Skip to content

Add new variables to Birmingham germline importer #180

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
NImeson merged 9 commits into from
Mar 9, 2026
Merged

Add new variables to Birmingham germline importer #180

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
6b9955d
new indications added to constants to import missing SRIs following c…
NImeson Feb 27, 2026
ca48352
Added test in for new PC indication, 3 possible teststatus scenarios
NImeson Feb 27, 2026
9df683a
re-adding test method that was deleted in error
NImeson Feb 27, 2026
500eb1a
added a missed addition to constants file
NImeson Feb 27, 2026
b82a7bf
Added comments on new test and added additional test for BAP1 indication
NImeson Mar 6, 2026
40c9f15
edited tests and added new moleculartestingtype
NImeson Mar 6, 2026
4d1bbb6
corrected BAP1 test
NImeson Mar 6, 2026
0b439a0
Update gene in test method
NImeson Mar 9, 2026
01a9baa
Merge branch 'develop' into feature/ndrs2-3690/add_new_birmimgham_crc…
NImeson Mar 9, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 18 additions & 6 deletions lib/import/helpers/colorectal/providers/rq3/rq3_constants.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,19 +18,22 @@ module Rq3Constants
'indirect testing' => :full_screen,
'pold1/ pole analysis' => :full_screen,
'prenatal diagnosis' => :targeted_mutation,
'presymptomatic' => :targeted_mutation }.freeze
'presymptomatic' => :targeted_mutation,
'mainstreaming' => :full_screen }.freeze

COLORECTAL_GENES_MAP = { 'PJS' => %w[STK11],
'PHTS' => %w[PTEN],
'MAP' => %w[MUTYH],
'FAP' => %w[APC],
'PPAP' => %w[POLE POLD1],
'COCA' => %w[MLH1 MSH2],
'POLY' => %w[APC MUTYH],
'NGS_COLON' => %w[MLH1 MSH2 MSH6 APC MUTYH],
'POLY' => %w[APC MUTYH NTHL1],
'NGS_COLON' => %w[MLH1 MSH2 MSH6 APC MUTYH NTHL1],
'COLON' => %w[MLH1 MSH2 MSH6 PMS2 APC MUTYH PTEN
SMAD4 BMPR1A STK11],
'HNPCC' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM] }.freeze
SMAD4 BMPR1A STK11 NTHL1],
'HNPCC' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM],
'PC' => %w[BRCA1 BRCA2 ATM CHEK2 PALB2 MLH1 MLH2 MSH6], #contents of the R430 panel
'BAP1' => %w[BAP1]}.freeze

COLORECTAL_GENES_REGEX = /(?<colorectal>APC|
BMPR1A|
Expand All @@ -45,7 +48,16 @@ module Rq3Constants
PTEN|
SMAD4|
STK11|
TACSTD1)/xi.freeze
TACSTD1|
BAP1|
NTHL1|
GREM1|
RNF43|
BRCA1|
BRCA2|
ATM|
CHEK2|
PALB2)/xi.freeze

CDNA_REGEX = /c\.(?<cdna>([0-9]+[^[:alnum:]][0-9][^[:alnum:]][0-9]+
[^[:alnum:]][0-9][a-z]+)|
Expand Down
3 changes: 2 additions & 1 deletion lib/import/helpers/colorectal/providers/rq3/rq3_helper.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -275,7 +275,8 @@ def sometimes_tested?(record)
record.raw_fields['indication'] == 'HNPCC' ||
record.raw_fields['indication'] == 'COLON' ||
record.raw_fields['indication'] == 'NGS_COLON' ||
record.raw_fields['indication'] == 'POLY'
record.raw_fields['indication'] == 'POLY' ||
record.raw_fields['indication'] == 'PC'
end

def process_testresult_multiple_cdnavariant
Expand Down
118 changes: 118 additions & 0 deletions test/lib/import/colorectal/providers/birmingham/birmingham_handler_colorectal_test.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,9 @@ def setup
@record.raw_fields['moleculartestingtype'] = 'RNA studies'
@handler.process_genetictestscope(@genotype, @record)
assert_equal 'Unable to assign Colorectal Lynch or MMR genetictestscope', @genotype.attribute_map['genetictestscope']
@record.raw_fields['moleculartestingtype'] = 'Mainstreaming'
@handler.process_genetictestscope(@genotype, @record)
assert_equal 'Full screen Colorectal Lynch or MMR', @genotype.attribute_map['genetictestscope']
end

