Artificial Intelligence in Post-translational Modification Site Prediction: Progress and Future Perspectives.
TL;DR
A comprehensive and up-to-date overview of AI-driven PTM site prediction across more than ten PTM classes, covering single-PTM site prediction, multiple-PTM site prediction, inter-site crosstalk prediction, and functional prediction of modification sites is provided.
Abstract
Post-translational modifications (PTMs) are pivotal in modulating protein function and cellular processes. However, experimental identification of PTM sites remains costly and labor-intensive. Recent advances in artificial intelligence (AI) have enabled accurate and scalable in silico PTM site prediction from large-scale proteomic data. In this review, we provide a comprehensive and up-to-date overview of AI-driven PTM site prediction across more than ten PTM classes, covering single-PTM site prediction, multiple-PTM site prediction, inter-site crosstalk prediction, and functional prediction of modification sites. We systematically analyze and compare key AI frameworks, from conventional machine learning to deep learning, and summarize representative tools. We also identify key challenges and propose future directions for improvement. To facilitate application and ongoing progress, we provide practical guidelines for method selection and have established a dedicated website, which serves as a community benchmarking resource for the development of PTM site prediction tools. This website will be regularly updated with emerging prediction tools. By integrating comprehensive literature analysis with a dynamic online resource, we aim to provide a reliable foundation for understanding current capabilities and guiding the future development of PTM site prediction tools, thereby promoting the integration of AI into practical biomedical research applications.