_Name,Sample_Plate,well_id_384,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,syndna_pool_number,Well_description
+Lane,Sample_ID,Sample_Name,Sample_Plate,Sample_Well,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,syndna_pool_number,Well_description
 1,CDPH-SAL__Salmonella__Typhi__MDL-143,CDPH-SAL..Salmonella..Typhi..MDL-143,StudyB_11661_P40,A1,iTru7_107_07,CCGACTAT,iTru5_01_A,ACCGACAA,StudyB_11661,pool1,CDPH-SAL_Salmonella Typhi_MDL-143
 1,CDPH-SAL_Salmonella_Typhi_MDL-144,CDPH-SAL.Salmonella.Typhi.MDL-144,StudyB_11661_P40,C1,iTru7_107_08,CCGACTAT,iTru5_02_A,CTTCGCAA,StudyB_11661,pool2,CDPH-SAL_Salmonella Typhi_MDL-144
 1,CDPH-SAL_Salmonella_Typhi_MDL-145,CDPH-SAL.Salmonella.Typhi.MDL-145,StudyB_11661_P40,E1,iTru7_107_09,GCCTTGTT,iTru5_03_A,AACACCAC,StudyB_11661,pool1,CDPH-SAL_Salmonella Typhi_MDL-145
diff --git a/tests/data/duplicate_sample-sample-sheet.csv b/tests/data/duplicate_sample-sample-sheet.csv
@@ -1,7 +1,7 @@
 [Header],,,,,,,,,,,
 IEMFileVersion,4,,,,,,,,,,
 SheetType,standard_metag,,,,,,,,,,
-SheetVersion,100,,,,,,,,,,
+SheetVersion,90,,,,,,,,,,
 Investigator Name,Knight,,,,,,,,,,
 Experiment Name,RKL0042,,,,,,,,,,
 Date,2020-02-26,,,,,,,,,,
@@ -19,7 +19,7 @@ Chemistry,Default,,,,,,,,,,
 ReverseComplement,0,,,,,,,,,,
 ,,,,,,,,,,,
 [Data],,,,,,,,,,,
-Lane,Sample_ID,Sample_Name,Sample_Plate,well_id_384,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,syndna_pool_number,Well_description
+Lane,Sample_ID,Sample_Name,Sample_Plate,Sample_Well,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,syndna_pool_number,Well_description
 1,CDPH-SAL_Salmonella_Typhi_MDL-143,CDPH-SAL.Salmonella.Typhi.MDL-143,StudyB_11661_P40,A1,iTru7_107_07,CCGACTAT,iTru5_01_A,ACCGACAA,StudyB_11661,pool1,CDPH-SAL_Salmonella Typhi_MDL-143
 1,CDPH-SAL_Salmonella_Typhi_MDL-144,CDPH-SAL.Salmonella.Typhi.MDL-144,StudyB_11661_P40,C1,iTru7_107_08,CCGACTAT,iTru5_02_A,CTTCGCAA,StudyB_11661,pool2,CDPH-SAL_Salmonella Typhi_MDL-144
 1,CDPH-SAL_Salmonella_Typhi_MDL-145,CDPH-SAL.Salmonella.Typhi.MDL-145,StudyB_11661_P40,E1,iTru7_107_09,GCCTTGTT,iTru5_03_A,AACACCAC,StudyB_11661,pool1,CDPH-SAL_Salmonella Typhi_MDL-145
diff --git a/tests/data/good-sample-sheet.csv b/tests/data/good-sample-sheet.csv
@@ -1,7 +1,7 @@
 [Header],,,,,,,,,,,
 IEMFileVersion,4,,,,,,,,,,
 SheetType,standard_metag,,,,,,,,,,
-SheetVersion,100,,,,,,,,,,
+SheetVersion,90,,,,,,,,,,
 Investigator Name,Knight,,,,,,,,,,
 Experiment Name,RKL0042,,,,,,,,,,
 Date,2020-02-26,,,,,,,,,,
@@ -19,7 +19,7 @@ Chemistry,Default,,,,,,,,,,
 ReverseComplement,0,,,,,,,,,,
 ,,,,,,,,,,,
 [Data],,,,,,,,,,,
-Lane,Sample_ID,Sample_Name,Sample_Plate,well_id_384,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,syndna_pool_number,Well_description
