Empirical Comparison and Analysis of Artificial Intelligence-Based Methods for Identifying Phosphorylation Sites of SARS-CoV-2 Infection
2024

AI Methods for Finding Phosphorylation Sites in SARS-CoV-2

publication Evidence: moderate

Author Information

Author(s): Hongyan Lai, Tao Zhu, Sijia Xie, Xinwei Luo, Feitong Hong, Diyu Luo, Fuying Dao, Hao Lin, Kunxian Shu, Hao Lv

Primary Institution: Chongqing University of Posts and Telecommunications

Hypothesis

The precise identification of phosphorylation sites in host cells infected with SARS-CoV-2 will help investigate potential antiviral responses and mechanisms.

Conclusion

This review highlights various AI-based methods for accurately identifying phosphorylation sites in SARS-CoV-2-infected cells, which could aid in developing antiviral therapies.

Supporting Evidence

  • Phosphorylation is crucial for understanding how SARS-CoV-2 interacts with host cells.
  • Numerous computational tools have been developed to predict phosphorylation sites.
  • Machine learning and deep learning methods are highlighted for their effectiveness in this area.
  • Benchmark datasets are essential for training and validating these computational models.

Takeaway

Scientists are using computers to find important spots on proteins that change when people get infected with a virus called SARS-CoV-2, which can help create new medicines.

Methodology

The review summarizes various computational tools and methods for predicting phosphorylation sites, including machine learning and deep learning approaches.

Limitations

Current methods may not fully capture complex interactions due to reliance on specific datasets and feature engineering.

Digital Object Identifier (DOI)

10.3390/ijms252413674

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication