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)

Define string constraints for annotations when gene location is absent.

ALT_LOC = 'alternate reference locus'

NOT_FOUND_ON_REFERENCE = 'not on reference assembly'

RESERVED = 'reserved'

UNPLACED = 'unplaced'

class gene.schemas.BaseGene(**data)

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

aliases: List[Annotated[str]]

associated_with: List[Annotated[str]]

concept_id: Annotated[str]

gene_type: Optional[Annotated[str]]

label: Optional[Annotated[str]]

location_annotations: List[Annotated[str]]

locations: Union[List[SequenceLocation], List[GeneSequenceLocation]]

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

previous_symbols: List[Annotated[str]]

strand: Optional[Strand]

symbol: Annotated[str]

symbol_status: Optional[SymbolStatus]

xrefs: List[Annotated[str]]

class gene.schemas.BaseNormalizationService(**data)

Base method providing shared attributes to Normalization service classes.

match_type: MatchType

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

query: Annotated[str]

service_meta_: ServiceMeta

warnings: List[Dict]

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

Define string constraints for chromosomes.

MITOCHONDRIA = 'MT'

class gene.schemas.DataLicenseAttributes(**data)

Define constraints for data license attributes.

attribution: Annotated[bool]

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

non_commercial: Annotated[bool]

share_alike: Annotated[bool]

class gene.schemas.Gene(**data)

match_type: MatchType

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

class gene.schemas.GeneGroup(**data)

A grouping of genes based on common attributes.

description: Annotated[str]

genes: List[Gene]

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

type_identifier: Annotated[str]

class gene.schemas.GeneSequenceLocation(**data)

Sequence Location model when storing in DynamoDB.

end: Annotated[int]

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

sequence_id: Annotated[str]

start: Annotated[int]

type: Literal['SequenceLocation']

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

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

ENSEMBL = 'ensembl_biotype'

HGNC = 'hgnc_locus_type'

NCBI = 'ncbi_gene_type'

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

Define string constraints for use in Match Type attributes.

ALIAS = 60

ASSOCIATED_WITH = 60

CONCEPT_ID = 100

FUZZY_MATCH = 20

NO_MATCH = 0

PREV_SYMBOL = 80

SYMBOL = 100

XREF = 60

class gene.schemas.MatchesNormalized(**data)

Matches associated with normalized concept from a single source.

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

records: List[BaseGene]

source_meta_: SourceMeta

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

Define string constraints for namespace prefixes on concept IDs.

CCDS = 'ccds'

CD = 'hcdmdb'

COSMIC = 'cosmic'

ENA = 'ena.embl'

ENSEMBL = 'ensembl'

ENTREZ = 'ncbigene'

HGNC = 'hgnc'

HOMEODB = 'homeodb'

HORDE = 'hordedb'

IMGT = 'imgt'

IMGT_GENE_DB = 'imgt/gene-db'

IUPHAR = 'iuphar'

KZNF = 'knzfgc'

LNCRNADB = 'lncrnadb'

MAMIT = 'mamittrnadb'

MEROPS = 'merops'

MIRBASE = 'mirbase'

NCBI = 'ncbigene'

OMIM = 'omim'

ORPHANET = 'orphanet'

PSEUDOGENE = 'pseudogene.org'

PUBMED = 'pubmed'

REFSEQ = 'refseq'

RFAM = 'rfam'

SNORNABASE = 'snornabase'

UCSC = 'ucsc'

UNIPROT = 'uniprot'

VEGA = 'vega'

class gene.schemas.NormalizeService(**data)

Define model for returning normalized concept.

gene: Optional[Gene]

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

normalized_id: Optional[str]

source_meta_: Dict[SourceName, SourceMeta]

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

Record item types.

IDENTITY = 'identity'

MERGER = 'merger'

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

Reference item types.

ALIASES = 'alias'

ASSOCIATED_WITH = 'associated_with'

PREVIOUS_SYMBOLS = 'prev_symbol'

SYMBOL = 'symbol'

XREFS = 'xref'

class gene.schemas.SearchService(**data)

Define model for returning highest match typed concepts from sources.

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

query: Annotated[str]

service_meta_: ServiceMeta

source_matches: Dict[SourceName, SourceSearchMatches]

warnings: List[Dict]

class gene.schemas.ServiceMeta(**data)

Metadata regarding the gene-normalization service.

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

name: Literal['gene-normalizer']

response_datetime: Annotated[str]

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

version: Annotated[str]

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

Define string constraints after namespace.

ENSEMBL = 'ENSG'

HGNC = ''

NCBI = ''

class gene.schemas.SourceMeta(**data)

Metadata for a given source to return in response object.

data_license: Annotated[str]

data_license_attributes: Dict[Annotated[str], Annotated[bool]]

data_license_url: Annotated[str]

data_url: Dict[Annotated[str], Annotated[str]]

genome_assemblies: List[Annotated[str]]

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

rdp_url: Optional[Annotated[str]]

version: Annotated[str]

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

Define string constraints to ensure consistent capitalization.

ENSEMBL = 'Ensembl'

HGNC = 'HGNC'

NCBI = 'NCBI'

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

Define priorities for sources when building merged concepts.

ENSEMBL = 2

HGNC = 1

NCBI = 3

class gene.schemas.SourceSearchMatches(**data)

Container for matching information from an individual source.

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

records: List[Gene]

source_meta_: SourceMeta

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

Define string constraints for strand attribute.

FORWARD = '+'

REVERSE = '-'

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

Define string constraints for symbol status attribute.

APPROVED = 'approved'

DISCONTINUED = 'discontinued'

WITHDRAWN = 'withdrawn'

class gene.schemas.UnmergedNormalizationService(**data)

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

model_computed_fields: ClassVar[dict[str, ComputedFieldInfo]] = {}

A dictionary of computed field names and their corresponding ComputedFieldInfo objects.

normalized_concept_id: Optional[Annotated[str]]

source_matches: Dict[SourceName, MatchesNormalized]