VacSol-ML Logo

Study Overview

The curated, machine-learning-ready benchmark dataset of VacSol-ML(ESKAPE), containing protective vaccine antigens against ESKAPE pathogens, the leading cause of hospital-acquired and nosocomial infections worldwide.

The dataset includes protective and non-protective proteins annotated with over 3,650 biological and physicochemical features, enabling robust ML model development in reverse vaccinology.

Dataset Overview

Target Pathogens The ESKAPE family, comprising Enterococcus faecium, Staphylococcus aureus, Klebsiella pneumoniae, Acinetobacter baumannii, Pseudomonas aeruginosa, and Enterobacter spp.
Total Samples 412 protein sequences
Features 3,650 descriptors
Label Final_predictions

Feature Composition

Publication

VacSol-ML (ESKAPE): Machine learning empowering vaccine antigen prediction for ESKAPE pathogens

Samavi Nasir, Farha Anwer, Zaara Ishaq, Muhammad Tariq Saeed, Amjad Ali

Vaccine, 2024, Volume 42, Issue 22, Article 126204

https://doi.org/10.1016/j.vaccine.2024.126204

Please cite this article when using the VacSol-ML (ESKAPE) dataset.