MindSpore Chemistry

Introduction

Conventional chemistry studies have long been confronted with numerous challenges. The process of experimental design, synthesis, characterization, and analysis can be time-consuming, costly, and highly dependent on experts’ experiences. The synergy between AI and chemistry offers unprecedented opportunities to overcome the limitations of conventional approaches and unlock new frontiers in scientific discovery and innovation. AI techniques can efficiently process vast amount of data, mining underneath patterns and generating predictive models. By leveraging AI, chemistry and material science researchers can accelerate the design and optimization of chemical processes and the design and analysis of novel materials.

MindSpore Chemistry(MindChemistry) is a toolkit built on MindSpore endeavoring to integrate AI with conventional chemistry research. It supports multi-scale tasks including molecular generation, property prediction and synthesis optimization on multiple chemistry systems such as organic, inorganic and composites chemistry systems. MindChemistry dedicates to enabling the joint research of AI and chemistry with high efficiency, and seek to facilitate an innovative paradigm of joint research between AI and chemistry, providing experts with novel perspectives and efficient tools.

MindChemistry Architecture

Latest News

  • 2025.07.07 Added Orb model support.

  • 2025.04.16 Added CrystalFlow model support.

  • 2025.03.30 MindChemistry 0.2.0 has been released, featuring several applications including NequIP, DeephE3nn, Matformer, and DiffCSP.

  • 2024.07.30 MindChemistry 0.1.0 has been released.

Models & Applications

Below is an overview of the currently supported main models and their purposes, for quick reference and example location:

Machine Learning Force Fields

Model

System

Dataset

Task

NequIP

Small molecules

Revised Molecular Dynamics 17 (rMD17) dataset

Molecular energy prediction using E(3)-equivariant GNNs

Orb

Molecular and crystalline materials

Large-scale 3D atomic-structure datasets; DFT calculations

General GNN interatomic potential for energy, forces, and stress; suitable for molecular dynamics simulation

Property Prediction

Model

System

Dataset

Task

DeephE3nn

Materials systems

Bilayer graphene dataset

E(3)-equivariant neural network for electronic Hamiltonian prediction

Matformer

Crystalline materials

JARVIS-DFT 3D dataset

Graph + Transformer for materials property prediction

Structure Generation

Model

System

Dataset

Task

DiffCSP

Crystalline materials

Stable crystal structure datasets (MP-20, MPTS-52, Carbon-24)

Crystal structure prediction/generation via joint diffusion

CrystalFlow

Crystalline materials

Materials database crystal structure datasets (MP-20, Carbon-24, MPTS-52)

Flow-based crystal structure generation

Community

Core Contributors

Thanks goes to these wonderful people:

Danyang Chen, Jianhuan Cen, Kunming Xu, wujian, wangyuheng, Lin Peijia, gengchenhua, caowenbin，Siyu Yang