Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Nov 2, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K

Multi-labelled proteins recognition for high-throughput microscopy images using deep convolutional neural networks.

Enze Zhang1,2, Boheng Zhang3, Shaohan Hu4

  • 1High Performance Computer Research Center, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China.

BMC Bioinformatics
|June 16, 2021
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Recent Advances in Vision-Based Beef Cattle Body Measurement Technologies.

Animals : an open access journal from MDPI·2026
Same author

Antagonism of β-klotho signaling by peptide 19 impairs wheel running in male mice and potentiates the cisplatin-induced decrease in wheel running.

Frontiers in pharmacology·2026
Same author

Light-regulated reconfigurable MXene-hydrogel gas sensing system via machine learning.

Journal of colloid and interface science·2026
Same author

Associations of nutrient and heavy metal gradients with the diversity, functional traits, and community assembly of marine planktonic ciliates.

Marine environmental research·2026
Same author

A knowledge-guided deep learning framework for quantitative nucleic acid testing.

Briefings in bioinformatics·2026
Same author

DyMamba: dynamic Mamba for microscopy image semantic segmentation.

Bioinformatics (Oxford, England)·2026

This study introduces an advanced deep learning model for automatic protein image classification. The novel method significantly improves accuracy in analyzing complex, high-throughput microscopy images, outperforming existing state-of-the-art approaches.

Area of Science:

  • Biotechnology
  • Cell Biology
  • Bioinformatics

Background:

  • Proteins are crucial for human bodily functions.
  • Advanced microscopy generates vast amounts of protein images daily.
  • Manual classification of these images is infeasible due to complexity and volume.

Purpose of the Study:

  • To develop an automatic and accurate method for analyzing mixed-pattern protein images.
  • To address challenges in classifying high-throughput microscopy protein data.

Main Methods:

  • A novel customized deep learning architecture with adaptive concatenate pooling and buffering layers.
  • A hard sampler to effectively identify samples from small classes.
  • A new loss function to manage label imbalance and sample effectiveness.
Keywords:
DNNsHigh-throughput microscopy imagesLabel imbalanceMulti-class and multi-labelProtein pattern recognition

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

730
Super-Resolution Imaging to Study Co-Localization of Proteins and Synaptic Markers in Primary Neurons
14:02

Super-Resolution Imaging to Study Co-Localization of Proteins and Synaptic Markers in Primary Neurons

Published on: October 31, 2020

6.0K

Related Experiment Videos

Last Updated: Nov 2, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.5K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

730
Super-Resolution Imaging to Study Co-Localization of Proteins and Synaptic Markers in Primary Neurons
14:02

Super-Resolution Imaging to Study Co-Localization of Proteins and Synaptic Markers in Primary Neurons

Published on: October 31, 2020

6.0K
  • Optimization strategies for training and post-processing.

    • Main Results:

    • The proposed method demonstrates superior performance in multi-label protein classification.
    • Achieved over 2% higher F1 score compared to the SOTA method (GapNet-PL) on the Human Protein Atlas dataset.

    Conclusions:

    • The developed methods provide good performance for automatic classification of multi-class, multi-label protein images.
    • Experimental results confirm the effectiveness on the Human Protein Atlas dataset.