+Lane,Sample_ID,Sample_Name,Sample_Plate,Sample_Well,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,syndna_pool_number,Well_description
 1,CDPH-SAL__Salmonella__Typhi__MDL-143,CDPH-SAL..Salmonella..Typhi..MDL-143,StudyB_11661_P40,A1,iTru7_107_07,CCGACTAT,iTru5_01_A,ACCGACAA,StudyB_11661,pool1,CDPH-SAL_Salmonella Typhi_MDL-143
 1,CDPH-SAL_Salmonella_Typhi_MDL-144,CDPH-SAL.Salmonella.Typhi.MDL-144,StudyB_11661_P40,C1,iTru7_107_08,CCGACTAT,iTru5_02_A,CTTCGCAA,StudyB_11661,pool2,CDPH-SAL_Salmonella Typhi_MDL-144
 1,CDPH-SAL_Salmonella_Typhi_MDL-145,CDPH-SAL.Salmonella.Typhi.MDL-145,StudyB_11661_P40,E1,iTru7_107_09,GCCTTGTT,iTru5_03_A,AACACCAC,StudyB_11661,pool1,CDPH-SAL_Salmonella Typhi_MDL-145
diff --git a/tests/data/good-sample-sheet_w_context.csv b/tests/data/good-sample-sheet_w_context.csv
@@ -805,10 +805,10 @@ Lane,Sample_ID,Sample_Name,Sample_Plate,well_id_384,I7_Index_ID,index,I5_Index_I
 1,EP479894B04,EP479894B04,StudyA_13059_P4,P24,iTru7_107_08,AGCTAACC,iTru5_124_H,AACGCCTT,StudyA_13059,pool1,EP479894B04
 ,,,,,,,,,,,
 [Bioinformatics],,,,,,,,,,,
-Sample_Project,QiitaID,BarcodesAreRC,ForwardAdapter,ReverseAdapter,HumanFiltering,library_construction_protocol,experiment_design_description,,,,
-StudyA_13059,13059,FALSE,AACC,GGTT,FALSE,Nextera,Equipment,,,,
-StudyB_11661,11661,FALSE,AACC,GGTT,FALSE,Nextera,Equipment,,,,
-StudyC_6123,6123,FALSE,AACC,GGTT,TRUE,Nextera,Equipment,,,,
+Sample_Project,QiitaID,BarcodesAreRC,ForwardAdapter,ReverseAdapter,HumanFiltering,library_construction_protocol,experiment_design_description,contains_replicates,,,
+StudyA_13059,13059,FALSE,AACC,GGTT,FALSE,Nextera,Equipment,False,,,
+StudyB_11661,11661,FALSE,AACC,GGTT,FALSE,Nextera,Equipment,False,,,
+StudyC_6123,6123,FALSE,AACC,GGTT,TRUE,Nextera,Equipment,False,,,
 ,,,,,,,,,,,
 [Contact],,,,,,,,,,,
 Email,Sample_Project,,,,,,,,,,
diff --git a/tests/data/good_sheet_w_replicates.csv b/tests/data/good_sheet_w_replicates.csv
@@ -19,7 +19,7 @@ Chemistry,Default,,,,,,,,,,
 ReverseComplement,0,,,,,,,,,,
 ,,,,,,,,,,,
 [Data],,,,,,,,,,,
-Lane,orig_name,Sample_ID,Sample_Name,source_well_384,destination_well_384,Sample_Plate,well_id_384,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,Well_description
+Lane,orig_name,Sample_ID,Sample_Name,well_id_384,destination_well_384,Sample_Plate,Sample_Well,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,Well_description
 1,BLANK.43.12G,BLANK_43_12G_A1,BLANK.43.12G.A1,A1,A1,StudyB_11661_P43,A1,iTru7_114_08,CCGACTAT,iTru5_01_A,AAGGCTGA,StudyB_11661,blue_quadrant
 1,BLANK.43.12H,BLANK_43_12H_A3,BLANK.43.12H.A3,A3,A3,StudyB_11661_P43,A3,iTru7_114_09,ACCGACAA,iTru5_02_A,CGATCGAT,StudyB_11661,blue_quadrant
 1,RMA.KHP.rpoS.Mage.Q97D,RMA_KHP_rpoS_Mage_Q97D_A5,RMA.KHP.rpoS.Mage.Q97D.A5,A5,A5,StudyB_11661_P43,A5,iTru7_114_10,CCGACTAT,iTru5_03_A,TTACCGAG,StudyB_11661,blue_quadrant
