Application and Comparison of Machine Learning and Database-Based Methods in Taxonomic Classification of...

Area of Science:

• Bioinformatics
• Computational Biology
• Genomics

Background:

• High-throughput sequencing generates vast data, increasing the need for efficient taxonomic classification.
• Current methods include database-based and machine learning approaches, each with limitations.

Purpose of the Study:

• To comparatively analyze database-based and machine learning methods for taxonomic classification.
• To evaluate the benefits of integrating multiple database-based methods.

Main Methods:

• Comparative analysis using simulated datasets.
• Performance evaluation of different taxonomic classification strategies.

Main Results:

• Database methods achieve higher accuracy with comprehensive reference databases.
• Machine learning methods perform better with sparse or absent reference sequences.
• Integrating multiple database methods enhances classification accuracy.

Conclusions:

• Database methods are generally superior for taxonomic classification when extensive reference data is available.
• Machine learning methods offer a viable alternative for limited reference data scenarios.
• Combined database approaches improve overall taxonomic classification performance.