A Survey of Data Mining and Deep Learning in Bioinformatics

Area of Science:

• Bioinformatics
• Health Informatics
• Data Science

Background:

• Massive data generation in medicine and health informatics necessitates advanced analytics.
• Novel technologies are emerging for knowledge discovery from large datasets.
• Machine learning and deep learning are increasingly vital for bioinformatics research.

Purpose of the Study:

• To survey recent research on data mining and deep learning in bioinformatics.
• To summarize algorithms and neural network architectures used in bioinformatics data analysis.
• To compare the advantages and disadvantages of these methods for industrial applications.

Main Methods:

• Review of data mining algorithms for preprocessing, classification, and clustering.
• Analysis of optimized neural network architectures in deep learning.
• Discussion of practical applications and industrial usage.

Main Results:

• Identification of key data mining and deep learning techniques in bioinformatics.
• Comparison of algorithm performance and suitability for specific tasks.
• Evaluation of the industrial relevance and potential of various methods.

Conclusions:

• Data analytics, particularly machine learning and deep learning, offers significant potential for bioinformatics.
• This review provides valuable insights for researchers entering the field of bioinformatics data analytics.
• Understanding the strengths and weaknesses of different methods is crucial for successful implementation.