Modeling Atomic Conformational Ensembles of Proteins via Test-Time Supervision of Boltz-2 on Cryo-EM Density Maps

• URL: http://arxiv.org/abs/2605.09832v1
• Date: Mon, 11 May 2026 00:18:05 GMT
• Title: Modeling Atomic Conformational Ensembles of Proteins via Test-Time Supervision of Boltz-2 on Cryo-EM Density Maps
• Abstract summary: We propose a new principle for fine-tuning pre-trained static structure prediction models directly on raw cryo-EM maps.<n>We apply this technique to the problem of atomic model building by fine-tuning Boltz-2 to generate atomic conformations from an input ensemble of cryo-EM maps.
• Score: 32.750519557768506
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge of a protein's atomic conformational ensemble is critical to determining its function, yet state-of-the-art ensemble prediction models are limited by lack of high-quality conformational data from simulation or experiment. Recent advances in heterogeneous reconstruction for cryo-electron microscopy (cryo-EM) have enabled scientists to visualize ensembles of density maps for larger proteins and complexes not typically accessible through simulation, but building atomic models into these maps remains a challenge. Traditionally, ensemble prediction models are trained via a two-stage process: experimental density maps are converted into atomic structural ensembles through model building, after which these structures are used to train sequence-to-atomic ensemble predictors. In this work, we propose a new principle for fine-tuning pre-trained static structure prediction models such as Boltz-2 directly on raw cryo-EM maps, bypassing the two-stage process. We apply this technique to the problem of atomic model building by fine-tuning Boltz-2 to generate atomic conformations from an input ensemble of cryo-EM maps, achieving superior model building accuracy compared to prior work. Beyond overfitting to individual map ensembles, our method, CryoSampler, also shows preliminary evidence of in-domain generalization after fine-tuning, sampling diverse atomic conformations for an unseen sequences within the same protein family without requiring cryo-EM data. These capabilities indicate that CryoSampler holds the potential to train next-generation atomic ensemble prediction models directly on raw cryo-EM measurements.

Related papers

• CryoACE: An Atom-centric Framework for Accurate and Automated Model Building in Cryo-EM [32.08829653115702]
  CryoACE is an end-to-end framework that reconstructs precise atomic graphs for both homogeneous and heterogeneous structures.<n>We present CryoACE, an end-to-end framework that reconstructs precise atomic graphs for both homogeneous and heterogeneous structures.
  arXiv  Detail & Related papers  (2026-06-30T08:33:38Z)
• Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials [51.342983349686556]
  General-purpose 3D chemical modeling encompasses molecules and materials, requiring both generative and predictive capabilities.<n>We introduce Zatom-1, the first end-to-end, fully open-source foundation model that unifies generative and predictive learning of 3D molecules and materials.
  arXiv  Detail & Related papers  (2026-02-24T20:52:39Z)
• A Gaussian Parameterization for Direct Atomic Structure Identification in Electron Tomography [0.6198237241838559]
  We reformulate the tomographic inverse problem to solve directly for the locations and properties of individual atoms.<n>This representation imparts a strong physical prior on the learned structure, which we show yields improved robustness to real-world imaging artifacts.
  arXiv  Detail & Related papers  (2025-12-17T02:52:32Z)
• Completion of partial structures using Patterson maps with the CrysFormer machine learning model [7.123623187944631]
  We introduce an initial dataset of small protein fragments taken from Protein Data Bank entries.<n>We demonstrate that our method is effective at both improving the phases of the crystallographic structure factors and completing the regions missing from partial structure templates.
  arXiv  Detail & Related papers  (2025-11-13T16:04:21Z)
• InstructPLM-mu: 1-Hour Fine-Tuning of ESM2 Beats ESM3 in Protein Mutation Predictions [54.19843038028329]
  We propose a fine-tuning framework called InstructPLM-mu.<n>We show that fine-tuning ESM2 with structural inputs can reach performance comparable to ESM3.
  arXiv  Detail & Related papers  (2025-10-03T07:42:22Z)
• CryoSplat: Gaussian Splatting for Cryo-EM Homogeneous Reconstruction [48.45613121595709]
  cryogenic electron microscopy (cryo-EM) facilitates the determination of macromolecular structures at near-atomic resolution.<n>The core computational task in single-particle cryo-EM is to reconstruct the 3D electrostatic potential of a molecule from noisy 2D projections acquired at unknown orientations.<n>We propose cryoSplat, a GMM-based method that integrates Gaussian splatting with the physics of cryo-EM image formation.
  arXiv  Detail & Related papers  (2025-08-06T23:24:43Z)
• Multiscale guidance of AlphaFold3 with heterogeneous cryo-EM data [33.562685684224995]
  cryo-electron microscopy (cryo-EM) has emerged as a powerful tool for imaging near-native structural heterogeneity.<n>Here, we combine cryo-EM density maps with the rich sequence and biophysical priors learned by protein structure prediction models.<n>Our method, CryoBoltz, guides the sampling trajectory of a pretrained protein structure prediction model using both global and local structural constraints.
  arXiv  Detail & Related papers  (2025-06-04T22:16:27Z)
• Higher-order topological Peierls insulator in a two-dimensional atom-cavity system [58.720142291102135]
  We show how photon-mediated interactions give rise to a plaquette-ordered bond pattern in the atomic ground state. The pattern opens a non-trivial topological gap in 2D, resulting in a higher-order topological phase hosting corner states. Our work shows how atomic quantum simulators can be harnessed to investigate novel strongly-correlated topological phenomena.
  arXiv  Detail & Related papers  (2023-05-05T10:25:14Z)
• Dynamic Latent Separation for Deep Learning [67.62190501599176]
  A core problem in machine learning is to learn expressive latent variables for model prediction on complex data. Here, we develop an approach that improves expressiveness, provides partial interpretation, and is not restricted to specific applications.
  arXiv  Detail & Related papers  (2022-10-07T17:56:53Z)
• State-specific protein-ligand complex structure prediction with a multi-scale deep generative model [68.28309982199902]
  We present NeuralPLexer, a computational approach that can directly predict protein-ligand complex structures. Our study suggests that a data-driven approach can capture the structural cooperativity between proteins and small molecules, showing promise in accelerating the design of enzymes, drug molecules, and beyond.
  arXiv  Detail & Related papers  (2022-09-30T01:46:38Z)
• Heterogeneous reconstruction of deformable atomic models in Cryo-EM [30.864688165021054]
  We describe a heterogeneous reconstruction method based on an atomistic representation whose deformation is reduced to a handful of collective motions. We show for each distribution that our approach is able to recapitulate the intermediate atomic models with atomic-level accuracy.
  arXiv  Detail & Related papers  (2022-09-29T22:35:35Z)
• Optimal radial basis for density-based atomic representations [58.720142291102135]
  We discuss how to build an adaptive, optimal numerical basis that is chosen to represent most efficiently the structural diversity of the dataset at hand. For each training dataset, this optimal basis is unique, and can be computed at no additional cost with respect to the primitive basis. We demonstrate that this construction yields representations that are accurate and computationally efficient.
  arXiv  Detail & Related papers  (2021-05-18T17:57:08Z)
• Sequence-guided protein structure determination using graph convolutional and recurrent networks [0.0]
  Single particle, cryogenic electron microscopy (cryo-EM) experiments now routinely produce high-resolution data for large proteins. Existing protocols for this type of task often rely on significant human intervention and can take hours to many days to produce an output. Here, we present a fully automated, template-free model building approach that is based entirely on neural networks.
  arXiv  Detail & Related papers  (2020-07-14T06:24:07Z)

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.