Exploiting the sequential nature of genomic data for improved analysis and identification.

Area of Science:

• Bioinformatics
• Genomics
• Computational Biology

Background:

• Exponential growth of genomic data presents challenges for sequence analysis and classification.
• Existing genome classification models often overlook the sequential nature of nucleotides and amino acids, crucial for understanding viral structure and function.

Purpose of the Study:

• To introduce GenoAnaCla, a novel approach for analyzing and classifying genome sequences using sequential pattern mining (SPM).
• To improve the accuracy and effectiveness of viral genome sequence classification and detection.

Main Methods:

• GenoAnaCla preprocesses RNA virus genome sequences (nucleotide, coding region, protein formats).
• Extracts frequent sequential patterns and rules in multiple forms and codons to capture sequential features.
• Utilizes eight different classifiers and evaluates their performance using various metrics.

Main Results:

• The proposed GenoAnaCla approach demonstrates superior performance compared to existing methods.
• Achieved an average accuracy increase of 3.18% over state-of-the-art genome sequence classification and detection techniques.

Conclusions:

• GenoAnaCla effectively incorporates sequential information for enhanced genome sequence analysis and classification.
• The method offers a significant advancement in managing and understanding viral genomic data, crucial for pandemic preparedness.