materials & chemistry: 24 curated resources
materials & chemistry
24 resources · page 1 of 1
BEEP
by Toyota Research Institute (Accelerated Materials Design & Discovery)
TRI BEEP GitHub repo: tools for battery evaluation and early prediction of cycle life from cycling data.
ChemCrow
ChemCrow GitHub repo: LLM agent package using chemistry tools for reasoning-intensive tasks.
CHGNet
by Ceder Group
CHGNet GitHub repo (Ceder Group): pretrained universal neural network potential for charge-informed atomistic modelling.
DeePMD-kit
by DeepModeling
DeePMD-kit GitHub repo: deep learning package for many-body potential energy and molecular dynamics.
DimeNet
by Johannes Gasteiger, né Klicpera
DimeNet GitHub repo: DimeNet and DimeNet++ directional message-passing models for molecules.
FAIR Chemistry
Meta FAIR Chemistry GitHub repo: machine learning methods and models for chemistry and materials.
FAIR Chemistry Documentation
FAIR Chemistry documentation: open catalysis, materials and molecule datasets such as Open Catalyst, OMat and OMol, plus models.
GemNet
by Data Analytics and Machine Learning Group
TUM-DAML GemNet GitHub repo: TensorFlow implementation of the GemNet directional message-passing model for molecules.
Lila Sciences
Lila Sciences: company building AI systems and automated labs for scientific discovery.
M3GNet
M3GNet GitHub repo: materials graph network with three-body interactions as an interatomic potential.
MACE
by ACEsuit
MACE GitHub repo: equivariant machine learning interatomic potentials for atomistic simulation.
materials
DeepMind materials_discovery GitHub repo: GNoME dataset of predicted stable crystals, models and Colabs.
MatterGen
by Microsoft
Microsoft MatterGen GitHub repo: generative model for designing inorganic materials.
NequIP
by MIR@Harvard
NequIP GitHub repo: E(3)-equivariant neural network interatomic potentials.
Periodic Labs
Periodic Labs: company using AI and autonomous labs for materials science discovery.
TorchANI
by AIQM
TorchANI GitHub repo: library for training and using ANI neural network potentials for molecules.
Uni-Mol
by DeepModeling
Uni-Mol GitHub repo (DP Technology): 3D molecular pretraining models for property prediction and docking.
Autonomous chemical research with large language models (Coscientist)
by Daniil A. Boiko et al. (Carnegie Mellon University)
Nature paper (2023) on Coscientist, autonomous chemical research with large language models.
Scaling deep learning for materials discovery (GNoME)
by Amil Merchant et al. (Google)
Nature paper (2023) on GNoME, scaling deep learning to discover new stable materials.
MatGL
by Materials Virtual Lab (UC San Diego)
MatGL: graph deep learning library for materials property prediction and interatomic potentials.
matminer
by Hacking Materials group (Lawrence Berkeley National Laboratory)
matminer documentation: Python library for mining materials data and generating features for ML models.
PaiNN
by Kristof T. Schütt et al. (Technische Universität Berlin)
arXiv HTML version of the PaiNN paper (2021) on equivariant message passing for molecular property prediction.
SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
by Kristof T. Schütt et al. (Technische Universität Berlin)
arXiv paper (2017) introducing SchNet, a continuous-filter convolutional network for modelling quantum interactions in molecules.
SchNet: a deep learning architecture for molecules and materials
by Kristof T. Schütt et al. (Technische Universität Berlin)
arXiv paper (2017) "SchNet - a deep learning architecture for molecules and materials", using continuous-filter convolutions to predict molecular energies and forces.