dae.gpf_instance package

Submodules

dae.gpf_instance.gpf_instance module

Defines GPFInstance class that gives access to different parts of GPF.

class dae.gpf_instance.gpf_instance.GPFInstance(dae_config: Box, dae_dir: str | Path, **kwargs: dict[str, Any])

Bases: object

Class to access different parts of a GPF instance.

static build(config_filename: str | Path | None = None, **kwargs: Any) → GPFInstance

Construct and return a GPF instance.

If the config_filename is None, tries to discover the GPF instance. First check if a DAE_DB_DIR environment variable is defined and if defined use it as a GPF instance directory.

Otherwise look for a gpf_instance.yaml file in the current directory and its parents. If found use it as a configuration file.

property denovo_gene_sets_db: DenovoGeneSetsDb

property gene_models: GeneModels

Return gene models used in the GPF instance.

property gene_scores_db: Any

Load and return gene scores db.

property gene_sets_db: GeneSetsDb

Return GeneSetsDb populated with gene sets from the GPFInstance.

property genomic_scores: GenomicScoresRegistry

Load and return genomic scores db.

property genotype_storages: Any

Construct and return genotype storage registry.

get_all_common_report_configs() → list[box.box.Box]

Return all common report configuration.

get_all_denovo_gene_sets(types: dict[str, Any], datasets: list[Any], collection_id: str) → list[dict[str, Any]]

get_all_gene_score_descs() → list[dae.gene_scores.gene_scores.ScoreDesc]

get_all_gene_scores() → list[dae.gene_scores.gene_scores.GeneScore]

get_all_gene_sets(collection_id: str) → list[dae.gene.gene_sets_db.GeneSet]

get_all_genotype_data() → list[dae.studies.study.GenotypeData]

get_all_phenotype_data() → list[dae.pheno.pheno_data.PhenotypeData]

get_annotation_pipeline() → AnnotationPipeline

Return the annotation pipeline configured in the GPF instance.

get_annotation_pipeline_config() → list[dict[str, Any]]

Return the annotation pipeline config.

get_common_report(study_id: str) → CommonReport | None

Load and return common report (dataset statistics) for a study.

get_dataset(dataset_id: str) → GenotypeData

get_denovo_gene_set(gene_set_id: str, types: dict[str, Any], datasets: list[dae.studies.study.GenotypeData], collection_id: str) → dict[str, Any]

get_denovo_gene_sets(datasets: list[dae.studies.study.GenotypeData]) → list[dict[str, Any]]

get_gene_score(gene_score_id: str) → GeneScore

get_gene_score_desc(score_id: str) → ScoreDesc

get_gene_set(collection_id: str, gene_set_id: str) → GeneSet

get_gene_sets_collections() → list[dict[str, Any]]

get_genotype_data(genotype_data_id: str) → GenotypeData

get_genotype_data_config(genotype_data_id: str) → Box | None

get_genotype_data_ids(local_only: bool = False) → list[str]

get_gp_configuration() → Box

get_gp_statistic(gene_symbol: str) → GPStatistic

get_phenotype_data(phenotype_data_id: str) → PhenotypeData

get_phenotype_data_config(phenotype_data_id: str) → Box | None

get_phenotype_data_ids() → list[str]

get_transcript_models(gene_symbol: str) → tuple[Optional[str], Optional[list[dae.genomic_resources.gene_models.TranscriptModel]]]

Get gene model by gene symbol.

property grr: GenomicResourceRepo

Return genomic resource repository configured for GPF instance.

has_denovo_gene_sets() → bool

has_gene_score(gene_score_id: str) → bool

has_gene_set_collection(gsc_id: str) → bool

has_phenotype_data(phenotype_data_id: str) → bool

load() → GPFInstance

Load all GPF instance attributes.

query_gp_statistics(page: int, symbol_like: str | None = None, sort_by: str | None = None, order: str | None = None) → list[dae.gene_profile.statistic.GPStatistic]

Query AGR statistics and return results.

property reference_genome: ReferenceGenome

Return reference genome defined in the GPFInstance config.

register_genotype_data(genotype_data: GenotypeData) → None

reload() → None

Reload GPF instance studies, de Novo gene sets, etc.

unregister_genotype_data(genotype_data: GenotypeData) → None

Module contents

class dae.gpf_instance.GPFInstance(dae_config: Box, dae_dir: str | Path, **kwargs: dict[str, Any])

Bases: object

Class to access different parts of a GPF instance.

static build(config_filename: str | Path | None = None, **kwargs: Any) → GPFInstance

Construct and return a GPF instance.

