Related Experiment Video
Updated: Jun 18, 2026

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
A sequence-based hybrid predictor for identifying conformationally ambivalent regions in proteins
Yu-Cheng Liu1, Meng-Han Yang, Win-Li Lin
1Institute of Biomedical Engineering, National Taiwan University, Taipei, Taiwan, Republic of China. f90548051@ntu.edu.tw
This study introduces a novel sequence-based predictor for identifying flexible protein regions. The hybrid predictor combines two supervised learning algorithms, outperforming existing methods and offering valuable insights for biologists.
Area of Science:
- Computational Biology
- Bioinformatics
- Protein Structure Prediction
Background:
- Proteins are dynamic macromolecules whose conformational flexibility is linked to biological functions.
- Predicting flexible protein regions is crucial, especially using sequence data due to limited tertiary structure availability.
- Existing predictors primarily analyze tertiary structures or solely sequence information.
Purpose of the Study:
- To develop a novel sequence-based predictor for identifying conformationally ambivalent regions in proteins.
- To leverage complementary prediction powers of two distinctive supervised learning algorithms for enhanced accuracy.
- To provide biologists with tools for identifying functional sites within protein chains.
Main Methods:
- Developed a hybrid predictor incorporating two classifiers based on distinct supervised learning algorithms.
- Evaluated performance using experimental results and an independent testing dataset.
- Implemented two operational modes: high-sensitivity and high-specificity.
Main Results:
- The proposed hybrid predictor demonstrated superior performance compared to existing sequence-based predictors.
- Achieved a sensitivity of 0.710 and specificity of 0.608 in high-sensitivity mode.
- Achieved a sensitivity of 0.451 and specificity of 0.787 in high-specificity mode.
Conclusions:
- The hybrid approach effectively utilizes complementary learning algorithms for improved protein region prediction.
- Further improvements can be achieved by incorporating additional physicochemical properties and advanced machine learning techniques.
- Continued development of advanced predictors for identifying conformationally ambivalent protein regions is essential for biological research.
More Related Videos
06:50Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions
Published on: January 26, 2024
16:02Demonstration of the Sequence Alignment to Predict Across Species Susceptibility Tool for Rapid Assessment of Protein Conservation
Published on: February 10, 2023
Related Concept Videos
Conserved Binding Sites
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally analyses the...
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...
Conservation of Protein Domains
A limited set of protein domains often duplicate and recombine during evolution. These domains can be organized in different combinations to form...
Multi-species Conserved Sequences
Although the genome of each species varies greatly from each other, a few sequences are highly conserved. Such conserved DNA...
Mitochondrial Precursor Proteins
Most of the mitochondrial precursors...
Peptide Identification Using Tandem Mass Spectrometry
This technique helps gather information regarding the protein from which the peptide was obtained and to study the peptides’ amino acid sequence. Identifying peptides from a complex mixture is an important component of the growing field of...