openprotein.fold

Create PDBs of your protein sequences via our folding models!

Note that for AlphaFold2 Models, you will also need to utilize our align. workflow.

Endpoints

class openprotein.fold.FoldAPI

Fold API provides a high level interface for making protein structure predictions.

esmfold: ESMFoldModel

alphafold2: AlphaFold2Model

af2: AlphaFold2Model

boltz_1: Boltz1Model

boltz1: Boltz1Model

boltz_1x: Boltz1xModel

boltz1x: Boltz1xModel

boltz_2: Boltz2Model

boltz2: Boltz2Model

__init__(session)

Parameters:

session (APISession)

list_models()

list models available for creating folds of your sequences

Return type:

list[FoldModel]

get_model(model_id)

Get model by model_id.

FoldModel allows all the usual job manipulation: e.g. making POST and GET requests for this model specifically.

Parameters:

model_id (str) – the model identifier

Returns:

The model

Return type:

FoldModel

Raises:

HTTPError – If the GET request does not succeed.

get_results(job)

Retrieves the results of a fold job.

Parameters:

job (Job) – The fold job whose results are to be retrieved.

Returns:

An instance of FoldResultFuture

Return type:

FoldResultFuture

Models

class openprotein.fold.Boltz2Model

Class providing inference endpoints for Boltz-2 structure prediction model which jointly models complex structures and binding affinities.

fold(proteins=None, dnas=None, rnas=None, ligands=None, diffusion_samples=1, recycling_steps=3, sampling_steps=200, step_scale=1.638, use_potentials=False, constraints=None, templates=None, properties=None, method=None)

Post sequences to Boltz-2 model.

Parameters:

• proteins (List[Protein] | MSAFuture | None) – List of protein sequences to include in folded output. Protein objects must be tagged with an msa, which can be a Protein.single_sequence_mode for single sequence mode. Alternatively, supply an MSAFuture to use all query sequences as a multimer.

• dna (List[DNA] | None) – List of DNA sequences to include in folded output.

• rna (List[RNA] | None) – List of RNA sequences to include in folded output.

• ligands (List[Ligand] | None) – List of ligands to include in folded output.

• diffusion_samples (int) – Number of diffusion samples to use

• recycling_steps (int) – Number of recycling steps to use

• sampling_steps (int) – Number of sampling steps to use

• step_scale (float) – Scaling factor for diffusion steps.

• use_potentials (bool = False.) – Whether or not to use potentials.

• constraints (list[dict] | None = None) – List of constraints.

• templates (list[dict] | None = None) – List of templates to use for structure prediction.

• properties (list[dict] | None = None) – List of additional properties to predict. Should match the BoltzProperties

• method (str | None) – The experimental method or supervision source used for the prediction. Defults to None. Supported values (case-insensitive) include: ‘MD’, ‘X-RAY DIFFRACTION’, ‘ELECTRON MICROSCOPY’, ‘SOLUTION NMR’, ‘SOLID-STATE NMR’, ‘NEUTRON DIFFRACTION’, ‘ELECTRON CRYSTALLOGRAPHY’, ‘FIBER DIFFRACTION’, ‘POWDER DIFFRACTION’, ‘INFRARED SPECTROSCOPY’, ‘FLUORESCENCE TRANSFER’, ‘EPR’, ‘THEORETICAL MODEL’, ‘SOLUTION SCATTERING’, ‘OTHER’, ‘AFDB’, ‘BOLTZ-1’. View the documentation on Boltz for upstream details.

• dnas (list[DNA] | None)

• rnas (list[RNA] | None)

Returns:

Future for the folding result.

Return type:

FoldComplexResultFuture

__init__(session, model_id, metadata=None)

Parameters:

• session (APISession)

• model_id (str)

• metadata (ModelMetadata | None)

classmethod create(session, model_id, default=None, **kwargs)

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

Parameters:

• session (APISession) – The API session to use.

