Nithin Chalapathi

Nithin Chalapathi

Ph.D. student ยท AI for Science

Learning the Shared Latent Structure of Cryo-EM Inverse Problems

Published in arXiv preprint, 2026

Nithin Chalapathi, Theo Sternlieb, Ethan Han, Sonya M. Hanson, Pilar Cossio, Aditi S. Krishnapriyan, Ritwik Gupta

PDF Code arXiv DOI BibTeX

EMber overview showing shared protein structures, cryo-EM image formation, and a shared encoder for pose, structure, and population inference.

Figure 1. Cryo-EM overview and shared inverse problems. Source paper.

Abstract summary

EMber learns reusable representations of cryo-EM particle images for several inverse problems, including analysis of molecular variability and reconstruction. Its vision transformers use self-distillation with global and local objectives, combining more than 50 million experimental particle images from 214 EMPIAR datasets with simulated views of 268,000 molecular assemblies. Controlled evaluations test whether the features capture molecular structure rather than acquisition conditions. The learned representations improve discrimination between molecular states and compositions, support population estimation with a linear probe, and accelerate reconstruction through useful particle assignments.