iEnhancer-MRBF: Identifying enhancers and their strength with a multiple Laplacian-regularized radial basis function...

Area of Science:

• Genomics
• Molecular Biology
• Bioinformatics

Background:

• Enhancers are vital DNA elements regulating gene expression in eukaryotes.
• Experimental methods for enhancer identification are time-consuming and costly.
• Computational approaches are needed for efficient enhancer identification and strength prediction.

Purpose of the Study:

• To develop a computational model for identifying enhancers and classifying their strength.
• To propose a two-layer model, iEnhancer-MRBF, for enhancer prediction.
• To differentiate between strong and weak enhancers based on their regulatory potential.

Main Methods:

• A novel Multiple Laplacian-Regularized Radial Basis Function Network (MLR-RBFN) classifier was developed.
• Three DNA sequence feature representation methods were employed: kmer, nucleotide binary profiles (NBP), and accumulated nucleotide frequency (ANF).
• Feature selection techniques were integrated for enhanced DNA sequence processing.

Main Results:

• The iEnhancer-MRBF model demonstrated superior performance compared to existing prediction models.
• The first layer achieved an independent test accuracy of 79.75% for enhancer identification.
• The second layer achieved an independent test accuracy of 83.50% for classifying enhancer strength (strong vs. weak).

Conclusions:

• The iEnhancer-MRBF model offers an effective computational solution for enhancer identification and strength prediction.
• The proposed MLR-RBFN classifier and feature representation methods contribute to improved accuracy in genomic sequence analysis.
• This approach addresses the need for faster and more cost-effective methods in enhancer research.