def test_ignores_unused_column_changes_in_compare_row(self):
releaseDiff.added_data = self.added_data
self.oldRow['pyhgvs_Protein'] = "NP_009225.1:p.?"
self.newRow['HGVS_Protein'] = "NM_000059:p.His1085Arg"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
self.assertIsNone(change_type)
def test_builds_diff_with_adjusted_column_names_to_match_db(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['pyhgvs_Protein'] = "NP_009225.1:p.?"
self.newRow['pyhgvs_Protein'] = "NM_000059:p.His1085Arg"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json[variant]
self.assertIs(diff[0]['field'], 'HGVS_Protein')
def test_properly_classifies_variants_with_removed_columns_of_empty_data(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow["Functional_analysis_result_LOVD"] = "-"
self.newRow['Source'] += ",ENIGMA"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json[variant]
self.assertEqual(len(diff), 1)
self.assertIs(change_type, "added_information")
def test_catches_reordered_source_urls(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow["Source_URL"] = "http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000075538, http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000144133, http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000109288"
self.newRow["Source_URL"] = "http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000144133, http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000075538, http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000109288"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_ignore_added_or_removed_white_space(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
self.oldRow['Synonyms'] = '-2498del2'
self.newRow['Synonyms'] = '-2498 del2'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_ignore_date_format_changes(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
self.oldRow['Date_last_evaluated_ENIGMA'] = '1 / 12 / 2015'
self.newRow['Date_last_evaluated_ENIGMA'] = '2015 - 01 - 12'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_ignore_white_spaces(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
self.oldRow['BIC_Nomenclature'] = 'IVS7-680del2'
self.newRow['BIC_Nomenclature'] = 'IVS 7-680del2'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_ignores_max_allele_frequency_field(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.newRow["Max_Allele_Frequency"] = "-"
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_catches_new_column_changes_in_compare_row(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['pyhgvs_Protein'] = "NP_009225.1:p.?"
self.newRow['pyhgvs_Protein'] = "NM_000059:p.His1085Arg"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json[variant]
self.assertEqual(change_type, "changed_information")
self.assertIs(diff[0]['removed'], 'NP_009225.1:p.?')
self.assertIs(diff[0]['added'], 'NM_000059:p.His1085Arg')
def test_catches_pathogenicity_changes(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Pathogenicity_all'] = "Pathogenic,not_provided (ClinVar); Class 5 (BIC)"
self.oldRow['Pathogenicity_expert'] = "Not Yet Classified"
self.newRow['Pathogenicity_all'] = "Pathogenic(ENIGMA); Pathogenic,not_provided (ClinVar); Class 5 (BIC)"
self.newRow['Pathogenicity_expert'] = "Pathogenic"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json[variant]
self.assertEqual(len(diff), 2)
self.assertIs(change_type, "changed_classification")
def test_catches_pathogenicity_changes(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Pathogenicity_all'] = "Pathogenic,not_provided (ClinVar); Class 5 (BIC)"
self.oldRow['Pathogenicity_expert'] = "Not Yet Classified"
self.newRow['Pathogenicity_all'] = "Pathogenic(ENIGMA); Pathogenic,not_provided (ClinVar); Class 5 (BIC)"
self.newRow['Pathogenicity_expert'] = "Pathogenic"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json[variant]
self.assertEqual(len(diff), 2)
self.assertIs(change_type, "changed_classification")
