Feature/36796/salisbury new rules #127
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,5 +1,3 @@ | ||
| module Import | ||
| module Brca | ||
| module Providers | ||
|
|
@@ -58,11 +56,11 @@ def process_row_case(genotypes, genotype, record) | |
| genotype_new.add_status(status) | ||
| extract_gene_row(genotype_new, record) | ||
| if [2, 10].include? status | ||
| handle_variant_record(genotype_new, record, genotypes) | ||
| else | ||
| genotypes << genotype_new | ||
| end | ||
| genotypes | ||
| end | ||
|
|
||
| def process_panel_case(genotypes, genotype, record) | ||
|
|
@@ -105,20 +103,21 @@ def process_hybrid_case(genotypes, genotype, record) | |
|
|
||
| def process_panel_record(genotypes, genotype, raw_record) | ||
| status_genes = extract_genes(%w[test genotype], raw_record) | ||
| status_genes.each do |status_gene| | ||
| status_found = @status_genes_hash[status_gene]&.uniq | ||
| if status_found.size > 1 | ||
| process_multi_status_genes([status_gene], status_found, genotype, genotypes, raw_record) | ||
| elsif UNKNOWN_STATUS.include? @status | ||
| process_status_genes([status_gene], 4, genotype, genotypes, raw_record) | ||
| elsif FAILED_TEST.match(@status) | ||
| process_status_genes(@all_genes, 9, genotype, genotypes, raw_record) | ||
| elsif ABNORMAL_STATUS.include? @status | ||
| process_status_genes([status_gene], 10, genotype, genotypes, raw_record) | ||
| elsif NEGATIVE_STATUS.include? @status | ||
| process_status_genes([status_gene], 1, genotype, genotypes, raw_record) | ||
| elsif POSITIVE_STATUS.include?(@status) || @status.match(/^variant*/ix) | ||
| process_status_genes([status_gene], 2, genotype, genotypes, raw_record) | ||
| end | ||
| end | ||
| end | ||
|
|
||
|
|
@@ -127,11 +126,12 @@ def prepare_gene_status_hash(record) | |
| assign_status_var(raw_record) | ||
|
|
||
| status_genes = extract_genes(%w[test genotype], raw_record) | ||
| status_genes.each do |status_gene| | ||
| if @status_genes_hash[status_gene] | ||
| @status_genes_hash[status_gene] << @status | ||
| else | ||
| @status_genes_hash[status_gene] = [@status] | ||
| end | ||
| end | ||
| end | ||
| end | ||
|
|
@@ -153,19 +153,21 @@ def assign_status_var(raw_record) | |
| end | ||
|
|
||
| # Use priority if more than one status is present for same gene for a given record | ||
| # rubocop:disable Metrics/CyclomaticComplexity, Metrics/AbcSize, Metrics/PerceivedComplexity | ||
| def process_multi_status_genes(status_genes, status_found, genotype, genotypes, raw_record) | ||
| if status_found.intersect?(POSITIVE_STATUS) || status_found.any? { |e| e.match(/^variant/) } | ||
| process_status_genes(status_genes, 2, genotype, genotypes, raw_record) if extract_teststatus_record == 2 | ||
| elsif status_found.intersect?(ABNORMAL_STATUS) | ||
| process_status_genes(status_genes, 10, genotype, genotypes, raw_record) if extract_teststatus_record == 10 | ||
| elsif status_found.intersect?(NEGATIVE_STATUS) | ||
| process_status_genes(status_genes, 1, genotype, genotypes, raw_record) if extract_teststatus_record == 1 | ||
| elsif status_found.match(FAILED_TEST) | ||
| process_status_genes(@all_genes, 9, genotype, genotypes, raw_record) if extract_teststatus_record == 9 | ||
| elsif status_found.intersect?(UNKNOWN_STATUS) | ||
| process_status_genes(status_genes, 4, genotype, genotypes, raw_record) if extract_teststatus_record == 4 | ||
| end | ||
| end | ||
| # rubocop:enable Metrics/CyclomaticComplexity, Metrics/AbcSize, Metrics/PerceivedComplexity | ||
|
|
||
| def process_status_genes(genes, status, genotype, genotypes, record) | ||
