Epigenomic annotation-based interpretation of genomic data: from enrichment analysis to machine learning

Area of Science:

• Genomics
• Bioinformatics
• Computational Biology

Background:

• Interpreting experimentally derived genomic regions of interest (ROIs) is challenging, as most lie outside protein-coding regions.
• Reference epigenomic datasets from initiatives like the International Human Epigenome Consortium provide valuable functional and regulatory annotations.
• Numerous computational tools leverage these epigenomic datasets for genomic data interpretation.

Purpose of the Study:

• To provide a structured overview of practical solutions for interpreting genomic regions of interest (ROIs) using epigenomic data.
• To review leading computational tools and machine learning methods that utilize epigenomic and 3D genome structure data.
• To present a practical guide for interpreting genome-wide ROIs within an epigenomic context.

Main Methods:

• Review of existing computational tools for epigenomic enrichment analysis.
• Discussion of machine learning methods applied to epigenomic and 3D genome structure data.
• Structured hierarchy of tools and methods for ROI interpretation.

Main Results:

• A comprehensive overview of practical solutions for ROI interpretation using epigenomic data.
• Identification and discussion of leading computational tools and machine learning approaches.
• A hierarchical framework for applying these methods to genome-wide ROIs.

Conclusions:

• Epigenomic data significantly aids in the interpretation of functional genomics findings.
• A structured approach using available tools and methods is crucial for understanding genome-wide ROIs.
• This review serves as a practical guide for researchers in the field.