CryoFM: A Flow-based Foundation Model for Cryo-EM Densities

• URL: http://arxiv.org/abs/2410.08631v1
• Date: Fri, 11 Oct 2024 08:53:58 GMT
• Title: CryoFM: A Flow-based Foundation Model for Cryo-EM Densities
• Authors: Yi Zhou, Yilai Li, Jing Yuan, Quanquan Gu,
• Abstract summary: We present CryoFM, a foundation model designed as a generative model, learning the distribution of high-quality density maps. Built on flow matching, CryoFM is trained to accurately capture the prior distribution of biomolecular density maps.
• Score: 50.291974465864364
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Cryo-electron microscopy (cryo-EM) is a powerful technique in structural biology and drug discovery, enabling the study of biomolecules at high resolution. Significant advancements by structural biologists using cryo-EM have led to the production of over 38,626 protein density maps at various resolutions1. However, cryo-EM data processing algorithms have yet to fully benefit from our knowledge of biomolecular density maps, with only a few recent models being data-driven but limited to specific tasks. In this study, we present CryoFM, a foundation model designed as a generative model, learning the distribution of high-quality density maps and generalizing effectively to downstream tasks. Built on flow matching, CryoFM is trained to accurately capture the prior distribution of biomolecular density maps. Furthermore, we introduce a flow posterior sampling method that leverages CRYOFM as a flexible prior for several downstream tasks in cryo-EM and cryo-electron tomography (cryo-ET) without the need for fine-tuning, achieving state-of-the-art performance on most tasks and demonstrating its potential as a foundational model for broader applications in these fields.

Related papers

• Data-Efficient Molecular Generation with Hierarchical Textual Inversion [48.816943690420224]
  We introduce Hierarchical textual Inversion for Molecular generation (HI-Mol), a novel data-efficient molecular generation method. HI-Mol is inspired by the importance of hierarchical information, e.g., both coarse- and fine-grained features, in understanding the molecule distribution. Compared to the conventional textual inversion method in the image domain using a single-level token embedding, our multi-level token embeddings allow the model to effectively learn the underlying low-shot molecule distribution.
  arXiv  Detail & Related papers  (2024-05-05T08:35:23Z)
• CryoMAE: Few-Shot Cryo-EM Particle Picking with Masked Autoencoders [8.896148074086762]
  We introduce cryoMAE, a novel approach based on few-shot learning to enable efficient selection of single particles in cryo-EM images. Contrary to conventional NN-based techniques, cryoMAE requires only a minimal set of positive particle images for training yet demonstrates high performance in particle detection. Experiments on large-scale cryo-EM datasets show that cryoMAE outperforms existing state-of-the-art (SOTA) methods, improving 3D reconstruction resolution by up to 22.4%.
  arXiv  Detail & Related papers  (2024-04-15T23:23:31Z)
• Tertiary Lymphoid Structures Generation through Graph-based Diffusion [54.37503714313661]
  In this work, we leverage state-of-the-art graph-based diffusion models to generate biologically meaningful cell-graphs. We show that the adopted graph diffusion model is able to accurately learn the distribution of cells in terms of their tertiary lymphoid structures (TLS) content.
  arXiv  Detail & Related papers  (2023-10-10T14:37:17Z)
• Learning Energy-Based Prior Model with Diffusion-Amortized MCMC [89.95629196907082]
  Common practice of learning latent space EBMs with non-convergent short-run MCMC for prior and posterior sampling is hindering the model from further progress. We introduce a simple but effective diffusion-based amortization method for long-run MCMC sampling and develop a novel learning algorithm for the latent space EBM based on it.
  arXiv  Detail & Related papers  (2023-10-05T00:23:34Z)
• Latent Space Diffusion Models of Cryo-EM Structures [6.968705314671148]
  We train a diffusion model as an expressive, learnable prior in the cryoDRGN framework. By learning an accurate model of the data distribution, our method unlocks tools in generative modeling, sampling, and distribution analysis.
  arXiv  Detail & Related papers  (2022-11-25T15:17:10Z)
• Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations [51.68332623405432]
  Molecular dynamics (MD) simulations allow atomistic insights into chemical and biological processes. Recently, machine learned force fields (MLFFs) emerged as an alternative means to execute MD simulations. This work proposes a general approach to constructing accurate MLFFs for large-scale molecular simulations.
  arXiv  Detail & Related papers  (2022-05-17T13:08:28Z)
• CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection [13.499994658675638]
  We show that reinforcement learning offers an effective way to plan cryo-EM data collection, successfully navigating heterogenous cryo-EM grids. The approach we developed, cryoRL, demonstrates better performance than average users for data collection under similar settings.
  arXiv  Detail & Related papers  (2022-04-15T17:00:06Z)
• SHREC 2021: Classification in cryo-electron tomograms [13.443446070180562]
  cryo-electron tomography (cryo-ET) is an imaging technique that allows three-dimensional visualization of macro-molecular assemblies. Cryo-ET comes with a number of challenges, mainly low signal-to-noise and inability to obtain images from all angles. We generate a novel simulated dataset to benchmark different methods of localization and classification of biological macromolecules in tomograms.
  arXiv  Detail & Related papers  (2022-03-18T16:08:22Z)
• Deep Generative Modeling for Volume Reconstruction in Cryo-Electron Microscopy [4.014524824655106]
  New breakthroughs in high resolution imaging of biomolecules in solution with cryo-electron microscopy (cryo-EM) have unlocked new doors for the reconstruction of molecular volumes. Despite significant headway, the immense challenges in cryo-EM data analysis remain legion and intricately inter-disciplinary in nature. Next-generation volume reconstruction algorithms that combine generative modeling with end-to-end unsupervised deep learning techniques have shown promising results on simulated data.
  arXiv  Detail & Related papers  (2022-01-08T17:45:18Z)
• Towards an Automatic Analysis of CHO-K1 Suspension Growth in Microfluidic Single-cell Cultivation [63.94623495501023]
  We propose a novel Machine Learning architecture, which allows us to infuse a neural deep network with human-powered abstraction on the level of data. Specifically, we train a generative model simultaneously on natural and synthetic data, so that it learns a shared representation, from which a target variable, such as the cell count, can be reliably estimated.
  arXiv  Detail & Related papers  (2020-10-20T08:36:51Z)

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.