Gene Annotation Engine

The annotation engine is responsible for enriching gene panels with genomic coordinates, transcript information, and gene descriptions.

Overview

The GeneAnnotator class provides comprehensive gene annotation functionality:

• HGNC standardization - Validates and standardizes gene symbols
• Genomic coordinates - Retrieves current coordinates from Ensembl
• Transcript information - Identifies canonical and MANE transcripts
• Gene descriptions - Adds descriptive information for each gene
• Quality control - Validates data consistency and completeness

API Reference

custom_panel.engine.annotator

Gene annotation engine.

This module provides functionality to annotate genes with genomic information using HGNC and Ensembl APIs.

GeneAnnotator

GeneAnnotator(config=None)

Gene annotation engine using HGNC and Ensembl APIs.

Initialize the gene annotator.

Parameters:

Name	Type	Description	Default
config	dict[str, Any] | None	Configuration dictionary	None

annotate_genes

annotate_genes(gene_df)

Annotate genes with genomic information.

Parameters:

Name	Type	Description	Default
gene_df	DataFrame	DataFrame with unique genes to annotate	required

Returns:

Type	Description
DataFrame	DataFrame with annotation columns added

clear_caches

clear_caches()

Clear API client caches.

get_annotation_summary

get_annotation_summary(annotated_df)

Generate summary statistics for annotations.

Parameters:

Name	Type	Description	Default
annotated_df	DataFrame	Annotated DataFrame	required

Returns:

Type	Description
dict[str, Any]	Summary statistics dictionary

get_cache_stats

get_cache_stats()

Get cache statistics from API clients.

standardize_gene_symbols

standardize_gene_symbols(gene_symbols)

Standardize gene symbols using parallel HGNC batch API calls.

This method is public to allow standardization before merging.

Parameters:

Name	Type	Description	Default
gene_symbols	list[str]	List of gene symbols to standardize	required

Returns:

Type	Description
dict[str, dict[str, str | None]]	Dictionary mapping original symbols to dict containing approved_symbol and hgnc_id