Computes (if necessary) and returns a mapping from each bond index to all the incoming bond indices. :return: A PyTorch tensor conta

Makes predictions. If smiles is provided, makes predictions on smiles. Otherwise makes predictions on args.test_data. :param args: Arguments

Gets the number of tasks in a data CSV file. :param path: Path to a CSV file. :return: The number of tasks.

Returns the smiles strings from a data CSV file (assuming the first line is a header). :param path: Path to a CSV file. :param header: W

Loads the task names a model was trained with. :param path: Path where model checkpoint is saved. :return: The task names that the model

Generates a binary Morgan fingerprint for a molecule. :param mol: A molecule (i.e. either a SMILES string or an RDKit molecule). :param

Generates a counts-based Morgan fingerprint for a molecule. :param mol: A molecule (i.e. either a SMILES string or an RDKit molecule). :

Computes the mean squared error. :param targets: A list of targets. :param preds: A list of predictions. :return: The computed mse.

Returns the number of prediction tasks. :return: The number of tasks.

syntax "[0] * int" only works properly for Python 3.5+ Note that in testing time, the length of a sentence might exceed the pre-defined m

Pandas Doc https://pandas.pydata.org/pandas-docs/stable/generated/pandas.set_option.html NumPy Doc -

Computes the area under the precision-recall curve. :param targets: A list of binary targets. :param preds: A list of prediction probabi

Generates RDKit 2D features for a molecule. :param mol: A molecule (i.e. either a SMILES string or an RDKit molecule). :retu

Registers a features generator. :param features_generator_name: The name to call the FeaturesGenerator. :return: A decorator which will

Remove the edge v1 -> v2 if present.

Resets the metric to to it's initial state. This is called at the start of each epoch.

Computes the root mean squared error. :param targets: A list of targets. :param preds: A list of predictions. :return: The computed

Saves features to a compressed .npz file with array name "features". :param path: Path to a .npz file where the features will be saved.

Freeze every seed for reproducibility. torch.cuda.manual_seed_all is useful when using random generation on GPUs. e.g. torch.cuda.FloatTe

Sets the targets of a molecule. :param targets: A list of floats containing the targets.

Show model parameters for logging.

Move Tensors to CUDA. If no device provided, default to the first card in CUDA_VISIBLE_DEVICES.

Validates a data CSV file, returning a set of errors. :param data_path: Path to a data CSV file. :return: A set of error messages.

Visualise the graph using networkx & matplotlib.