oktoberfest.pr.Predictor

class oktoberfest.pr.Predictor(predictor, model_name)

Abstracts common prediction operations away from their actual implementation via the DLomix or Koina interface.

Parameters:

  • predictor (PredictionInterface)

  • model_name (str)

__init__(predictor, model_name)

Initialize from Koina or DLomix instance.

Parameters:

Methods

ce_calibration(library, ce_range, ...[, xl])

Calculate best collision energy for peptide property predictions.

from_config(config, model_type, **kwargs)

Load from config object.

from_dlomix(model_type, model_path, ...[, ...])

Create DLomix predictor.

from_koina(model_name[, server_url, ssl, ...])

Create Koina predictor.

predict_at_once(data[, xl])

Retrieve and return predictions in one go.

predict_in_chunks(data, chunk_idx[, xl])

Retrieve and return predictions in chunks.

predict_in_chunks_xl(data, chunk_idx[, xl])

Retrieve and return predictions in chunks.

predict_intensities(data[, xl, chunk_idx])

Generate intensity predictions and add them to the provided data object.

predict_rt(data, **kwargs)

Generate retention time predictions and add them to the provided data object.