Assessment of vector-host-pathogen relationships using data mining and machine learning.

Area of Science:

• Computational biology
• Infectious disease epidemiology
• Systems biology

Background:

• Vector-borne diseases pose significant global health challenges.
• Big data necessitates advanced computational approaches for understanding complex disease dynamics.
• Integrating diverse datasets is key to generating new biological knowledge in this field.

Purpose of the Study:

• To review the application of data mining and machine learning in studying vector-host-pathogen interactions.
• To assess current trends, challenges, and future directions in this research area.
• To evaluate the quality of data using FAIR compliance criteria for reproducibility.

Main Methods:

• Systematic literature review using PRISMA guidelines.
• Analysis of data mining and machine learning techniques applied to vector-host-pathogen data.
• Assessment of research data quality based on FAIR (Findable, Accessible, Interoperable, Reusable) principles.

Main Results:

• A notable increase in the use of data mining and machine learning techniques (prediction, classification, clustering, deep learning) over the past decade.
• Identification of critical challenges in applying these methods to systems biology levels of vector-host-pathogen interactions.
• Data quality assessment revealed areas for improvement in research reproducibility and shareability.

Conclusions:

• Data mining and machine learning hold significant potential for advancing the understanding of vector-host-pathogen relationships.
• Encouraging the application of these computational methods is vital for generating new hypotheses and knowledge.
• Further implementation of methods like deep learning and association rule analysis, alongside established techniques, can accelerate discovery.