scmidas.utils

scmidas.utils#

scmidas.utils.convert_tensor_to_list(data: Tensor | List[List[Any]]) → List[List[Any]][source]#

Convert a 2D tensor or list into a 2D list.

Parameters:

data – torch.Tensor or list of lists Input data to be converted.

Returns:

list of lists

Converted 2D list.

scmidas.utils.convert_tensors_to_cuda(x: Dict[str, Any], device: device) → Dict[str, Any][source]#

Recursively convert all tensors in a dictionary to CUDA.

Parameters:

  • x – dict Dictionary containing tensors or nested dictionaries.

  • device – torch.device Device to move the tensors to (e.g., CUDA or CPU).

Returns:

dict

A new dictionary with all tensors moved to the specified device.

scmidas.utils.detach_tensors(x: Dict[str, Any]) → Dict[str, Any][source]#

Recursively detach all tensors in a dictionary.

Parameters:

x – dict Dictionary containing tensors or nested dictionaries.

Returns:

dict

A new dictionary with all tensors detached.

scmidas.utils.exp(x: Tensor, eps: float = 1e-12) → Tensor[source]#

Compute a numerically stable exponential transformation.

Handles negative and positive values to avoid numerical instability.

Parameters:

  • x – torch.Tensor Input tensor.

  • eps – float, optional A small epsilon value to avoid division by zero, by default 1e-12.

Returns:

torch.Tensor

Transformed tensor with the exponential applied.

scmidas.utils.extract_params(config: dict, prefix: str) → dict[source]#

Extract parameters from a configuration dictionary with a specific prefix.

Removes the specified prefix from the keys in the resulting dictionary.

Parameters:

  • config – dict Configuration dictionary containing various parameters.

  • prefix – str Prefix to filter and remove from the keys.

Returns:

dict

A new dictionary containing the filtered parameters with the prefix removed.

scmidas.utils.extract_values(x: List[Any] | Tuple[Any] | Dict[Any, Any] | Any) → List[Any][source]#

Recursively extract all values from a tuple, list, or dictionary.

Parameters:

x – list, tuple, dict, or any type The input structure containing nested values.

Returns:

list

A flattened list of all values extracted from the input.

scmidas.utils.filter_keys(d: Dict[str, Any], substring: str) → Dict[str, Any][source]#

Filter a dictionary to include only keys that contain a specific substring.

Parameters:

  • d – Dict[str, Any] The input dictionary to filter.

  • substring – str The substring to look for in the keys.

Returns:

Dict[str, Any]

A new dictionary containing only the keys from the original dictionary that include the specified substring.

scmidas.utils.generate_all_combinations(mods: List[str]) → List[Tuple[Tuple[str, ...], List[str]]][source]#

Generate all possible input-output combinations for a given list of modalities.

For N modalities, generate all combinations of size r (1 <= r < N) as input, and the remaining modalities as output.

Parameters:

mods – list of str List of modality names.

Returns:

list of tuple

A list of tuples, where each tuple contains: - A tuple of input modalities. - A list of output modalities.

scmidas.utils.get_filenames(directory: str, extension: str) → List[str][source]#

Get sorted filenames with the given extension in the specified directory.

Parameters:

  • directory – str The directory to search for files.

  • extension – str The file extension to filter by.

Returns:

list of str

Sorted list of filenames with the specified extension.

scmidas.utils.get_name_fmt(file_num: int) → str[source]#

Generate a format string for filenames based on the total number of files.

Parameters:

file_num – int Total number of files to be named.

Returns:

str

Format string for filenames, e.g., ‘%03d’ for three-digit naming.

scmidas.utils.get_pred_dirs(pred_dir: str, combs: List[List[str]], joint_latent: bool, mod_latent: bool, impute: bool, batch_correct: bool, translate: bool, input: bool) → Dict[int, Dict[str, Dict[str, str]]][source]#

Generate directory paths for predictions based on configurations.

Parameters:

  • pred_dir – str Base directory for predictions.

  • combs – list of list of str Combinations of modalities for each batch.

  • joint_latent – bool Include joint latent variables.

  • mod_latent – bool Include modality-specific latent variables.

  • impute – bool Include imputed data.

  • batch_correct – bool Include batch-corrected data.

  • translate – bool Include translated data.

  • input – bool Include input data.

Returns:

dict

Dictionary of directories for each batch and variable.

scmidas.utils.get_s_joint_mods(combs: List[List[str]])[source]#

Generate s_joint and mods from a list of modality combinations.

