# Protein Graph Neural Networks for Heterogeneous Cryo-EM Reconstruction

arXiv: https://arxiv.org/abs/2602.21915 · HTML: https://mlsanity.com/paper/2602.21915/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 25 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Amortized Inference for Heterogeneous Reconstruction in Cryo-EM](https://mlsanity.com/paper/2210.07387/) (2022)
- [Inferring a Continuous Distribution of Atom Coordinates from Cryo-EM Images using VAEs](https://mlsanity.com/paper/2106.14108/) (2021)
- [CryoBench: Diverse and challenging datasets for the heterogeneity problem in cryo-EM](https://mlsanity.com/paper/2408.05526/) (2024)
- [Deep learning based mixed-dimensional GMM for characterizing variability in CryoEM](https://mlsanity.com/paper/2101.10356/) (2021)
- [Regularising orientation estimation in Cryo-EM 3D map refinement through measure-based lifting over Riemannian manifolds](https://mlsanity.com/paper/2209.03045/) (2022)
- [Using VAEs to Learn Latent Variables: Observations on Applications in cryo-EM](https://mlsanity.com/paper/2303.07487/) (2023)

## Abstract (arXiv)

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.