Related Experiment Video
Updated: Jun 8, 2026

Optimization of Synthetic Proteins: Identification of Interpositional Dependencies Indicating Structurally and/or Functionally Linked Residues
Published on: July 14, 2015
SMpred: a support vector machine approach to identify structural motifs in protein structure without using
Ganesan Pugalenthi1, Krishna Kumar Kandaswamy, P N Suganthan
1Laboratory of Structural Biochemistry, Genome Institute of Singapore, 60 Biopolis Street, Singapore 138672.
This study introduces SMpred, a novel SVM method for identifying protein structural motifs from single structures. SMpred effectively identifies these crucial motifs even without homologous sequences or structures.
Area of Science:
- Structural bioinformatics
- Computational biology
- Protein structure analysis
Background:
- Protein structure and function are intrinsically linked, with structural motifs playing a key role in determining protein fold and stability.
- Identifying these motifs typically requires homologous sequences and structures to infer evolutionary and conservation information.
- A significant challenge exists as many protein structures lack sufficient homologous data in existing databases.
Purpose of the Study:
- To develop a novel method, SMpred, for identifying structural motifs from individual protein structures.
- To overcome the limitations of methods requiring sequence and structural homologs.
- To provide a tool for motif identification in proteins with limited or no known homologs.
Main Methods:
- Development of a Support Vector Machine (SVM) based method named SMpred.
- Training and testing SMpred using 132 protein domains encompassing 581 motifs.
- Evaluating SMpred's performance against the MegaMotifBase dataset, comprising 188 proteins and 1161 motifs.
Main Results:
- SMpred achieved an accuracy of 78.79%, with 79.06% sensitivity and 78.53% specificity during initial training and testing.
- The method correctly identified 1503 structural motifs from the 1161 motifs present in the MegaMotifBase evaluation.
- SMpred demonstrated utility for length-deviant and single-member superfamilies, highlighting its applicability across diverse protein families.
Conclusions:
- SMpred offers a viable approach for identifying structural motifs in proteins lacking sequence or structural homologs.
- This method facilitates the analysis of protein structures where traditional comparative methods are not feasible.
- The developed algorithm and dataset are publicly available, promoting further research in structural motif discovery.
Related Concept Videos
Structural Protein Function
Collagen, the most abundant protein in mammals, is found throughout the body. In connective tissue, such as skin, ligaments, and tendons, it provides tensile strength and elasticity. In bones and teeth, it mineralizes to form...
Structural Protein Function
Collagen, the most abundant protein in mammals, is found throughout the body. In connective tissue, such as skin, ligaments, and tendons, it provides tensile strength and elasticity. In bones and teeth, it mineralizes to form...
Protein and Protein Structure
A protein's shape is critical to its function. For example, an enzyme can...
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...
Protein and Protein Structures
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...
