PDeepPP:A Deep learning framework with Pretrained Protein language for peptide classification

2025-02-21

AI Summary

Experimental identification of post-translational modification (PTM) sites and classification of bioactive peptides (BPs) suffer from high costs, while existing computational methods exhibit poor generalizability and inadequate sequence modeling capacity. Method: We propose a multi-task deep learning framework that integrates pretrained protein language models (e.g., ESM) with a parallel Transformer-CNN architecture. This is the first work to hybridize multi-head self-attention and 1D convolutional layers for peptide functional prediction, enabling unified modeling of 33 heterogeneous PTM/BP tasks within a single model. Contribution/Results: Through large-scale peptide data fine-tuning and joint multi-task training, our model achieves state-of-the-art performance on 25 tasks—outperforming leading tools significantly. It demonstrates high accuracy, strong generalizability across diverse peptide functions, and scalability to new tasks, establishing an efficient computational paradigm for large-scale peptide functional annotation and de novo peptide discovery.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Multi-modal Vision

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Protein post-translational modifications (PTMs) and bioactive peptides (BPs) play critical roles in various biological processes and have significant therapeutic potential. However, identifying PTM sites and bioactive peptides through experimental methods is often labor-intensive, costly, and time-consuming. As a result, computational tools, particularly those based on deep learning, have become effective solutions for predicting PTM sites and peptide bioactivity. Despite progress in this field, existing methods still struggle with the complexity of protein sequences and the challenge of requiring high-quality predictions across diverse datasets. To address these issues, we propose a deep learning framework that integrates pretrained protein language models with a neural network combining transformer and CNN for peptide classification. By leveraging the ability of pretrained models to capture complex relationships within protein sequences, combined with the predictive power of parallel networks, our approach improves feature extraction while enhancing prediction accuracy. This framework was applied to multiple tasks involving PTM site and bioactive peptide prediction, utilizing large-scale datasets to enhance the model's robustness. In the comparison across 33 tasks, the model achieved state-of-the-art (SOTA) performance in 25 of them, surpassing existing methods and demonstrating its versatility across different datasets. Our results suggest that this approach provides a scalable and effective solution for large-scale peptide discovery and PTM analysis, paving the way for more efficient peptide classification and functional annotation.

Problem

• Predicts PTM sites and bioactive peptides
• Leverages pretrained protein language models
• Enhances peptide classification accuracy

Innovation

• Integrates pretrained protein language models
• Combines transformer and CNN networks
• Enhances peptide classification accuracy