Comment on page
Job: Regroup 3D
Regroup 3D classes via spectral clustering
Regroup 3D is new job in CryoSPARC v4.4+ that regroups particles from an upstream classification job into a smaller set of ‘superclasses’ using a light-weight 3D-voxel-based spectral clustering approach.
- Particles (
particles_all_classes
from 3D Classification or Heterogeneous Refinement) - Volume series (from 3D Classification or Heterogeneous Refinement)
- [Optional] Mask
- Class alignment3D prefix
- By default, this parameter is set such that class assignments are expected to come from 3D classification. If using this job with an upstream heterogeneous refinement, this should be changed to the non-default value of
alignments_class_
.
- Minimum class size (particles)
- Only classes with this many particles will be regrouped. This parameter may be useful when there are (near-)empty classes with poorly resolved volumes.
- Regrouped particles
- Note that all particle assignments are recomputed by maximizing over the class posteriors in the upstream dataset. Upstream posterior probabilities are ignored except as a proxy for class assignment. Regrouped particles are given ‘hard’ (one-hot) class posteriors based on the new set of superclasses.
- Per-superclass particles
- Superclass average volumes
- These volumes are the real-space average of class volumes that belong to each superclass. To recover back-projected volumes from super-class particle assignments, use the Heterogeneous Reconstruction Only job with the
regrouped_particles
output group.
- Superclass volume series
- [If supplied] Mask
- Remaining particles
- Heterogeneous Reconstruction Only
- Further 3D classification
Last modified 1mo ago