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 Concept Videos

Amyloid Fibrils03:03

Amyloid Fibrils

9.7K
Amyloid fibrils are aggregates of misfolded proteins.  Under most circumstances, misfolded proteins are either refolded by chaperone proteins or degraded by the proteasome. However, in the case of a mutation or a disease, these proteins can accumulate to form large clusters and often further assemble to form elongated fibers, called fibrils. 
Amyloid deposits were observed as early as 1639 in the liver and the spleen.   In 1854, Rudolph Virchow performed iodine staining,...
9.7K

You might also read

Related Articles

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

Sort by
Same author

Macro- and micro-scale mechanical properties and energy evolution analysis during unidirectional freeze-thaw cycling of sandstone.

Scientific reports·2026
Same author

Identification of Genes Directly Regulated by LvBlimp1 in Shrimp Macrophage-like Phagocytes.

Developmental and comparative immunology·2026
Same author

LvBlimp1 and LvHes1 coregulate the function of macrophage-like phagocytes in shrimp hemolymph.

Fish & shellfish immunology·2026
Same author

Transcriptomic profiling and experimental validation of myeloid-cell-differentiation-related key genes in osteoarthritis.

Frontiers in genetics·2026
Same author

Damage characteristics and constitutive modeling of coal under real-time temperatures.

PloS one·2026
Same author

SLC2A9-Mediated Uric Acid Homeostasis Modulates Apoptosis in TNBC.

Breast cancer (Dove Medical Press)·2026

Related Experiment Video

Updated: Aug 5, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.2K

ECAmyloid: An amyloid predictor based on ensemble learning and comprehensive sequence-derived features.

Runtao Yang1, Jiaming Liu1, Lina Zhang1

  • 1School of Mechanical, Electrical and Information Engineering, Shandong University at Weihai, 264209, China.

Computational Biology and Chemistry
|March 29, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces ECAmyloid, an ensemble learning model that accurately predicts amyloid proteins using sequence-derived features. The model shows high accuracy, aiding in understanding amyloid diseases and developing new amyloid materials.

Keywords:
AmyloidCorrelation-Based Feature Subset SelectionEnsemble LearningSequence-derived FeaturesSynthetic Minority Over-sampling Technique

More Related Videos

A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

68.8K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.6K

Related Experiment Videos

Last Updated: Aug 5, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.2K
A Protocol for Computer-Based Protein Structure and Function Prediction
16:41

A Protocol for Computer-Based Protein Structure and Function Prediction

Published on: November 3, 2011

68.8K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.6K

Area of Science:

  • Biochemistry and Molecular Biology
  • Computational Biology and Bioinformatics
  • Neuroscience

Background:

  • Amyloid fibrils, formed by mis-aggregated amyloid proteins, are implicated in neurodegenerative diseases like Alzheimer's.
  • Accurate prediction of amyloid proteins is crucial for understanding their properties, formation mechanisms, and therapeutic targets.
  • Identifying amyloidogenic proteins also holds potential for developing novel amyloid-based biomaterials.

Purpose of the Study:

  • To develop an accurate and efficient computational model for identifying amyloid proteins.
  • To leverage sequence-derived features for improved prediction accuracy.
  • To provide a tool for large-scale determination of amyloidogenic proteins.

Main Methods:

  • An ensemble learning model, ECAmyloid, was developed using sequence-derived features: Pseudo Position Specificity Score Matrix (Pse-PSSM), Split Amino Acid Composition (SAAC), Solvent Accessibility (SA), and Secondary Structure Information (SSI).
  • An increment classifier selection strategy was used to choose individual learners, with final predictions determined by majority voting.
  • Data balancing was performed using Synthetic Minority Over-sampling Technique (SMOTE), and feature selection was achieved through correlation-based feature subset (CFS) selection combined with a heuristic search.

Main Results:

  • The ECAmyloid ensemble classifier achieved high performance with 98.29% accuracy, 0.992 sensitivity, and 0.974 specificity on the training dataset via 10-fold cross-validation.
  • The optimized feature subset further improved the ensemble method's performance metrics, including accuracy, sensitivity, specificity, MCC, F1-score, and G-Mean.
  • Comparative analysis against existing methods on independent test datasets confirmed ECAmyloid as an effective predictor for large-scale amyloid protein identification.

Conclusions:

  • ECAmyloid demonstrates superior performance in identifying amyloid proteins compared to its individual components and existing methods.
  • The model's ability to integrate diverse sequence-derived features contributes to its predictive power.
  • The freely available data and code facilitate further research and application in amyloid protein studies and disease treatment.