Skip to content

Feature/ndrs2 2040/sheffield crc missing sris #151

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 20 commits into from
Jul 17, 2025
Merged

Feature/ndrs2 2040/sheffield crc missing sris #151

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
20 commits
Select commit Hold shift + click to select a range
2a8dc81
update sheffield colorectal importer rules
lauramccluskey1 Jul 30, 2024
a9d1f41
Merge branch 'develop' into feature/36582/sheffield_importer
lauramccluskey1 Sep 5, 2024
085bae0
updated panels
NImeson Mar 19, 2025
f525d5f
added new panels, expanded variant regexes
NImeson Mar 27, 2025
76ca248
Merge remote-tracking branch 'origin/develop' into feature/ndrs2_2040…
NImeson Apr 14, 2025
ad17074
Merge branch 'develop' of https://github.com/NHSDigital/data_manageme…
NImeson May 30, 2025
a4d9fad
correcte typo
NImeson Jun 2, 2025
1ee36ca
corrected variant regexes
NImeson Jun 2, 2025
95d13dd
Merge remote-tracking branch 'origin/feature/36582/sheffield_importer…
NImeson Jun 3, 2025
d7b8587
pulled in Laura's original changes'
NImeson Jun 9, 2025
1a3f6eb
small corrections
NImeson Jun 16, 2025
25dbd2a
removed no gene teststatud addition - causes problems elsewhere
NImeson Jun 16, 2025
2853279
added facility to add test status where no genes are present for othe…
NImeson Jun 16, 2025
1430753
code updated - counts look better
NImeson Jun 16, 2025
78291ce
removed duplicate code
NImeson Jun 19, 2025
9a04eeb
removed comments
NImeson Jun 19, 2025
55c76e3
removed comments
NImeson Jun 19, 2025
b634c6b
fixing issue with no gene and not creating a duplicate object
NImeson Jun 23, 2025
c1d683d
removed commented out line
NImeson Jun 30, 2025
8232801
few code review changes, added tests
NImeson Jul 7, 2025
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
47 changes: 41 additions & 6 deletions lib/import/colorectal/providers/sheffield/sheffield_handler_colorectal.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ class SheffieldHandlerColorectal < Import::Germline::ProviderHandler

def process_fields(record)
genotype_str = record.raw_fields['genetictestscope'].strip
return if NON_CRC_GENTICTESCOPE.include? genotype_str.downcase
return if NON_CRC_GENETICTESTSCOPE.include? genotype_str.downcase

genocolorectal = Import::Colorectal::Core::Genocolorectal.new(record)
genocolorectal.add_passthrough_fields(record.mapped_fields,
Expand All @@ -32,6 +32,9 @@ def add_test_scope_from_geno_karyo(genocolorectal, record)
genotype_str = record.raw_fields['genetictestscope'].strip
karyo = record.raw_fields['karyotypingmethod'].strip
moleculartestingtype = record.raw_fields['moleculartestingtype'].strip
if genotype_str.downcase.match(/r211\s::\sinherited\spolyposis\sand\searly\sonset\scolorectal\scancer/)
genotype_str="r211 :: inherited polyposis and early onset colorectal cancer, germline testing"
end
process_method = GENETICTESTSCOPE_METHOD_MAPPING[genotype_str.downcase]
if process_method
public_send(process_method, karyo, genocolorectal, moleculartestingtype)
Expand Down Expand Up @@ -90,6 +93,9 @@ def process_scope_r210(karyo, genocolorectal, moleculartestingtype)
end

def process_scope_r211(karyo, genocolorectal, moleculartestingtype)
if karyo.downcase.match(/r211.1\s::\ssmall\spanel\sin\sleeds.*send\sdna\ssample/)
karyo='R211.1 :: Small panel in Leeds - send DNA sample'
end
if R211_PANEL_GENE_MAPPING_FS.keys.include? karyo
@logger.debug "ADDED FULL_SCREEN TEST for: #{karyo}"
genocolorectal.add_test_scope(:full_screen)
Expand All @@ -106,6 +112,17 @@ def process_scope_r211(karyo, genocolorectal, moleculartestingtype)
end
end


