A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ojeda, Sebastian, Velasquez, Rafael, Aparicio, Nicolás, Puentes, Juanita, Cárdenas, Paula, Andrade, Nicolás, González, Gabriel, Rincón, Sergio, Muñoz-Camargo, Carolina, Arbeláez, Pablo
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914142104846336
author Ojeda, Sebastian
Velasquez, Rafael
Aparicio, Nicolás
Puentes, Juanita
Cárdenas, Paula
Andrade, Nicolás
González, Gabriel
Rincón, Sergio
Muñoz-Camargo, Carolina
Arbeláez, Pablo
author_facet Ojeda, Sebastian
Velasquez, Rafael
Aparicio, Nicolás
Puentes, Juanita
Cárdenas, Paula
Andrade, Nicolás
González, Gabriel
Rincón, Sergio
Muñoz-Camargo, Carolina
Arbeláez, Pablo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04814
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification
Ojeda, Sebastian
Velasquez, Rafael
Aparicio, Nicolás
Puentes, Juanita
Cárdenas, Paula
Andrade, Nicolás
González, Gabriel
Rincón, Sergio
Muñoz-Camargo, Carolina
Arbeláez, Pablo
Machine Learning
Artificial Intelligence
Biomolecules
68T07, 62H30, 62P10
I.2.6; I.2.1; I.5.1; I.5.2
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.
title A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification
topic Machine Learning
Artificial Intelligence
Biomolecules
68T07, 62H30, 62P10
I.2.6; I.2.1; I.5.1; I.5.2
url https://arxiv.org/abs/2511.04814