PaddleMaterials is a data-mechanism dual-driven, foundation model development and deployment, end to end toolkit based on PaddlePaddle deep learning framework for materials science.

Generating Deep Potential with Python

Machine‑Learning / Molecular‑Mechanics (ML/MM) hybrid calculator and CLI toolset for Mechanistic Investigation of Enzymatic Reactions.

Automated enzyme reaction path modeling from PDB structures

MLIP (Machine Learning Interatomic Potential) plugins for ORCA ExtTool (ProgExt) interface.

Model zoo and experimental features of machine learning interatomic potentials.

MLIP (Machine Learning Interatomic Potential) plugins for Gaussian 16 External interface.

LCAONet - MPNN including electronic structure and orbital information, physically motivatied by the LCAO method.

🦀 CPU-based neighbor list construction in Rust for atomistic simulations — naive O(N²) and cell list O(N) algorithms

MLIP (Machine Learning Interatomic Potential) plugins for ML/MM MD simulations with AmberTools25.

LEIGNN MLIP Training on ISO17 Dataset

MLIP NequIP on the MD17 Dataset