def test_change_type_ignores_reorders(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Pathogenicity_all'] = "Pathogenic(ENIGMA); not_provided,Pathogenic (ClinVar); Class 5 (BIC)"
self.oldRow['Pathogenicity_expert'] = "Pathogenic"
self.newRow['Pathogenicity_all'] = "Pathogenic(ENIGMA); Pathogenic,not_provided (ClinVar); Class 5 (BIC)"
self.newRow['Pathogenicity_expert'] = "Pathogenic"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(len(diff), 0)
self.assertIsNone(change_type)
def test_properly_ignores_exac_minus_tcga_rounding_changes_for_generic_allele_frequency(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_Frequency'] = '9.419e-06 (ExAC minus TCGA)'
self.newRow['Allele_Frequency'] = '9.42e-06 (ExAC minus TCGA)'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_ignored_exac_minus_tcga_instead_of_exac(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_Frequency'] = '9.42e-06 (ExAC)'
self.newRow['Allele_Frequency'] = '9.42e-06 (ExAC minus TCGA)'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_catches_reordered_source_urls(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow[
"Source_URL"] = "http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000075538, http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000144133, http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000109288"
self.newRow[
"Source_URL"] = "http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000144133, http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000075538, http://www.ncbi.nlm.nih.gov/clinvar/?term=SCV000109288"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_handles_null_data_in_new_columns_in_v2_data_correctly(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.updated_fieldnames = self.fieldnames + ['Genetic_origin_LOVD', 'RNA_LOVD', 'Submitters_LOVD']
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.updated_fieldnames)
self.newRow["Genetic_origin_LOVD"] = ""
self.newRow["RNA_LOVD"] = None
self.newRow["Submitters_LOVD"] = "-"
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_ignored_exac_minus_tcga_instead_of_exac(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_Frequency'] = '9.42e-06 (ExAC)'
self.newRow['Allele_Frequency'] = '9.42e-06 (ExAC minus TCGA)'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_ignores_rounding_for_exac_af_fields(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_frequency_FIN_ExAC'] = '9.4181237657'
self.newRow['Allele_frequency_FIN_ExAC'] = '9.42'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_handles_new_data_in_new_columns_in_v2_data_correctly(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.updated_fieldnames = self.fieldnames + ['Genetic_origin_LOVD', 'RNA_LOVD', 'Submitters_LOVD']
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.updated_fieldnames)
self.newRow["Genetic_origin_LOVD"] = "lorem ipsum"
self.newRow["RNA_LOVD"] = "lorem ipsum"
self.newRow["Submitters_LOVD"] = "lorem ipsum"
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(change_type, "added_information")
self.assertTrue(len(diff[variant]) == 3)
def test_ignores_rounding_for_exac_af_fields(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_frequency_FIN_ExAC'] = '9.4181237657'
self.newRow['Allele_frequency_FIN_ExAC'] = '9.42'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_catches_changed_numeric_values_after_normalization(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow['Allele_frequency_ExAC'] = '9.841e-06'
self.newRow['Allele_frequency_ExAC'] = '9.841e-07'
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(len(diff), 1)
self.assertIs(change_type, "changed_information")
def test_change_type_ignores_reorders(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Pathogenicity_all'] = "Pathogenic(ENIGMA); not_provided,Pathogenic (ClinVar); Class 5 (BIC)"
self.oldRow['Pathogenicity_expert'] = "Pathogenic"
self.newRow['Pathogenicity_all'] = "Pathogenic(ENIGMA); Pathogenic,not_provided (ClinVar); Class 5 (BIC)"