diff --git a/tests/data/good_sheet_w_replicates_and_context_demux_1.csv b/tests/data/good_sheet_w_replicates_and_context_demux_1.csv
@@ -42,11 +42,11 @@ EP159692B04_C7,EP159692B04,C7,iTru7_108_10,AAGCACTG,iTru5_02_B,GTGGTATG,ProjectN
 EP987683A01_C9,EP987683A01,C9,iTru7_108_11,CCAAGCAA,iTru5_03_B,TGAGCTGT,ProjectN_13059,C9,ProjectN_13059_P1,C9,blue_quadrant
 ,,,,,,,,,,,
 [Bioinformatics],,,,,,,,,,,
-Sample_Project,QiitaID,BarcodesAreRC,ForwardAdapter,ReverseAdapter,HumanFiltering,library_construction_protocol,experiment_design_description,,,,
-ProjectF_11661,11661,False,AACC,GGTT,False,Nextera,Equipment,,,,
-ProjectN_13059,13059,False,AACC,GGTT,False,Knight Lab Kapa HP,Equipment,,,,
-TMI_10317,10317,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,,,,
-Other_11223,11223,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,,,,
+Sample_Project,QiitaID,BarcodesAreRC,ForwardAdapter,ReverseAdapter,HumanFiltering,library_construction_protocol,experiment_design_description,contains_replicates,,,
+ProjectF_11661,11661,False,AACC,GGTT,False,Nextera,Equipment,False,,,
+ProjectN_13059,13059,False,AACC,GGTT,False,Knight Lab Kapa HP,Equipment,False,,,
+TMI_10317,10317,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,False,,,
+Other_11223,11223,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,False,,,
 ,,,,,,,,,,,
 [Contact],,,,,,,,,,,
 Email,Sample_Project,,,,,,,,,,
diff --git a/tests/data/good_sheet_w_replicates_and_context_demux_2.csv b/tests/data/good_sheet_w_replicates_and_context_demux_2.csv
@@ -42,11 +42,11 @@ LP127890A01_C6,LP127890A01,C6,iTru7_108_09,TCTATAGG,iTru5_01_B,AGTCGCAA,ProjectN
 EP159692B04_C8,EP159692B04,C8,iTru7_108_10,AAGTTATG,iTru5_02_B,GTGGAATG,ProjectN_13059,C8,ProjectN_13059_P1,C7,green_quadrant
 ,,,,,,,,,,,
 [Bioinformatics],,,,,,,,,,,
-Sample_Project,QiitaID,BarcodesAreRC,ForwardAdapter,ReverseAdapter,HumanFiltering,library_construction_protocol,experiment_design_description,,,,
-ProjectF_11661,11661,False,AACC,GGTT,False,Nextera,Equipment,,,,
-ProjectN_13059,13059,False,AACC,GGTT,False,Knight Lab Kapa HP,Equipment,,,,
-TMI_10317,10317,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,,,,
-Other_11223,11223,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,,,,
+Sample_Project,QiitaID,BarcodesAreRC,ForwardAdapter,ReverseAdapter,HumanFiltering,library_construction_protocol,experiment_design_description,contains_replicates,,,
+ProjectF_11661,11661,False,AACC,GGTT,False,Nextera,Equipment,False,,,
+ProjectN_13059,13059,False,AACC,GGTT,False,Knight Lab Kapa HP,Equipment,False,,,
+TMI_10317,10317,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,False,,,
+Other_11223,11223,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,False,,,
 ,,,,,,,,,,,
 [Contact],,,,,,,,,,,
