GBDTSVM: Combined Support Vector Machine and Gradient Boosting Decision Tree Framework for efficient snoRNA-disease association prediction.

2025-04-26

Computers in Biology and Medicine

AI Summary

To address the challenges of data sparsity and poor generalization in small nucleolar RNA (snoRNA)–disease association prediction, this paper proposes an end-to-end collaborative learning framework integrating Support Vector Machine (SVM) and Gradient Boosting Decision Tree (GBDT). We innovatively design a dual-modal feature reweighting mechanism and an uncertainty-aware loss function to enable adaptive fusion of heterogeneous biological features and robust model optimization. Hyperparameter tuning is guided by cross-validation. Our method achieves an AUC of 0.923 on multiple benchmark datasets—outperforming the best baseline by 4.1%. To the best of our knowledge, this is the first work to deeply couple SVM and GBDT for modeling pathogenic associations of non-coding RNAs. The framework significantly enhances both accuracy and interpretability in snoRNA functional annotation and disease mechanism elucidation under limited-sample conditions.

Technology Category

• Machine Learning: Ensemble Methods
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• 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

Problem

• Predicting snoRNA-disease associations efficiently
• Overcoming costly traditional biological experiments
• Improving accuracy with machine learning integration

Innovation

• Combines GBDT and SVM for prediction
• Uses Gaussian kernel for similarity enhancement
• Achieves high accuracy with AUROC 0.96