| return unless genes&.all? { |gene| @all_genes.include?(gene) } | ||
|
|
@@ -176,10 +178,25 @@ def process_status_genes(genes, status, genotype, genotypes, record) | |
| genotype_new.add_gene(gene) | ||
| genotype_new.add_status(status) | ||
| if [2, 10].include? status | ||
| handle_variant_record(genotype_new, record, genotypes) | ||
| else | ||
| genotypes << genotype_new | ||
| end | ||
| end | ||
| genotypes | ||
| end | ||
|
|
||
| def handle_variant_record(genotype_new, record, genotypes) | ||
| assign_variantpathclass_record(genotype_new) | ||
| variant = record['genotype'] | ||
| if variant.present? | ||
| if variant.scan(CDNA_REGEX).size > 1 || | ||
| variant.scan(EXON_VARIANT_REGEX).size > 1 | ||
|
There was a problem hiding this comment. does this need to be if (variant.scan(CDNA_REGEX).size + variant.scan(EXON_VARIANT_REGEX).size) >1 There was a problem hiding this comment. Yes @lauramccluskey1 good point, have now fixed it in 9f1ea0e |
||
| process_multi_vars(genotype_new, variant, genotypes) | ||
| else | ||
| process_variants(genotype_new, variant, genotypes) | ||
| end | ||
| else | ||
| genotypes << genotype_new | ||
| end | ||
| end | ||
|
|
@@ -232,10 +249,24 @@ def extract_gene_row(genotype, record) | |
| genotype.add_gene(gene.first) | ||
| end | ||
|
|
||
| def process_multi_vars(genotype_new, variant, genotypes) | ||
| variants = variant.split(/;|,/) | ||
| variants.each do |var| | ||
| genotype_dup = genotype_new.dup | ||
| gene = var&.scan(BRCA_REGEX)&.flatten&.uniq | ||
| if gene.present? | ||
| genotype_dup.add_gene(gene[0]) | ||
| @all_genes -= gene if @all_genes.present? | ||
|
There was a problem hiding this comment. Do we need to try and ensure we keep the structure of the database if there happened to be two variants in the same gene written e.g. "BRCA1 c123A>C; BRCA1 c456G>A"? - this would ideally need to create one record in genetic_test_results which two child records in genetic_sequence_variants, rather than two BRCA1 records As discussed, this might be a wider problem in the importers? There was a problem hiding this comment. Happy with this after investigations into persister functioning |
||
| end | ||
| process_variants(genotype_dup, var, genotypes) | ||
| end | ||
| end | ||
|
|
||
| def process_variants(genotype_new, variant, genotypes) | ||
| process_cdna_variant(genotype_new, variant) | ||
| process_exonic_variant(genotype_new, variant) | ||
| process_protein_impact(genotype_new, variant) | ||
| genotypes << genotype_new | ||
| end | ||
|
|
||
| def process_exonic_variant(genotype, variant) | ||
|
|
@@ -259,10 +290,6 @@ def process_protein_impact(genotype, variant) | |
| genotype.add_protein_impact($LAST_MATCH_INFO[:impact]) | ||
| @logger.debug "SUCCESSFUL protein parse for: #{$LAST_MATCH_INFO[:impact]}" | ||
| end | ||
| end | ||
| end | ||
| end | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
How can the variantpathclass be handled before assigning the variant? What happens in the case of multiple variants?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi @lauramccluskey1 , As per rules variantpathclass is assigned based on 'status' of record and not variant. For multivariants we will be duplicating genotype object and each having variantpathclass depending on status of raw_record and then capturing the variant present in it. Also to note this method gets called only for teststatus 2 and 10 records.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@lauramccluskey1 @NImeson committed updated rule as discussed in d5f8aa5, Thanks☺️
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Fix looks fine :-)