Get an item from the Redis database.

Load the object from a JSON file. Parameters ---------- path : Path The path to the file. Returns

Pad a tensor along a given dimension. Parameters ---------- data : Tensor The input tensor. dim : int The dimension t

Delegate a log call to the underlying logger, after prefixing its message with the rank of the process it's being logged from. If `'rank'` is

MLX version of torch.one_hot. Args: indices: integer MLX array of any shape, containing class indices in [0, num_classes). n

Center and randomly augment the input coordinates. Parameters ---------- atom_coords : Tensor The atom coordinates. atom_mask

Dump the object to a JSON file. Parameters ---------- path : Path The path to the file.

Root Mean Square Layer Normalization :param d: model size :param p: partial RMSNorm, valid value [0, 1], default -1.0 (di

Pick a random token from the data. Parameters ---------- tokens : np.ndarray The token data. random : np.ndarray The

Calculate TM-score between two PDB files, each containing only one chain and only CA atoms. Args: model_pdb_path (str): path to P

Takes a list of tensors with the following dimensions: [(d_11, ..., d_1K), (d_21, ..., d_2K),

Create a rigid 4x4 transformation matrix from two axes and transl.

Compute the data coefficient along the path

Compute the noise coefficient along the path

Filter structures based on their resolution. Parameters ---------- record : Record The record to filter.

Compute features. Parameters ---------- data : Tokenized The tokenized data. max_tokens : int, optional

Tokenize the input data. Parameters ---------- data : Input The input data. Returns -------

Compute rmsd of the aligned atom coordinates. Parameters ---------- pred_atom_coords : torch.Tensor Predicted atom coordinates

Construct a layernorm layer in the TF style (eps inside the sqrt).

Creates paths for folders

Applies optional utilities before the task is started. Utilities: - Ignoring python warnings - Setting tags from command line

Get the absolute path to a config file using importlib.resources.

Instantiates callbacks from config. :param callbacks_cfg: A DictConfig object containing callback configurations. :return: A list of instanti

Controls which config parts are saved by Lightning loggers. Additionally saves: - Number of model parameters :param object_dict: A d

Unique key to lookup bonds.

Parse a Boltz input yaml / json. The input file should be a dictionary with the following format: version: 1 sequences: - protei

Parse an MMCIF ligand. First tries to get the SMILES string from the RCSB. Then, tries to infer atom ordering using RDKit. Parameters

Process an MSA file. Parameters ---------- lines : TextIO The lines of the MSA file. taxonomy : dict[str, str] The ta

Define chi-angle rigid groups via one-hot representations.

Download all the required data. Parameters ---------- cache : Path The cache directory.

Generate chain tags. Yields ------ str The next chain tag

Retrieve an rdkit object for a deemed conformer. Inspired by `pdbeccdutils.core.component.Component`. Parameters ---------- mol: Mol

Retrieve an rdkit object for a deemed conformer. Inspired by `pdbeccdutils.core.component.Component`. Parameters ---------- mol: Mol

Instantiates loggers from config. :param logger_cfg: A DictConfig object containing logger configurations. :return: A list of instantiated lo

Load the given input data. Parameters ---------- record : Record The record to load. target_dir : Path The path to th

Process the input data and output directory. Parameters ---------- data : list[Path] The input data. out_dir : Path T

Remove invalid chains. Parameters ---------- structure : Structure The structure to process. Returns

Write a structure into an MMCIF file. Parameters ---------- structure : Structure The input structure Returns -------

Write a structure into a PDB file. Parameters ---------- structure : Structure The input structure Returns ------- s

Compute weighted alignment. Parameters ---------- true_coords: torch.Tensor The ground truth atom coordinates pred_coords: to

Initialize the training dataset. Parameters ---------- manifest : Manifest The manifest to load data from.

Initialize the training dataset.

Return a tensor where each element has the absolute value taken from the, corresponding element of a, with sign taken from the corresponding

Returns atom indices needed to compute chi angles for all residue types. Returns: A tensor of shape [residue_types=21, chis=4, atoms=4]. The re

Matrices to map atoms to symmetry partners in ambiguous case.

Mask which atoms are ambiguous in atom14.

Mask of which atoms are present for which residue type in atom14.

Map from atom14 to atom37 per residue type.

Mask of which atoms are present for which residue type in atom37.

Map from atom37 to atom14 per residue type.

Create Map from rigidgroups to atom37 indices.

Fill the arrays above.

Returns [num_res_types, num_atom_types] mask array.

Perform average product correct, used for contact prediction.