by AstraZeneca
AiZynthFinder is an open-source tool for retrosynthetic planning. It searches for routes that break a target molecule down into purchasable precursors.
Web appFree
Step 1: Create a conda environment with a supported Python version.
Step 2: Install the package from PyPI with pip.
Step 3: Run the public data download command to fetch the stock file and policy networks and create a config.yml.
Step 4: Run aizynthcli with your config and a text file of SMILES, or start aizynthapp with the config.
Step 5: Review the proposed routes to purchasable precursors.
You need a stock file and a trained expansion policy network. A trained filter policy network is optional.
Yes. The tool supports multiple search algorithms and expansion policies, and the setup is described as fully customizable.
Linux, Windows and macOS, as long as the dependencies are supported. It was developed on Linux and tested on Windows 10 and macOS Catalina.
Yes. The maintainers welcome issues and pull requests, with code formatted using black and following pep8.
Universal Cell EmbeddingsUniversal Cell Embeddings is a PyTorch implementation of the UCE model for embedding single-cell RNA sequencing datasets. It adds a cell embedding to each cell in an AnnData file.
BioImage Model ZooThe BioImage Model Zoo is a community-driven, open resource for sharing standardized AI models for bioimage analysis. You can browse models, use them in partner software or download them for your own code.