A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification
This work addresses the need for a reproducible evaluation framework to accelerate AI-driven discovery of antimicrobial peptides, which is crucial for combating antimicrobial resistance.
The authors tackled the problem of fragmented datasets and inconsistent annotations in antimicrobial peptide research by creating ESCAPE, a standardized benchmark integrating over 80,000 peptides, and proposed a transformer-based model that achieved a 2.56% relative improvement in mean Average Precision over the second-best method.
Antimicrobial peptides have emerged as promising molecules to combat antimicrobial resistance. However, fragmented datasets, inconsistent annotations, and the lack of standardized benchmarks hinder computational approaches and slow down the discovery of new candidates. To address these challenges, we present the Expanded Standardized Collection for Antimicrobial Peptide Evaluation (ESCAPE), an experimental framework integrating over 80.000 peptides from 27 validated repositories. Our dataset separates antimicrobial peptides from negative sequences and incorporates their functional annotations into a biologically coherent multilabel hierarchy, capturing activities across antibacterial, antifungal, antiviral, and antiparasitic classes. Building on ESCAPE, we propose a transformer-based model that leverages sequence and structural information to predict multiple functional activities of peptides. Our method achieves up to a 2.56% relative average improvement in mean Average Precision over the second-best method adapted for this task, establishing a new state-of-the-art multilabel peptide classification. ESCAPE provides a comprehensive and reproducible evaluation framework to advance AI-driven antimicrobial peptide research.