gene.schemas#

Contains data models for representing VICC normalized gene records.

class gene.schemas.Annotation(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Define string constraints for annotations when gene location is absent.

ALT_LOC = 'alternate reference locus'[source]#

NOT_FOUND_ON_REFERENCE = 'not on reference assembly'[source]#

RESERVED = 'reserved'[source]#

UNPLACED = 'unplaced'[source]#

class gene.schemas.BaseGene(**data)[source]#

Base gene model. Provide shared resources for records produced by /search and /normalize_unmerged.

aliases: list[Annotated[str]][source]#

associated_with: list[Annotated[str]][source]#

concept_id: Annotated[str][source]#

gene_type: Optional[Annotated[str]][source]#

label: Optional[Annotated[str]][source]#

location_annotations: list[Annotated[str]][source]#

locations: list[SequenceLocation] | list[GeneSequenceLocation][source]#

previous_symbols: list[Annotated[str]][source]#

strand: Optional[Strand][source]#

symbol: Annotated[str][source]#

symbol_status: Optional[SymbolStatus][source]#

xrefs: list[Annotated[str]][source]#

class gene.schemas.BaseNormalizationService(**data)[source]#

Base method providing shared attributes to Normalization service classes.

match_type: MatchType[source]#

query: Annotated[str][source]#

service_meta_: ServiceMeta[source]#

warnings: list[dict][source]#

class gene.schemas.Chromosome(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Define string constraints for chromosomes.

MITOCHONDRIA = 'MT'[source]#

class gene.schemas.DataLicenseAttributes(**data)[source]#

Define constraints for data license attributes.

attribution: Annotated[bool][source]#

non_commercial: Annotated[bool][source]#

share_alike: Annotated[bool][source]#

class gene.schemas.Gene(**data)[source]#

match_type: MatchType[source]#

class gene.schemas.GeneSequenceLocation(**data)[source]#

Sequence Location model when storing in DynamoDB.

end: Annotated[int][source]#

sequence_id: Annotated[str][source]#

start: Annotated[int][source]#

type: Literal['SequenceLocation'][source]#

class gene.schemas.GeneTypeFieldName(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Designate source-specific gene type field names for Extensions and internal records.

ENSEMBL = 'ensembl_biotype'[source]#

HGNC = 'hgnc_locus_type'[source]#

NCBI = 'ncbi_gene_type'[source]#

class gene.schemas.MatchType(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Define string constraints for use in Match Type attributes.

ALIAS = 60[source]#

ASSOCIATED_WITH = 60[source]#

CONCEPT_ID = 100[source]#

NO_MATCH = 0[source]#

PREV_SYMBOL = 80[source]#

SYMBOL = 100[source]#

XREF = 60[source]#

class gene.schemas.MatchesNormalized(**data)[source]#

Matches associated with normalized concept from a single source.

records: list[BaseGene][source]#

source_meta_: SourceMeta[source]#

class gene.schemas.NamespacePrefix(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Define string constraints for namespace prefixes on concept IDs.

CCDS = 'ccds'[source]#

CD = 'hcdmdb'[source]#

COSMIC = 'cosmic'[source]#

ENA = 'ena.embl'[source]#

ENSEMBL = 'ensembl'[source]#

ENTREZ = 'ncbigene'[source]#

HGNC = 'hgnc'[source]#

HOMEODB = 'homeodb'[source]#

HORDE = 'hordedb'[source]#

IMGT = 'imgt'[source]#

IMGT_GENE_DB = 'imgt/gene-db'[source]#

IUPHAR = 'iuphar'[source]#

IUPHAR_RECEPTOR = 'iuphar.receptor'[source]#

LNCRNADB = 'lncrnadb'[source]#

MAMIT = 'mamittrnadb'[source]#

MEROPS = 'merops'[source]#

MIRBASE = 'mirbase'[source]#

NCBI = 'ncbigene'[source]#

OMIM = 'omim'[source]#

ORPHANET = 'orphanet'[source]#

PSEUDOGENE = 'pseudogene.org'[source]#

PUBMED = 'pubmed'[source]#

REFSEQ = 'refseq'[source]#

RFAM = 'rfam'[source]#

SNORNABASE = 'snornabase'[source]#

UCSC = 'ucsc'[source]#

UNIPROT = 'uniprot'[source]#

VEGA = 'vega'[source]#

class gene.schemas.NormalizeService(**data)[source]#

Define model for returning normalized concept.

gene: Optional[MappableConcept][source]#

source_meta_: dict[SourceName, SourceMeta][source]#

class gene.schemas.RecordType(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Record item types.