 Email,Sample_Project,,,,,,,,,,
diff --git a/tests/data/good_sheet_w_replicates_and_context_demux_3.csv b/tests/data/good_sheet_w_replicates_and_context_demux_3.csv
@@ -42,11 +42,11 @@ LP127890A01_D6,LP127890A01,D6,iTru7_108_09,TGTCTAGG,iTru5_01_B,AGTGGCAA,ProjectN
 EP159692B04_D8,EP159692B04,D8,iTru7_108_10,AGGCACTG,iTru5_02_B,GTGGTATG,ProjectN_13059,D8,ProjectN_13059_P1,C7,yellow_quadrant
 ,,,,,,,,,,,
 [Bioinformatics],,,,,,,,,,,
-Sample_Project,QiitaID,BarcodesAreRC,ForwardAdapter,ReverseAdapter,HumanFiltering,library_construction_protocol,experiment_design_description,,,,
-ProjectF_11661,11661,False,AACC,GGTT,False,Nextera,Equipment,,,,
-ProjectN_13059,13059,False,AACC,GGTT,False,Knight Lab Kapa HP,Equipment,,,,
-TMI_10317,10317,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,,,,
-Other_11223,11223,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,,,,
+Sample_Project,QiitaID,BarcodesAreRC,ForwardAdapter,ReverseAdapter,HumanFiltering,library_construction_protocol,experiment_design_description,contains_replicates,,,
+ProjectF_11661,11661,False,AACC,GGTT,False,Nextera,Equipment,False,,,
+ProjectN_13059,13059,False,AACC,GGTT,False,Knight Lab Kapa HP,Equipment,False,,,
+TMI_10317,10317,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,False,,,
+Other_11223,11223,False,AACC,GGTT,False,Knight Lab Kapa HP,Eqiiperiment,False,,,
 ,,,,,,,,,,,
 [Contact],,,,,,,,,,,
 Email,Sample_Project,,,,,,,,,,
diff --git a/tests/data/good_sheet_w_replicates_demux_1.csv b/tests/data/good_sheet_w_replicates_demux_1.csv
@@ -1,7 +1,7 @@
 [Header],,,,,,,,,,,,
 IEMFileVersion,4,,,,,,,,,,,
 SheetType,standard_metag,,,,,,,,,,,
-SheetVersion,100,,,,,,,,,,,
+SheetVersion,90,,,,,,,,,,,
 Investigator Name,Knight,,,,,,,,,,,
 Experiment Name,RKL0042,,,,,,,,,,,
 Date,2020-02-26,,,,,,,,,,,
@@ -19,7 +19,7 @@ Chemistry,Default,,,,,,,,,,,
 ReverseComplement,0,,,,,,,,,,,
 ,,,,,,,,,,,,
 [Data],,,,,,,,,,,,
-lane,Sample_Name,source_well_384,destination_well_384,sample_plate,well_id_384,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,well_description,Sample_ID
+lane,Sample_Name,source_well_384,destination_well_384,sample_plate,Sample_Well,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,well_description,Sample_ID
 1,BLANK.43.12G,A1,A1,StudyB_11661_P43,A1,iTru7_114_08,CCGACTAT,iTru5_01_A,AAGGCTGA,StudyB_11661,blue_quadrant,BLANK_43_12G_A1
 1,RMA.KHP.rpoS.Mage.Q97E,A11,A11,StudyB_11661_P43,A11,iTru7_201_01,AACACCAC,iTru5_06_A,CATCTGCT,StudyB_11661,blue_quadrant,RMA_KHP_rpoS_Mage_Q97E_A11
 1,JBI.KHP.HGL.021,A13,A13,StudyB_11661_P43,A13,iTru7_201_02,AACTTGCC,iTru5_07_A,GAAGGTTC,StudyB_11661,blue_quadrant,JBI_KHP_HGL_021_A13
diff --git a/tests/data/good_sheet_w_replicates_demux_2.csv b/tests/data/good_sheet_w_replicates_demux_2.csv
@@ -1,7 +1,7 @@
 [Header],,,,,,,,,,,,
