Deep Signature: Characterization of Large-Scale Molecular Dynamics

• URL: http://arxiv.org/abs/2410.02847v1
• Date: Thu, 3 Oct 2024 16:37:48 GMT
• Title: Deep Signature: Characterization of Large-Scale Molecular Dynamics
• Authors: Tiexin Qin, Mengxu Zhu, Chunyang Li, Terry Lyons, Hong Yan, Haoliang Li,
• Abstract summary: Deep Signature is a novel computationally tractable framework that characterizes complex dynamics and interatomic interactions. Our approach incorporates soft spectral clustering that locally aggregates cooperative dynamics to reduce the size of the system, as well as signature transform to provide a global characterization of the non-smooth interactive dynamics.
• Score: 29.67824486345836
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding protein dynamics are essential for deciphering protein functional mechanisms and developing molecular therapies. However, the complex high-dimensional dynamics and interatomic interactions of biological processes pose significant challenge for existing computational techniques. In this paper, we approach this problem for the first time by introducing Deep Signature, a novel computationally tractable framework that characterizes complex dynamics and interatomic interactions based on their evolving trajectories. Specifically, our approach incorporates soft spectral clustering that locally aggregates cooperative dynamics to reduce the size of the system, as well as signature transform that collects iterated integrals to provide a global characterization of the non-smooth interactive dynamics. Theoretical analysis demonstrates that Deep Signature exhibits several desirable properties, including invariance to translation, near invariance to rotation, equivariance to permutation of atomic coordinates, and invariance under time reparameterization. Furthermore, experimental results on three benchmarks of biological processes verify that our approach can achieve superior performance compared to baseline methods.

Related papers

• Structure Language Models for Protein Conformation Generation [66.42864253026053]
  Traditional physics-based simulation methods often struggle with sampling equilibrium conformations. Deep generative models have shown promise in generating protein conformations as a more efficient alternative. We introduce Structure Language Modeling as a novel framework for efficient protein conformation generation.
  arXiv  Detail & Related papers  (2024-10-24T03:38:51Z)
• The Latent Road to Atoms: Backmapping Coarse-grained Protein Structures with Latent Diffusion [19.85659309869674]
  Latent Diffusion Backmapping (LDB) is a novel approach leveraging denoising diffusion within latent space to address these challenges. We evaluate LDB's state-of-the-art performance on three distinct protein datasets. Our results position LDB as a powerful and scalable approach for backmapping, effectively bridging the gap between CG simulations and atomic-level analyses in computational biology.
  arXiv  Detail & Related papers  (2024-10-17T06:38:07Z)
• Decomposing heterogeneous dynamical systems with graph neural networks [0.16492989697868887]
  We show that graph neural networks can be designed to jointly learn the interaction rules and the structure of the heterogeneous system. The learned latent structure and dynamics can be used to virtually decompose the complex system.
  arXiv  Detail & Related papers  (2024-07-27T04:03:12Z)
• Predicting Topological Entanglement Entropy in a Rydberg analog simulator [0.0]
  This work focuses on the dynamical preparation of a quantum-spin-liquid state on a Rydberg-atom simulator. The flexibility of our approach does not only allow one to match the physically correct form of the Rydberg-atom Hamiltonian but also the relevant lattice topology. We show that, while the simulated state exhibits (global) topological order and local properties resembling those of a resonating-valence-bond (RVB) state, it lacks the latter's characteristic topological entanglement entropy signature.
  arXiv  Detail & Related papers  (2024-06-28T12:27:42Z)
• Dynamic Kernel-Based Adaptive Spatial Aggregation for Learned Image Compression [63.56922682378755]
  We focus on extending spatial aggregation capability and propose a dynamic kernel-based transform coding. The proposed adaptive aggregation generates kernel offsets to capture valid information in the content-conditioned range to help transform. Experimental results demonstrate that our method achieves superior rate-distortion performance on three benchmarks compared to the state-of-the-art learning-based methods.
  arXiv  Detail & Related papers  (2023-08-17T01:34:51Z)
• Learning minimal representations of stochastic processes with variational autoencoders [52.99137594502433]
  We introduce an unsupervised machine learning approach to determine the minimal set of parameters required to describe a process. Our approach enables for the autonomous discovery of unknown parameters describing processes.
  arXiv  Detail & Related papers  (2023-07-21T14:25:06Z)
• Towards Predicting Equilibrium Distributions for Molecular Systems with Deep Learning [60.02391969049972]
  We introduce a novel deep learning framework, called Distributional Graphormer (DiG), in an attempt to predict the equilibrium distribution of molecular systems. DiG employs deep neural networks to transform a simple distribution towards the equilibrium distribution, conditioned on a descriptor of a molecular system.
  arXiv  Detail & Related papers  (2023-06-08T17:12:08Z)
• Investigation of Machine Learning-based Coarse-Grained Mapping Schemes for Organic Molecules [0.0]
  Coarse-graining (CG) allows to establish a link between different system resolutions. We explore the application of a Machine Learning strategy, based on Variational Autoencoders, for the development of suitable mapping schemes.
  arXiv  Detail & Related papers  (2022-09-26T18:30:51Z)
• A2I Transformer: Permutation-equivariant attention network for pairwise and many-body interactions with minimal featurization [0.1469945565246172]
  In this work, we suggest an end-to-end model which directly predicts per-atom energy from the coordinates of particles. We tested our model against several challenges in molecular simulation problems, including periodic boundary condition (PBC), $n$-body interaction, and binary composition.
  arXiv  Detail & Related papers  (2021-10-27T12:18:25Z)
• Harnessing Heterogeneity: Learning from Decomposed Feedback in Bayesian Modeling [68.69431580852535]
  We introduce a novel GP regression to incorporate the subgroup feedback. Our modified regression has provably lower variance -- and thus a more accurate posterior -- compared to previous approaches. We execute our algorithm on two disparate social problems.
  arXiv  Detail & Related papers  (2021-07-07T03:57:22Z)
• Learning Neural Generative Dynamics for Molecular Conformation Generation [89.03173504444415]
  We study how to generate molecule conformations (textiti.e., 3D structures) from a molecular graph. We propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.
  arXiv  Detail & Related papers  (2021-02-20T03:17:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.