self.newRow['Pathogenicity_expert'] = "Pathogenic"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(len(diff), 0)
self.assertIsNone(change_type)
def test_ignores_change_from_none_to_empty_string(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow["Submitter_ClinVar"] = "Quest_Diagnostics_Nichols_Institute_San_Juan_Capistrano"
self.newRow["Submitter_ClinVar"] = ",Quest_Diagnostics_Nichols_Institute_San_Juan_Capistrano"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_properly_ignores_exac_minus_tcga_rounding_changes_for_generic_allele_frequency(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_Frequency'] = '9.419e-06 (ExAC minus TCGA)'
self.newRow['Allele_Frequency'] = '9.42e-06 (ExAC minus TCGA)'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_ignores_change_from_none_to_empty_string(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow["Submitter_ClinVar"] = "Quest_Diagnostics_Nichols_Institute_San_Juan_Capistrano"
self.newRow["Submitter_ClinVar"] = ",Quest_Diagnostics_Nichols_Institute_San_Juan_Capistrano"
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_ignores_polyphen_fields(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.newRow["Polyphen_Score"] = "0.283"
self.newRow["Polyphen_Prediction"] = "probably_damaging"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_handles_null_data_in_new_columns_in_v2_data_correctly(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.updated_fieldnames = self.fieldnames + ['Genetic_origin_LOVD', 'RNA_LOVD', 'Submitters_LOVD']
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.updated_fieldnames)
self.newRow["Genetic_origin_LOVD"] = ""
self.newRow["RNA_LOVD"] = None
self.newRow["Submitters_LOVD"] = "-"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_ignores_polyphen_fields(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.newRow["Polyphen_Score"] = "0.283"
self.newRow["Polyphen_Prediction"] = "probably_damaging"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_handles_new_data_in_new_columns_in_v2_data_correctly(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.updated_fieldnames = self.fieldnames + ['Genetic_origin_LOVD', 'RNA_LOVD', 'Submitters_LOVD']
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.updated_fieldnames)
self.newRow["Genetic_origin_LOVD"] = "lorem ipsum"
self.newRow["RNA_LOVD"] = "lorem ipsum"
self.newRow["Submitters_LOVD"] = "lorem ipsum"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(change_type, "added_information")
self.assertTrue(len(diff[variant]) == 3)
def test_catches_changed_numeric_values_after_normalization(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow['Allele_frequency_ExAC'] = '9.841e-06'
self.newRow['Allele_frequency_ExAC'] = '9.841e-07'
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(len(diff), 1)
self.assertIs(change_type, "changed_information")
def test_add_gs_to_genomic_coordinate(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
self.oldRow['pyhgvs_Genomic_Coordinate_38'] = "chr17:43049067:C>T"
self.newRow['pyhgvs_Genomic_Coordinate_38'] = "chr17:g.43049067:C>T"
self.oldRow['pyhgvs_Genomic_Coordinate_37'] = "chr17:43049067:C>T"
self.newRow['pyhgvs_Genomic_Coordinate_37'] = "chr17:g.43049067:C>T"
self.oldRow['pyhgvs_Genomic_Coordinate_36'] = "chr17:43049067:C>T"
self.newRow['pyhgvs_Genomic_Coordinate_36'] = "chr17:g.43049067:C>T"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow = releaseDiff.addGsIfNecessary(self.oldRow)
self.oldRow = releaseDiff.addGsIfNecessary(self.newRow)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
self.assertIsNone(change_type)
def test_add_gs_to_genomic_coordinate(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
self.oldRow['pyhgvs_Genomic_Coordinate_38'] = "chr17:43049067:C>T"
self.newRow['pyhgvs_Genomic_Coordinate_38'] = "chr17:g.43049067:C>T"
self.oldRow['pyhgvs_Genomic_Coordinate_37'] = "chr17:43049067:C>T"
self.newRow['pyhgvs_Genomic_Coordinate_37'] = "chr17:g.43049067:C>T"
