A review of deep learning applications in human genomics using next-generation sequencing data

Area of Science:

• Genomics
• Bioinformatics
• Computational Biology

Background:

• Human genomics generates massive datasets due to high-throughput technologies.
• Extracting meaningful insights from this data requires advanced analytical approaches.
• Artificial intelligence, particularly deep learning, offers powerful tools for genomic data analysis.

Purpose of the Study:

• To review the development and application of deep learning methods in human genomics.
• To identify both well-established and emerging areas of deep learning application in genomics.
• To provide guidance for scientists on utilizing deep learning for genomic data analysis.

Main Methods:

• Literature review of deep learning applications in human genomics.
• Assessment of deep learning techniques across various genomic subfields.
• Discussion of underlying deep learning algorithms and genomic tools.

Main Results:

• Deep learning is instrumental in extracting knowledge and patterns from large-scale genomic data.
• The review covers diverse applications, highlighting both over- and under-charted areas.
• Key deep learning algorithms and their genomic tool implementations are briefly discussed.

Conclusions:

• This review offers timely insights for biotechnology and genomic scientists.
• It provides a framework for understanding when and how to apply deep learning to human genomic data.
• The effective use of deep learning can accelerate discoveries in human genomics.