Overcoming the preferred-orientation problem in cryo-EM with self-supervised deep learning.

While advances in single-particle cryo-EM have enabled the structural determination of macromolecular complexes at atomic resolution, particle orientation bias (the 'preferred' orientation problem) remains a complication for most specimens. Existing solutions have relied on biochemical and physical strategies applied to the specimen and are often complex and challenging. Here, we develop spIsoNet, an end-to-end self-supervised deep learning-based software to address map anisotropy and particle misalignment caused by the preferred-orientation problem. Using preferred-orientation views to recover molecular information in under-sampled views, spIsoNet improves both angular isotropy and particle alignment accuracy during 3D reconstruction. We demonstrate spIsoNet's ability to generate near-isotropic reconstructions from representative biological systems with limited views, including ribosomes, β-galactosidases and a previously intractable hemagglutinin trimer dataset. spIsoNet can also be generalized to improve map isotropy and particle alignment of preferentially oriented molecules in subtomogram averaging. Therefore, without additional specimen-preparation procedures, spIsoNet provides a general computational solution to the preferred-orientation problem.