openprotein.embeddings.PoETModel#

class openprotein.embeddings.PoETModel(session, model_id, metadata=None)[source]#

Class for OpenProtein’s foundation model PoET.

Note

PoET functions are dependent on a prompt supplied via the prompt endpoints.

Examples

View specific model details (including supported tokens) with the ? operator.

>>> import openprotein
>>> session = openprotein.connect(username="user", password="password")
>>> session.embedding.poet.<embeddings_method>
Parameters:

  • session (APISession)

  • model_id (list[str] | str)

  • metadata (ModelMetadata | None)

__init__(session, model_id, metadata=None)[source]#
Parameters:

  • session (APISession)

  • model_id (str)

  • metadata (ModelMetadata | None)

Methods

__init__(session, model_id[, metadata])

attn()

Attention is not available for PoET.

create(session, model_id[, default])

Create and return an instance of the appropriate EmbeddingModel subclass based on the model_id.

embed(sequences[, prompt, reduction])

Embed sequences using the PoET model.

fit_gp(assay, properties[, prompt])

Fit a Gaussian Process (GP) on assay using this embedding model and hyperparameters.

fit_svd([prompt, sequences, assay, ...])

Fit an SVD on the embedding results of PoET.

fit_umap([prompt, sequences, assay, ...])

Fit a UMAP on assay using PoET and hyperparameters.

generate(prompt[, num_samples, temperature, ...])

Generate protein sequences conditioned on a prompt.

get_metadata()

Get model metadata for this model.

get_model()

Get the model_id(s) for this EmbeddingModel subclass.

indel(sequence[, prompt, insert, delete])

Score all indels of the query sequence using the specified prompt.

logits(sequences[, prompt])

Compute logits for sequences using the PoET model.

score(sequences[, prompt])

Score query sequences using the specified prompt.

single_site(sequence[, prompt])

Score all single substitutions of the query sequence using the specified prompt.

Attributes

metadata

ModelMetadata for this model.

model_id