openad 0.7.1

Open Accelerated Discovery Client

OpenAD

Open-source framework for molecular and materials discovery

Open Accelerated Discovery (aka OpenAD) is an open-source framework for molecular and materials discovery developed at IBM Research.

The OpenAD client is accessible from our command line interface, via Jupyter Notebook or our API. It provides unified access to a variety of tools and AI models for literature knowledge extraction, forward and retrosynthesis prediction, generative methods and property inference. OpenAD lets you train models on your own data, to then visualize and filter your candidate molecules.

INSTALLATION     GETTING STARTED     COMMANDS     MODELS SERVICE

PLUGINS     AI ASSISTANT     DEVELOPERS

Useful links

• Homepage
  accelerate.science/projects/openad
• GitHub
  github.com/acceleratedscience/open-ad-toolkit
• Pip install
  pypi.org/project/openad
• Documentation
  acceleratedscience.github.io/openad-docs

Quick Install

[!IMPORTANT] This will install OpenAD in your global space. If you wish to use a virtual environment (recommended), please refer to the Installation page.

pip install openad
openad

Get started with Jupyter Notebook examples:

init_magic
init_examples
jupyter lab ~/openad_notebooks/Table_of_Contents.ipynb

If you get an error when running init_magic, you may first need to setup the default iPython profile for magic commands.

ipython profile create

What's New

• %Openadd has been added to the magic commands for commands that return data.

• Upgraded SkyPilot to 0.6.0

• Support for deploying in OpenShift AI/Open Data hub workbench or Podman/Docker image. See the workbench repo.

• Support for application API

• New property and dataset generation services. See OpenAD Models Service

  • GT4SD Generation Services
  • GT4SD Property Services
  • GT4SD MoleR Generation
  • GT4SD Molformer

  You'll need an AWS account and the ability to launch your own EC2 instances and catalog a remote service via URL. Instructions provided.

Feedback

• Feature requests, feedback and questions:
  [e-mail]
• Bug reports:
  Create issue on GitHub

Learn

• OpenAD blog
• Demo Notebooks: See init_examples under installation

Contribute

Stay tuned for detailed instructions on how to build your own OpenAD plugins.
Check the Developers section for guidance with other contributions.