If the config_filename is None, tries to discover the GPF instance. First check if a DAE_DB_DIR environment variable is defined and if defined use it as a GPF instance directory.

Otherwise look for a gpf_instance.yaml file in the current directory and its parents. If found use it as a configuration file.

property denovo_gene_sets_db: DenovoGeneSetsDb

property gene_models: GeneModels

Return gene models used in the GPF instance.

property gene_scores_db: Any

Load and return gene scores db.

property gene_sets_db: GeneSetsDb

Return GeneSetsDb populated with gene sets from the GPFInstance.

property genomic_scores: GenomicScoresRegistry

Load and return genomic scores db.

property genotype_storages: Any

Construct and return genotype storage registry.

get_all_common_report_configs() → list[box.box.Box]

Return all common report configuration.

get_all_denovo_gene_sets(types: dict[str, Any], datasets: list[Any], collection_id: str) → list[dict[str, Any]]

get_all_gene_score_descs() → list[dae.gene_scores.gene_scores.ScoreDesc]

get_all_gene_scores() → list[dae.gene_scores.gene_scores.GeneScore]

get_all_gene_sets(collection_id: str) → list[dae.gene.gene_sets_db.GeneSet]

get_all_genotype_data() → list[dae.studies.study.GenotypeData]

get_all_phenotype_data() → list[dae.pheno.pheno_data.PhenotypeData]

get_annotation_pipeline() → AnnotationPipeline

Return the annotation pipeline configured in the GPF instance.

get_annotation_pipeline_config() → list[dict[str, Any]]

Return the annotation pipeline config.

get_common_report(study_id: str) → CommonReport | None

Load and return common report (dataset statistics) for a study.

get_dataset(dataset_id: str) → GenotypeData

get_denovo_gene_set(gene_set_id: str, types: dict[str, Any], datasets: list[dae.studies.study.GenotypeData], collection_id: str) → dict[str, Any]

get_denovo_gene_sets(datasets: list[dae.studies.study.GenotypeData]) → list[dict[str, Any]]

get_gene_score(gene_score_id: str) → GeneScore

get_gene_score_desc(score_id: str) → ScoreDesc

get_gene_set(collection_id: str, gene_set_id: str) → GeneSet

get_gene_sets_collections() → list[dict[str, Any]]

get_genotype_data(genotype_data_id: str) → GenotypeData

get_genotype_data_config(genotype_data_id: str) → Box | None

get_genotype_data_ids(local_only: bool = False) → list[str]

get_gp_configuration() → Box

get_gp_statistic(gene_symbol: str) → GPStatistic

get_phenotype_data(phenotype_data_id: str) → PhenotypeData

get_phenotype_data_config(phenotype_data_id: str) → Box | None

get_phenotype_data_ids() → list[str]

get_transcript_models(gene_symbol: str) → tuple[Optional[str], Optional[list[dae.genomic_resources.gene_models.TranscriptModel]]]

Get gene model by gene symbol.

property grr: GenomicResourceRepo

Return genomic resource repository configured for GPF instance.

has_denovo_gene_sets() → bool

has_gene_score(gene_score_id: str) → bool

has_gene_set_collection(gsc_id: str) → bool

has_phenotype_data(phenotype_data_id: str) → bool

load() → GPFInstance

Load all GPF instance attributes.

query_gp_statistics(page: int, symbol_like: str | None = None, sort_by: str | None = None, order: str | None = None) → list[dae.gene_profile.statistic.GPStatistic]

Query AGR statistics and return results.

property reference_genome: ReferenceGenome

Return reference genome defined in the GPFInstance config.

register_genotype_data(genotype_data: GenotypeData) → None

reload() → None

Reload GPF instance studies, de Novo gene sets, etc.

unregister_genotype_data(genotype_data: GenotypeData) → None