 IEMFileVersion,4,,,,,,,,,,,
 SheetType,standard_metag,,,,,,,,,,,
-SheetVersion,100,,,,,,,,,,,
+SheetVersion,90,,,,,,,,,,,
 Investigator Name,Knight,,,,,,,,,,,
 Experiment Name,RKL0042,,,,,,,,,,,
 Date,2020-02-26,,,,,,,,,,,
@@ -19,7 +19,7 @@ Chemistry,Default,,,,,,,,,,,
 ReverseComplement,0,,,,,,,,,,,
 ,,,,,,,,,,,,
 [Data],,,,,,,,,,,,
-lane,Sample_Name,source_well_384,destination_well_384,sample_plate,well_id_384,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,well_description,Sample_ID
+lane,Sample_Name,source_well_384,destination_well_384,sample_plate,Sample_Well,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,well_description,Sample_ID
 1,RMA.KHP.rpoS.Mage.Q97N,A9,A10,StudyB_11661_P43,A10,iTru7_114_12,GAAGTACC,iTru5_05_A,TGTTCGAG,StudyB_11661,green_quadrant,RMA_KHP_rpoS_Mage_Q97N_A10
 1,RMA.KHP.rpoS.Mage.Q97E,A11,A12,StudyB_11661_P43,A12,iTru7_201_01,AGTGGCAA,iTru5_06_A,TACTCCAG,StudyB_11661,green_quadrant,RMA_KHP_rpoS_Mage_Q97E_A12
 1,JBI.KHP.HGL.021,A13,A14,StudyB_11661_P43,A14,iTru7_201_02,CAGGAATC,iTru5_07_A,CTCGTCTT,StudyB_11661,green_quadrant,JBI_KHP_HGL_021_A14
diff --git a/tests/data/good_sheet_w_replicates_demux_3.csv b/tests/data/good_sheet_w_replicates_demux_3.csv
@@ -1,7 +1,7 @@
 [Header],,,,,,,,,,,,
 IEMFileVersion,4,,,,,,,,,,,
 SheetType,standard_metag,,,,,,,,,,,
-SheetVersion,100,,,,,,,,,,,
+SheetVersion,90,,,,,,,,,,,
 Investigator Name,Knight,,,,,,,,,,,
 Experiment Name,RKL0042,,,,,,,,,,,
 Date,2020-02-26,,,,,,,,,,,
@@ -19,7 +19,7 @@ Chemistry,Default,,,,,,,,,,,
 ReverseComplement,0,,,,,,,,,,,
 ,,,,,,,,,,,,
 [Data],,,,,,,,,,,,
-lane,Sample_Name,source_well_384,destination_well_384,sample_plate,well_id_384,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,well_description,Sample_ID
+lane,Sample_Name,source_well_384,destination_well_384,sample_plate,Sample_Well,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,well_description,Sample_ID
 1,RMA.KHP.rpoS.Mage.Q97N,A9,B10,StudyB_11661_P43,B10,iTru7_114_12,AAGTCGAG,iTru5_05_A,TGGCACTA,StudyB_11661,yellow_quadrant,RMA_KHP_rpoS_Mage_Q97N_B10
 1,RMA.KHP.rpoS.Mage.Q97E,A11,B12,StudyB_11661_P43,B12,iTru7_201_01,TGCCTCAA,iTru5_06_A,CCATGAAC,StudyB_11661,yellow_quadrant,RMA_KHP_rpoS_Mage_Q97E_B12
 1,JBI.KHP.HGL.021,A13,B14,StudyB_11661_P43,B14,iTru7_201_02,TATCGGTC,iTru5_07_A,GGTTGTCA,StudyB_11661,yellow_quadrant,JBI_KHP_HGL_021_B14
diff --git a/tests/data/multi-project-sheet.csv b/tests/data/multi-project-sheet.csv
@@ -28,9 +28,9 @@ Lane,Sample_ID,Sample_Name,Sample_Plate,well_id_384,I7_Index_ID,index,I5_Index_I
 1,8A,8A,Something,L23,iTru7_402_04,GTCCACAT,iTru5_110_H,TCCAGCAA,Wisconsin_U19_NA_15446,pool1,8A
 ,,,,,,,,,,,
 [Bioinformatics],,,,,,,,,,,
-Sample_Project,QiitaID,BarcodesAreRC,ForwardAdapter,ReverseAdapter,HumanFiltering,library_construction_protocol,experiment_design_description,,,,
