Related Experiment Video
Updated: Jun 26, 2026

A Protocol for Computer-Based Protein Structure and Function Prediction
Published on: November 3, 2011
Comparing predictors of disordered protein
1School of Electrical Engineering and Computer Sciences, Washington State University, Pullman, WA 99164-2752, USA. xiahong@livegrip.com
Researchers identified key amino acid sequence attributes that predict ordered or disordered protein structures. These attributes, including coordination number and net charge, improve artificial neural network (ANN) models for protein structure prediction.
Area of Science:
- Biochemistry and Structural Biology
- Computational Biology and Bioinformatics
Background:
- Protein structure, whether ordered or disordered, is crucial for biological function.
- Predicting protein structural states from amino acid sequences remains a significant challenge in molecular biology.
Purpose of the Study:
- To identify and rank amino acid sequence attributes that best indicate ordered or disordered protein structures.
- To develop and evaluate novel artificial neural network (ANN) predictors for protein structure determination.
Main Methods:
- Ranking over 6,000 amino acid sequence attributes by conditional probabilities.
- Utilizing logistic regression for attribute selection from merged attribute groups.
- Developing and comparing five artificial neural network (ANN) predictors using the top 12 selected attributes.
Main Results:
- Identified key attributes favoring ordered states (e.g., average Coordination Number, aromatic content) and disordered states (e.g., Net Charge, Flexibility Index).
- The interplay of multiple attributes significantly influences the determination of protein order or disorder.
- The best ANN predictor demonstrated substantially improved generalization capabilities compared to previous models.
Conclusions:
- A combination of specific amino acid sequence attributes effectively predicts protein structural states.
- The developed ANN models offer enhanced accuracy for predicting protein order and disorder.
- This work advances computational approaches to understanding protein structure-function relationships.
Related Concept Videos
Conservation of Protein Domains Over Different Proteins
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to form...
Intrinsically Disordered Proteins
Protein-protein Interfaces
Protein Networks
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
Protein Organization
The primary structure of a protein is its amino acid sequence.
Intrinsically Disordered Proteins

