Improving the performance of DomainDiscovery of protein domain boundary assignment using inter-domain linker index

Abstract

Background: Knowledge of protein domain boundaries is critical for the characterisation and understanding of protein function. The ability to identify domains without the knowledge of the structure--by using sequence information only--is an essential step in many types of protein analyses. In this present study, we demonstrate that the performance of DomainDiscovery is improved significantly by including the inter-domain linker index value for domain identification from sequence-based information. Improved DomainDiscovery uses a Support Vector Machine (SVM) approach and a unique training dataset built on the principle of consensus among experts in defining domains in protein structure. The SVM was trained using a PSSM (Position Specific Scoring Matrix), secondary structure, solvent accessibility information and inter-domain linker index to detect possible domain boundaries for a target sequence.

Results: Improved DomainDiscovery is compared with other methods by benchmarking against a structurally non-redundant dataset and also CASP5 targets. Improved DomainDiscovery achieves 70% accuracy for domain boundary identification in multi-domains proteins.

Conclusion: Improved DomainDiscovery compares favourably to the performance of other methods and excels in the identification of domain boundaries for multi-domain proteins as a result of introducing support vector machine with benchmark_2 dataset.

Figure 1

Example of Input Array for a Window Size of 21. True boundary here is the residue that SCOP defines as a boundary residue. In case of positive example, we select 10 residues from each side of the true boundary residue and for negative example; we randomly select 21 residues from the rest of the protein chain.

Figure 2

Six-fold cross-validation results for DomainDiscovery (in average). Six-fold cross-validation results for DomainDiscovery; determined by using SVM classifiers for the Benchmark_2 dataset.

Figure 3

Six-fold cross-validation results for Improved DomainDiscovery (in average). Six-fold cross-validation results for Improved DomainDiscovery; determined by using SVM classifiers for the Benchmark_2 dataset.

Figure 4

Percentage of Correct Prediction by different methods. Percentage of correct predictions for the number of domains defined for each method. If the boundary falls within 30% of the SCOP value the prediction is counted as correct.

Figure 5

An Example of Domain Boundary Assignment by Improved DomainDiscovery. Domain Boundary is at the residue 73.