self.oldRow['pyhgvs_Genomic_Coordinate_36'] = "chr17:43049067:C>T"
self.newRow['pyhgvs_Genomic_Coordinate_36'] = "chr17:g.43049067:C>T"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow = releaseDiff.addGsIfNecessary(self.oldRow)
self.oldRow = releaseDiff.addGsIfNecessary(self.newRow)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
self.assertIsNone(change_type)
def test_handle_repeat_data_correctly(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow["Pathogenicity_all"] = "Pathogenic,Pathogenic,not_provided"
self.newRow["Pathogenicity_all"] = "Pathogenic,not_provided"
self.oldRow["Clinical_Significance_ClinVar"] = "Pathogenic,Pathogenic,not_provided"
self.newRow["Clinical_Significance_ClinVar"] = "Pathogenic,not_provided"
self.oldRow["Submitter_ClinVar"] = "PreventionGenetics"
self.newRow["Submitter_ClinVar"] = "PreventionGenetics,PreventionGenetics"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_handle_repeat_data_correctly(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow["Pathogenicity_all"] = "Pathogenic,Pathogenic,not_provided"
self.newRow["Pathogenicity_all"] = "Pathogenic,not_provided"
self.oldRow["Clinical_Significance_ClinVar"] = "Pathogenic,Pathogenic,not_provided"
self.newRow["Clinical_Significance_ClinVar"] = "Pathogenic,not_provided"
self.oldRow["Submitter_ClinVar"] = "PreventionGenetics"
self.newRow["Submitter_ClinVar"] = "PreventionGenetics,PreventionGenetics"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_displays_integers_as_integers_not_floats(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_count_AFR'] = '-'
self.newRow['Allele_count_AFR'] = '567'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
v_diff = diff['chr17:g.43049067:C>T'][0]
self.assertEqual(len(diff), 1)
self.assertEqual(v_diff['field'], 'Allele_count_AFR')
self.assertEqual(v_diff['added'], '567')
self.assertEqual(v_diff['removed'], '-')
def test_displays_integers_as_integers_not_floats(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_count_AFR'] = '-'
self.newRow['Allele_count_AFR'] = '567'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
v_diff = diff['chr17:g.43049067:C>T'][0]
self.assertEqual(len(diff), 1)
self.assertEqual(v_diff['field'], 'Allele_count_AFR')
self.assertEqual(v_diff['added'], '567')
self.assertEqual(v_diff['removed'], '-')
def test_properly_handles_field_name_changes_same_data(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.updated_fieldnames = self.fieldnames + ['Minor_allele_frequency_percent_ESP']
self.fieldnames = self.fieldnames + ['Minor_allele_frequency_ESP']
self.oldRow['Minor_allele_frequency_ESP'] = '2.5'
self.newRow['Minor_allele_frequency_percent_ESP'] = '2.5'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.updated_fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_properly_handles_field_name_changes_same_data(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.updated_fieldnames = self.fieldnames + ['Minor_allele_frequency_percent_ESP']
self.fieldnames = self.fieldnames + ['Minor_allele_frequency_ESP']
self.oldRow['Minor_allele_frequency_ESP'] = '2.5'
self.newRow['Minor_allele_frequency_percent_ESP'] = '2.5'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.updated_fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_different_values_for_exac_af_fields(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_frequency_FIN_ExAC'] = '9.4181237657'
self.newRow['Allele_frequency_FIN_ExAC'] = '9.41'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
v_diff = diff['chr17:g.43049067:C>T'][0]
self.assertEqual(len(diff), 1)
self.assertEqual(v_diff['field'], 'Allele_frequency_FIN_ExAC')
self.assertEqual(v_diff['added'], '9.41')
self.assertEqual(v_diff['removed'], '9.42')
self.assertEqual(change_type, "changed_information")
def test_catches_value_change_for_exac_allele_frequency(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_Frequency'] = '9.42e-06 (ExAC)'
self.newRow['Allele_Frequency'] = '9.99e-06 (ExAC minus TCGA)'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
