Systems and Methods for Uncertainty-Aware-Single-Particle Cryo-EM Data Collection Using Online Feedback
AssigneeThe Regents of the University of Michigan
InventorsMichael Cianfrocco, Ambuj Tewari, Lai Wei
Life of this patent
Estimating the term…
Loading patent…
AssigneeThe Regents of the University of Michigan
InventorsMichael Cianfrocco, Ambuj Tewari, Lai Wei
Estimating the term…
A system and method are disclosed for automating cryogenic electron microscopy (cryo-EM) data collection by optimizing a sampling strategy. The system identifies, from patch-level images taken by a cryo-EM instrument, a plurality of holes within a cryo-EM grid, each representing a candidate data collection point. The system predicts an expected reward for each identified hole based on features extracted from the patch-level images. The system determines, using stochastic approximation, a dynamically adjusted threshold quality score representing an estimated optimal time-average reward. Holes are selected from the identified plurality based on the expected reward by minimizing an objective function that depends on the dynamically adjusted threshold quality score. The dynamically adjusted threshold quality score may be based at least in part on observed rewards from the selected holes and microscope operation times.
A computing system for automated data collection in cryogenic electron microscopy (cryo-EM), the computing system comprising:
A computer implemented method for automated data collection in cryogenic electron microscopy (cryo-EM), the method comprising:
A non-transitory computer-readable medium having stored thereon computer-executable instructions that, when executed by a processor, cause a computing system to perform operations for automated data collection in cryogenic electron microscopy (cryo-EM), the operations comprising:
Dependencies are inferred from the claim text.