API Documentation

AIdsorb is a Python package for deep learning on molecular point clouds.

AIdsorb adopts the following conventions

• A pcd is represented as a numpy.ndarray of shape (N, 3+C).

• A molecular pcd is represented as a numpy.ndarray of shape (N, 4+C) where N is the number of atoms, pcd[:, :3] are the atomic coordinates, pcd[:, 3] are the atomic numbers and pcd[:, 4:] any additional features. If C == 0, then the only features are the atomic numbers.

Submodules

aidsorb.utils	This module provides helper functions for creating and handling molecular point clouds.
aidsorb.visualize	This module provides helper functions for visualizing molecular point clouds.
aidsorb.data	This module provides helper functions and classes for creating datasets and handling point clouds of variable sizes.
aidsorb.datamodules	This module provides LightningDataModule's for use with PyTorch Lightning.
aidsorb.transforms	This module provides helper functions and classes for transforming point clouds.
aidsorb.modules	This module provides torch.nn.Module's for building the architectures in aidsorb.models.
aidsorb.models	This module provides deep learning architectures for point cloud processing.
aidsorb.litmodels	This module provides LightningModule's for use with PyTorch Lightning.