openprotein.design#

Design new sequences based on your stated objectives and our genetic algorithm!

class openprotein.design.DesignAPI[source]#

Interface for calling Designer endpoints

__init__(session)[source]#
Parameters:

session (APISession)

list_designs()[source]#

List designs.

Return type:

list[DesignFuture]

get_design(design_id)[source]#

Get design.

Parameters:

design_id (str) – ID of design to retrieve

Returns:

A future object representing the design job and its results.

Return type:

DesignFuture

create_genetic_algorithm_design(assay, criteria, num_steps=25, pop_size=1024, n_offsprings=5120, crossover_prob=1.0, crossover_prob_pointwise=0.2, mutation_average_mutations_per_seq=1, allowed_tokens={})[source]#

Start a protein design job based on your assaydata, a trained ML model and Criteria (specified here).

Parameters:

  • assay (AssayDataset) – The AssayDataset to design from.

  • criteria (Criteria | Subcriterion | Criterion) – Criteria for evaluating the design. Use documentation for syntactic sugar to easily create.

  • num_steps (int) – The number of steps in the genetic algo. Default is 8.

  • pop_size (int) – The population size for the genetic algo. Default is 1024.

  • n_offsprings (int) – The number of offspring for the genetic algo. Default is 5120.

  • crossover_prob (float) – The crossover probability for the genetic algo. Default is 1.0.

  • crossover_prob_pointwise (float) – The pointwise crossover probability for the genetic algo. Default is 0.2.

  • mutation_average_mutations_per_seq (int) – The average number of mutations per sequence. Default is 1.

  • allowed_tokens (DesignConstraint | dict[int, list[str]]) – A dict of positions and allows tokens (e.g. {1:[‘G’,’L’]}) ) designating how mutations may occur. Defaults to empty dict.

Returns:

A future object representing the design job and its results.

Return type:

DesignFuture

class openprotein.design.DesignFuture[source]#

A future object that will hold the results of the design job.

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

Construct a future for a design job.

Takes in either a design job, or the design metadata.

Parameters:

  • session (APISession)

  • job (DesignJob | None)

  • metadata (Design | None)

property id#

ID of the design.

property assay: AssayDataset#

Assay used in the design.

property algorithm: DesignAlgorithm#

Algorithm used in the design.

property criteria: Criteria#

Criteria used in the design.

property num_steps#

Number of steps used in the design.

property num_rows#

Number of rows in the total design output (across all steps).

property allowed_tokens: dict[str, list[str]] | None#

Allowed tokens used in the design.

property pop_size: int#

Population size used in the design.

property n_offsprings: int#

Number of offsprings used in the design.

property crossover_prob: float#

Crossover probability used in the design.

property crossover_prob_pointwise: float#

Crossover probability pointwise used in the design.

property mutation_average_mutations_per_seq: int#

Average mutations per sequence used in the design.

property metadata#

Design metadata.

stream(step=None)[source]#

Return the results from this job as a generator.

Parameters:

step (int | None)

Return type:

Generator

get_assay()[source]#

Get assay used for design job.

Returns:

Assay dataset used for design.

Return type:

AssayDataset