Learning Matter @ MIT

Atomistic-Adversarial-Attacks

Code for performing adversarial attacks on atomistic systems using NN potentials

Coarse-Graining-Auto-encoders

GenZProt

geom

GEOM: Energy-annotated molecular conformations

GLAMOUR

Graph Learning over Macromolecule Representations

NeuralForceField

Neural Network Force Field based on PyTorch

PatentChem

Downloads USPTO patents and finds molecules related to keyword queries

peptimizer

Peptide optimization with Machine Learning

surface-sampling

MCMC-based algorithm for sampling surface reconstructions

uvvisml

Predict optical properties of molecules with machine learning.

learningmatter-mit/NeuralForceField

Neural Network Force Field based on PyTorch

learningmatter-mit/peptimizer

Peptide optimization with Machine Learning

learningmatter-mit/PatentChem

Downloads USPTO patents and finds molecules related to keyword queries

learningmatter-mit/Atomistic-Adversarial-Attacks

Code for performing adversarial attacks on atomistic systems using NN potentials

learningmatter-mit/GenZProt

learningmatter-mit/uvvisml

Predict optical properties of molecules with machine learning.

learningmatter-mit/GLAMOUR

Graph Learning over Macromolecule Representations

learningmatter-mit/surface-sampling

MCMC-based algorithm for sampling surface reconstructions

learningmatter-mit/Chem-prop-pred

Repository for predicting conductivities through Arrhenius parameters for polymer electrolytes.

learningmatter-mit/alchemical-mlip

Alchemical machine learning interatomic potentials

learningmatter-mit/atom_by_atom

Atom-by-atom design of metal oxide catalysts for the oxygen evolution reaction with Machine Learning

learningmatter-mit/Segal

learningmatter-mit/VOID

Library to dock molecules in crystal structures, including nanoporous materials

learningmatter-mit/ChemArr

Chemprop model incorporating the Arrhenius equation at the output to add physics to predictions

learningmatter-mit/PerovskiteOrderingGCNNs

Repo for our paper "Learning Ordering in Crystalline Materials with Symmetry-Aware Graph Neural Networks"

learningmatter-mit/azo_barriers

Repository for computing the thermal barriers of azobenzene derivatives

learningmatter-mit/Perovskite-Ordering-Descriptors

Repo for our paper "Data-Driven Physics-Informed Descriptors of Cation Ordering in Multicomponent Perovskite Oxides"

learningmatter-mit/AutoBADDIE

Autonomously train class 1 and class 2 interatomic potentials for MD using gas-phase DFT training data

learningmatter-mit/geodesic-interpolation-cv

Geodesic interpolation for collective variables

learningmatter-mit/PerovskiteOrderingGCNNs_cgcnn

Supplementary repo for our paper "Learning Orderings in Crystalline Materials with Symmetry-Aware Graph Neural Networks"

learningmatter-mit/SingleAtom-LocalEnv

Active learning accelerated exploration of the single atom local environments in multimetallic systems for oxygen electrocatalysis

learningmatter-mit/UQ_singleNN

Code for performing adversarial attacks on atomistic systems using NN potentials

learningmatter-mit/Tutorial_ActivationFreeEnergy

Tutorial accompanying: Dietschreit, J. C. B. et al., J. Chem. Phys, 2022, "From Free-Energy Profiles to Activation Free Energies"

learningmatter-mit/per-site_cgcnn

Crystal graph convolutional neural networks for predicting material properties.

learningmatter-mit/per-site_painn

Fork of PaiNN for PerovskiteOrderingGCNNs

learningmatter-mit/PerovskiteOrderingGCNNs_alignn

Atomistic Line Graph Neural Network

learningmatter-mit/PerovskiteOrderingGCNNs_painn

Supplementary repo for our paper "Learning Orderings in Crystalline Materials with Symmetry-Aware Graph Neural Networks"

learningmatter-mit/zeobind

learningmatter-mit/ReactionGraphNeuralNetwork

Graph Neural Network to predict the reaction related properties for reinforcement learning

learningmatter-mit/RLVacDiffSim

Reinforcement learning driven simulation of vacancy diffusion