Recent Advances on the Machine Learning Methods in Identifying DNA Replication Origins in Eukaryotic Genomics

Area of Science:

• Molecular Biology
• Genetics
• Bioinformatics

Background:

• Origins of replication (ORI) are crucial regulatory sites for DNA replication, cell division, and gene expression in all organisms.
• Understanding ORI function is vital for cell cycle research and developing strategies against genetic diseases.
• Accurate ORI identification offers key insights for DNA replication studies and clinical medicine.

Purpose of the Study:

• To review the progress in computational prediction of eukaryotic origins of replication (ORI).
• To highlight the application of machine learning techniques in ORI identification.
• To provide future perspectives on ORI prediction methods.

Main Methods:

• Collection and curation of benchmark datasets for ORI prediction.
• Application of machine learning-based techniques for computational analysis.
• Development and construction of web servers for high-throughput ORI identification.

Main Results:

• Bioinformatics-based methods offer a time-effective and cost-efficient alternative to conventional experiments for ORI identification.
• Machine learning approaches have shown significant promise in accurately predicting eukaryotic ORIs from DNA sequence information.
• The review summarizes current results and discusses the utility of developed web servers.

Conclusions:

• Computational prediction of eukaryotic ORIs using machine learning is a rapidly advancing field.
• These methods provide valuable tools for in-depth study of DNA replication and potential therapeutic targets for genetic defects.
• The review serves as a comprehensive resource for researchers in DNA replication and genetic disease therapy.