chenggroup/ai2-kit

ai2-kit (pronounced as "AI Squared Kit") is a command line and python toolkit featured artificial intelligence × ab initio for complex chemistry systems research.

• Collection of tools to facilitate the development of automated workflows for computational chemistry research.
• Use with oh-my-batch to build your own workflow with shell script.
• Provide reusable skills under ./skills for building code related to ai2-kit.
  • build-tesla: a skill for building TESLA workflows from existing examples.

ai2-kit is developed and tested on Linux systems, and it should work on macOS as well. For Windows, most of the ai2-kit features are expected to work. However, some third-party libraries (such as dscribe) may not function properly on Windows. In such cases, it is recommended to use ai2-kit through Windows Subsystem for Linux (WSL).

If you are using the latest version of Python, some third-party libraries may not yet provide pre-built binary releases, which can cause pip install to fail. It is therefore suggested to use ai2-kit with Python 3.10–3.12. We strongly recommend creating a dedicated Conda environment to avoid unexpected issues caused by incompatible package versions.

You can use the following command to install ai2-kit:

# for users who just use most common features
pip install ai2-kit

# for users who want to use all features
pip install ai2-kit[all]

If you want to run ai2-kit from source, you can run the following commands in the project folder:

pip install poetry
# If you meet ConnectionError, you can try to set the max-workers to a smaller number, e.g
# poetry config installer.max-workers 4
poetry install
poetry run ai2-kit

All ai2-kit commands can be accessed via the command line interface ai2-kit. You can run the following command to see the available commands and sub-commands:

ai2-kit
# e.g.
ai2-kit tool
ai2-kit tool dpdata

For detailed usage of each command, you can run the following command to view the help information:

ai2-kit <sub-command> --help
# e.g.
ai2-kit tool dpdata read --help

• ASE Toolkit: commands to process trajectory files with ASE
• DPData Toolkit: commands to process system data with dpdata
• Model Deviation Toolkit: a toolkit to filter structures by model deviation

These workflows are built with oh-my-batch and example shell scripts, which can be easily adapted to your own research purpose. It provides more flexibility and transparency to run and customize their own workflows.

• TESLA: A customizable active learning workflow for training machine learning potentials.
• TESLA PIMD: A customizable active learning workflow for training machine learning potentials with path integral molecular dynamics.
• TESLA for ec-MLP: A customizable active learning workflow for training machine learning potentials for electrolyte systems.

These workflows are driven by configuration files, which can be easily modified to fit your own research purpose.

• CLL MLP Training Workflow (zh)

• NMRNet: A toolkit for predict NMR with deep learning network.
• Proton Transfer Analysis Toolkit
• Amorphous Oxides Structure Analysis Toolkit
• Re-weighting Toolkit
• ai2-cat: A toolkit for dynamic catalysis researching.

• NMRPeak Online App: AI tools for NMR analysis.
• Electrolyte Designer: run electrolyte simulations with ease.
• NMRNet Prediction: an online app to predict NMR chemical shifts with pre-trained NMRNet models.

• Tips: useful tips for using ai2-kit