fix: adding support for "no classification from unflagged records" re…

…view status (#171)
varfish-org · Dec 11, 2023 · f144e74 · f144e74
1 parent 7b76770
commit f144e74
Show file tree

Hide file tree

Showing 4 changed files with 254 additions and 1 deletion.
diff --git a/clinvar_data/models.py b/clinvar_data/models.py
@@ -99,7 +99,8 @@ class ReviewStatus(enum.Enum):
     - 3 stars: reviewed by expert panel
     - 4 stars: reviewed by professional society
 
-    In the case that a submission was flagged as duplicate, `FLAGGED_SUBMISSION` is used.
+    In the case that a submission was flagged as duplicate, ``FLAGGED_SUBMISSION`` is used.
+    When no unflagged submission is found, ``NO_UNFLAGGED_CLASSIFICATION`` is used.
     """
 
     NO_ASSERTION_PROVIDED = "no assertion provided"
@@ -110,6 +111,7 @@ class ReviewStatus(enum.Enum):
     REVIEWED_BY_EXPERT_PANEL = "reviewed by expert panel"
     PRACTICE_GUIDELINE = "practice guideline"
     FLAGGED_SUBMISSION = "flagged submission"
+    NO_UNFLAGGED_CLASSIFICATION = "no classifications from unflagged records"
 
