> ## Documentation Index
> Fetch the complete documentation index at: https://bagel.softnanolab.com/llms.txt
> Use this file to discover all available pages before exploring further.

# ESM-2

> Object that uses ESM-2 to predict the embeddings of the residues in the chains.

`ESM2` is an embedding oracle that wraps Meta's ESM-2 protein language model. It produces high-dimensional per-residue embeddings that capture biochemical and evolutionary context, which are used by embedding-based energy terms like `EmbeddingsSimilarityEnergy`.

By default, BAGEL uses the 650M parameter version of ESM-2, but any ESM-2 model size can be specified via the `config` parameter. For multimers, ESM-2 uses the same linker and positional encoding approach as ESMFold.

<Info>
  ESM-2 inference is powered by [boileroom](/boileroom-api/models/esm2). boileroom handles model loading, GPU execution, and dependency isolation — either serverlessly via Modal or locally via Apptainer. See the [boileroom ESM-2 reference](/boileroom-api/models/esm2) for backend configuration details.
</Info>

## Parameters

<ResponseField name="use_modal" type="bool" default="False">
  Whether to run ESM-2 on Modal's serverless GPU infrastructure. Set to `True` for serverless execution (no local GPU required), or `False` for local GPU execution.
</ResponseField>

<ResponseField name="config" type="dict[str, Any]" default="{}">
  Model-specific configuration. Can be used to specify model size, linker parameters, and other options.
</ResponseField>

<ResponseField name="modal_app_context" type="App | None" default="None">
  Optional Modal app context for reusing an existing Modal session.
</ResponseField>

## Methods

### embed

Calculate the embeddings of the residues in the chains.

**Parameters**

<ResponseField name="chains" type="list[Chain]" required>
  The chains to embed. Sequences are concatenated with appropriate linker handling.
</ResponseField>

## Example

```python theme={null}
import bagel as bg

# Create an ESM-2 oracle using Modal
esm2 = bg.oracles.ESM2(use_modal=True)

# Extract reference embeddings from a conserved region
reference_embeddings = esm2.predict(chains).embeddings

# Use with EmbeddingsSimilarityEnergy to maintain functional similarity
state = bg.State(
    chains=[chain],
    energy_terms=[
        bg.energies.EmbeddingsSimilarityEnergy(
            oracle=esm2,
            weight=1.0,
            residues=[conserved_residues],
            reference_embeddings=reference_embeddings,
        ),
    ],
    name="enzyme_variant",
)
```