Parameters:#

combslist

A list where each element is a list of strings representing combinations of modalities for a specific batch.

Returns:#

tuple

A tuple containing: - s_joint: A list of dictionaries, where each dictionary maps the modalities

to their corresponding indices for each batch.

  • mods: A list of all unique modalities across the dataset.

scmidas.utils.load_csv(filename: str) → list[source]#

Load a CSV file and return its contents as a list of rows.

Parameters:

filename – str Path to the CSV file.

Returns:

list

A list of rows, where each row is a list of strings.

scmidas.utils.load_predicted(pred_dir: str, combs: List[List[str]], joint_latent: bool = True, mod_latent: bool = False, impute: bool = False, batch_correct: bool = False, translate: bool = False, input: bool = False, group_by: str = 'modality') → Dict[int, Dict[str, Any]] | Dict[str, Dict[str, ndarray]][source]#

Load predicted variables from a specified directory.

Parameters:

  • pred_dir – str Path to the prediction directory.

  • combs – list of list of str Combinations of modalities for each batch. Example: [[‘rna’], [‘rna’, ‘adt’]].

  • joint_latent – bool, optional Whether to include joint latent variables, by default True.

  • mod_latent – bool, optional Whether to include modality-specific latent variables, by default False.

  • impute – bool, optional Whether to include imputed data, by default False.

  • batch_correct – bool, optional Whether to include batch-corrected data, by default False.

  • translate – bool, optional Whether to include translated data, by default False.

  • input – bool, optional Whether to include input data, by default False.

  • group_by – str, optional Grouping method for the data, either ‘modality’ or ‘batch’, by default ‘modality’.

Returns:

dict

Loaded predicted data grouped by the specified method.

scmidas.utils.log(x: Tensor, eps: float = 1e-12) → Tensor[source]#

Compute a numerically stable logarithm transformation.

Ensures numerical stability by adding a small epsilon.

Parameters:

  • x – torch.Tensor Input tensor.

  • eps – float, optional A small epsilon value to avoid log(0), by default 1e-12.

Returns:

torch.Tensor

Transformed tensor with the logarithm applied.

scmidas.utils.mkdir(directory: str, remove_old: bool = False)[source]#

Create a directory, optionally removing the old one.

Parameters:

  • directory – str Path to the directory.

  • remove_old – bool, optional Whether to remove the old directory if it exists, by default False.

scmidas.utils.mkdirs(directories: str | List[str] | Dict[str, Any], remove_old: bool = False)[source]#

Recursively create directories.

Parameters:

  • directories – str, list, or dict Path(s) to directories to create.

  • remove_old – bool, optional Whether to remove old directories if they exist, by default False.

scmidas.utils.ref_sort(x: List[str], ref: List[str]) → List[str][source]#

Sort the elements of x based on the order defined in ref.

Parameters:

  • x – list of str List of elements to be sorted.

  • ref – list of str Reference list defining the sort order.

Returns:

list of str

A sorted list of elements from x that appear in ref, maintaining the order of ref.

scmidas.utils.reverse_dict(original_dict: Dict[str, Dict[str, Any]]) → Dict[str, Dict[str, Any]][source]#

Reverse the keys and sub-keys of a nested dictionary.

Parameters:

original_dict – dict The original nested dictionary to be reversed.

Returns:

dict

A reconstructed dictionary where the keys and sub-keys are swapped.

scmidas.utils.reverse_trsf(name: str, data: ndarray, **kwargs) → ndarray[source]#

Apply a reverse transformation to the given data.

Parameters:

  • name – str Name of the transformation to reverse (e.g., ‘log1p’).

  • data – np.ndarray Data to transform.

  • kwargs – dict Additional transformation parameters.

Returns:

np.ndarray

Transformed data.

scmidas.utils.rmdir(directory: str)[source]#

Remove a directory if it exists.

Parameters:

directory – str Path to the directory to remove.

scmidas.utils.save_list_to_csv(data: List[List[Any]], filename: str, delimiter: str = ',')[source]#

Save a 2D list to a CSV file.

Parameters:

  • data – list of lists Input data to be saved.

  • filename – str Path to the CSV file.

  • delimiter – str, optional Delimiter to separate values in the CSV file, by default ‘,’.

scmidas.utils.save_tensor_to_csv(data: Tensor, filename: str, delimiter: str = ',')[source]#

Save a 2D tensor to a CSV file.

Parameters:

  • data – torch.Tensor Input tensor to be saved.

  • filename – str Path to the CSV file.

  • delimiter – str, optional Delimiter to separate values in the CSV file, by default ‘,’.