gain.gene_sets package

Subpackages

gain.gene_sets.implementations package

Submodules

gain.gene_sets.gene_set module

Classes for handling of gene sets and gene set collections.

class gain.gene_sets.gene_set.BaseGeneSetCollection(collection_id: str)[source]

Bases: ABC

Base class for gene set collections.

abstractmethod get_all_gene_sets() → list[GeneSet][source]: Return list of all gene sets in the collection.

abstractmethod get_gene_set(gene_set_id: str) → GeneSet | None[source]: Return the gene set if found; returns None if not found.

abstractmethod load() → BaseGeneSetCollection[source]: Load the gene sets from the resource.

class gain.gene_sets.gene_set.BaseResourceSchema(*, type: str | None = None, meta: MetaSchema | None = None)[source]

Bases: BaseModel

meta: MetaSchema | None

model_config = {}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

type: str | None

Bases: BaseModel

displayed_values_count: int | None

displayed_values_percent: float | None

enforce_type: bool | None

label_rotation: int | None

model_config = {}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

natural_order: bool | None

plot_function: str | None

type: Literal['categorical']

value_order: list[str | int] | None

y_log_scale: bool | None

class gain.gene_sets.gene_set.GeneSet(name: str, desc: str, syms: list[str])[source]

Bases: object

Class representing a set of genes.

count: int

desc: str

name: str

syms: list[str]

class gain.gene_sets.gene_set.GeneSetCollection(resource: GenomicResource)[source]

Bases: BaseGeneSetCollection

Class representing a collection of gene sets in a resource.

property files: set[str]: Return a list of resource files the implementation utilises.

gene_sets: dict[str, GeneSet]

get_all_gene_sets() → list[GeneSet][source]: Return list of all gene sets in the collection.

get_gene_collection_count_statistics() → dict | None[source]: Get gene collection count statistics from the resource.

get_gene_set(gene_set_id: str) → GeneSet | None[source]: Return the gene set if found; returns None if not found.

get_gene_sets_list_statistics() → list[dict] | None[source]: Get gene sets list statistics from the resource.

get_gene_sets_per_gene_hist() → NullHistogram | CategoricalHistogram | NumberHistogram | None[source]

get_gene_sets_per_gene_hist_filename() → str[source]

get_gene_sets_per_gene_hist_image_filename() → str[source]

get_genes_per_gene_set_hist() → NullHistogram | CategoricalHistogram | NumberHistogram | None[source]

get_genes_per_gene_set_hist_filename() → str[source]

get_genes_per_gene_set_hist_image_filename() → str[source]

is_loaded() → bool[source]: Check if the gene sets have been loaded.

load() → GeneSetCollection[source]: Load the gene sets from the resource.

load_gene_sets() → dict[str, GeneSet][source]: Build a gene set collection from a given GenomicResource.

class gain.gene_sets.gene_set.GeneSetResourceSchema(*, id: str, filename: str | None = None, directory: str | None = None, format: str | None, web_label: str | None = None, web_format_str: str | None = None, histograms: dict[Literal['genes_per_gene_set', 'gene_sets_per_gene'], Annotated[NumericHistogramSchema | CategoricalHistogramSchema, FieldInfo(annotation=NoneType, required=True, discriminator='type')]] | None = None)[source]

Bases: BaseModel

directory: str | None

filename: str | None

histograms: dict[Literal['genes_per_gene_set', 'gene_sets_per_gene'], HistogramConfig] | None

model_config = {}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

resource_format: str | None

resource_id: str

web_format_str: str | None

web_label: str | None

class gain.gene_sets.gene_set.MetaSchema(*, description: str | None = None, labels: dict[str, Any] | None = None)[source]

Bases: BaseModel

description: str | None

labels: dict[str, Any] | None

model_config = {}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

Bases: BaseModel

displayed_values_count: int | None

model_config = {}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

number_of_bins: int | None

plot_function: str | None

type: Literal['number']

value_order: list[str | int] | None

view_range: ViewRangeSchema | None

x_log_scale: bool | None

x_min_log: float | None

y_log_scale: bool | None

class gain.gene_sets.gene_set.ViewRangeSchema(*, min: float | None = None, max: float | None = None)[source]

Bases: BaseModel

max: float | None

min: float | None

model_config = {}: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

gain.gene_sets.gene_set.build_gene_set_collection_from_file(filename: str, collection_id: str | None = None, collection_format: str | None = None, web_label: str | None = None, web_format_str: str | None = None) → GeneSetCollection[source]: Return a Gene Set Collection by adapting a file to a local resource.

gain.gene_sets.gene_set.build_gene_set_collection_from_resource(resource: GenomicResource) → GeneSetCollection[source]: Return a Gene Set Collection built from a resource.

gain.gene_sets.gene_set.build_gene_set_collection_from_resource_id(resource_id: str, grr: GenomicResourceRepo | None = None) → GeneSetCollection[source]

gain.gene_sets.gene_term module

class gain.gene_sets.gene_term.GeneInfo(gene_id: str, gene_sym: str, synonyms: set[str], description: str)[source]

Bases: object

description: str

gene_id: str

gene_sym: str

synonyms: set[str]

class gain.gene_sets.gene_term.GeneTerms[source]

Bases: object

Class representing gene terms.

filter_genes(filter_fun: Callable[[list[str]], list[str]]) → None[source]: Filter the genes.

g2t: dict[str, Any]

gene_ns: str | None

rename_genes(gene_ns: str | None, rename_fn: Callable[[str], str | None]) → None[source]: Rename genese.

save(fname: str) → None[source]: Save to fname.

t2g: dict[str, Any]

t_desc: dict[str, Any]

class gain.gene_sets.gene_term.NCBIGeneInfo(genes: dict[str, gain.gene_sets.gene_term.GeneInfo], ns_tokens: dict[str, dict[str, list[gain.gene_sets.gene_term.GeneInfo]]])[source]

Bases: object

genes: dict[str, GeneInfo]

ns_tokens: dict[str, dict[str, list[GeneInfo]]]

gain.gene_sets.gene_term.dd() → dict[str, int][source]

gain.gene_sets.gene_term.get_clean_gene_id(ncbi_gene_info: NCBIGeneInfo, ns: str, term: str) → str | None[source]: Gene gene ID from NCBI gene info data.

gain.gene_sets.gene_term.load_gene_terms(path: str) → GeneTerms | None[source]: Load gene terms from a file.

gain.gene_sets.gene_term.load_ncbi_gene_info(gene_info_file: str) → NCBIGeneInfo[source]

gain.gene_sets.gene_term.read_ewa_set_file(set_files: list[IO]) → GeneTerms[source]: Read a set of ewa files.

gain.gene_sets.gene_term.read_gmt_file(input_file: IO) → GeneTerms[source]: Read a gmt file.

gain.gene_sets.gene_term.read_mapping_file(input_file: IO, names_file: IO | None) → GeneTerms[source]: Read a mapping file.

gain.gene_sets.gene_term.rename_gene_terms(gene_terms: GeneTerms, gene_ns: str, ncbi_gene_info: NCBIGeneInfo) → GeneTerms[source]: Rename gene terms using NCBI gene info data.

gain.gene_sets package

Subpackages

Submodules

gain.gene_sets.gene_set module

gain.gene_sets.gene_term module

Module contents