• model_id (str) – The model identifier.

• default (type[FoldModel] or None, optional) – Default FoldModel subclass to use if no match is found.

• **kwargs (dict, optional) – Additional keyword arguments to pass to the model constructor.

Returns:

An instance of the appropriate FoldModel subclass.

Return type:

FoldModel

Raises:

ValueError – If no suitable FoldModel subclass is found and no default is provided.

get_metadata()

Get model metadata for this model.

Returns:

The metadata associated with this model.

Return type:

ModelMetadata

classmethod get_model()

Get the model_id(s) for this FoldModel subclass.

Returns:

List of model_id strings associated with this class.

Return type:

list of str

property metadata

Model metadata for this model.

Type:

ModelMetadata

class openprotein.fold.Boltz1xModel

Class providing inference endpoints for Boltz-1x open-source structure prediction model, which adds the use of inference potentials to improve performance.

fold(proteins=None, dnas=None, rnas=None, ligands=None, diffusion_samples=1, recycling_steps=3, sampling_steps=200, step_scale=1.638, constraints=None)

Post sequences to Boltz-1x model. Uses potentials with Boltz-1 model.

Parameters:

• proteins (List[Protein] | MSAFuture | None) – List of protein sequences to include in folded output. Protein objects must be tagged with an msa, which can be a Protein.single_sequence_mode for single sequence mode. Alternatively, supply an MSAFuture to use all query sequences as a multimer.

• dna (List[DNA] | None) – List of DNA sequences to include in folded output.

• rna (List[RNA] | None) – List of RNA sequences to include in folded output.

• ligands (List[Ligand] | None) – List of ligands to include in folded output.

• diffusion_samples (int) – Number of diffusion samples to use

• recycling_steps (int) – Number of recycling steps to use

• sampling_steps (int) – Number of sampling steps to use

• step_scale (float) – Scaling factor for diffusion steps.

• constraints (Optional[List[dict]]) – List of constraints.

• dnas (list[DNA] | None)

• rnas (list[RNA] | None)

Returns:

Future for the folding complex result.

Return type:

FoldComplexResultFuture

__init__(session, model_id, metadata=None)

Parameters:

• session (APISession)

• model_id (str)

• metadata (ModelMetadata | None)

classmethod create(session, model_id, default=None, **kwargs)

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

Parameters:

• session (APISession) – The API session to use.

• model_id (str) – The model identifier.

• default (type[FoldModel] or None, optional) – Default FoldModel subclass to use if no match is found.

• **kwargs (dict, optional) – Additional keyword arguments to pass to the model constructor.

Returns:

An instance of the appropriate FoldModel subclass.

Return type:

FoldModel

Raises:

ValueError – If no suitable FoldModel subclass is found and no default is provided.

get_metadata()

Get model metadata for this model.

Returns:

The metadata associated with this model.

Return type:

ModelMetadata

classmethod get_model()

Get the model_id(s) for this FoldModel subclass.

Returns:

List of model_id strings associated with this class.

Return type:

list of str

property metadata

Model metadata for this model.

Type:

ModelMetadata

class openprotein.fold.Boltz1Model

Class providing inference endpoints for Boltz-1 open-source structure prediction model.

fold(proteins=None, dnas=None, rnas=None, ligands=None, diffusion_samples=1, recycling_steps=3, sampling_steps=200, step_scale=1.638, use_potentials=False, constraints=None)

Post sequences to Boltz-1 model.

Parameters:

• proteins (List[Protein] | MSAFuture | None) – List of protein sequences to include in folded output. Protein objects must be tagged with an msa, which can be a Protein.single_sequence_mode for single sequence mode. Alternatively, supply an MSAFuture to use all query sequences as a multimer.

• dna (List[DNA] | None) – List of DNA sequences to include in folded output.

• rna (List[RNA] | None) – List of RNA sequences to include in folded output.

• ligands (List[Ligand] | None) – List of ligands to include in folded output.

