A Study and Analysis of Disease Identification using Genomic Sequence Processing Models: An Empirical Review.

Area of Science:

• Genomics
• Bioinformatics
• Machine Learning

Background:

• Human gene sequences offer comprehensive health information for disease prediction.
• Machine learning models are crucial for analyzing genomic sequences to identify various diseases.
• Existing models present trade-offs in accuracy, scalability, and performance.

Purpose of the Study:

• To survey and compare different machine learning models for genomic sequence processing.
• To provide a framework for selecting optimal models based on specific application and performance needs.
• To assist genomic system designers in identifying suitable models for clinical scenarios.

Main Methods:

• Detailed survey of machine learning models for genomic data.
• Analysis of functional nuances, advantages, and limitations of each model.
• Quantitative comparison of models based on accuracy, delay, precision, scalability, and deployment cost.

Main Results:

• Models vary significantly in performance characteristics, such as speed vs. accuracy and scalability.
• A novel Genome Processing Efficiency Rank (GPER) is introduced for model evaluation.
• Quantitative data aids in comparing models for real-time clinical applications.

Conclusions:

• This survey provides critical insights into the landscape of genomic processing models.
• Researchers can leverage the detailed comparison and GPER to select appropriate models.
• Informed model selection can enhance the efficiency and accuracy of disease prediction from genomic data.