v_diff = diff['chr17:g.43049067:C>T'][0]
self.assertEqual(len(diff), 1)
self.assertEqual(v_diff['field'], 'Allele_Frequency')
self.assertEqual(v_diff['added'], '9.99e-06 (ExAC minus TCGA)')
self.assertEqual(v_diff['removed'], '9.42e-06 (ExAC minus TCGA)')
self.assertEqual(change_type, "changed_information")
def test_different_values_for_exac_af_fields(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_frequency_FIN_ExAC'] = '9.4181237657'
self.newRow['Allele_frequency_FIN_ExAC'] = '9.41'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
v_diff = diff['chr17:g.43049067:C>T'][0]
self.assertEqual(len(diff), 1)
self.assertEqual(v_diff['field'], 'Allele_frequency_FIN_ExAC')
self.assertEqual(v_diff['added'], '9.41')
self.assertEqual(v_diff['removed'], '9.42')
self.assertEqual(change_type, "changed_information")
def test_catches_value_change_for_exac_allele_frequency(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.oldRow['Allele_Frequency'] = '9.42e-06 (ExAC)'
self.newRow['Allele_Frequency'] = '9.99e-06 (ExAC minus TCGA)'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
v_diff = diff['chr17:g.43049067:C>T'][0]
self.assertEqual(len(diff), 1)
self.assertEqual(v_diff['field'], 'Allele_Frequency')
self.assertEqual(v_diff['added'], '9.99e-06 (ExAC minus TCGA)')
self.assertEqual(v_diff['removed'], '9.42e-06 (ExAC minus TCGA)')
self.assertEqual(change_type, "changed_information")
def test_ignores_cosmetic_changes_in_diff(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow[
"Submitter_ClinVar"] = "The_Consortium_of_Investigators_of_Modifiers_of_BRCA1/2_(CIMBA),c/o_University_of_Cambridge"
self.newRow[
"Submitter_ClinVar"] = "Consortium_of_Investigators_of_Modifiers_of_BRCA1/2_(CIMBA),_c/o_University_of_Cambridge"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
self.oldRow[
"Submitter_ClinVar"] = "Consortium_of_Investigators_of_Modifiers_of_BRCA1/2_(CIMBA),_c/o_University_of_Cambridge"
self.newRow[
"Submitter_ClinVar"] = "The_Consortium_of_Investigators_of_Modifiers_of_BRCA1/2_(CIMBA),c/o_University_of_Cambridge"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
self.newRow['EAS_Allele_frequency_1000_Genomes'] = '0.0'
self.newRow['Allele_frequency_ExAC'] = '9.841e-06'
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
self.oldRow['EAS_Allele_frequency_1000_Genomes'] = '0.0'
self.oldRow['Allele_frequency_ExAC'] = '9.841e-06'
self.newRow['EAS_Allele_frequency_1000_Genomes'] = '0'
self.newRow['Allele_frequency_ExAC'] = '9.841E-06'
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_handles_fields_with_commas_in_parentheses_correctly(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.updated_fieldnames = self.fieldnames + ['Genetic_origin_LOVD', 'RNA_LOVD', 'Submitters_LOVD']
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.updated_fieldnames)
self.newRow["Submitters_LOVD"] = "Ans M.W. van den Ouweland (Rotterdam,NL), Genevieve Michils (Leuven,BE), Rien Blok (Maastricht NL)"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(len(diff), 1)
v_diff = diff['chr17:g.43049067:C>T'][0]
self.assertEqual(v_diff['field'], 'Submitters_LOVD')
self.assertEqual(len(v_diff['added']), 3)
self.assertIn("Ans M.W. van den Ouweland (Rotterdam,NL)", v_diff['added'])
self.assertIn("Genevieve Michils (Leuven,BE)", v_diff['added'])
self.assertIn("Rien Blok (Maastricht NL)", v_diff['added'])
def test_handles_fields_with_commas_in_parentheses_correctly(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.updated_fieldnames = self.fieldnames + ['Genetic_origin_LOVD', 'RNA_LOVD', 'Submitters_LOVD']
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.updated_fieldnames)
self.newRow["Submitters_LOVD"] = "Ans M.W. van den Ouweland (Rotterdam,NL), Genevieve Michils (Leuven,BE), Rien Blok (Maastricht NL)"
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
self.assertEqual(len(diff), 1)
v_diff = diff['chr17:g.43049067:C>T'][0]
