Movie
Controller
Structure viewers
About Yorodumi Papers
+Search query
-Structure paper
| Title | Template Learning: Deep learning with domain randomization for particle picking in cryo-electron tomography. |
|---|---|
| Journal, issue, pages | Nat Commun, Vol. 16, Issue 1, Page 8833, Year 2025 |
| Publish date | Oct 3, 2025 |
 Authors | Mohamad Harastani / Gurudatt Patra / Charles Kervrann / Mikhail Eltsov /  |
| PubMed Abstract | Cryo-electron tomography (cryo-ET) enables three-dimensional visualization of biomolecules and cellular components in their near-native state. A key challenge in cryo-ET data analysis is particle ...Cryo-electron tomography (cryo-ET) enables three-dimensional visualization of biomolecules and cellular components in their near-native state. A key challenge in cryo-ET data analysis is particle picking, often performed by template matching, which relies on cross-correlating tomograms with known structural templates. Current deep learning-based methods improve accuracy but require labor-intensive annotated datasets for supervised training. Here, we present Template Learning, a technique that combines deep learning accuracy with the convenience of training on biomolecular templates via domain randomization. Template Learning automates synthetic dataset generation, modeling molecular crowding, structural variability, and data acquisition variation, thereby reducing or eliminating the need for annotated experimental data. We show that models trained using Template Learning, and optionally fine-tuned with experimental data, outperform those trained solely on annotations. Furthermore, Template Learning provides higher precision and more uniform orientation detection than template matching, particularly for small non-spherical particles. Template Learning software is open-source, Python-based, and GPU/CPU parallelized. |
 External links | Nat Commun / PubMed:41044063 / PubMed Central |
| Methods | EM (subtomogram averaging) |
| Resolution | 11.0 - 18.0 Å |
| Structure data |  EMDB-19823: Subtomogram average of nucleosomes annotated by Template Learning in isolated mitotic chromosomes  EMDB-19825: Subtomogram average of nucleosomes annotated by template matching in isolated mitotic chromosomes  EMDB-51648: Reproduced subtomogram average of S. pombe 80S ribosomes from DEF tomograms acquired on cryo-FIB-lamellae based on expert-validated annotations  EMDB-51651: Subtomogram average of S. pombe 80S ribosomes from DEF tomograms acquired on cryo-FIB-lamellae based on raw Template Learning annotations  EMDB-51652: Subtomogram average of S. pombe 80S ribosomes from DEF tomograms acquired on cryo-FIB-lamellae based on true positive Template Learning annotations  EMDB-51653: Subtomogram average of S. pombe 80S ribosomes from DEF tomograms acquired on cryo-FIB-lamellae based on Template Learning additional annotations non-overlapping with previous expert-validated annotations  EMDB-51694: Subtomogram average of nucleosomes extracted using Template Learning from cryo-tomograms of Drosophila melanogaster embryos  EMDB-51695: Subtomogram average of nucleosomes extracted using 3D template matching from cryo-tomograms of Drosophila melanogaster embryos  EMDB-51696: Subtomogram average of nucleosomes extracted using DeepFinder from cryo-tomograms of Drosophila melanogaster embryos |
| Source |
|
Gallus gallus (chicken)
Schizosaccharomyces pombe (fission yeast)
Drosophila melanogaster (fruit fly)