mlcolvar (J. Chem. Phys. 2023)
github.com/luigibonati/mlcolvarUnified framework for machine-learning collective variables in enhanced-sampling molecular dynamics, implementing autoencoder, variational, SINDy, and graph-neural-network CVs with a PyTorch training API for learning slow modes and free-energy barriers from simulation data; deploys learned CVs to PLUMED and OpenMM for umbrella sampling, metadynamics, and umbrella integration of rare events such as conformational transitions, ligand binding, and chemical reactions (Bonati, Trizio, Rizzi & Parrinello, 147+ stars, MIT License, actively maintained)
Sourced from
- Awesome AI for Science — github.com/luigibonati/mlcolvar
Related resources
Universal generative physics simulation platform integrating rigid body, FEM, MPM, particle (PBD/SPH), and cloth solvers with explicit multi-solver coupling in a single differentiable scene, GPU-graph-accelerated massively parallel simulation, a photorealistic renderer (Nyx), and a cross-platform compiler (CUDA/ROCm/Metal/Vulkan/CPU); scales from laptops to datacenter GPUs for physics simulation, synthetic data generation, and physical-AI/robotics research (30K+ stars, Apache 2.0, actively maintained, now officially supported by Genesis AI)
Graph neural network library for PyTorch enabling molecular modeling, materials discovery, protein interaction networks, and scientific knowledge graph learning (23.7k+ stars)
Deep Graph Library for scalable deep learning on graphs, powering molecular modeling, materials discovery, protein interaction networks, and scientific knowledge graph learning across PyTorch, TensorFlow, and MXNet backends (14K+ stars)
Open-source SDK for working with quantum computers at the level of extended quantum circuits, operators, and primitives, enabling quantum algorithm development for quantum chemistry, materials science, and optimization research (IBM, 7.4K+ stars, Apache 2.0)
Python framework for writing high-performance GPU simulation and graphics kernels with first-class automatic differentiation, enabling differentiable physics, molecular dynamics, soft-body and cloth simulation, robotics, and CFD adjoints compiled to CUDA; serves as the underlying engine for differentiable simulation projects like Newton and integrates with PyTorch, JAX, and OpenUSD (NVIDIA, 7.1K+ stars, Apache 2.0)