Topology-enhanced machine learning model (Top-ML) for anticancer peptide prediction

2024-07-12

arXiv.org

AI Summary

Current anticancer peptide (ACP) identification methods suffer from weak sequence feature representation and poor interpretability, hindering efficient screening. To address this, we propose a novel topological representation framework for peptide sequences, introducing— for the first time—“connectivity relation vectors” and “spectral topological descriptors” that jointly encode local connectivity patterns and global spectral properties. This yields a lightweight, highly interpretable machine learning model. By integrating topological feature engineering with an Extra-Trees ensemble classifier, our approach achieves state-of-the-art (SOTA) or top-tier performance on the AntiCP 2.0 and mACPpred 2.0 benchmarks, significantly improving both classification accuracy and generalization capability. Crucially, the model’s design ensures mechanistic interpretability without sacrificing predictive power. Our work establishes a new paradigm for ACP discovery that simultaneously delivers high performance and biologically meaningful insights.

Technology Category

• Machine Learning: Representation Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Recently, therapeutic peptides have demonstrated great promise for cancer treatment. To explore powerful anticancer peptides, artificial intelligence (AI)-based approaches have been developed to systematically screen potential candidates. However, the lack of efficient featurization of peptides has become a bottleneck for these machine-learning models. In this paper, we propose a topology-enhanced machine learning model (Top-ML) for anticancer peptides prediction. Our Top-ML employs peptide topological features derived from its sequence"connection"information characterized by vector and spectral descriptors. Our Top-ML model, employing an Extra-Trees classifier, has been validated on the AntiCP 2.0 and mACPpred 2.0 benchmark datasets, achieving state-of-the-art performance or results comparable to existing deep learning models, while providing greater interpretability. Our results highlight the potential of leveraging novel topology-based featurization to accelerate the identification of anticancer peptides.

Problem

• Cancer Peptide Identification
• Feature Understanding
• Efficient Model

Innovation

• Top-ML
• Cancer-fighting Peptides
• Transparent Prediction Logic