@@ -624,29 +624,21 @@ def test_luigi_proxy(self, mock_hostname):
624624 'message_data_type' : 'Expression Outlier' ,
625625 'header' : ['sampleID' , 'project' , 'geneID' , 'tissue' , 'detail' , 'pValue' , 'padjust' , 'zScore' ],
626626 'optional_headers' : ['detail' ],
627- 'loaded_data_row' : ['NA19675_D2' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'muscle' , 'detail1' ,
628- 0.01 , 0.001 , - 3.1 ],
629- 'no_existing_data' : ['NA19678' , '1kg project nåme with uniçøde' , 'ENSG00000233750' , 'muscle' , 'detail1' ,
630- 0.064 , '0.0000057' , 7.8 ],
627+ 'loaded_data_row' : ['NA19675_D2' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'muscle' , 'detail1' , 0.01 , 0.001 , - 3.1 ],
628+ 'no_existing_data' : ['NA19678' , '1kg project nåme with uniçøde' , 'ENSG00000233750' , 'muscle' , 'detail1' , 0.064 , '0.0000057' , 7.8 ],
631629 'duplicated_indiv_id_data' : [
632- ['NA20870' , 'Test Reprocessed Project' , 'ENSG00000233750' , 'muscle' , 'detail1' , 0.064 , '0.0000057' ,
633- 7.8 ],
634- ['NA20870' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'fibroblasts' , 'detail2' , 0.01 , 0.13 ,
635- - 3.1 ],
630+ ['NA20870' , 'Test Reprocessed Project' , 'ENSG00000233750' , 'muscle' , 'detail1' , 0.064 , '0.0000057' , 7.8 ],
631+ ['NA20870' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'fibroblasts' , 'detail2' , 0.01 , 0.13 , - 3.1 ],
636632 ],
637633 'write_data' : {
638634 '{"gene_id": "ENSG00000233750", "p_value": "0.064", "p_adjust": "0.0000057", "z_score": "7.8"}\n ' ,
639635 '{"gene_id": "ENSG00000240361", "p_value": "0.01", "p_adjust": "0.13", "z_score": "-3.1"}\n '
640636 },
641637 'new_data' : [
642- ['NA19675_D2' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'muscle' , 'detail1' , 0.01 , 0.13 ,
643- - 3.1 ],
644- ['NA19675_D2' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'muscle' , 'detail2' , 0.01 , 0.13 ,
645- - 3.1 ],
646- ['NA19675_D2' , '1kg project nåme with uniçøde' , 'ENSG00000233750' , 'muscle' , 'detail1' , 0.064 ,
647- '0.0000057' , 7.8 ],
648- ['NA19675_D3' , 'Test Reprocessed Project' , 'ENSG00000233750' , 'muscle' , 'detail1' , 0.064 , '0.0000057' ,
649- 7.8 ],
638+ ['NA19675_D2' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'muscle' , 'detail1' , 0.01 , 0.13 , - 3.1 ],
639+ ['NA19675_D2' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'muscle' , 'detail2' , 0.01 , 0.13 , - 3.1 ],
640+ ['NA19675_D2' , '1kg project nåme with uniçøde' , 'ENSG00000233750' , 'muscle' , 'detail1' , 0.064 , '0.0000057' , 7.8 ],
641+ ['NA19675_D3' , 'Test Reprocessed Project' , 'ENSG00000233750' , 'muscle' , 'detail1' , 0.064 , '0.0000057' , 7.8 ],
650642 ['NA20888' , 'Test Reprocessed Project' , 'ENSG00000240361' , 'muscle' , '' , 0.04 , 0.112 , 1.9 ],
651643 ],
652644 'skipped_samples' : 'NA19675_D3 (Test Reprocessed Project)' ,
@@ -662,10 +654,8 @@ def test_luigi_proxy(self, mock_hostname):
662654 'message_data_type' : 'Expression' ,
663655 'header' : ['sample_id' , 'project' , 'gene_id' , 'individual_id' , 'tissue' , 'TPM' ],
664656 'optional_headers' : ['individual_id' ],
665- 'loaded_data_row' : ['NA19675_D2' , '1kg project nåme with uniçøde' , 'ENSG00000135953' , 'NA19675_D3' ,
666- 'muscle' , 1.34 ],
667- 'no_existing_data' : ['NA19678' , '1kg project nåme with uniçøde' , 'ENSG00000233750' , 'NA19678' , 'muscle' ,
668- 0.064 ],
657+ 'loaded_data_row' : ['NA19675_D2' , '1kg project nåme with uniçøde' , 'ENSG00000135953' , 'NA19675_D3' , 'muscle' , 1.34 ],
658+ 'no_existing_data' : ['NA19678' , '1kg project nåme with uniçøde' , 'ENSG00000233750' , 'NA19678' , 'muscle' , 0.064 ],