def process_scope_r414(karyo, genocolorectal, moleculartestingtype)
if R414_PANEL_GENE_MAPPING_FS.keys.include? karyo
@logger.debug "ADDED FULL_SCREEN TEST for: #{karyo}"
genocolorectal.add_test_scope(:full_screen)
@genes_set = R414_PANEL_GENE_MAPPING_FS[karyo]
else
genocolorectal.add_test_scope(:no_genetictestscope)
end
end

def process_scope_fap_familial(karyo, genocolorectal, _moleculartestingtype)
if FAP_FAM_PANEL_GENE_MAPPING_TAR.keys.include? karyo
@logger.debug "ADDED TARGETED TEST for: #{karyo}"
Expand Down Expand Up @@ -149,7 +166,7 @@ def process_scope_myh(karyo, genocolorectal, moleculartestingtype)
scope = MOLECULAR_SCOPE_MAPPING[moleculartestingtype.downcase]
@logger.debug "ADDED #{scope} TEST for: #{moleculartestingtype}"
genocolorectal.add_test_scope(scope)
@genes_set = %w[APC MUTYH]
@genes_set = %w[MUTYH]
else
genocolorectal.add_test_scope(:no_genetictestscope)
end
Expand Down Expand Up @@ -218,12 +235,25 @@ def process_fullscreen_records(genocolorectal, record, genocolorectals)

def process_targeted_no_scope_records(genocolorectal, record, genocolorectals)
genotype_str = record.raw_fields['genotype']
if normal?(genotype_str)
if genotype_str.scan(/fail/i).size.positive?
gene=get_gene(record)
genocolorectal.add_status(9)
genocolorectals.append(genocolorectal)
elsif normal?(genotype_str)
process_normal_targeted(genocolorectal, record, genocolorectals)
elsif positive_cdna?(genotype_str) || positive_exonvariant?(genotype_str)
process_variant_targeted(genocolorectal, record, genocolorectals)
elsif only_protein_impact?(genotype_str)
process_only_protein_rec(genocolorectal, record, genocolorectals)
elsif genotype_str.scan(/^pathogenic\smutation\sdetected/).size.positive?
gene = get_gene(record)
genocolorectal.add_status(2)
genocolorectals.append(genocolorectal)
else
gene=get_gene(record)
genocolorectal.add_status(4)
genocolorectals.append(genocolorectal)

end
end

Expand All @@ -242,7 +272,13 @@ def process_normal_targeted(genocolorectal, record, genocolorectals)

def process_normal_full_screen(genocolorectal, genocolorectals)
negative_genes = @genes_set
add_other_genes_with_status(negative_genes, genocolorectal, genocolorectals, 1)
if !negative_genes.empty?
add_other_genes_with_status(negative_genes, genocolorectal, genocolorectals, 1)
else
genocolorectals.append(genocolorectal)
end


genocolorectals
end

Expand All @@ -256,8 +292,7 @@ def add_other_genes_with_status(other_genes, genocolorectal, genocolorectals, st
genotype_othr.add_gene_location(nil)
genocolorectals.append(genotype_othr)
end
genocolorectals
end
end

def positive_cdna?(genotype_string)
genotype_string.scan(CDNA_REGEX).size.positive?
Expand Down
34 changes: 26 additions & 8 deletions lib/import/helpers/colorectal/providers/rcu/constants.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ module Constants
genotype
age].freeze

