Protein Graph Neural Networks for Heterogeneous Cryo-EM Reconstruction
KTH Royal Institute of Technology(皇家理工学院);Harvard University(哈佛大学);Department of Mathematics(数学系);School of Engineering and Applied Sciences(工程与应用科学学院)
Jonathan Krook, Axel Janson, Joakim Andén, Melanie Weber, Ozan Öktem
We present a geometry-aware method for heterogeneous single-particle cryogenic electron microscopy (cryo-EM) reconstruction that predicts atomic backbone conformations. To incorporate protein-structure priors, we represent the backbone as a graph and use a graph neural network (GNN) autodecoder that maps per-image latent variables to 3D displacements of a template conformation. The objective combines a data-discrepancy term based on a differentiable cryo-EM forward model with geometric regularization, and it supports unknown orientations via ellipsoidal support lifting (ESL) pose estimation. On synthetic datasets derived from molecular dynamics trajectories, the proposed GNN achieves higher accuracy compared to a multilayer perceptron (MLP) of comparable size, highlighting the benefits of a geometry-informed inductive bias.
Resolving compositional and conformational heterogeneity in cryo-EM with deformable 3D Gaussian representations
Research Center for Mathematics and Interdisciplinary Sciences (Ministry of Education Frontiers Science Center for Nonlinear Expectations)(数学与交叉科学研究中心(教育部前沿非线性期望科学中心));College of Medical Information and Engineering(医学信息与工程学院);School of Medical Technology(医学技术学院);State Key Laboratory of Microbial Technology(微生物技术国家重点实验室);King Abdullah University of Science and Technology (KAUST)(国王 Abdullah 科学技术大学(KAUST))
ProFusion: 3D Reconstruction of Protein Complex Structures from Multi-view AFM Images
Department of Electrical and Computer Engineering, Iowa State University(电气与计算机工程系,爱荷华州立大学);Department of Mechanical Engineering, Iowa State University(机械工程系,爱荷华州立大学);Roy J. Carver Department of Biochemistry, Biophysics and Molecular Biology, Iowa State University(罗伊·J·卡弗生物化学、生物物理和分子生物学系,爱荷华州立大学);Target & Protein Sciences, Janssen R&D, Johnson & Johnson(贾尼斯森研发部,强生公司);Department of Chemistry, Iowa State University(化学系,爱荷华州立大学);Departments of Internal Medicine and Biophysics, University of Texas Southwestern Medical Center(内科学与生物物理学系,德克萨斯西南医学中心)
Affinity-VAE: incorporating prior knowledge in representation learning from scientific images
Alan Turing Institute(阿兰·图灵研究所);Science and Technology Facilities Council(科学与技术设施委员会);University of Oxford(牛津大学);Rosalind Franklin Institute(罗莎琳德·富兰克林研究所)