DeepCryoPicker: fully automated deep neural network for single protein particle picking in cryo-EM

BMC Bioinformatics

Table 4 The results of test micrographs scaling operations

Dataset	Original micrograph dimension	Original particle size	Scaling operation and best factor	Scaled particle size	Scaled micrograph dimensions	Unified micrograph size
Apoferritin top-view	1200 × 1240	94 × 94	Up-sampling (2.375)	224 × 224	3373 × 3373	3374 × 3374
KLH (top-view)	2048 × 2048	187 × 187	No-scaling	187 × 187	2048 × 2048	2048 × 2048
KLH (side-view)	2048 × 2048	221 × 221	No-scaling	221 × 221	2048 × 2048	2048 × 2048
Ribosome Ribosome irregular shape	4096 × 4096	320 × 320	Down-sampling (0.625)	200 × 200	4030 × 4030	4030 × 4030
β-Galactosidase complex particle shape	4096 × 4096	188 × 188	Up-sampling (1.125)	212 × 212	4608 × 4608	4608 × 4608

The second column shows the original test micrographs dimensions, the third column the detected particle patches’ coordinates (dimensions) using AutoCryoPicker [24] and SuperCryoEMPicker [25], the fourth column the selected scaling operation and best factor, the fifth column the scaled particle size using the selected scaling factor, the sixth column the scaled micrograph dimensions, and the last column the unified micrograph size

ISSN: 1471-2105