NON_CRC_GENTICTESCOPE = [
NON_CRC_GENETICTESTSCOPE = [
'r208 :: inherited breast cancer and ovarian cancer',
'r208 :: brca1 and brca2 testing at high familial risk',
'r205 :: inherited breast cancer (without ovarian cancer) at very high familial risk',
Expand Down Expand Up @@ -62,7 +62,9 @@ module Constants
'fap familial mutation' => :process_scope_fap_familial,
'hnpcc' => :process_scope_hnpcc,
'myh' => :process_scope_myh,
'breast ovarian & colorectal cancer panel' => :process_scope_colo_ovarian_panel
'breast ovarian & colorectal cancer panel' => :process_scope_colo_ovarian_panel,
'r211 :: inherited polyposis and early onset colorectal cancer, germline testing'=> :process_scope_r211,
'r414 :: apc associated polyposis'=> :process_scope_r414
}.freeze

COLO_PANEL_GENE_MAPPING_FS = {
Expand All @@ -74,8 +76,7 @@ module Constants
'Extended CRC panel - analysis only' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM
APC MUTYH BMPR1A PTEN POLD1
POLE SMAD4 STK11],
'Full panel' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM APC MUTYH BMPR1A PTEN POLD1 POLE SMAD4
STK11],
'Full panel' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM APC MUTYH BMPR1A PTEN POLD1 POLE SMAD4 STK11],
'MLH1 MSH2 MSH6 PMS1 & PMS2' => %w[MLH1 MSH2 MSH6 PMS1 PMS2],
'MLH1 MSH2 MSH6 and PMS2' => %w[MLH1 MSH2 MSH6 PMS2],
'MLH1 MSH2 and MSH6' => %w[MLH1 MSH2 MSH6],
Expand All @@ -90,6 +91,11 @@ module Constants
'STK11 familial mutation' => %w[STK11]
}.freeze


R414_PANEL_GENE_MAPPING_FS = {
'R414.1 :: APC sequencing in Leeds' => %w[APC]
}.freeze

R209_PANEL_GENE_MAPPING_FS = {
'R209.1 :: NGS - APC and MUTYH only' => %w[APC MUTYH],
'R209.1 :: Small panel in Leeds' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM APC MUTYH BMPR1A
Expand All @@ -110,13 +116,19 @@ module Constants
R210_PANEL_GENE_MAPPING_FS = {
'R210.2 :: Small panel in Leeds' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM],
'R210.2 :: Unknown mutation(s) by Small panel' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM],
'R210.5 :: Unknown mutation(s) by MLPA or equivalent' => %w[MLH1 MSH2 EPCAM]
'R210.5 :: Unknown mutation(s) by MLPA or equivalent' => %w[MLH1 MSH2 EPCAM],
'R210.1 :: Unknown mutation(s) by Microsatellite instability'=> %w[MLH1 MSH2 MSH6 PMS2 EPCAM],
'R210.2 :: Small panel in Leeds - Send DNA'=> %w[MLH1 MSH2 MSH6 PMS2 EPCAM]
}.freeze

R210_PANEL_GENE_MAPPING_TAR = {
'R240.1 :: Diagnostic familial' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM],
'R242.1 :: Predictive MLPA' => %w[MLH1 MSH2 EPCAM],
'R242.1 :: Predictive testing' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM]
'R242.1 :: Predictive testing' => %w[MLH1 MSH2 MSH6 PMS2 EPCAM],
'R242.1 :: Predictive testing - MLPA in Leeds - Send Blood'=> %w[MLH1 MSH2 MSH6 PMS2 EPCAM],
'R242.1 :: Predictive testing - MLPA in Leeds - Send DNA'=> %w[MLH1 MSH2 MSH6 PMS2 EPCAM],
'R242.1 :: Predictive testing - Seq in Leeds - Send Blood'=> %w[MLH1 MSH2 MSH6 PMS2 EPCAM],
'R242.1 :: Predictive testing - Seq in Leeds - Send DNA'=> %w[MLH1 MSH2 MSH6 PMS2 EPCAM]
}.freeze

R210_PANEL_GENE_MAPPING_MOL = {
Expand All @@ -125,13 +137,19 @@ module Constants
}.freeze

