Fold'EM: Direct atomic structure inference from Cryo-EM particles
Fold'EM infers atomic protein structures directly from few cryo-EM images, skipping density reconstruction.
Fold'EM combines priors from protein generative models with cryo-EM particle images to infer atomic structures from a small number of images. It bypasses intermediate electrostatic-potential map reconstruction and downstream fitting of an atomic model to that map. On synthetic and experimental datasets it recovers structures with known orientations and when orientations are inferred jointly. In heterogeneous samples it separates conformational states without building a density map and model for each state.
- Pairs protein generative-model priors with raw cryo-EM particle images.
- Skips density-map reconstruction and later atomic model fitting.
- Handles known orientations and joint ab initio orientation inference.
- Resolves distinct conformational states from mixed particle populations.
From the original article
1 min read at arxiv.orgSingle-particle cryo-electron microscopy (cryo-EM) has become a widely adopted technique for biomolecular structure determination. The conventional cryo-EM computational pipeline first combines many particle images to reconstruct an electrostatic potential (ESP) map and then fits an atomic model to the recovered map.
By Advaith Maddipatla · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.