openprotein.predictor.PredictorModel#

class openprotein.predictor.PredictorModel(session, job=None, metadata=None)[source]#

Class providing predict endpoint for fitted predictor models.

Also implements a Future that waits for train job.

Parameters:

__init__(session, job=None, metadata=None)[source]#

Construct a predictor model.

Takes in either a train job, or the predictor metadata.

Parameters:

Methods

`__init__`(session[, job, metadata])	Construct a predictor model.
`cancelled`()	Check if the job has been cancelled.
`create`(session[, job_id, job, response])	Create an instance of the appropriate Future class based on the job type.
`crossvalidate`([n_splits])	Run a crossvalidation on the trained predictor.
`delete`()	Delete this predictor model.
`done`()	Check if the job has completed.
`get`([verbose])	Returns the train loss curves.
`get_assay`()	Get assay used for train job.
`get_model`()	Retrieve the embeddings or SVD model used to create embeddings to train on.
`predict`(sequences)	Make predictions about the trained properties for a list of sequences.
`refresh`()	Refresh the job status and internal job object.
`single_site`(sequence)	Compute the single-site mutated predictions of a base sequence.
`wait`([interval, timeout, verbose])	Wait for the job to complete, then fetch results.
`wait_until_done`([interval, timeout, verbose])	Wait for the job to complete.

Attributes

`created_date`	The creation timestamp of the job.
`end_date`	The end timestamp of the job.
`id`	ID of predictor.
`job_id`	The unique identifier of the job.
`job_type`	The type of the job.
`metadata`	The predictor metadata.
`model`	The embeddings or SVD model used to create embeddings to train on.
`progress_counter`	The progress counter of the job.
`reduction`	The reduction of th embeddings used to train the predictor, if any.
`sequence_length`	The sequence length constraint on the predictor, if any.
`start_date`	The start timestamp of the job.
`status`	The current status of the job.
`training_assay`	The assay the predictor was trained on.
`training_properties`	The list of properties the predictor was trained on.
`job`
`session`