self.assertEqual(v_diff['field'], 'Submitters_LOVD')
self.assertEqual(len(v_diff['added']), 3)
self.assertIn("Ans M.W. van den Ouweland (Rotterdam,NL)", v_diff['added'])
self.assertIn("Genevieve Michils (Leuven,BE)", v_diff['added'])
self.assertIn("Rien Blok (Maastricht NL)", v_diff['added'])
def test_properly_handles_field_name_changes_added_data(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.updated_fieldnames = self.fieldnames + ['Minor_allele_frequency_percent_ESP']
self.fieldnames = self.fieldnames + ['Minor_allele_frequency_ESP']
self.oldRow['Minor_allele_frequency_ESP'] = '-'
self.newRow['Minor_allele_frequency_percent_ESP'] = '2.5'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.updated_fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
v_diff = diff['chr17:g.43049067:C>T'][0]
self.assertEqual(len(diff), 1)
self.assertEqual(v_diff['field'], 'Minor_allele_frequency_percent_ESP')
self.assertEqual(v_diff['added'], '2.5')
self.assertEqual(v_diff['removed'], '-')
self.assertEqual(change_type, "added_information")
def test_properly_handles_field_name_changes_added_data(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
self.updated_fieldnames = self.fieldnames + ['Minor_allele_frequency_percent_ESP']
self.fieldnames = self.fieldnames + ['Minor_allele_frequency_ESP']
self.oldRow['Minor_allele_frequency_ESP'] = '-'
self.newRow['Minor_allele_frequency_percent_ESP'] = '2.5'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.updated_fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow, False)
diff = releaseDiff.diff_json
v_diff = diff['chr17:g.43049067:C>T'][0]
self.assertEqual(len(diff), 1)
self.assertEqual(v_diff['field'], 'Minor_allele_frequency_percent_ESP')
self.assertEqual(v_diff['added'], '2.5')
self.assertEqual(v_diff['removed'], '-')
self.assertEqual(change_type, "added_information")
def test_ignores_cosmetic_changes_in_diff(self):
releaseDiff.added_data = self.added_data
releaseDiff.diff = self.diff
releaseDiff.diff_json = self.diff_json
variant = 'chr17:g.43049067:C>T'
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
self.oldRow["Submitter_ClinVar"] = "The_Consortium_of_Investigators_of_Modifiers_of_BRCA1/2_(CIMBA),c/o_University_of_Cambridge"
self.newRow["Submitter_ClinVar"] = "Consortium_of_Investigators_of_Modifiers_of_BRCA1/2_(CIMBA),_c/o_University_of_Cambridge"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
self.oldRow["Submitter_ClinVar"] = "Consortium_of_Investigators_of_Modifiers_of_BRCA1/2_(CIMBA),_c/o_University_of_Cambridge"
self.newRow["Submitter_ClinVar"] = "The_Consortium_of_Investigators_of_Modifiers_of_BRCA1/2_(CIMBA),c/o_University_of_Cambridge"
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
self.newRow['EAS_Allele_frequency_1000_Genomes'] = '0.0'
self.newRow['Allele_frequency_ExAC'] = '9.841e-06'
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
self.oldRow['EAS_Allele_frequency_1000_Genomes'] = '0.0'
self.oldRow['Allele_frequency_ExAC'] = '9.841e-06'
self.newRow['EAS_Allele_frequency_1000_Genomes'] = '0'
self.newRow['Allele_frequency_ExAC'] = '9.841E-06'
change_type = v1v2.compareRow(self.oldRow, self.newRow)
diff = releaseDiff.diff_json
self.assertEqual(diff, {})
self.assertIsNone(change_type)
def test_compare_row_added_data(self):
releaseDiff.added_data = self.added_data
self.newRow['Source'] += ",ENIGMA"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
self.assertEqual(change_type, "added_information")
def test_compare_row_equal_rows(self):
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
self.assertIsNone(change_type)
def test_compare_row_added_data(self):
releaseDiff.added_data = self.added_data
self.newRow['Source'] += ",ENIGMA"
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
self.assertEqual(change_type, "added_information")
def test_compare_row_equal_rows(self):
v1v2 = releaseDiff.v1ToV2(self.fieldnames, self.fieldnames)
change_type = v1v2.compareRow(self.oldRow, self.newRow)
self.assertIsNone(change_type)