Variational autoencoder molecular dynamics. Using the atomic coordinates of Ni polycrystalline, we ...

Variational autoencoder molecular dynamics. Using the atomic coordinates of Ni polycrystalline, we show that the combination of the VAE and DDPM improves reconstruction accuracy compared with the VAE alone Feb 21, 2024 · We introduce a computational approach for the design of target-specific peptides. However, extensive sampling in the protein conformational space requires large computational resources and takes a prohibitive amount of time. In this study, we demonstrated that variational a …. ICVAE established a linear mapping between latent variables and molecular properties. We convert high-dimensional protein structural data into a continuous, low-dimensional Nov 12, 2025 · Recent 3D molecular representations include spatial and conformational features that are important for modelling interactions; nevertheless, they are computationally expensive and only work with tiny molecules [23]. 3 days ago · The Attention-based Contrastive Variational Autoencoder (ACVAE) extends a standard -VAE framework with dual encoders and an integrated attention mechanism to learn disentangled, hierarchical representations of STC matrices. Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation No-Regret Online Prediction with Strategic Experts Uncovering motifs of concurrent signaling across multiple neuronal populations Here, we present autoCell, a graph-embedded Gaussian mixture variational autoencoder network algorithm for scRNA-seq dropout imputation and feature extraction. Hierarchical Variational Autoencoder (HierVAE) combines these advantages through multi-stage latent modelling [24]. While variational autoencoders (VAEs) excel at latent space modeling and discrete flow matching (DFM) enables efficient continuous-time sampling, existing approaches still face critical limitations. Our network learns an SO(3)-equivariant latent space. ABSTRACT: Molecular dynamics (MD) simulations have been extensively used to study protein dynamics and sub-sequently functions. A method combining a variational autoencoder (VAE) and a denoising diffusion probabilistic model (DDPM) is proposed to e ciently ffi compress and reconstruct complex, large-scale atomic coordinates, such as those in polycrystals. Subsequently, molecular dynamics simulations are employed to narrow down the selection of peptides for experimental assays. 7, 8 With the ever-increasing computational power, the accessible simulation timescale for protein systems Mar 28, 2024 · Mapping the ensemble of protein conformations that contribute to function and can be targeted by small molecule drugs remains an outstanding challenge. 9) 2025-04-23 0 Feb 21, 2024 · Our method integrates a Gated Recurrent Unit-based Variational Autoencoder with Rosetta FlexPepDock for peptide sequence generation and binding affinity assessment. Molecular dynamics (MD) simulations are computational tools to provide protein conformational changes by integrating the dynamical equations of motions starting from an initial structure and velocity of each particle in molecular models. Here, we explore the use of variational autoencoders for reducing the challenge of dimensionality in the protein structure ensemble generation problem. The Hsp90 active site is in its N-terminal domain (NTD). Variational Dynamical Encoder (VDE) Often the analysis of time-dependent chemical and biophysical systems produces high-dimensional time-series data for which it can be difficult to interpret which features are most salient in defining the observed dynamics. However, MD simulations are often insu cient to explore adequate conformational space for protein functions within reachable timescales. Our autoCell provides a deep-learning toolbox for end-to-end analysis of large-scale single-cell/nucleus RNA-seq data, including visualization, clustering, imputation, and disease 3DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Design Deep Variational Graph Convolutional Recurrent Network for Multivariate Time Series Anomaly Detection Differentially Private Coordinate Descent for Composite Empirical Risk Minimization Calibrated Learning to Defer with One-vs-All Classifiers These data holograms are inputs to our SO(3)-equivariant (variational) autoencoder in spherical Fourier space, with a fully equivariant encoder-decoder architecture trained to reconstruct the Fourier coefficients of the input; we term this approach holographic-(V)AE [or H-(V)AE]. The generative capability of the variational autoencoder, coupled with a postprocessing pipeline based on multidimensional scaling and short molecular dynamics, enables the recovery of physically meaningful configurations. Accordingly, many enhanced sampling methods, including variational autoencoder (VAE) based methods, have been developed to address Jul 11, 2023 · The heat shock protein 90 (Hsp90) is a molecular chaperone that controls the folding and activation of client proteins using the free energy of ATP hydrolysis. Abstract Molecular graph generation is a key task in drug discovery, aiming to efficiently identify novel compounds with desired properties. Feb 10, 2026 · 0 求助 应助 收藏 ICVAE：用于De Novo分子设计的可解释条件变分自编码器 ICVAE: Interpretable Conditional Variational Autoencoder for De Novo Molecular Design INTERNATIONAL JOURNAL OF MOLECULAR SCIENCES (IF:4. VAE decoders struggle with permutation invariance and Nov 12, 2021 · Molecular dynamics (MD) simulations have been actively used in the study of protein structure and function. Dec 10, 2025 · Here, we explore this approach by training a Variational Autoencoder (VAE) on distance matrices computed from coarse-grained molecular dynamics simulations of a polyethylene globule at different temperatures. Using dihedral The generative capability of the variational autoencoder, coupled with a postprocessing pipeline based on multidimensional scaling and short molecular dynamics, enables the recovery of physically meaningful configurations. Our method integrates a Gated Recurrent Unit-based Variational Autoencoder with Rosetta FlexPepDo Apr 23, 2025 · To address this issue, we propose the Interpretable Conditional Variational Autoencoder (ICVAE), which introduces a modified loss function that correlates the latent value with molecular properties. Our goal is to characterize the dynamics of NTD using an autoencoder-learned collective variable (CV) in conjunction with adaptive biasing force Langevin dynamics. ikg hko xvv vlg ghu kno zmt gvc zol jwx wbz tby jat czu mtz