 
 @enum.unique

diff --git a/tests/clinvar_data/data/ex_no_unflagged.xml b/tests/clinvar_data/data/ex_no_unflagged.xml
@@ -0,0 +1,249 @@
+<?xml version="1.0" encoding="utf-8" standalone="yes"?>
+<ReleaseSet xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" Dated="2023-07-30" Type="full" xsi:noNamespaceSchemaLocation="http://ftp.ncbi.nlm.nih.gov/pub/clinvar/xsd_public/clinvar_public_1.70.xsd">
+
+    <ClinVarSet ID="170238667">
+        <RecordStatus>current</RecordStatus>
+        <Title>NM_014780.5(CUL7):c.2592T&gt;G (p.Tyr864Ter) AND 3M syndrome 1</Title>
+        <ReferenceClinVarAssertion ID="269569" DateLastUpdated="2023-12-09" DateCreated="2014-05-09">
+          <ClinVarAccession Acc="RCV000115042" Version="3" Type="RCV" DateUpdated="2023-12-09" DateCreated="2014-05-09"/>
+          <RecordStatus>current</RecordStatus>
+          <ClinicalSignificance>
+            <ReviewStatus>no classifications from unflagged records</ReviewStatus>
+            <Description>no classifications from unflagged records</Description>
+          </ClinicalSignificance>
+          <Assertion Type="variation to disease"/>
+          <ObservedIn>
+            <Sample>
+              <Origin>germline</Origin>
+              <Ethnicity>Arab</Ethnicity>
+              <Species TaxonomyId="9606">human</Species>
+              <AffectedStatus>yes</AffectedStatus>
+            </Sample>
+            <Method>
+              <MethodType>research</MethodType>
+            </Method>
+            <ObservedData ID="142028773">
+              <Attribute Type="Description">not provided</Attribute>
+            </ObservedData>
+          </ObservedIn>
+          <MeasureSet Type="Variant" ID="127244" Acc="VCV000127244" Version="1">
+            <Measure Type="single nucleotide variant" ID="132701">
+              <Name>
+                <ElementValue Type="Preferred">NM_014780.5(CUL7):c.2592T&gt;G (p.Tyr864Ter)</ElementValue>
+              </Name>
+              <CanonicalSPDI>NC_000006.12:43046303:A:C</CanonicalSPDI>
+              <AttributeSet>
+                <Attribute Type="FunctionalConsequence">protein loss of function</Attribute>
+                <XRef ID="0043" DB="Variation Ontology"/>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NM_001374873" Version="1" Change="c.2592T&gt;G" Type="HGVS, coding, RefSeq">NM_001374873.1:c.2592T&gt;G</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NM_001374874" Version="1" Change="c.2592T&gt;G" Type="HGVS, coding, RefSeq">NM_001374874.1:c.2592T&gt;G</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NM_014780" Version="5" Change="c.2592T&gt;G" Type="HGVS, coding, RefSeq" MANESelect="true">NM_014780.5:c.2592T&gt;G</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NM_001168370" Version="2" Change="c.2688T&gt;G" Type="HGVS, coding, RefSeq">NM_001168370.2:c.2688T&gt;G</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NM_001374872" Version="1" Change="c.2688T&gt;G" Type="HGVS, coding, RefSeq">NM_001374872.1:c.2688T&gt;G</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NG_016205" Version="1" Change="g.12642T&gt;G" Type="HGVS, genomic, RefSeqGene">NG_016205.1:g.12642T&gt;G</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NC_000006" Version="12" Change="g.43046304A&gt;C" Type="HGVS, genomic, top level" integerValue="38">NC_000006.12:g.43046304A&gt;C</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NC_000006" Version="11" Change="g.43014042A&gt;C" Type="HGVS, genomic, top level, previous" integerValue="37">NC_000006.11:g.43014042A&gt;C</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NM_001168370" Version="1" Change="c.2844T&gt;G" Type="HGVS, previous">NM_001168370.1:c.2844T&gt;G</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="HGVS, protein">p.Y948*</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NP_001361802" Version="1" Change="p.Tyr864Ter" Type="HGVS, protein, RefSeq">NP_001361802.1:p.Tyr864Ter</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NP_001361803" Version="1" Change="p.Tyr864Ter" Type="HGVS, protein, RefSeq">NP_001361803.1:p.Tyr864Ter</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NP_055595" Version="2" Change="p.Tyr864Ter" Type="HGVS, protein, RefSeq">NP_055595.2:p.Tyr864Ter</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NP_001161842" Version="2" Change="p.Tyr896Ter" Type="HGVS, protein, RefSeq">NP_001161842.2:p.Tyr896Ter</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NP_001361801" Version="1" Change="p.Tyr896Ter" Type="HGVS, protein, RefSeq">NP_001361801.1:p.Tyr896Ter</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Accession="NP_001161842" Version="1" Change="p.Tyr948Ter" Type="HGVS, protein, RefSeq">NP_001161842.1:p.Tyr948Ter</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="MolecularConsequence">nonsense</Attribute>
