REVIEW 18 cited by
GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Predicting molecular conformations from molecular graphs is a fundamental problem in cheminformatics and drug discovery. Recently, significant progress has been achieved with machine learning approaches, especially with deep generative models. Inspired by the diffusion process in classical non-equilibrium thermodynamics where heated particles will diffuse from original states to a noise distribution, in this paper, we propose a novel generative model named GeoDiff for molecular conformation prediction. GeoDiff treats each atom as a particle and learns to directly reverse the diffusion process (i.e., transforming from a noise distribution to stable conformations) as a Markov chain. Modeling such a generation process is however very challenging as the likelihood of conformations should be roto-translational invariant. We theoretically show that Markov chains evolving with equivariant Markov kernels can induce an invariant distribution by design, and further propose building blocks for the Markov kernels to preserve the desirable equivariance property. The whole framework can be efficiently trained in an end-to-end fashion by optimizing a weighted variational lower bound to the (conditional) likelihood. Experiments on multiple benchmarks show that GeoDiff is superior or comparable to existing state-of-the-art approaches, especially on large molecules.
Forward citations
Cited by 18 Pith papers
-
D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples
Mask-guided self-attention fusion creates well-aligned target images that stay visually close to poorly-aligned base images, with full denoising trajectories, and DPO on these pairs improves alignment.
-
Generalized Fine-Tuning of Diffusion Models via Stochastic Control and FBSDEs
Diffusion fine-tuning is generalized to arbitrary running costs and solved through HJB/FBSDE, but the main theorems are not proven as stated.
-
FLOWR.root: A flow matching based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity prediction
A flow-matching model jointly generates pocket-aware 3D ligands and predicts their binding affinities, reporting state-of-the-art generation and competitive affinity accuracy with a speed advantage.
-
Feynman-Kac-Flow: Inference Steering of Conditional Flow Matching to an Energy-Tilted Posterior
Feynman-Kac particle steering, previously diffusion-only, is derived for conditional flow matching and used to generate chirality-correct chemical transition states.
-
Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
SO(3)-Averaged Flow matching with reflow and distillation enables high-quality one-step molecular conformer generation, reporting new SOTA on GEOM-QM9 and strong one-step results on GEOM-Drugs.
-
Geometric Generative Modeling with Noise-Conditioned Graph Networks
Adapting graph neural network connectivity and resolution to the noise level improves flow-based generation of 3D point clouds, spatial transcriptomics, and images.
-
MODA: A Unified 3D Diffusion Framework for Multi-Task Target-Aware Molecular Generation
A single masked-diffusion model trained jointly on four molecular-editing tasks outperforms or matches task-specific diffusion baselines across docking, chemical property, and geometry metrics.
-
A Benchmark for Quantum Chemistry Relaxations via Machine Learning Interatomic Potentials
PubChemQCR is a large public dataset of DFT-based molecular relaxation trajectories with energy and force labels, benchmarked with nine machine learning interatomic potentials.
-
Tokenizing Electron Cloud in Protein-Ligand Interaction Learning
ECBind tokenizes electron cloud densities via quantized embeddings and improves protein-ligand binding affinity prediction, especially per-structure correlations on MISATO.
-
A Minimalist Method for Fine-tuning Text-to-Image Diffusion Models
A one-step RL method learns a prompt-conditioned initial noise distribution for a frozen diffusion model, improving scores on the training reward models, with the largest gains at low inference steps.
-
Valid Property-Enhanced Contrastive Learning for Targeted Optimization & Resampling for Novel Drug Design
VECTOR+ combines contrastive learning and Gaussian mixture sampling to generate novel, synthetically plausible inhibitors from low-data datasets, with improved docking scores over known compounds.
-
IBEX: Information-Bottleneck-EXplored Coarse-to-Fine Molecular Generation under Limited Data
IBEX trains a 3D diffusion model on scaffold-hopping tasks and refines generated poses with a six-degree-of-freedom physics optimization, raising zero-shot docking success from 53% to 64% on CBGBench.
-
PQCAD-DM: Progressive Quantization and Calibration-Assisted Distillation for Extremely Efficient Diffusion Model
PQCAD-DM combines progressive two-stage quantization with calibration-assisted distillation to halve the sampling steps of a quantized diffusion model while keeping FID scores close to baseline.
-
Solving Inverse Problems via Diffusion-Based Priors: An Approximation-Free Ensemble Sampling Approach
A weighted-particle sampler evolves the posterior through the diffusion model's reverse dynamics, with theoretical error bounds and improved image reconstructions.
-
Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation
LLMol fine-tunes an LLM on simplified SELFIES and uses GRPO with RDKit-derived rewards for targeted molecular generation, but its own benchmark tables contradict the claimed state-of-the-art performance.
-
Stochastic and Non-local Closure Modeling for Nonlinear Dynamical Systems via Latent Score-based Generative Models
Joint training of autoencoders with diffusion models in latent space gives stochastic turbulence closure accuracy close to physical-space diffusion models at roughly 5-7x lower cost.
-
Beyond Equilibrium: Non-Equilibrium Foundations Should Underpin Generative Processes in Complex Dynamical Systems
A position paper arguing that non-equilibrium-physics-inspired generative models (like diffusion models) are, and should be, the foundation for modeling time-varying complex systems, supported by one 2D simulation.
-
Graph Neural Networks in Modern AI-aided Drug Discovery
A comprehensive model-centric review of graph neural network methods and applications in AI-aided drug discovery, from molecular representation to synthesis planning.
Discussion (0). Sign in to comment.