Auto3D: Automatic Generation of the Low-energy 3D Structures with ANI Neural Network Potentials (standalone).
ConfGF: ConfGF, as introduced in ICML 2021, learns gradient fields for molecular conformation generation, featuring an official implementation for their methodology.
Conformer-RL: An open-source deep reinforcement learning library for conformer generation.
COSMIC:
diffusion-conformer: Physics-informed generative model for drug-like molecule conformers
DMCG: DMCG, featured in TMLR2022, is focused on direct molecular conformation generation, supporting both small-scale and large-scale GEOM datasets.
GeoDiff: GeoDiff introduces a geometric diffusion model aimed at generating molecular conformations, as detailed in their ICLR 2022 presentation.
GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles (standalone).
GINGER:
Gypsum-DL: Gypsum-DL is a software that transforms 1D and 2D small-molecule representations into 3D models, considering various isomeric and conformational states.
TensorVAE:
Uni-Mol: Uni-Mol offers a universal 3D molecular pretraining framework, enhancing representation capacity and scope in drug design with superior performance in multiple prediction tasks.