test 'process_multiple_tests_from_fullscreen' do
Expand Down Expand Up @@ -176,6 +179,121 @@ def setup
assert_equal 62, genocolorectals[0].attribute_map['gene']
end

test 'process_variants_from_report_new_pc_indication_two_genes' do
# where 2 genes are indicated in the report field
pathogenic_record = build_raw_record('pseudo_id1' => 'bob')
pathogenic_record.raw_fields['indication'] = 'PC'
pathogenic_record.raw_fields['report'] = 'Next Generation Sequencing of coding regions in BRCA1 (NM_007294.4) and BRCA2 (NM_000059.3) (Illumina TruSight Hereditary Cancer Panel)'
pathogenic_record.raw_fields['overall2'] = 'Pathogenic'
pathogenic_record.raw_fields['teststatus'] = 'Heterozygous pathogenic variant c.1234_5678del p.(Asn1234Lysfs*3) identified in the BRCA2 gene in germline blood DNA'
processor = variant_processor_for(pathogenic_record)
genocolorectals = processor.process_variants_from_report
assert_equal 1, genocolorectals[0].attribute_map['teststatus']
assert_equal 7, genocolorectals[0].attribute_map['gene']
assert_equal 2, genocolorectals[1].attribute_map['teststatus']
assert_equal 'p.Asn1234LysfsTer3', genocolorectals[1].attribute_map['proteinimpact']
assert_equal 'c.1234_5678delp', genocolorectals[1].attribute_map['codingdnasequencechange']
assert_equal 8, genocolorectals[1].attribute_map['gene']

normal_record = build_raw_record('pseudo_id1' => 'bob')
normal_record.raw_fields['indication'] = 'PC'
normal_record.raw_fields['report'] = 'Next Generation Sequencing of coding regions in BRCA1 (NM_007294.4) and BRCA2 (NM_000059.3) (Illumina TruSight Hereditary Cancer Panel)'
normal_record.raw_fields['overall2'] = 'Normal'
normal_record.raw_fields['teststatus'] = 'No evidence of a pathogenic variant in BRCA1 or BRCA2'
processor = variant_processor_for(normal_record)
genocolorectals2 = processor.process_variants_from_report
assert_equal 1, genocolorectals2[0].attribute_map['teststatus']
assert_equal 7, genocolorectals2[0].attribute_map['gene']
assert_equal 1, genocolorectals2[1].attribute_map['teststatus']
assert_equal 8, genocolorectals2[1].attribute_map['gene']
end

test 'process_variants_from_report_new_pc_indication_8_standard_genes' do
# where 8 genes are indicated in the report field
normal_record = build_raw_record('pseudo_id1' => 'bob')
normal_record.raw_fields['indication'] = 'PC'
normal_record.raw_fields['report'] = 'Next Generation Sequencing of coding regions in ATM (NM_000051.3), BRCA1 (NM_007294.4),
BRCA2 (NM_000059.3), CHEK2 exons 2-10 plus codon 367 (NM_007194.4), MLH1 (NM_000249.4),
MSH2 (NM_000251.3), MSH6 (NM_000179.3) and PALB2 (NM_024675.4) (Illumina TruSight Hereditary Cancer Panel)'
normal_record.raw_fields['overall2'] = 'Normal'
normal_record.raw_fields['teststatus'] = 'No evidence of a pathogenic variant in BRCA1, BRCA2, MLH1, MSH2, MSH6 or PALB2.'
processor = variant_processor_for(normal_record)
genocolorectals = processor.process_variants_from_report
assert_equal 8, genocolorectals.size
assert(genocolorectals.all? { |g| g.attribute_map['teststatus'] == 1 })

normal_record = build_raw_record('pseudo_id1' => 'bob')
normal_record.raw_fields['indication'] = 'PC'
normal_record.raw_fields['report'] = 'Next Generation Sequencing of coding regions in ATM (NM_000051.3), BRCA1 (NM_007294.4),
BRCA2 (NM_000059.3), CHEK2 exons 2-10 plus codon 367 (NM_007194.4), MLH1 (NM_000249.4),
MSH2 (NM_000251.3), MSH6 (NM_000179.3) and PALB2 (NM_024675.4) (Illumina TruSight Hereditary Cancer Panel)'
normal_record.raw_fields['overall2'] = 'Normal'
normal_record.raw_fields['teststatus'] = 'HHeterozygous pathogenic variant c.1447C>T p.(Gln483*) identified in the MLH1 gene.'
processor = variant_processor_for(normal_record)
genocolorectals2 = processor.process_variants_from_report
assert_equal 8, genocolorectals2.size
assert_equal 1, genocolorectals2[4].attribute_map['teststatus']
assert_nil genocolorectals2[4].attribute_map['codingdnasequencechange']
assert_nil genocolorectals2[4].attribute_map['proteinimpact']
assert_equal 2744, genocolorectals2[4].attribute_map['gene']
end

