genos.api

Genos API subpackage.

This package contains modules that wrap individual Genos API endpoints: - HealthAPI: /health endpoint - VariantPredictorAPI: /predict endpoint

class HealthAPI(session: Session, base_url: str, timeout: int = 30)

Bases: BaseAPI

Wrapper class for the Health Check API endpoint.

This class handles requests to the /health endpoint, allowing clients to verify that the Genos service is running and responsive.

check() → dict

Perform a health check request.

Returns:

JSON response from the health endpoint, typically containing:

  • ”status”: “healthy” or “unhealthy”

  • ”message”: optional status message

Return type:

dict

Raises:

APIRequestError – If the request fails or the server is unreachable.

class VariantPredictorAPI(session: Session, base_url: str, timeout: int = 30)

Bases: BaseAPI

Wrapper class for the Variant Prediction API endpoint.

This class handles requests to the /predict endpoint for variant pathogenicity prediction. It validates input and raises structured SDK exceptions on errors.

predict(assembly: str, chrom: str, pos: int, ref: str, alt: str) → dict

Predict the pathogenicity of a genetic variant.

Parameters:

  • assembly (str) – Reference genome version, allowed values: ‘hg38’ or ‘hg19’.

  • chrom (str) – Chromosome, e.g., ‘chr6’.

  • pos (int) – Position, 1-based coordinate.

  • ref (str) – Reference allele, single letter or sequence.

  • alt (str) – Alternate allele, single letter or sequence.

Returns:

Prediction result, typically containing:

  • ”variant”: input variant

  • ”prediction”: “Pathogenic” or “Benign”

  • ”score_Benign”: float

  • ”score_Pathogenic”: float

Return type:

dict

Raises:

  • ValueError – If any argument is invalid.

  • APIRequestError – If the API request fails or the server returns an error.

class EmbeddingExtractorAPI(session: Session, base_url: str, timeout: int = 30, config=None)

Bases: BaseAPI

Wrapper class for the Embedding Extraction API endpoints.

This class handles requests to the embedding extraction endpoints, including single sequence and batch processing.

extract(sequence: str, model_name: str = 'Genos-1.2B', pooling_method: str = 'mean') → dict | List[dict]

Extracts a numerical embedding representation for a given nucleotide sequence.

Parameters:

  • sequence (str) – DNA sequence string .

  • model_name (str, optional) – Model name to use. Default is “Genos-1.2B”. Options: “Genos-1.2B”, “Genos-10B”

  • pooling_method (str, optional) – Pooling method. Default is “mean”. Options: “mean”, “max”, “last”, “none”

Returns:

  • “token_count”: number of tokens

  • ”embedding_shape”: shape of embedding array

  • ”embedding_dim”: dimension of embedding

  • ”embedding”: embedding array (list)

Return type:

dict

Raises:

  • ValueError – If sequence is not a valid string or list.

  • ValidationError – If parameters are invalid.

  • APIRequestError – If the API request fails.

Examples

>>> # Single sequence
>>> result = embedding_api.extract("ATCGATCGATCG")
>>> print(result['embedding_dim'])
4096
class RNASeqCoverageTrackPredictionAPI(session: Session, base_url: str, timeout: int = 30)

Bases: BaseAPI

Client for the RNA-seq Coverage Track Prediction service in GeneOS.

This class provides access to RNA-seq Coverage Track Prediction models, allowing users to predict the coverage track of an RNA-seq experiment based on the genomic coordinates.

predict(chrom: str, start_pos: int) → dict

Predict the coverage track of an RNA-seq experiment based on the genomic coordinates.

Parameters:

  • chrom (str) – Chromosome name.

  • start_pos (int) – Start position.

Returns:

A JSON response from the RNA-seq Coverage Track Prediction model containing the predicted coverage track.

Return type:

dict

Raises:

  • ValueError – If the parameters are invalid.

  • APIRequestError – If the API request fails.

Modules

embedding_extractor

health

rna_seq_coverage_track_prediction

variant_predictor