paper-with-me

홈 › Papers

Molecular relaxation by reverse diffusion with time step prediction

2024-04-16 · Khaled Kahouli, Stefaan Simon Pierre Hessmann, Klaus-Robert Müller, Shinichi Nakajima, Stefan Gugler, Niklas Wolf Andreas Gebauer

Molecular relaxation, finding the equilibrium state of a non-equilibrium structure, is an essential component of computational chemistry to understand reactivity. Classical force field (FF) methods often rely on insufficient local energy minimization, while neural network FF models require large labeled datasets encompassing both equilibrium and non-equilibrium structures. As a remedy, we propose MoreRed, molecular relaxation by reverse diffusion, a conceptually novel and purely statistical approach where non-equilibrium structures are treated as noisy instances of their corresponding equilibrium states. To enable the denoising of arbitrarily noisy inputs via a generative diffusion model, we further introduce a novel diffusion time step predictor. Notably, MoreRed learns a simpler pseudo potential energy surface (PES) instead of the complex physical PES. It is trained on a significantly smaller, and thus computationally cheaper, dataset consisting of solely unlabeled equilibrium structures, avoiding the computation of non-equilibrium structures altogether. We compare MoreRed to classical FFs, equivariant neural network FFs trained on a large dataset of equilibrium and non-equilibrium data, as well as a semi-empirical tight-binding model. To assess this quantitatively, we evaluate the root-mean-square deviation between the found equilibrium structures and the reference equilibrium structures as well as their energies.

📄 PDF Abstract BibTeX arXiv:2404.10935

Code (1)

khaledkah/morered 공식 구현 pytorch

Tasks

Computational chemistryDenoisingPrediction

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Breaking the Bottlenecks: Scalable Diffusion Models for 3D Molecular Generation

2026-01-13 · Adrita Das, Peiran Jiang, Dantong Zhu, Barnabas Poczos 외 arxiv

Diffusion models have emerged as a powerful class of generative models for molecular design, capable of capturing complex structural distributions and achieving high fidelity in 3D molecule generation. However, their wid…

Conditional Synthesis of 3D Molecules with Time Correction Sampler

2024-11-01 · Hojung Jung, Youngrok Park, Laura Schmid, Jaehyeong Jo 외

Diffusion models have demonstrated remarkable success in various domains, including molecular generation. However, conditional molecular generation remains a fundamental challenge due to an intrinsic trade-off between ta…

Drug Discovery

Diffusion Models are Molecular Dynamics Simulators

2025-11-21 · Justin Diamond, Markus Lill arxiv

We prove that a denoising diffusion sampler equipped with a sequential bias across the batch dimension is exactly an Euler-Maruyama integrator for overdamped Langevin dynamics. Each reverse denoising step, with its assoc…

FlashMol: High-Quality Molecule Generation in as Few as Four Steps

2026-05-07 · Xinyuan Wei, Zian Li, Shaoheng Yan, Cai Zhou 외 arxiv

Generating chemically valid 3D molecular conformations is critical for computational drug discovery. Classical diffusion-based models like GeoLDM perform well but require hundreds of steps, making large-scale in silico s…

Drug Discovery

Generative Pseudo-Force Fields for Molecular Generation

2026-05-18 · Stefaan Simon Pierre Hessmann, Khaled Kahouli, Stefan Gugler, Michael Plainer 외 arxiv

Generating stable molecular conformations typically forces a tradeoff between the physical realism of energy-based relaxation and the sampling efficiency of data-driven generative models. While machine learning force fie…