-Wisconsin_U19_15445,15445,False,AACC,GGTT,True,Nextera,Equipment,,,,
-Wisconsin_U19_NA_15446,15446,False,AACC,GGTT,True,Nextera,Equipment,,,,
+Sample_Project,QiitaID,BarcodesAreRC,ForwardAdapter,ReverseAdapter,HumanFiltering,library_construction_protocol,experiment_design_description,contains_replicates,,,
+Wisconsin_U19_15445,15445,False,AACC,GGTT,True,Nextera,Equipment,False,,,
+Wisconsin_U19_NA_15446,15446,False,AACC,GGTT,True,Nextera,Equipment,False,,,
 ,,,,,,,,,,,
 [Contact],,,,,,,,,,,
 Email,Sample_Project,,,,,,,,,,
diff --git a/tests/data/sample-sheets/metagenomic/illumina/good_sheet1.csv b/tests/data/sample-sheets/metagenomic/illumina/good_sheet1.csv
@@ -1,7 +1,7 @@
 [Header],,,,,,,,,,,
 IEMFileVersion,4,,,,,,,,,,
 SheetType,standard_metag,,,,,,,,,,
-SheetVersion,100,,,,,,,,,,
+SheetVersion,90,,,,,,,,,,
 Investigator Name,Knight,,,,,,,,,,
 Experiment Name,RKL0042,,,,,,,,,,
 Date,2020-02-26,,,,,,,,,,
@@ -19,7 +19,7 @@ Chemistry,Default,,,,,,,,,,
 ReverseComplement,0,,,,,,,,,,
 ,,,,,,,,,,,
 [Data],,,,,,,,,,,
-Lane,Sample_ID,Sample_Name,Sample_Plate,well_id_384,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,syndna_pool_number,Well_description
+Lane,Sample_ID,Sample_Name,Sample_Plate,Sample_Well,I7_Index_ID,index,I5_Index_ID,index2,Sample_Project,syndna_pool_number,Well_description
 1,CDPH-SAL_Salmonella_Typhi_MDL-143,CDPH-SAL.Salmonella.Typhi.MDL-143,StudyB_11661_P40,A1,iTru7_107_07,CCGACTAT,iTru5_01_A,ACCGACAA,StudyB_11661,pool1,CDPH-SAL_Salmonella Typhi_MDL-143
 1,CDPH-SAL_Salmonella_Typhi_MDL-144,CDPH-SAL.Salmonella.Typhi.MDL-144,StudyB_11661_P40,C1,iTru7_107_08,CCGACTAT,iTru5_02_A,CTTCGCAA,StudyB_11661,pool2,CDPH-SAL_Salmonella Typhi_MDL-144
 1,CDPH-SAL_Salmonella_Typhi_MDL-145,CDPH-SAL.Salmonella.Typhi.MDL-145,StudyB_11661_P40,E1,iTru7_107_09,GCCTTGTT,iTru5_03_A,AACACCAC,StudyB_11661,pool1,CDPH-SAL_Salmonella Typhi_MDL-145
diff --git a/tests/data/sample-sheets/metatranscriptomic/illumina/good_sheet1.csv b/tests/data/sample-sheets/metatranscriptomic/illumina/good_sheet1.csv
@@ -318,3 +318,6 @@ StudyC_6123,6123,False,AACC,GGTT,True,Nextera,Equipment,,,,
 Email,Sample_Project,,,,,,,,,,
 test@lol.com,StudyB_11661,,,,,,,,,,
 ,,,,,,,,,,,
+
+
+
diff --git a/tests/test_Pipeline.py b/tests/test_Pipeline.py
@@ -544,11 +544,6 @@ def _help_test_generate_sample_information_files_with_multiple_preps(
                 header = curr_obs_lines[0].strip()
                 self.assertEqual(header, '\t'.join(Pipeline.sif_header))
 
-                # confirm that the file contains the expected number of lines:
-                # 1 header + # blanks
-                curr_expected_len = len(curr_expected_blanks) + 1
-                self.assertEqual(len(curr_obs_lines), curr_expected_len)