• diffusion_samples (int) – Number of diffusion samples to use

• recycling_steps (int) – Number of recycling steps to use

• sampling_steps (int) – Number of sampling steps to use

• step_scale (float) – Scaling factor for diffusion steps.

• use_potentials (bool = False.) – Whether or not to use potentials.

• constraints (Optional[List[dict]]) – List of constraints.

• dnas (list[DNA] | None)

• rnas (list[RNA] | None)

Returns:

Future for the folding complex result.

Return type:

FoldComplexResultFuture

__init__(session, model_id, metadata=None)

Parameters:

• session (APISession)

• model_id (str)

• metadata (ModelMetadata | None)

classmethod create(session, model_id, default=None, **kwargs)

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

Parameters:

• session (APISession) – The API session to use.

• model_id (str) – The model identifier.

• default (type[FoldModel] or None, optional) – Default FoldModel subclass to use if no match is found.

• **kwargs (dict, optional) – Additional keyword arguments to pass to the model constructor.

Returns:

An instance of the appropriate FoldModel subclass.

Return type:

FoldModel

Raises:

ValueError – If no suitable FoldModel subclass is found and no default is provided.

get_metadata()

Get model metadata for this model.

Returns:

The metadata associated with this model.

Return type:

ModelMetadata

classmethod get_model()

Get the model_id(s) for this FoldModel subclass.

Returns:

List of model_id strings associated with this class.

Return type:

list of str

property metadata

Model metadata for this model.

Type:

ModelMetadata

class openprotein.fold.AlphaFold2Model

Class providing inference endpoints for AlphaFold2 structure prediction models, based on the implementation by ColabFold.

__init__(session, model_id, metadata=None)

Parameters:

• session (APISession)

• model_id (str)

• metadata (ModelMetadata | None)

fold(proteins=None, num_recycles=None, num_models=1, num_relax=0, **kwargs)

Post sequences to alphafold model.

Parameters:

• proteins (List[Protein] | MSAFuture) – List of protein sequences to fold. Protein objects must be tagged with an msa. Alternatively, supply an MSAFuture to use all query sequences as a multimer.

• num_recycles (int) – number of times to recycle models

• num_models (int) – number of models to train - best model will be used

• max_msa (Union[str, int]) – maximum number of sequences in the msa to use.

• relax_max_iterations (int) – maximum number of iterations

• num_relax (int)

Returns:

job

Return type:

Job

classmethod create(session, model_id, default=None, **kwargs)

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

Parameters:

• session (APISession) – The API session to use.

• model_id (str) – The model identifier.

• default (type[FoldModel] or None, optional) – Default FoldModel subclass to use if no match is found.

• **kwargs (dict, optional) – Additional keyword arguments to pass to the model constructor.

Returns:

An instance of the appropriate FoldModel subclass.

Return type:

FoldModel

Raises:

ValueError – If no suitable FoldModel subclass is found and no default is provided.

get_metadata()

Get model metadata for this model.

Returns:

The metadata associated with this model.

Return type:

ModelMetadata

classmethod get_model()

Get the model_id(s) for this FoldModel subclass.

Returns:

List of model_id strings associated with this class.

Return type:

list of str

property metadata

Model metadata for this model.

Type:

ModelMetadata

class openprotein.fold.ESMFoldModel

Class providing inference endpoints for Facebook’s ESMFold structure prediction models.

model_id: str = 'esmfold'

__init__(session, model_id, metadata=None)

Parameters:

• session (APISession)

• model_id (str)

• metadata (ModelMetadata | None)

fold(sequences, num_recycles=None)

Fold sequences using this model.

Parameters:

• sequences (Sequence[bytes | str]) – sequences to fold

• num_recycles (int | None) – number of times to recycle models

Return type:

FoldResultFuture

classmethod create(session, model_id, default=None, **kwargs)

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

Parameters:

• session (APISession) – The API session to use.