test 'process_variants_from_report_new_pc_indication_nine_genes' do
# where 9 genes are indicated in the report field
uv_record = build_raw_record('pseudo_id1' => 'bob')
uv_record.raw_fields['indication'] = 'PC'
uv_record.raw_fields['overall2'] = 'UV'
uv_record.raw_fields['report'] = 'Next Generation Sequencing of coding regions in ATM (NM_000051.3), BRCA1 (NM_007294.4),
BRCA2 (NM_000059.3), CHEK2 exons 2-10 plus codon 367 (NM_007194.4), MLH1 (NM_000249.4),
MSH2 (NM_000251.3), MSH6 (NM_000179.3) and PALB2 (NM_024675.4). MLPA of EPCAM.'
uv_record.raw_fields['teststatus'] = 'Heterozygous inframe deletion variant of uncertain significance c.12_34del p.(Asp12_Leu17del) detected in the MLH1 gene'
processor = variant_processor_for(uv_record)
genocolorectals = processor.process_variants_from_report
assert_equal 9, genocolorectals.size
assert_equal 2744, genocolorectals[8].attribute_map['gene']
assert_equal 2, genocolorectals[8].attribute_map['teststatus']
assert_equal 3, genocolorectals[8].attribute_map['variantpathclass']
assert_equal 'c.12_34delp', genocolorectals[8].attribute_map['codingdnasequencechange']

normal_record = build_raw_record('pseudo_id1' => 'bob')
normal_record.raw_fields['indication'] = 'PC'
normal_record.raw_fields['overall2'] = 'Normal'
normal_record.raw_fields['report'] = 'Next Generation Sequencing of coding regions in ATM (NM_000051.3), BRCA1 (NM_007294.4),
BRCA2 (NM_000059.3), CHEK2 exons 2-10 plus codon 367 (NM_007194.4), MLH1 (NM_000249.4),
MSH2 (NM_000251.3), MSH6 (NM_000179.3) and PALB2 (NM_024675.4). MLPA of EPCAM.'
normal_record.raw_fields['teststatus'] = 'No evidence of a pathogenic variant in BRCA1, BRCA2, MLH1, MSH2, MSH6 or PALB2.'
processor = variant_processor_for(normal_record)
genocolorectals = processor.process_variants_from_report
assert_equal 9, genocolorectals.size
assert(genocolorectals.all? { |g| g.attribute_map['teststatus'] == 1 })
end


test 'process_variants_from_report_new_bap1_indication' do
pathogenic_record = build_raw_record('pseudo_id1' => 'bob')
pathogenic_record.raw_fields['indication'] = 'BAP1'
pathogenic_record.raw_fields['report'] = 'Sanger sequencing analysis was used to detect the familial variant in the BAP1 gene. '
pathogenic_record.raw_fields['overall2'] = 'Pathogenic'
pathogenic_record.raw_fields['teststatus'] = 'Molecular analysis shows the presence of the familial pathogenic variant c.123-1G>A in the BAP1 gene'
processor = variant_processor_for(pathogenic_record)
genocolorectal = processor.process_variants_from_report
assert_equal 1, genocolorectal.size
assert_equal 2, genocolorectal[0].attribute_map['teststatus']
assert_equal 'c.123-1G>A', genocolorectal[0].attribute_map['codingdnasequencechange']
assert_equal 517, genocolorectal[0].attribute_map['gene']

normal_record = build_raw_record('pseudo_id1' => 'bob')
normal_record.raw_fields['indication'] = 'BAP1'
normal_record.raw_fields['report'] = 'Next Generation Sequencing of coding regions in BAP1 (NM_004656.4) (Illumina TruSight Hereditary Cancer Panel'
normal_record.raw_fields['overall2'] = 'Normal'
normal_record.raw_fields['teststatus'] = 'Molecular analysis shows no evidence of the familial pathogenic variant in the BAP1 gene'
processor = variant_processor_for(normal_record)
genocolorectal2 = processor.process_variants_from_report
assert_equal 1, genocolorectal2.size
assert_equal 1, genocolorectal2[0].attribute_map['teststatus']
assert_equal 517, genocolorectal2[0].attribute_map['gene']
end

private

def variant_processor_for(record)
Expand Down
Loading