Runs processing on features to augment, pair and merge. Args: all_chain_features: A MutableMap of dictionaries of features for each chain. R

Computes predicted TM alignment or predicted interface TM alignment score. Args: logits: [num_res, num_res, num_bins] the logits output from

Database Versions: Training: uniref90: v2022_05 bfd: reduces_bfd:

Pointwise left multiplication of the rotation with a tensor. Can be used to e.g. mask the Rotation. Args:

Pointwise left multiplication of the transformation with a tensor. Can be used to e.g. mask the Rigid. Args:

Determines if template is valid (without parsing the template mmcif file). Args: hit: HhrHit for the template. hit_pdb_code: The

Gets mapping from indices in original query sequence to indices in the hit. hit_query_sequence and hit_sequence are two aligned sequences contain

Calculates expected aligned distance errors for every pair of residues. Args: alignment_confidence_breaks: [num_bins - 1] the error bin edges.

Checks if the distance between unmasked neighbor residues is ok.

Merges paired and block-diagonalised features.

Adds features that need to be computed/recomputed post merging.

Creates mapping from species to msa dataframe of that species.

Crops msa sequences to `msa_crop_size`.

Extracts sequence identifier from description. Returns None if no match.

Tries to find the template chain in the given pdb file. This method tries the three following things in order: 1. Tries if there is an ex

Gets atom positions and mask from a list of Biopython Residues.

Returns list of atom sites; contains data not present in the structure.

Returns the first model in a Biopython structure.

Returns a basic header containing method, release date and resolution.

Extracts polymer information for protein chains only. Args: parsed_info: _mmcif_dict produced by the Biopython parser. Returns:

Checks if the template date is after the release date cutoff. Args: pdb_id: 4 letter pdb code. release_dates: Dictionary mapping

Checks if a list of chains represents a homomer/monomer example.

Returns False if data is a special mmCIF character indicating 'unset'.

Makes dataframe with msa features needed for msa pairing.

Finds MSA sequence pairings across chains based on sequence similarity. Each chain's MSA sequences are first sorted by their sequence similarity to

Merge all identical chains, making the resulting MSA dense. Args: chains: An iterable of features for each chain. Returns: A list of fea

For each chain pad the number of templates to a fixed size. Args: chains: A list of protein chains. max_templates: Each chain will be padde

Parses the detailed HMM HMM comparison section for a single Hit. This works on .hhr files generated from both HHBlits and HHSearch. Args:

Parses the hmmsearch A3M sequence description line.

Parses the data file from PDB that lists which PDB ids are obsolete.

Parses release dates file, returns a mapping from PDBs to release dates.

Gets accession id and species from an msa sequence identifier. The sequence identifier has the format specified by _UNIPROT_TREMBL_ENTRY_NAME

Aligns template from the mmcif_object to the query. In case PDB70 contains a different version of the template sequence, we need to perform a

Generates a new obsolete by tracing all cross-references and store the latest leaf to all referencing nodes

Converts sequences to an a3m file.

Function to add restraints to specified group of atoms Code adapted from https://gist.github.com/peastman/ad8cda653242d731d75e18c836b2a3a5

Aligns the sequences and returns the alignment in A3M string. Args: sequences: A list of query sequence strings. The sequences have

Applies a Rotation -> Rotation function to the stored rotation object. Args: fn: A function of t

Applies a Tensor -> Tensor function to the stored translation. Args: fn: A function of

Args: x_denoised: predicted atom positions, torch.Tensor, [..., num_samples, num_atoms, 3] x_gt: ground truth atom positions, tor

Args: x_denoised: predicted atom positions, torch.Tensor, [..., num_samples, num_atoms, 3] x_gt: ground truth atom positions, tor

Args: x_denoised: predicted atom positions, torch.Tensor, [..., num_samples, num_atoms, 3] x_gt: ground truth atom positions, tor

Args: x_denoised: predicted atom positions, torch.Tensor, [..., num_samples, num_atoms, 3] x_gt: ground truth atom positions, tor

Builds a HHM for the aligned sequences given as an A3M string. Args: sto: A string with the aligned sequences in the Stockholm form

Args: x_pred: predicted atom positions, torch.Tensor, [..., num_atoms, 3] x_gt: ground truth atom positions, torch.Tensor, [...,

Args: x_pred: predicted atom positions, torch.Tensor, [..., num_atoms, 3] x_gt: ground truth atom positions, torch.Tensor, [...,

Args: x_pred: predicted atom positions, torch.Tensor, [..., num_atoms, 3] x_gt: ground truth atom positions, torch.Tensor, [...,

Args: x_pred: predicted atom positions, torch.Tensor, [..., num_atoms, 3] x_gt: ground truth atom positions, torch.Tensor, [...,

Compose the rotation matrices of the current Rotation object with those of another. Args: r:

Computes per-residue pLDDT from logits. Args: logits: [num_res, num_bins] output from the PredictedLDDTHead. Returns: plddt: [num_res] p

Computes aligned confidence metrics from logits. Args: logits: [num_res, num_res, num_bins] the logits output from PredictedAlignedErrorH

Converts MSA in Stockholm format to the A3M format.

Crops the MSAs for a set of chains. Args: chains_list: A list of chains to be cropped. msa_crop_size: The total number of sequences to crop

Args: logits: logits, torch.Tensor, [..., num_classes] labels: labels, torch.Tensor, [...]

Args: logits: logits, torch.Tensor, [..., num_classes] labels: labels, torch.Tensor, [...]

Args: logits: logits, torch.Tensor, [..., num_classes] labels: labels, torch.Tensor, [...]

Args: logits: logits, torch.Tensor, [..., num_classes] labels: labels, torch.Tensor, [...]