iORI-ENST: identifying origin of replication sites based on elastic net and stacking learning

Area of Science:

• Genomics
• Molecular Biology
• Bioinformatics

Background:

• DNA replication is fundamental to inheritance and cell division.
• Accurate identification of replication origins (ORIs) is crucial for understanding gene expression regulation and genetic diseases.

Purpose of the Study:

• To develop a novel, feasible, and powerful computational model (iORI-ENST) for identifying DNA replication origins (ORIs).

Main Methods:

• Feature extraction using mono-nucleotide binary encoding and dinucleotide-based spatial autocorrelation.
• Feature selection via elastic net.
• Prediction using a stacking ensemble of random forest, adaboost, gradient boosting decision tree, extra trees, and support vector machine.

Main Results:

• Achieved accuracies of 91.41% and 95.07% on benchmark datasets.
• Validated model transferability and performance on an independent dataset with 91.10% accuracy.
• Outperformed state-of-the-art methods in ORI identification.

Conclusions:

• The iORI-ENST model is a feasible, effective, and powerful tool for identifying DNA replication origins.
• The model aids in understanding gene expression regulation and has implications for treating genetic diseases.