R211_PANEL_GENE_MAPPING_FS = {
'R211.1 :: Small Panel in Leeds' => %w[APC BMPR1A EPCAM MLH1 MSH2 MSH6 MUTYH NTHL1 PMS2 POLD1 POLE PTEN RNF43 SMAD4 STK11],
'R211.1 :: Small panel in Leeds - send DNA sample'=> %w[APC BMPR1A EPCAM MLH1 MSH2 MSH6 MUTYH NTHL1 PMS2 POLD1 POLE PTEN RNF43 SMAD4 STK11],
'R211.1 :: APC and MUTYH genes in Leeds' => %w[APC MUTYH],
'R211.2 :: Unknown mutation(s) by MLPA or equivalent' => %w[APC MUTYH]
}.freeze

R211_PANEL_GENE_MAPPING_TAR = {
'R240.1 :: Diagnostic familial' => %w[APC MUTYH],
'R242.1 :: Predictive testing' => %w[APC MUTYH]
'R240.1 :: Diagnostic familial - Seq in Leeds - Send Blood'=> %w[APC BMPR1A EPCAM MLH1 MSH2 MSH6 MUTYH NTHL1 PMS2 POLD1 POLE PTEN RNF43 SMAD4 STK11],
'R242.1 :: Predictive testing' => %w[APC BMPR1A EPCAM MLH1 MSH2 MSH6 MUTYH NTHL1 PMS2 POLD1 POLE PTEN RNF43 SMAD4 STK11],
'R242.1 :: Predictive testing - Seq in Leeds - Send Blood' => %w[APC BMPR1A EPCAM MLH1 MSH2 MSH6 MUTYH NTHL1 PMS2 POLD1 POLE PTEN RNF43 SMAD4 STK11],
'R242.1 :: Predictive testing - Seq in Leeds - Analysis only'=> %w[APC BMPR1A EPCAM MLH1 MSH2 MSH6 MUTYH NTHL1 PMS2 POLD1 POLE PTEN RNF43 SMAD4 STK11],
'R242.1 :: Predictive testing - Seq in Leeds - Send DNA'=> %w[APC BMPR1A EPCAM MLH1 MSH2 MSH6 MUTYH NTHL1 PMS2 POLD1 POLE PTEN RNF43 SMAD4 STK11]
}.freeze

R211_PANEL_GENE_MAPPING_MOL = {
Expand Down Expand Up @@ -185,7 +203,7 @@ module Constants

# rubocop:disable Lint/MixedRegexpCaptureTypes
NORMAL_VAR_REGEX = %r{(?<not>no|not)[a-z /]+
(?<det>detected|reported|deteected|deteceted)+}ix.freeze
(?<det>detected|reported|deteected|deteceted|present)+}ix.freeze

CDNA_REGEX = /c\.\[?(?<cdna>
([0-9]+[+>_-][0-9][+>_-][0-9]+[+>_-][0-9][ACGTdelinsup]+)|
Expand Down
62 changes: 62 additions & 0 deletions test/lib/import/colorectal/providers/sheffield/sheffield_handler_colorectal_test.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -163,6 +163,52 @@ def setup
assert_nil genocolorectals[0].attribute_map['gene']
end

test 'process_targeted_no_scope_failure' do
exon_record = build_raw_record('pseudo_id1' => 'bob')
exon_record.raw_fields['genetictestscope'] = 'efgh'
exon_record.raw_fields['karyotypingmethod'] = 'abcd'
exon_record.raw_fields['genotype'] = 'Fail'
exon_record.raw_fields['moleculartestingtype'] = 'Diagnostic testing'
@handler.add_test_scope_from_geno_karyo(@genotype, exon_record)
genocolorectals = @handler.process_variants_from_record(@genotype, exon_record)
assert_equal 1, genocolorectals.size
assert_equal 'Unable to assign Colorectal Lynch or MMR genetictestscope', @genotype.attribute_map['genetictestscope']
assert_nil genocolorectals[0].attribute_map['proteinimpact']
assert_equal 9, genocolorectals[0].attribute_map['teststatus']
end

