IntelLabs / matsciml
Open MatSci ML Toolkit is a framework for prototyping and scaling out deep learning models for materials discovery supporting widely used materials science datasets, and built on top of PyTorch Lightning, the Deep Graph Library, and PyTorch Geometric.
☆170Updated last week
Alternatives and similar repositories for matsciml:
Users that are interested in matsciml are comparing it to the libraries listed below
- Workflow for creating and analyzing the Open Catalyst Dataset☆106Updated last month
- An evaluation framework for machine learning models simulating high-throughput materials discovery.☆132Updated this week
- Neural Network Force Field based on PyTorch☆265Updated 3 weeks ago
- Matbench: Benchmarks for materials science property prediction☆143Updated 6 months ago
- MatDeepLearn, package for graph neural networks in materials chemistry☆183Updated last year
- GemNet model in PyTorch, as proposed in "GemNet: Universal Directional Graph Neural Networks for Molecules" (NeurIPS 2021)☆194Updated last year
- Corresponding dataset and tools for the AdsorbML manuscript.☆40Updated last month
- This repository contains a collection of resources and papers on GNN Models on Crystal Solid State Materials☆88Updated 2 weeks ago
- [TMLR 2023] Training and simulating MD with ML force fields☆111Updated 4 months ago
- Higher-order equivariant neural networks for charge density prediction in materials☆47Updated 2 weeks ago
- Build neural networks for machine learning force fields with JAX☆110Updated last month
- train and use graph-based ML models of potential energy surfaces☆78Updated 3 weeks ago
- FTCP code☆33Updated last year
- ASAP is a package that can quickly analyze and visualize datasets of crystal or molecular structures.☆145Updated 8 months ago
- Reference implementation of "SpookyNet: Learning force fields with electronic degrees of freedom and nonlocal effects"☆70Updated 2 years ago
- A public repository collecting links to state of the art QA and evaluation sets for various ML and LLM applications☆89Updated 7 months ago
- Training neural network potentials☆380Updated last week
- [TMLR 2024] Generalizing Denoising to Non-Equilibrium Structures Improves Equivariant Force Fields☆31Updated last month
- SevenNet - a graph neural network interatomic potential package supporting efficient multi-GPU parallel molecular dynamics simulations.☆155Updated this week
- Foundation Model for Materials - FM4M☆163Updated last month
- Pytorch differentiable molecular dynamics☆173Updated 2 years ago
- An SE(3)-invariant autoencoder for generating the periodic structure of materials [ICLR 2022]☆275Updated 7 months ago
- Unsupervised learning of atomic scale dynamics from molecular dynamics.☆80Updated 3 years ago
- SLICES: An Invertible, Invariant, and String-based Crystal Representation [2023, Nature Communications] MatterGPT, SLICES-PLUS☆97Updated this week
- A repository for implementing graph network models based on atomic structures.☆75Updated 7 months ago
- The QMOF Database: A database of quantum-mechanical properties for metal-organic frameworks.☆138Updated 3 weeks ago
- Graph deep learning library for materials☆315Updated this week
- Official code for Periodic Graph Transformers for Crystal Material Property Prediction (NeurIPS 2022)☆89Updated last year
- LAMMPS pair style for Allegro deep learning interatomic potentials with parallelization support☆41Updated 4 months ago
- MACE-MP models☆78Updated last month