• model_id (str) – The model identifier.

• default (type[FoldModel] or None, optional) – Default FoldModel subclass to use if no match is found.

• **kwargs (dict, optional) – Additional keyword arguments to pass to the model constructor.

Returns:

An instance of the appropriate FoldModel subclass.

Return type:

FoldModel

Raises:

ValueError – If no suitable FoldModel subclass is found and no default is provided.

get_metadata()

Get model metadata for this model.

Returns:

The metadata associated with this model.

Return type:

ModelMetadata

classmethod get_model()

Get the model_id(s) for this FoldModel subclass.

Returns:

List of model_id strings associated with this class.

Return type:

list of str

property metadata

Model metadata for this model.

Type:

ModelMetadata

Results

class openprotein.fold.FoldResultFuture

Fold results represented as a future.

job

The fold job associated with this future.

Type:

FoldJob

__init__(session, job, sequences=None, max_workers=10)

Initialize a FoldResultFuture instance.

Parameters:

• session (APISession) – The API session to use for requests.

• job (FoldJob) – The fold job associated with this future.

• sequences (list[bytes], optional) – List of sequences submitted for the fold request. If None, sequences will be fetched.

• max_workers (int, optional) – Maximum number of concurrent workers. Default is config.MAX_CONCURRENT_WORKERS.

classmethod create(session, job, **kwargs)

Factory method to create a FoldResultFuture or FoldComplexResultFuture.

Parameters:

• session (APISession) – The API session to use for requests.

• job (FoldJob) – The fold job associated with this future.

• **kwargs – Additional keyword arguments.

Returns:

An instance of FoldResultFuture or FoldComplexResultFuture depending on the model.

Return type:

FoldResultFuture or FoldComplexResultFuture

property sequences: list[bytes]

Get the sequences submitted for the fold request.

Returns:

List of sequences.

Return type:

list[bytes]

property model_id: str

Get the model ID used for the fold request.

Returns:

Model ID.

Return type:

str

property id

Get the ID of the fold request.

Returns:

Fold job ID.

Return type:

str

keys()

Get the list of sequences submitted for the fold request.

Returns:

List of sequences.

Return type:

list[bytes]

get(verbose=False)

Retrieve the fold results as a list of tuples mapping sequence to PDB-encoded string.

Parameters:

verbose (bool, optional) – If True, print verbose output. Default is False.

Returns:

List of tuples mapping sequence to PDB-encoded string.

Return type:

list[tuple[str, str]]

get_item(sequence)

Get fold results for a specified sequence.

Parameters:

sequence (bytes) – Sequence to fetch results for.

Returns:

Fold result for the specified sequence.

Return type:

bytes

cancelled()

check if job is cancelled

Return type:

bool

done()

Check if job is complete

Return type:

bool

refresh()

Refresh job status.

stream()

Retrieve results for this job as a stream.

wait(interval=5, timeout=None, verbose=False)

Wait for job to complete, then fetch results.

Parameters:

• interval (int, optional) – time between polling. Defaults to config.POLLING_INTERVAL.

• timeout (int, optional) – max time to wait. Defaults to None.

• verbose (bool, optional) – verbosity flag. Defaults to False.

Returns:

results of job

Return type:

results

wait_until_done(interval=5, timeout=None, verbose=False)

Wait for job to complete. Do not fetch results (unlike wait())

Parameters:

• interval (int, optional) – time between polling. Defaults to config.POLLING_INTERVAL.

• timeout (int, optional) – max time to wait. Defaults to None.

• verbose (bool, optional) – verbosity flag. Defaults to False.

Returns:

results of job

Return type:

results

class openprotein.fold.FoldComplexResultFuture

Future for manipulating results of a fold complex request.

job

The fold job associated with this future.

Type:

FoldJob

__init__(session, job, model_id=None, proteins=None, ligands=None, dnas=None, rnas=None)

Initialize a FoldComplexResultFuture instance.

