skbio.embedding.ProteinEmbedding#

class skbio.embedding.ProteinEmbedding(embedding, sequence, clip_head=False, clip_tail=False, **kwargs)[source]#

Embedding of a protein sequence.

Parameters:

embeddingarray_like: The embedding of the protein sequence. Row vectors correspond to the latent residues coordinates.
sequencestr, Protein, or 1D ndarray: Characters representing the protein sequence itself.
clip_headbool, optional: If True, then the first row of the embedding will be removed. Some language models specify start tokens, and this parameter can be used to account for this.
clip_tailbool, optional: If True, then the last row of the embedding will be removed. Some language models specify end tokens, and this parameter can be used to account for this.

See also

skbio.sequence.Protein

Examples

>>> from skbio.embedding import ProteinEmbedding
>>> import numpy as np
>>> embedding = np.random.rand(10, 3)
>>> sequence = "ACDEFGHIKL"
>>> ProteinEmbedding(embedding, sequence)
ProteinEmbedding
--------------------------
Stats:
    length: 10
    embedding dimension: 3
    has gaps: False
    has degenerates: False
    has definites: True
    has stops: False
--------------------------
0 ACDEFGHIKL

Attributes

`default_write_format`	Default write format for this object: `embed`.
`residues`	Array containing underlying residue characters.

Attributes (inherited)

`embedding`	The embedding tensor.
`ids`	IDs corresponding to each row of the embedding.
`sequence`	String representation of the underlying sequence.

Methods (inherited)

`bytes`	Bytes representation of string encoding.
`read`	Create a new `ProteinEmbedding` instance from a file.
`write`	Write an instance of `ProteinEmbedding` to a file.

Special methods (inherited)

`__eq__`	Return self==value.
`__ge__`	Return self>=value.
`__getstate__`	Helper for pickle.
`__gt__`	Return self>value.
`__hash__`	Return hash(self).
`__le__`	Return self<=value.
`__lt__`	Return self<value.
`__ne__`	Return self!=value.
`__str__`	String representation of the underlying sequence.

Details

default_write_format = 'embed'#: Default write format for this object: embed.

residues#: Array containing underlying residue characters.