Generate random rotations as 3x3 rotation matrices. Args: n: Number of rotation matrices in a batch to return. dtype: Type t

Compute weighted alignment. Parameters ---------- pred_coords: torch.Tensor The predicted atom coordinates

Make layer symmetric in final two dimensions, used for contact prediction.

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These ma

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These ma

cond: (B, N, D) Drops conditions to enable classifier-free guidance.

cond: (B, N, D) Drops conditions to enable classifier-free guidance.

Get the training dataloader. Returns ------- DataLoader The training dataloader.

Input shape: Time x Batch x Channel Args: key_padding_mask (ByteTensor, optional): mask to exclude keys that are

Get the positional encoding for each coordinate. Args: pos: (*, in_dim) Returns: out:

xq: [B, H, N, D] xk: [B, H, N, D] pos: [B, N, in_dim]

Get an item from the resource.

Get an item from the dataset. Returns ------- Dict[str, Tensor] The sampled data features.

Get an item from the dataset. Parameters ---------- idx : int The data index. Returns -------

Initialize the redis database.

Initializes a multi-GPU-friendly python command line logger that logs on all processes with their rank prefixed in the log message. :

Initialize the writer. Parameters ---------- output_dir : str The directory to save the predictions.

Initialize the cropper. Modulates the type of cropping to be performed. Smaller neighborhoods result in more spatial cropping

Initialize the cropper. Modulates the type of cropping to be performed. Smaller neighborhoods result in more spatial cropping

Initialize the filter. Parameters ---------- min_len : float, optional The minimum allowed length. max_le

Initialize the filter. Parameters ---------- max_dist : float, optional The maximum allowed distance.

Initialize the filter. Parameters ---------- dist : float, optional The maximum distance for a clash. fre

Initialize the filter. Parameters ---------- min_chains : int The minimum number of chains allowed. max_c

Initialize the filter. Parameters ---------- subset : str The subset of data to consider, one per line.

Initialize the filter. Parameters ---------- resolution : float, optional The maximum allowed resolution.

Initialize the filter. Parameters ---------- min_chains : int The minimum number of chains allowed. max_c

Initialize the filter. Parameters ---------- date : str, optional The maximum date of PDB entries to filter

Initialize the DataModule. Parameters ---------- config : DataConfig The data configuration.