-
                 # for lines after header, get the value before the first tab
                 # and confirm that it matches the expected blank name--
                 # i.e., that the *second* well location, which is present in
@@ -568,7 +563,7 @@ def test_generate_sample_information_files_multiple_preps_no_context(self):
         # the blanks are linked to only one project in the data table, so there
         # is only one SIF generated
         expected_blanks_by_qiita_id = {
-            '11661': ['BLANK.43.12G', 'BLANK.43.12H'],
+            '11661': ['BLANK.43.12G', 'BLANK.43.12H']
         }
 
         self._help_test_generate_sample_information_files_with_multiple_preps(
@@ -580,8 +575,8 @@ def test_generate_sample_information_files_multiple_preps_w_context(self):
         # projects (although not all blanks belong to each project!)
         # so there are three SIFs generated, one for each project.
         expected_blanks_by_qiita_id = {
-            '11661': ['BLANK.43.12G', 'BLANK.43.12H'],
-            '10317': ['BLANK.43.12G', 'BLANK.43.12H'],
+            '11661': ['BLANK.43.12H', 'BLANK.43.12G'],
+            '10317': ['BLANK.43.12H', 'BLANK.43.12G'],
             '11223': ['BLANK.43.12G']
         }
 
@@ -1675,10 +1670,10 @@ def test_identify_reserved_words(self):
         self.assertEqual(obs, [])
 
         # assert that 'well_id_384' is a reserved word.
-        obs = pipeline.identify_reserved_words(['well_id_384',
+        obs = pipeline.identify_reserved_words(['sample_well',
                                                 'NOT_A_RESERVED_WORD'])
 
-        self.assertEqual(obs, ['well_id_384'])
+        self.assertEqual(obs, ['sample_well'])
 
         # create new pipeline using a/legacy (v90) metagenomic sample-sheet.
         pipeline = Pipeline(self.good_config_file, self.good_run_id,
diff --git a/tests/test_helpers.py b/tests/test_helpers.py
@@ -337,11 +337,11 @@ def test_project_metadata_check(self):
         # step and fake_client is used.
         wf._project_metadata_check()
 
-        self.fake_client.info_in_11661['categories'].append('well_id_384')
-        self.fake_client.info_in_13059['categories'].append('well_id_384')
+        self.fake_client.info_in_11661['categories'].append('sample_well')
+        self.fake_client.info_in_13059['categories'].append('sample_well')
 
-        msg = ("'well_id_384' exists in Qiita study 13059's sample metadata"
-               "\n'well_id_384' exists in Qiita study 11661's sample metadata")
+        msg = ("'sample_well' exists in Qiita study 13059's sample metadata"
+               "\n'sample_well' exists in Qiita study 11661's sample metadata")
         with self.assertRaisesRegex(WorkflowError, msg):
             wf._project_metadata_check()
 
