MIST
2026MIST is a family of molecular foundation models for molecular property prediction.
MIST is a family of molecular foundation models for molecular property prediction.
Smirk is a chemistry-specific tokenizer that provides complete coverage of the OpenSMILES specification.
A lightweight workflow and simulation manager for reproducible atomistic simulations that can be transferred across environments, calculators and structures on Unix systems. .
A bottom up cost model used for modeling manufacturing and materials cost in the julia programming language. This model takes cell design, material prices, demand, labor prices, and capital investment as inputs and caluclates materials, manufacturing, and overhead costs (as well as total cost)
AtomicGraphNets.jl implements graph-based models for machine learning on atomic systems, such as Crystal Graph Convolutional Neural Nets, in Julia. It makes use of the Flux ecosystem for model building and the JuliaGraphs ecosystem for graph representation and visualization, as well as adapting some features from GeometricFlux.
Flexible, modular, invertible featurization for Chemellia models including AtomicGraphnets.jl and WeaveModel.jl.
Herein you can find the code used for analysis and plotting for https://aip.scitation.org/doi/full/10.1063/5.0023611