+                <XRef ID="SO:0001587" DB="Sequence Ontology"/>
+                <XRef ID="NM_001168370.2:c.2688T&gt;G" DB="RefSeq"/>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="MolecularConsequence">nonsense</Attribute>
+                <XRef ID="SO:0001587" DB="Sequence Ontology"/>
+                <XRef ID="NM_001374872.1:c.2688T&gt;G" DB="RefSeq"/>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="MolecularConsequence">nonsense</Attribute>
+                <XRef ID="SO:0001587" DB="Sequence Ontology"/>
+                <XRef ID="NM_001374873.1:c.2592T&gt;G" DB="RefSeq"/>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="MolecularConsequence">nonsense</Attribute>
+                <XRef ID="SO:0001587" DB="Sequence Ontology"/>
+                <XRef ID="NM_001374874.1:c.2592T&gt;G" DB="RefSeq"/>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="MolecularConsequence">nonsense</Attribute>
+                <XRef ID="SO:0001587" DB="Sequence Ontology"/>
+                <XRef ID="NM_014780.5:c.2592T&gt;G" DB="RefSeq"/>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="ProteinChange1LetterCode">Y864*</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="ProteinChange1LetterCode">Y896*</Attribute>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="ProteinChange1LetterCode">Y948*</Attribute>
+              </AttributeSet>
+              <GlobalMinorAlleleFrequency Value="0.00020" Source="1000 Genomes Project" MinorAllele="G"/>
+              <CytogeneticLocation>6p21.1</CytogeneticLocation>
+              <SequenceLocation Assembly="GRCh38" AssemblyAccessionVersion="GCF_000001405.38" AssemblyStatus="current" Chr="6" Accession="NC_000006.12" start="43046304" stop="43046304" display_start="43046304" display_stop="43046304" variantLength="1" positionVCF="43046304" referenceAlleleVCF="A" alternateAlleleVCF="C"/>
+              <SequenceLocation Assembly="GRCh37" AssemblyAccessionVersion="GCF_000001405.25" AssemblyStatus="previous" Chr="6" Accession="NC_000006.11" start="43014042" stop="43014042" display_start="43014042" display_stop="43014042" variantLength="1" positionVCF="43014042" referenceAlleleVCF="A" alternateAlleleVCF="C"/>
+              <MeasureRelationship Type="within single gene">
+                <Name>
+                  <ElementValue Type="Preferred">cullin 7</ElementValue>
+                </Name>
+                <Symbol>
+                  <ElementValue Type="Preferred">CUL7</ElementValue>
+                </Symbol>
+                <SequenceLocation Assembly="GRCh38" AssemblyAccessionVersion="GCF_000001405.38" AssemblyStatus="current" Chr="6" Accession="NC_000006.12" start="43037617" stop="43053851" display_start="43037617" display_stop="43053851" Strand="-"/>
+                <SequenceLocation Assembly="GRCh37" AssemblyAccessionVersion="GCF_000001405.25" AssemblyStatus="previous" Chr="6" Accession="NC_000006.11" start="43005354" stop="43021682" display_start="43005354" display_stop="43021682" variantLength="16329" Strand="-"/>
+                <XRef ID="9820" DB="Gene"/>
+                <XRef Type="MIM" ID="609577" DB="OMIM"/>
+                <XRef ID="HGNC:21024" DB="HGNC"/>
+              </MeasureRelationship>
+              <XRef Type="rs" ID="201406974" DB="dbSNP"/>
+            </Measure>
+            <Name>
+              <ElementValue Type="Preferred">NM_014780.5(CUL7):c.2592T&gt;G (p.Tyr864Ter)</ElementValue>
+            </Name>
+            <Name>
+              <ElementValue Type="Preferred">NM_014780.5(CUL7):c.2592T&gt;G (p.Tyr864Ter)</ElementValue>
+            </Name>
+            <XRef ID="CA236446" DB="ClinGen"/>
+          </MeasureSet>
+          <TraitSet Type="Disease" ID="415">
+            <Trait ID="6044" Type="Disease">
+              <Name>
+                <ElementValue Type="Preferred">3M syndrome 1</ElementValue>
+                <XRef ID="MONDO:0010117" DB="MONDO"/>
+              </Name>
+              <Name>
+                <ElementValue Type="Alternate">Three M syndrome 1</ElementValue>
+                <XRef ID="Three+M+syndrome/7072" DB="Genetic Alliance"/>
+              </Name>
+              <Symbol>
+                <ElementValue Type="Alternate">3M1</ElementValue>
+                <XRef Type="MIM" ID="273750" DB="OMIM"/>
+              </Symbol>
+              <AttributeSet>
