
by MIT
Chemprop is a PyTorch-based framework for training and evaluating message-passing neural networks that predict molecular properties. The site hosts its documentation for version 2.3.1.
Web appFree
Step 1: Read the Installation page and install Chemprop.
Step 2: Follow the Quickstart page.
Step 3: Work through the command line tutorials to train a model.
Step 4: Try the Jupyter notebook examples for Python use.
Step 5: Check the CLI and API references for options.
It trains and evaluates message-passing neural networks for molecular property prediction.
It was rewritten from the ground up; a guide compares v1 and v2 CLI arguments and default hyperparameters.
The documentation asks users to cite the papers listed there when they train or develop a model with Chemprop.
Yes, the docs include Python module tutorials, notebook examples and an API reference.
ASKCOSASKCOS is a hosted set of computer-aided design tools for organic synthesis. You enter or draw a molecule or reaction SMILES and see the tasks available for it, such as synthetic planning modules.
Therapeutics Data CommonsTherapeutics Data Commons is a collection of AI-ready datasets, tasks and benchmarks for drug discovery. Everything is accessed through an open Python library.
TDC-2Therapeutics Data Commons (TDC) is a resource of AI-ready datasets, learning tasks and benchmarks for therapeutic science, accessed through an open Python library.
StarDistDeep-learning microscopy segmentation tool for detecting star-convex cell nuclei and biological objects
MatterGenMatterGen is a generative model from Microsoft for designing inorganic materials across the periodic table. It can be fine-tuned to steer generation toward property constraints.
scGPTscGPT is a foundation model for single-cell multi-omics built with generative AI. The repository has the code, pretrained checkpoints and tutorials.