Update: 2023.12.03-21.16

➕ Added Projects

Projects that were recently added to this best-of list.

• Open Databases Integration for Materials Design (OPTIMADE) (🥈17 · ⭐ 59 · ➕) - Specification of a common REST API for access to materials databases. CC-BY-4.0
• MODNet (🥇17 · ⭐ 53 · ➕) - MODNet: a framework for machine learning materials properties. MIT pre-trained small-data transfer-learning
• Metatensor (🥉15 · ⭐ 25 · ➕) - Storage format for equivariant atomistic machine learning. BSD-3
• mlcolvar (🥈16 · ⭐ 59 · ➕) - A unified framework for machine learning collective variables for enhanced sampling simulations. MIT enhanced-sampling
• JAX-DFT (🥇25 · ⭐ 32K · ➕) - Google Research. Apache-2
• DIG: Dive into Graphs (🥈21 · ⭐ 1.7K · ➕) - A library for graph deep learning research. GPL-3.0
• ATOM3D (🥇18 · ⭐ 280 · 💤) - ATOM3D: tasks on molecules in three dimensions. MIT biomolecules benchmarking
• ChemCrow (🥇17 · ⭐ 320 · 🐣) - Chemcrow. MIT
• ChemDataExtractor (🥈16 · ⭐ 270 · 💀) - Automatically extract chemical information from scientific documents. MIT literature-data
• ChemNLP project (🥈16 · ⭐ 110 · ➕) - ChemNLP project. MIT datasets
• GT4SD - Generative Toolkit for Scientific Discovery (🥈15 · ⭐ 280 · ➕) - Gradio apps of generative models in GT4SD. MIT generative pre-trained drug-discovery
• dlpack (🥉14 · ⭐ 800 · 💤) - common in-memory tensor structure. Apache-2 C++
• Geometric GNN Dojo (🥇12 · ⭐ 350 · ➕) - New to geometric GNNs: try our practical notebook, prepared for MPhil students at the University of Cambridge. MIT rep-learn
• QH9: A Quantum Hamiltonian Prediction Benchmark (🥈12 · ⭐ 280 · ➕) - Artificial Intelligence for Science (AIRS). CC-BY-NC-SA 4.0 ML-DFT
• QHNet (🥈12 · ⭐ 280 · ➕) - Artificial Intelligence for Science (AIRS). GPL-3.0 rep-learn
• Grad DFT (🥈12 · ⭐ 43 · ➕) - Grad-DFT is a JAX-based library enabling the differentiable design and experimentation of exchange-correlation.. Apache-2
• pretrained-gnns (🥇10 · ⭐ 870 · ➕) - Strategies for Pre-training Graph Neural Networks. MIT pre-trained
• DSECOP (🥈10 · ⭐ 31 · ➕) - This repository contains data science educational materials developed by DSECOP Fellows. CCO-1.0
• pair_nequip (🥉10 · ⭐ 29 · 💀) - LAMMPS pair style for NequIP. MIT ML-IAP rep-learn
• tinker-hp (🥉9 · ⭐ 69 · ➕) - Tinker-HP: High-Performance Massively Parallel Evolution of Tinker on CPUs & GPUs. Custom
• lie-nn (🥈9 · ⭐ 22 · ➕) - Tools for building equivariant polynomials on reductive Lie groups. MIT rep-learn
• TurboGAP (🥉9 · ⭐ 14 · ➕) - The TurboGAP code. Custom Fortran
• MoLFormers UI (🥉8 · ⭐ 140 · ➕) - Repository for MolFormer. Apache-2 transformer Language models pre-trained drug-discovery
• MoLFormer (🥉8 · ⭐ 140 · ➕) - Repository for MolFormer. Apache-2 transformer pre-trained drug-discovery
• pair_allegro (🥉8 · ⭐ 26 · ➕) - LAMMPS pair style for Allegro deep learning interatomic potentials with parallelization support. MIT ML-IAP rep-learn
• chemlift (🥉8 · ⭐ 10 · 🐣) - Language-interfaced fine-tuning for chemistry. MIT
• T-e3nn (🥉8 · ⭐ 6 · 💤) - Time-reversal Euclidean neural networks based on e3nn. MIT magnetism
• Awesome Neural Geometry (🥉7 · ⭐ 780 · ➕) - A curated collection of resources and research related to the geometry of representations in the brain, deep networks,.. Unlicensed educational rep-learn
• COATI (🥉6 · ⭐ 59 · 🐣) - COATI: multi-modal contrastive pre-training for representing and traversing chemical space. Apache-2 drug-discovery pre-trained rep-learn
• Mat2Spec (🥉6 · ⭐ 24 · 💀) - MIT spectroscopy
• NequIP-JAX (🥉5 · ⭐ 10 · ➕) - JAX implementation of the NequIP interatomic potential. Unlicensed
• MAPI_LLM (🥉5 · ⭐ 4 · ➕) - A LLM application developed during the LLM March MADNESS Hackathon https://doi.org/10.1039/D3DD00113J. MIT dataset
• soap_turbo (🥉5 · ⭐ 4 · 💤) - soap_turbo comprises a series of libraries to be used in combination with QUIP/GAP and TurboGAP. Custom Fortran
• MACE-tutorials (🥉5 · ⭐ 3 · 🐣) - Another set of tutorials for the MACE interatomic potential by one of the authors. MIT ML-IAP rep-learn MD
• Point Edge Transformer (PET) (🥉5 · ➕) - Point Edge Transformer. Unlicensed rep-learn transformer
• ChemDataWriter (🥉4 · ⭐ 8 · 🐣) - ChemDataWriter is a transformer-based library for automatically generating research books in the chemistry area. MIT literature-data
• torch_spex (🥉4 · ➕) - Spherical expansions in PyTorch. Unlicensed
• PeriodicPotentials (🥉4 · 💀) - A Periodic table app that displays potentials based on the selected elements. MIT community-resource viz JavaScript
• SciBot (🥉3 · ⭐ 14 · 🐣) - SciBot is a simple demo of building a domain-specific chatbot for science. Unlicensed
• CatBERTa (🥉3 · ⭐ 13 · ➕) - Large Language Model for Catalyst Property Prediction. Unlicensed transformer catalysis
• A3MD (🥉2 · ⭐ 5 · 💀) - MPNN-like + Analytic Density Model = Accurate electron densities. Unlicensed representation-learning single-paper
• LAMMPS-style pair potentials with GAP (🥉2 · ⭐ 3 · 💀) - A tutorial on how to create LAMMPS-style pair potentials and use them in combination with GAP potentials to run MD.. Unlicensed ML-IAP MD rep-eng
• MEGNetSparse (🥉2 · ⭐ 1 · 🐣) - A library imlementing a graph neural network with sparse representation from Code for Kazeev, N., Al-Maeeni, A.R.,.. MIT material-defect
• Allegro-JAX (🥉1 · ⭐ 11 · 🐣) - JAX implementation of the Allegro interatomic potential. Unlicensed
• APET (🥉1 · ⭐ 2 · ➕) - Atomic Positional Embedding-based Transformer. GPL-3.0 density-of-states transformer
• mlp (🥉1 · ⭐ 1 · 💀) - Proper orthogonal descriptors for efficient and accurate interatomic potentials... Unlicensed Julia