Addressing preferred orientation in single-particle cryo-EM through AI-generated auxiliary particles

TL;DR

The paper introduces cryoPROS, an AI-based method that generates auxiliary particles to mitigate preferred orientation bias in cryo-EM, enabling near-atomic resolution structures without special experimental setups.

Contribution

We present cryoPROS, a novel AI-driven approach that generates auxiliary particles to address preferred orientation in cryo-EM, improving resolution without additional experimental modifications.

Findings

Successfully restored near-atomic resolution of hemagglutinin trimer.

Significantly improved membrane protein NaX resolution with cryoPROS-MP.

Demonstrated low model bias and high robustness of the method.

Abstract

The single-particle cryo-EM field faces the persistent challenge of preferred orientation, lacking general computational solutions. We introduce cryoPROS, an AI-based approach designed to address the above issue. By generating the auxiliary particles with a conditional deep generative model, cryoPROS addresses the intrinsic bias in orientation estimation for the observed particles. We effectively employed cryoPROS in the cryo-EM single particle analysis of the hemagglutinin trimer, showing the ability to restore the near-atomic resolution structure on non-tilt data. Moreover, the enhanced version named cryoPROS-MP significantly improves the resolution of the membrane protein NaX using the no-tilted data that contains the effects of micelles. Compared to the classical approaches, cryoPROS does not need special experimental or image acquisition techniques, providing a purely computational yet effective solution for the preferred orientation problem. Finally, we conduct extensive experiments that establish the low risk of model bias and the high robustness of cryoPROS.