MindSpore SPONGE Documents

MindSpore SPONGE is a computative biology suite based on MindSpore, supporting common functions such as molecular dynamics and protein folding.

The molecular simulation or modeling process has a high degree of logic consistency with the AI model training/inferring process, so the molecular simulation can in principle be unified with the AI training/inferring mode. MindSpore SPONGE integrates molecular simulation and AI training/inferring under the same programming structure. The overall structure view is as follows:

MindSpore SPONGE Architecture

Different from traditional molecular simulation software, AI molecular simulation library has completely new features, such as:

  1. Instead of manual derivative programming, automatic differential technology provides a unified programming paradigm for different energy functions or the construction of complex scoring functions;

  2. Fully compatible with neural network models, supporting AI inferring within molecular simulation, or simulation as an engine for AI training;

  3. The end-to-end differentiable modeling method can realize the meta-optimization of the physical model;

  4. Hierarchical code architecture, using efficient language operator at the bottom; Provide users with object-oriented Python API to facilitate user customization;

  5. Automatic adaptation of multiple back-end. Users only need to write a simple Python code to accelerate execution on multiple back-end, such as GPU and NPU;

  6. High-throughput simulation supported by automatic parallel. Users do not need to distinguish between single or multi-machine execution of code, can concurrently simulate multiple systems on a single hardware unit, without special MPI programming.

Combined with these new features, the unified framework of molecular simulation and AI can support a wide range of molecular modeling and application scenarios, such as:

  • Molecular simulation based on AI improved force field or enhanced sampling;

  • Data-driven & physics-driven molecular docking;

  • Protein structure prediction and force field optimization;

  • High throughput molecular simulation;

  • Molecular design, etc.

Code repository address: <https://gitee.com/mindspore/mindscience/tree/master/MindSPONGE>



  • Python>=3.7

  • MindSpore>=2.0

Please refer to MindSpore installation tutorial.

Source Code Installation

git clone https://gitee.com/mindspore/mindscience.git
cd mindscience/MindSPONGE
  • dependency install

    pip install -r requirements.txt
  • Ascend backend

    Enable c if you want to use Cybertron.

    bash build.sh -e ascend -c on
  • GPU backend

    Enable c if you want to use Cybertron.

    Enable t if you want to use traditional MD.

    export CUDA_PATH={your_cuda_path}
    bash build.sh -e gpu -j32 -t on -c on
  • Install whl package

    cd output/
    pip install mindsponge*.whl
    pip install cybertron*.whl # if "-c on" is used



Special Interesting Group

MindSpore SPONGE SIG (Special Interesting Group) is a team composed of a group of people who are interested and have a mission to make achievements in the field of AI × biological computing.

MindSpore SPONGE SIG group provides efficient and easy-to-use AI computational biology software for researchers, teachers and students, and provides a platform for people with strong abilities or strong interests in this field to communicate and cooperate together.

At present, the SIG group has six core teachers. After members joining the SIG group, our teachers will lead the team to carry out scientific research and develop the software function development. Of course, members are also welcome to do research on their own topics using MindSpore SPONGE.

In the SIG group, we will hold various activities, including summer school, public lecture, technology communication meeting and other large-scale activities. Small-scale activities like weekly meetings, blogs writing will also be held in the group. By joining the activities, there will be lots of chances to communicate with our experts. During the summer school program ended on August 15th, we invited 13 teachers to have a five-day lecture mainly including three themes of MindSpore basics, molecular dynamics and advanced AI × Science courses. You can get the replay here.

In the SIG group, we will also release the public intelligence task and open source internship task, welcome everyone to claim it.

Core Contributor

Contribution Guide

Molecular Simulation Introduction