test 'process_targeted_no_scope_normal' do
exon_record = build_raw_record('pseudo_id1' => 'bob')
exon_record.raw_fields['genetictestscope'] = 'efgh'
exon_record.raw_fields['karyotypingmethod'] = 'abcd'
exon_record.raw_fields['genotype'] = 'no pathogenic variant detected'
exon_record.raw_fields['moleculartestingtype'] = 'Diagnostic testing'
@handler.add_test_scope_from_geno_karyo(@genotype, exon_record)
genocolorectals = @handler.process_variants_from_record(@genotype, exon_record)
assert_equal 1, genocolorectals.size
assert_equal 'Unable to assign Colorectal Lynch or MMR genetictestscope', @genotype.attribute_map['genetictestscope']
assert_nil genocolorectals[0].attribute_map['proteinimpact']
assert_nil genocolorectals[0].attribute_map['codingdnasequencechange']
assert_equal 1, genocolorectals[0].attribute_map['teststatus']
assert_nil genocolorectals[0].attribute_map['gene']
end

test 'process_targeted_no_scope_abnormal' do
exon_record = build_raw_record('pseudo_id1' => 'bob')
exon_record.raw_fields['genetictestscope'] = 'efgh'
exon_record.raw_fields['karyotypingmethod'] = 'abcd'
exon_record.raw_fields['genotype'] = 'MSH2-c.1234_1345del-p.(Gln123fs)-Heterozygous-UV4'
exon_record.raw_fields['moleculartestingtype'] = 'Diagnostic testing'
@handler.add_test_scope_from_geno_karyo(@genotype, exon_record)
genocolorectals = @handler.process_variants_from_record(@genotype, exon_record)
assert_equal 1, genocolorectals.size
assert_equal 'Unable to assign Colorectal Lynch or MMR genetictestscope', @genotype.attribute_map['genetictestscope']
assert_equal 2, genocolorectals[0].attribute_map['teststatus']
assert_equal 'p.Gln123fs', genocolorectals[0].attribute_map['proteinimpact']
assert_equal 'c.1234_1345del', genocolorectals[0].attribute_map['codingdnasequencechange']
assert_equal 2804, genocolorectals[0].attribute_map['gene']
end

test 'process_cdna_change' do
@logger.expects(:debug).with('SUCCESSFUL cdna change parse for: 1653dup')
@handler.process_cdna_change(@genotype, @record.raw_fields['genotype'])
Expand Down Expand Up @@ -202,6 +248,22 @@ def setup
assert_equal 1, genocolorectals[0].attribute_map['variantgenotype']
end

test 'unusual characters in panel name' do
exon_record = build_raw_record('pseudo_id1' => 'bob')
exon_record.raw_fields['genetictestscope'] = 'R211 :: Inherited polyposis and early onset colorectal cancer – germline testing'
exon_record.raw_fields['karyotypingmethod'] = 'R211.1 :: Small panel in Leeds – send DNA sample'
exon_record.raw_fields['genotype'] = 'PMS2-c.[1234A>G]-Heterozygous-UV5'
exon_record.raw_fields['moleculartestingtype'] = 'Diagnostic testing'
@handler.add_test_scope_from_geno_karyo(@genotype, exon_record)
genocolorectals = @handler.process_variants_from_record(@genotype, exon_record)
assert_equal 15, genocolorectals.size
assert_equal 'Full screen Colorectal Lynch or MMR', genocolorectals[0].attribute_map['genetictestscope']
assert_nil genocolorectals[0].attribute_map['proteinimpact']
assert_equal 'c.1234A>G', genocolorectals[0].attribute_map['codingdnasequencechange']
assert_equal 1, genocolorectals[0].attribute_map['sequencevarianttype']
assert_equal 3394, genocolorectals[0].attribute_map['gene']
end

private

def clinical_json
Expand Down
Loading