label transformation helper function Args: y (list): a list of labels binary (bool): whether or not to conduct binarization threshol

convert .log file to configs in .json

a wrapper to download, process and load multiple(>2)-instance prediction task datasets. assume the downloaded file is already processed Args:

print the statistics of the dataset

a wrapper to download, process and load single-instance prediction task datasets Args: name (str): the rough dataset name path (str): the

copied from https://github.com/mcs07/PubChemPy/blob/e3c4f4a9b6120433e5cc3383464c7a79e9b2b86e/pubchempy.py#L238 Construct API request from parameter

Reinitialize model parameters.

Reinitialize model parameters.

get the set of available labels for query dataset Args: name (str): rough dataset name Returns: list: a list of available labels

for distributed training

for resumed training

call the evaluator function on targets and predictions Args: *args: targets, predictions, and other information **kwargs: other auxil

MLP layers construction Paramters --------- num_layers: int The number of linear layers input_dim: int

input_dim (int) output_dim (int) hidden_dims_lst (list, each element is a integer, indicating the hidden size)

empty data loader class, to be overwritten

Create Protein-Protein Interaction Prediction dataloader object

Create Catalyst Prediction dataloader object

Create Drug-Drug Interaction (DDI) Prediction dataloader object

Create Reaction Type Prediction dataloader object

Summary Args: name (TYPE): Description path (str, optional): Description label_name (None, option

Create Yields (Reaction Yields Prediction) dataloader object.

create dataloader object Args: name (str): name of dataloader path (str): the path where data is saved label_name (str): name of label

Create a base dataloader object that each multi-instance prediction task dataloader class can inherit from. Args: name

Create Drug-Target Interaction Prediction dataloader object

Create ReactType (Reaction Type Prediction) dataloader object.

Create a testing case dataloader.

Create an Epitope prediction dataloader object.

Create a base dataloader object that each single instance prediction task dataloader class can inherit from. Raises: ValueError: for a dataset

Create Yields (Reaction Yields Prediction) dataloader object.

Create QM (Quantum Mechanics Modeling) dataloader object.

Create ADME dataloader object.

Create a Tox (Toxicity Prediction) dataloader object.

Create a BioAct dataloader object.

create an evaluate object

Init function :param mapping: the mapping dict for (param_name->argument_name). :param instance: the target instance to initi

get number of data points Returns: int: number of data points

__repr__function :return:

It is a config helper to parser for get_config. Gather values form config and params. Should be written by designer and used by user

The same as Config.add_argument but add argument check whether the argument name is in the list of class :param parser: The parser to

r""" Reference: Zhou et al. BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition, CVPR 2020.

binarization of a label list given a pre-specified threshold Args: y (list): a list of labels threshold (float): the threshold for turnin

binarize the labels Args: threshold (float, optional): the threshold to binarize the label. order (str, opti

SMILES string from PubChem CID Args: cid (str): PubChem CID Returns: str: SMILES string

conversion from log-scale helper Args: y (list): a list of labels in log-scale Returns: np.array: an array of nM->p labels