drugforge.ml.data_augmentation.JitterFixed

class drugforge.ml.data_augmentation.JitterFixed(mean: float = 0, std: float = 1, rand_seed: int | None = None, dict_key: str = 'pos')

Bases: object

Jitter an input pose by drawing noise from a fixed normal distribution. Noise is generated per-atom.

__init__(mean: float = 0, std: float = 1, rand_seed: int | None = None, dict_key: str = 'pos')

Parameters:

• mean (float, default=1) – Mean of noise distribution

• std (float, default=0.1) – Standard deviation of noise distribution

• rand_seed (int, optional) – Random seed for noise generation

• dict_key (str, default=”pos”) – If the inputs are a dict, this will be the key used to access the coords in the dict

Methods

__init__([mean, std, rand_seed, dict_key])