Analogous to the to() method of torch Tensors Args: device: A torch device

Concatenates transformations along a new dimension. Args: ts: A list of T objects

Returns a copy of the Rotation whose underlying Tensor has been detached from its torch graph. Returns:

Parses FASTA string and returns list of strings with amino-acid sequences. Arguments: fasta_string: The string contents of a FASTA file.

Parses sequences and deletion matrix from stockholm format alignment. Args: stockholm_string: The string contents of a stockholm file. Th

Constructs a feature dict of MSA features.

Returns the underlying rotation as a rotation matrix tensor. Returns: The rotation as a rotation matrix tens

Parses sequences and deletion matrix from stockholm format alignment. Args: stockholm_string: The string contents of a stockholm file. Th

Returns the underlying rotation as a quaternion tensor. Depending on whether the Rotation was initialized with a

Extracts loop associated with a prefix from mmCIF data as a list. Reference for loop_ in mmCIF: http://mmcif.wwpdb.org/docs/tutorials/mecha

Parses sequences and deletion matrix from a3m format alignment. Args: a3m_string: The string contents of a a3m file. The first sequence i

Analogous to torch.unsqueeze. The dimension is relative to the shared dimensions of the rotation/translation.

Implements Algorithm 28. Weighted Rigid Align Args: x_pred: predicted atom positions, torch.Tensor, [..., num_samples, num_atoms, 3]

Produces an ordered sequence of tensor slices that, when used in sequence on a tensor with shape dims, yields tensors that contain ev

Applies the transformation to a coordinate tensor. Args: pts: A [*, 3] coordinate tensor. Return

Gets parsed template hits from the raw string output by the tool

Computes the templates for a given query sequence

Performs matrix multiplication of two rotation matrix tensors. Written out by hand to avoid AMP downcasting. Args:

Applies a rotation to a vector. Written out by hand to avoid transfer to avoid AMP downcasting. Args: r: [*, 3,

Builds a HMM for the aligned sequences given as an MSA string. Args: msa: A string with the aligned sequences, in A3M or STO format

Gets the bin centers from the bin edges. Args: breaks: [num_bins - 1] the error bin edges. Returns: bin_centers: [num_bins] the error bi

Parses atom positions in the target structure and aligns with the query. Atoms for each residue in the template structure are indexed to coincide

Returns indices for non-gap/insert residues starting at the given index.

Returns PDB id and chain id for an HHSearch Hit.

Function to decide which lines to keep.

Merge features from multiple chains. Args: chains: A list of feature dictionaries that we want to merge. pair_msa_sequences: Whether to con

Tries to extract template features from a single HHSearch hit.

Queries the database chunk using Jackhmmer.

Queries the database chunk using Jackhmmer.

Computes the relative indices for each residue with respect to the original sequence.

Moves the transformation object to GPU memory Returns: A version of the transformation on GPU

Helper function to get activation function from string. Args: act_fn (str): Name of activation function. Returns: nn.Module:

Function that minimizes energy, given topology, OpenMM system, and positions