Related Experiment Video
Updated: Jul 4, 2026

A Protocol for Computer-Based Protein Structure and Function Prediction
Published on: November 3, 2011
SP5: improving protein fold recognition by using torsion angle profiles and profile-based gap penalty model
Wei Zhang1, Song Liu, Yaoqi Zhou
1Indiana University School of Informatics and Center for Computational Biology and Bioinformatics, Indiana University School of Medicine, Indiana University-Purdue University Indianapolis, Indianapolis, Indiana, United States of America.
We developed SP(5), a new protein structure prediction method. It improves fold recognition accuracy by incorporating real-value dihedral angles and updated profiles, outperforming previous methods.
Area of Science:
- Computational Biology
- Structural Bioinformatics
- Protein Science
Background:
- Protein structure prediction remains a significant challenge in bioinformatics.
- Accurate recognition of protein structural folds is crucial for understanding protein function.
- Previous methods, like SPARKS and its successors (SP(2)-SP(4)), showed incremental improvements using profile matching.
Purpose of the Study:
- To introduce and evaluate a novel protein fold recognition method, SP(5).
- To enhance the accuracy and sensitivity of identifying correct protein structural folds, especially for remote homologs.
- To improve the overall modeling accuracy in protein structure prediction.
Main Methods:
- Development of SP(5), a method utilizing a new profile-profile comparison term based on real-value dihedral torsion angles.
- Integration of an updated real-value solvent accessibility profile.
- Implementation of a variable gap-penalty model using fractional power of insertion/deletion profiles.
- Weighted matching of sequence and structure-based profiles.
Main Results:
- SP(5) demonstrated a 2% absolute increase (5% relative improvement) in alignment accuracy over SP(4) on two benchmarks.
- A 7% absolute increase (22% relative improvement) in recognizing correct structural folds was achieved.
- Model accuracy for top-ranked models improved by 12% over SP(4) for difficult targets in the CASP 7 test set.
- Significant improvements in model accuracy within the same fold were observed on the Lindahl benchmark (32% relative improvement).
Conclusions:
- The SP(5) method offers a robust improvement in protein fold recognition accuracy and sensitivity.
- Harnessing predicted structural properties, such as dihedral angles and solvent accessibility, is vital for challenging remote-homolog recognition.
- The SP(5) server is publicly available for researchers to utilize.
Related Concept Videos
Protein Folding
Protein Structure Is Critical to Its Biological Function
Proteins perform a wide range of biological functions such as catalyzing chemical reactions, providing...
Protein Folding
Protein Folding
Protein Folding Quality Check in the RER
Protein and Protein Structure
A protein's shape is critical to its function. For example, an enzyme can...
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...