IDENTITY = 'identity'[source]#

MERGER = 'merger'[source]#

class gene.schemas.RefType(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Reference item types.

ALIASES = 'alias'[source]#

ASSOCIATED_WITH = 'associated_with'[source]#

PREVIOUS_SYMBOLS = 'prev_symbol'[source]#

SYMBOL = 'symbol'[source]#

XREFS = 'xref'[source]#

class gene.schemas.SearchService(**data)[source]#

Define model for returning highest match typed concepts from sources.

query: Annotated[str][source]#

service_meta_: ServiceMeta[source]#

source_matches: dict[SourceName, SourceSearchMatches][source]#

warnings: list[dict][source]#

class gene.schemas.ServiceEnvironment(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Define current runtime environment.

DEV = 'dev'[source]#

PROD = 'prod'[source]#

STAGING = 'staging'[source]#

class gene.schemas.ServiceInfo(**data)[source]#

Define response structure for GA4GH /service_info endpoint.

contactUrl: Literal['Alex.Wagner@nationwidechildrens.org'][source]#

createdAt: Literal['2025-01-01T00:00:00+00:00'][source]#

description: Literal['The Gene Normalizer provides tools for resolving ambiguous gene references to consistently-structured, normalized terms.'][source]#

documentationUrl: Literal['https://github.com/cancervariants/gene-normalization'][source]#

environment: ServiceEnvironment[source]#

id: Literal['org.cancervariants.gene_normalizer'][source]#

name: Literal['Gene Normalizer'][source]#

organization: ServiceOrganization[source]#

type: ServiceType[source]#

updatedAt: Literal['2025-01-01T00:00:00+00:00'][source]#

version: Literal['0.11.3'][source]#

class gene.schemas.ServiceMeta(**data)[source]#

Metadata regarding the gene-normalization service.

name: Literal['gene-normalizer'][source]#

response_datetime: Annotated[str][source]#

url: Literal['https://github.com/cancervariants/gene-normalization'][source]#

version: Annotated[str][source]#

class gene.schemas.ServiceOrganization(**data)[source]#

Define service_info response for organization field

name: Literal['Variant Interpretation for Cancer Consortium'][source]#

url: Literal['https://cancervariants.org/'][source]#

class gene.schemas.ServiceType(**data)[source]#

Define service_info response for type field

artifact: Literal['Gene Normalizer API'][source]#

group: Literal['org.cancervariants'][source]#

version: Literal['0.11.3'][source]#

class gene.schemas.SourceIDAfterNamespace(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Define string constraints after namespace.

ENSEMBL = 'ENSG'[source]#

HGNC = ''[source]#

NCBI = ''[source]#

class gene.schemas.SourceMeta(**data)[source]#

Metadata for a given source to return in response object.

data_license: Annotated[str][source]#

data_license_attributes: DataLicenseAttributes[source]#

data_license_url: Annotated[str][source]#

data_url: dict[Annotated[str], Annotated[str]][source]#

genome_assemblies: list[Annotated[str]][source]#

rdp_url: Optional[Annotated[str]][source]#

version: Annotated[str][source]#

class gene.schemas.SourceName(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Define string constraints to ensure consistent capitalization.

ENSEMBL = 'Ensembl'[source]#

HGNC = 'HGNC'[source]#

NCBI = 'NCBI'[source]#

class gene.schemas.SourcePriority(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Define priorities for sources when building merged concepts.

ENSEMBL = 2[source]#

HGNC = 1[source]#

NCBI = 3[source]#

class gene.schemas.SourceSearchMatches(**data)[source]#

Container for matching information from an individual source.

records: list[Gene][source]#

source_meta_: SourceMeta[source]#

class gene.schemas.Strand(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Define string constraints for strand attribute.

FORWARD = '+'[source]#

REVERSE = '-'[source]#

class gene.schemas.SymbolStatus(value, names=None, *, module=None, qualname=None, type=None, start=1, boundary=None)[source]#

Define string constraints for symbol status attribute.

APPROVED = 'approved'[source]#

DISCONTINUED = 'discontinued'[source]#

WITHDRAWN = 'withdrawn'[source]#

class gene.schemas.UnmergedNormalizationService(**data)[source]#

Response providing source records corresponding to normalization of user query. Enables retrieval of normalized concept while retaining sourcing for accompanying attributes.

normalized_concept_id: Optional[Annotated[str]][source]#

source_matches: dict[SourceName, MatchesNormalized][source]#