English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Cryo-electron microscopy (cryo-EM) remains pivotal in structural biology, yetthe task of protein particle picking, integral for 3D protein structureconstruction, is laden with manual inefficiencies. While recent AI tools suchas Topaz and crYOLO are advancing the field, they do not fully address thechallenges of cryo-EM images, including low contrast, complex shapes, andheterogeneous conformations. This study explored prompt-based learning to adaptthe state-of-the-art image segmentation foundation model Segment Anything Model(SAM) for cryo-EM. This focus was driven by the desire to optimize modelperformance with a small number of labeled data without altering pre-trainedparameters, aiming for a balance between adaptability and foundationalknowledge retention. Through trials with three prompt-based learningstrategies, namely head prompt, prefix prompt, and encoder prompt, we observedenhanced performance and reduced computational requirements compared to thefine-tuning approach. This work not only highlights the potential of promptingSAM in protein identification from cryo-EM micrographs but also suggests itsbroader promise in biomedical image segmentation and object detection.

Adapting Segment Anything Model (SAM) through Prompt-based Learning for Enhanced Protein Identification in Cryo-EM Micrographs