+                <Attribute Type="public definition">Three M syndrome is characterized by severe pre- and postnatal growth deficiency (final height 5-6 SD below the mean; i.e., 120-130 cm), characteristic facies, and normal intelligence. Additional features of three M syndrome include short broad neck, prominent trapezii, deformed sternum, short thorax, square shoulders, winged scapulae, hyperlordosis, short fifth fingers, prominent heels, and loose joints. Males with three M syndrome have hypogonadism and occasionally hypospadias.</Attribute>
+                <XRef ID="NBK1481" DB="GeneReviews"/>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="GARD id" integerValue="15239"/>
+                <XRef ID="15239" DB="Office of Rare Diseases"/>
+              </AttributeSet>
+              <Citation Type="review" Abbrev="GeneReviews">
+                <ID Source="PubMed">20301654</ID>
+                <ID Source="BookShelf">NBK1481</ID>
+              </Citation>
+              <Citation Type="Translational/Evidence-based" Abbrev="EuroGentest, 2011">
+                <ID Source="PubMed">21364696</ID>
+              </Citation>
+              <XRef ID="MONDO:0010117" DB="MONDO"/>
+              <XRef ID="C2678312" DB="MedGen"/>
+              <XRef ID="2616" DB="Orphanet"/>
+              <XRef Type="MIM" ID="273750" DB="OMIM"/>
+            </Trait>
+          </TraitSet>
+        </ReferenceClinVarAssertion>
+        <ClinVarAssertion ID="269551" SubmissionName="2045">
+          <ClinVarSubmissionID localKey="NM_001168370.1:c.2844T&gt;G|OMIM:273750" submitter="Developmental Genetics Unit, King Faisal Specialist Hospital &amp; Research Centre" submitterDate="2014-05-08"/>
+          <ClinVarAccession Acc="SCV000108552" Version="1" Type="SCV" OrgID="500184" OrganizationCategory="laboratory" OrgType="primary" DateUpdated="2014-05-09" DateCreated="2014-05-09"/>
+          <RecordStatus>current</RecordStatus>
+          <ClinicalSignificance>
+            <ReviewStatus>flagged submission</ReviewStatus>
+            <Description>Pathogenic</Description>
+          </ClinicalSignificance>
+          <Assertion Type="variation to disease"/>
+          <ObservedIn>
+            <Sample>
+              <Origin>germline</Origin>
+              <Ethnicity>Arab</Ethnicity>
+              <GeographicOrigin>Saudi Arabia</GeographicOrigin>
+              <Species TaxonomyId="9606">human</Species>
+              <AffectedStatus>yes</AffectedStatus>
+              <Gender>male</Gender>
+            </Sample>
+            <Method>
+              <MethodType>research</MethodType>
+            </Method>
+            <ObservedData>
+              <Attribute Type="Description">not provided</Attribute>
+            </ObservedData>
+            <TraitSet Type="Disease">
+              <Trait ClinicalFeaturesAffectedStatus="present" Type="Finding">
+                <Name>
+                  <ElementValue Type="Preferred">Small and mal-aligned teeth, skin and joint laxity, and normal motor and cognitive development</ElementValue>
+                </Name>
+              </Trait>
+            </TraitSet>
+          </ObservedIn>
+          <MeasureSet Type="Variant">
+            <Measure Type="Variation">
+              <Name>
+                <ElementValue Type="Alternate">p.Y948*</ElementValue>
+              </Name>
+              <AttributeSet>
+                <Attribute Type="FunctionalConsequence">protein loss of function</Attribute>
+                <XRef DB="Variation Ontology" ID="0043" URL="http://www.variationontology.org/cgi-bin/amivario/term-details.cgi?term=VariO:0043"/>
+              </AttributeSet>
+              <AttributeSet>
+                <Attribute Type="HGVS">NM_001168370.1:c.2844T&gt;G</Attribute>
+              </AttributeSet>
+              <MeasureRelationship Type="variant in gene">
+                <Symbol>
+                  <ElementValue Type="Preferred">CUL7</ElementValue>
+                </Symbol>
+              </MeasureRelationship>
+            </Measure>
+          </MeasureSet>
+          <TraitSet Type="Disease">
+            <Trait Type="Disease">
+              <Name>
+                <ElementValue Type="Preferred">Three M syndrome 1</ElementValue>
+              </Name>
+              <XRef DB="OMIM" ID="273750" Type="MIM"/>
+            </Trait>
+          </TraitSet>
+          <StudyName>Genomic Analysis of Primordial Dwarfism Reveals Novel Disease Genes</StudyName>
+          <Comment DataSource="NCBI" Type="FlaggedComment">Reason: This record appears to be redundant with a more recent record from the same submitter.</Comment>
+          <Comment DataSource="NCBI" Type="FlaggedComment">Notes: SCV000108552 appears to be redundant with SCV000221722.</Comment>
+        </ClinVarAssertion>
+      </ClinVarSet>
+
+</ReleaseSet>