669659 'duplicated_indiv_id_data' : [
670660 ['NA20870' , 'Test Reprocessed Project' , 'ENSG00000240361' , 'NA20870' , 'muscle' , 7.8 ],
671661 ['NA20870' , '1kg project nåme with uniçøde' , 'ENSG00000233750' , 'NA20870' , 'fibroblasts' , 0.0 ],
@@ -695,20 +685,14 @@ def test_luigi_proxy(self, mock_hostname):
695685 'model_cls' : RnaSeqSpliceOutlier ,
696686 'data_type' : 'S' ,
697687 'message_data_type' : 'Splice Outlier' ,
698- 'header' : ['sampleID' , 'projectName' , 'geneID' , 'chrom' , 'start' , 'end' , 'strand' , 'type' , 'pValue' ,
699- 'pAdjust' ,
700- 'deltaIntronJaccardIndex' , 'counts' , 'meanCounts' , 'totalCounts' , 'meanTotalCounts' , 'tissue' ,
701- 'rareDiseaseSamplesWithThisJunction' ,
688+ 'header' : ['sampleID' , 'projectName' , 'geneID' , 'chrom' , 'start' , 'end' , 'strand' , 'type' , 'pValue' , 'pAdjust' ,
689+ 'deltaIntronJaccardIndex' , 'counts' , 'meanCounts' , 'totalCounts' , 'meanTotalCounts' , 'tissue' , 'rareDiseaseSamplesWithThisJunction' ,
702690 'rareDiseaseSamplesTotal' ],
703691 'optional_headers' : [],
704- 'loaded_data_row' : ['NA19675_1' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'chr7' , 132885746 ,
705- 132886973 , '*' ,
706- 'psi5' , 1.08E-56 , 3.08E-56 , 12.34 , 1297 , 197 , 129 , 1297 , 'fibroblasts' , 0.53953638 , 1 ,
707- 20 ],
708- 'no_existing_data' : ['NA19678' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'chr7' , 132885746 ,
709- 132886973 , '*' ,
710- 'psi5' , 1.08E-56 , 3.08E-56 , 12.34 , 1297 , 197 , 129 , 1297 , 'fibroblasts' , 0.53953638 , 1 ,
711- 20 ],
692+ 'loaded_data_row' : ['NA19675_1' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'chr7' , 132885746 , 132886973 , '*' ,
693+ 'psi5' , 1.08E-56 , 3.08E-56 , 12.34 , 1297 , 197 , 129 , 1297 , 'fibroblasts' , 0.53953638 , 1 , 20 ],
694+ 'no_existing_data' : ['NA19678' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'chr7' , 132885746 , 132886973 , '*' ,
695+ 'psi5' , 1.08E-56 , 3.08E-56 , 12.34 , 1297 , 197 , 129 , 1297 , 'fibroblasts' , 0.53953638 , 1 , 20 ],
712696 'duplicated_indiv_id_data' : [
713697 ['NA20870' , 'Test Reprocessed Project' , 'ENSG00000233750' , 'chr2' , 167258096 , 167258349 , '*' ,
714698 'psi3' , 1.56E-25 , 6.33 , 0.45 , 143 , 143 , 143 , 143 , 'fibroblasts' , 1 , 20 ],
@@ -725,14 +709,12 @@ def test_luigi_proxy(self, mock_hostname):
725709 ' "delta_intron_jaccard_index": "0.45", "counts": "143",'
726710 ' "mean_counts": "143", "total_counts": "143", "mean_total_counts": "143",'
727711 ' "rare_disease_samples_with_this_junction": "1", "rare_disease_samples_total": "20", "gene_id": "ENSG00000135953"}\n ' ,
728- },
712+ },
729713 'new_data' : [
730714 # existing sample NA19675_1
731- ['NA19675_1' , '1kg project nåme with uniçøde' , 'ENSG00000233750;ENSG00000240361' , 'chr2' , 167254166 ,
732- 167258349 , '*' , 'psi3' ,
715+ ['NA19675_1' , '1kg project nåme with uniçøde' , 'ENSG00000233750;ENSG00000240361' , 'chr2' , 167254166 , 167258349 , '*' , 'psi3' ,
733716 1.56E-25 , - 4.9 , - 0.46 , 166 , 16.6 , 1660 , 1.66 , 'fibroblasts' , 1 , 20 ],
734- ['NA19675_1' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'chr7' , 132885746 , 132975168 , '*' ,
735- 'psi5' ,
717+ ['NA19675_1' , '1kg project nåme with uniçøde' , 'ENSG00000240361' , 'chr7' , 132885746 , 132975168 , '*' , 'psi5' ,
736718 1.08E-56 , - 6.53 , - 0.85 , 231 , 0.231 , 2313 , 231.3 , 'fibroblasts' , 1 , 20 ],
737719 # no matched individual NA19675_D3
738720 ['NA19675_D3' , '1kg project nåme with uniçøde' , 'ENSG00000233750' , 'chr2' , 167258096 , 167258349 , '*' ,
0 commit comments