openfold.data.templates¶

Functions for getting templates and calculating template features.

Classes

`CustomHitFeaturizer`(mmcif_dir, ...[, ...])	Featurizer for templates given in folder.
`HhsearchHitFeaturizer`(mmcif_dir, ...[, ...])
`HmmsearchHitFeaturizer`(mmcif_dir, ...[, ...])
`PrefilterResult`(valid, error, warning)
`SingleHitResult`(features, error, warning)
`TemplateHitFeaturizer`(mmcif_dir, ...[, ...])	An abstract base class for turning template hits to features.
`TemplateSearchResult`(features, errors, warnings)

Functions

`empty_template_feats`(n_res)
`generate_release_dates_cache`(mmcif_dir, out_path)
`get_custom_template_features`(mmcif_path, ...)

Exceptions

`AlignRatioError`	An error indicating that the hit align ratio to the query was too small.
`CaDistanceError`	An error indicating that a CA atom distance exceeds a threshold.
`DateError`	An error indicating that the hit date was after the max allowed date.
`DuplicateError`	An error indicating that the hit was an exact subsequence of the query.
`LengthError`	An error indicating that the hit was too short.
`NoAtomDataInTemplateError`	An error indicating that template mmCIF didn't contain atom positions.
`NoChainsError`	An error indicating that template mmCIF didn't have any chains.
`PrefilterError`	A base class for template prefilter exceptions.
`QueryToTemplateAlignError`	An error indicating that the query can't be aligned to the template.
`SequenceNotInTemplateError`	An error indicating that template mmCIF didn't contain the sequence.
`TemplateAtomMaskAllZerosError`	An error indicating that template mmCIF had all atom positions masked.

exception AlignRatioError¶

Bases: PrefilterError

An error indicating that the hit align ratio to the query was too small.

exception CaDistanceError¶

Bases: Error

An error indicating that a CA atom distance exceeds a threshold.

exception DateError¶

Bases: PrefilterError

An error indicating that the hit date was after the max allowed date.

exception DuplicateError¶

Bases: PrefilterError

An error indicating that the hit was an exact subsequence of the query.

exception LengthError¶

Bases: PrefilterError

An error indicating that the hit was too short.

exception NoAtomDataInTemplateError¶

Bases: Error

An error indicating that template mmCIF didn’t contain atom positions.

exception NoChainsError¶

Bases: Error

An error indicating that template mmCIF didn’t have any chains.

exception PrefilterError¶

Bases: Exception

A base class for template prefilter exceptions.

exception QueryToTemplateAlignError¶

Bases: Error

An error indicating that the query can’t be aligned to the template.

exception SequenceNotInTemplateError¶

Bases: Error

An error indicating that template mmCIF didn’t contain the sequence.

exception TemplateAtomMaskAllZerosError¶

Bases: Error

An error indicating that template mmCIF had all atom positions masked.

class CustomHitFeaturizer(mmcif_dir, max_template_date, max_hits, kalign_binary_path, release_dates_path=None, obsolete_pdbs_path=None, strict_error_check=False, _shuffle_top_k_prefiltered=None, _zero_center_positions=True)¶

Bases: TemplateHitFeaturizer

Featurizer for templates given in folder. Chain of interest has to be chain A and of same sequence length as input sequence.

Parameters:

mmcif_dir (str)
max_template_date (str)
max_hits (int)
kalign_binary_path (str)
release_dates_path (str | None)
obsolete_pdbs_path (str | None)
strict_error_check (bool)
_shuffle_top_k_prefiltered (int | None)
_zero_center_positions (bool)

get_templates(query_sequence, hits)¶

Computes the templates for given query sequence (more details above).

Parameters:

query_sequence (str)
hits (Sequence[TemplateHit])

Return type:

TemplateSearchResult

class HhsearchHitFeaturizer(mmcif_dir, max_template_date, max_hits, kalign_binary_path, release_dates_path=None, obsolete_pdbs_path=None, strict_error_check=False, _shuffle_top_k_prefiltered=None, _zero_center_positions=True)¶

Bases: TemplateHitFeaturizer

Parameters:

mmcif_dir (str)
max_template_date (str)
max_hits (int)
kalign_binary_path (str)
release_dates_path (str | None)
obsolete_pdbs_path (str | None)
strict_error_check (bool)
_shuffle_top_k_prefiltered (int | None)
_zero_center_positions (bool)

get_templates(query_sequence, hits)¶

Computes the templates for given query sequence (more details above).

Parameters:

query_sequence (str)
hits (Sequence[TemplateHit])

Return type:

TemplateSearchResult

class HmmsearchHitFeaturizer(mmcif_dir, max_template_date, max_hits, kalign_binary_path, release_dates_path=None, obsolete_pdbs_path=None, strict_error_check=False, _shuffle_top_k_prefiltered=None, _zero_center_positions=True)¶

Bases: TemplateHitFeaturizer

Parameters:

mmcif_dir (str)
max_template_date (str)
max_hits (int)
kalign_binary_path (str)
release_dates_path (str | None)
obsolete_pdbs_path (str | None)
strict_error_check (bool)
_shuffle_top_k_prefiltered (int | None)
_zero_center_positions (bool)

get_templates(query_sequence, hits)¶

Parameters:

query_sequence (str)
hits (Sequence[TemplateHit])

Return type:

TemplateSearchResult

class PrefilterResult(valid: bool, error: str | None, warning: str | None)¶

Parameters:

valid (bool)
error (str | None)
warning (str | None)

error: str | None¶

valid: bool¶

warning: str | None¶

class SingleHitResult(features: Mapping[str, Any] | None, error: str | None, warning: str | None)¶

Parameters:

features (Mapping[str, Any] | None)
error (str | None)
warning (str | None)

error: str | None¶

features: Mapping[str, Any] | None¶

warning: str | None¶

class TemplateHitFeaturizer(mmcif_dir, max_template_date, max_hits, kalign_binary_path, release_dates_path=None, obsolete_pdbs_path=None, strict_error_check=False, _shuffle_top_k_prefiltered=None, _zero_center_positions=True)¶

Bases: ABC

An abstract base class for turning template hits to features.

Parameters:

mmcif_dir (str)
max_template_date (str)
max_hits (int)
kalign_binary_path (str)
release_dates_path (str | None)
obsolete_pdbs_path (str | None)
strict_error_check (bool)
_shuffle_top_k_prefiltered (int | None)
_zero_center_positions (bool)

abstract get_templates(query_sequence, hits)¶

Computes the templates for a given query sequence

Parameters:

query_sequence (str)
hits (Sequence[TemplateHit])

Return type:

TemplateSearchResult

class TemplateSearchResult(features: Mapping[str, Any], errors: Sequence[str], warnings: Sequence[str])¶

Parameters:

features (Mapping[str, Any])
errors (Sequence[str])
warnings (Sequence[str])

errors: Sequence[str]¶

features: Mapping[str, Any]¶

warnings: Sequence[str]¶

empty_template_feats(n_res)¶

generate_release_dates_cache(mmcif_dir, out_path)¶

Parameters:

mmcif_dir (str)
out_path (str)

get_custom_template_features(mmcif_path, query_sequence, pdb_id, chain_id='A', kalign_binary_path=None)¶

Parameters:

mmcif_path (str)
query_sequence (str)
pdb_id (str)
chain_id (str | None)
kalign_binary_path (str | None)