MicrographCleaner: a python package for cryo-EM micrograph cleaning using deep learning

Sánchez-García, Rubén; Segura, Joan; Maluenda, David; Sorzano, C.O.S.; Carazo, José Marı́a

doi:10.1101/677542

Cited by 2 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recall was 0.81 and precision 0.51. As STRIPER supports binary masks, we masked out the carbon area using the MicrographCleaner tool [21] and repeated the selection ( Supplementary Fig. S2).…”

Section: Evaluation On Test Data Setsmentioning

confidence: 99%

“…This mask divides an image into valid picking regions and regions with carbon or contamination. This masking option is especially useful as deep learning-based carbon and contamination detection just recently became available[7,21]. These programs determine valid and non-valid regions with high accuracy and create binary masks, which then can be directly used in STRIPER to remove false-positive selections.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Two particle picking procedures for filamentous proteins: SPHIRE-crYOLO filament mode and SPHIRE-STRIPER

Wagner

Lusnig

Pospich

et al. 2020

Preprint

View full text Add to dashboard Cite

Structure determination of filamentous molecular complexes involves the selection of filaments from cryo-EM micrographs. The automatic selection of helical specimens is particularly difficult and thus many challenging samples with issues such as contamination or aggregation are still manually picked. Here we present two approaches for selecting filamentous complexes: one uses a trained deep neural network to identify the filaments and is integrated in SPHIRE-crYOLO, the other one, called SPHIRE-STRIPER, is based on a classical line detection approach. The advantage of the crYOLO based procedure is that it accurately performs on very challenging data sets and selects filaments with high accuracy.Although STRIPER is less precise, the user benefits from less intervention, since in contrast to crYOLO, STRIPER does not require training. We evaluate the performance of both procedures on tobacco mosaic virus and filamentous F-actin data sets to demonstrate the robustness of each method.

show abstract

Section: Evaluation On Test Data Setsmentioning

confidence: 99%

mentioning

confidence: 99%