Biological Embeddings (skbio.embedding)#

This module provides support for storing embeddings for biological objects, such as protein embeddings outputted from protein language models (pLMs).

Embedding types#

Embedding(embedding, ids, **kwargs)

Embedding for a biological object.

SequenceEmbedding(embedding, sequence, **kwargs)

Embedding for a biological sequence.

ProteinEmbedding(embedding, sequence[, ...])

Embedding of a protein sequence.

Embedding vector types#

SequenceVector(vector, sequence, **kwargs)

Vector representation for a biological sequence.

ProteinVector(vector, sequence, **kwargs)

Vector representation for a protein sequence.

Embedding vector utilities#

embed_vec_to_numpy(vectors[, validate])

Convert an iterable of EmbeddingVector objects to a NumPy array.

embed_vec_to_distances(vectors[, metric, ...])

Convert EmbeddingVector objects to a DistanceMatrix object.

embed_vec_to_ordination(vectors[, validate])

Convert EmbeddingVector objects to an Ordination object.

embed_vec_to_dataframe(vectors[, validate])

Convert a list of SequenceVector objects to a pandas DataFrame.