Parameters:

• session (APISession) – The API session to use for requests.

• job (FoldJob) – The fold job associated with this future.

• model_id (str, optional) – Model ID used for the fold request.

• proteins (list[Protein], optional) – List of proteins submitted for fold request.

• ligands (list[Ligand], optional) – List of ligands submitted for fold request.

• dnas (list[DNA], optional) – List of DNAs submitted for fold request.

• rnas (list[RNA], optional) – List of RNAs submitted for fold request.

property model_id: str

Get the model ID used for the fold request.

Returns:

Model ID.

Return type:

str

property proteins: list[Protein] | None

Get the proteins submitted for the fold request.

Returns:

List of Protein objects or None.

Return type:

list[Protein] or None

property dnas: list[DNA] | None

Get the DNAs submitted for the fold request.

Returns:

List of DNA objects or None.

Return type:

list[DNA] or None

property rnas: list[RNA] | None

Get the RNAs submitted for the fold request.

Returns:

List of RNA objects or None.

Return type:

list[RNA] or None

property ligands: list[Ligand] | None

Get the ligands submitted for the fold request.

Returns:

List of Ligand objects or None.

Return type:

list[Ligand] or None

property pae: ndarray

Get the Predicted Aligned Error (PAE) matrix.

Returns:

PAE matrix.

Return type:

np.ndarray

Raises:

AttributeError – If PAE is not supported for the model.

property pde: ndarray

Get the Predicted Distance Error (PDE) matrix.

Returns:

PDE matrix.

Return type:

np.ndarray

Raises:

AttributeError – If PDE is not supported for the model.

property plddt: ndarray

Get the Predicted Local Distance Difference Test (pLDDT) scores.

Returns:

pLDDT scores.

Return type:

np.ndarray

Raises:

AttributeError – If pLDDT is not supported for the model.

property confidence: list[BoltzConfidence]

Retrieve the confidences of the structure prediction.

Note

This is only currently supported for Boltz models.

Returns:

List of BoltzConfidence objects.

Return type:

list[BoltzConfidence]

Raises:

AttributeError – If confidence is not supported for the model.

property affinity: BoltzAffinity

Retrieve the predicted binding affinities.

Note

This is only currently supported for Boltz models.

Returns:

BoltzAffinity object containing the predicted affinities.

Return type:

BoltzAffinity

Raises:

AttributeError – If affinity is not supported for the model.

property id

Get the ID of the fold request.

Returns:

Fold job ID.

Return type:

str

get(format='mmcif', verbose=False)

Retrieve the fold results as a single bytestring.

Defaults to mmCIF for complexes. Additional predicted properties like plddt and pae should be accessed from their respective properties, i.e. .plddt and .pae.

Parameters:

• format ({'pdb', 'mmcif'}, optional) – Output format. Default is ‘mmcif’.

• verbose (bool, optional) – If True, print verbose output. Default is False.

Returns:

Fold result as a bytestring.

Return type:

bytes

cancelled()

check if job is cancelled

Return type:

bool

done()

Check if job is complete

Return type:

bool

refresh()

Refresh job status.

wait(interval=5, timeout=None, verbose=False)

Wait for job to complete, then fetch results.

Parameters:

• interval (int, optional) – time between polling. Defaults to config.POLLING_INTERVAL.

• timeout (int, optional) – max time to wait. Defaults to None.

• verbose (bool, optional) – verbosity flag. Defaults to False.

Returns:

results of job

Return type:

results

wait_until_done(interval=5, timeout=None, verbose=False)

Wait for job to complete. Do not fetch results (unlike wait())

Parameters:

• interval (int, optional) – time between polling. Defaults to config.POLLING_INTERVAL.

• timeout (int, optional) – max time to wait. Defaults to None.

• verbose (bool, optional) – verbosity flag. Defaults to False.

Returns:

results of job

Return type:

results