A descriptor-free machine learning framework to improve antigen discovery for bacterial pathogens

• Published in: PloS one Vol. 20; no. 6; p. e0323895
• Main Authors: Podda, Marco, Savojardo, Castrense, Luigi Martelli, Pier, Casadio, Rita, Sîrbu, Alina, Priami, Corrado, Brozzi, Alessandro
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 05.06.2025; Public Library of Science (PLoS)
• Subjects: Amino acid sequence; Amino acids; Analysis; Antigens; Antigens - immunology; Artificial neural networks; Bacterial Infections - immunology; Bacterial Infections - prevention & control; Bacterial Infections - therapy; Bacterial Vaccines - immunology; Bioinformatics; Biology and Life Sciences; Clinical trials; Computational linguistics; Computer and Information Sciences; Computer applications; Computer Simulation; Dosage and administration; Drug Evaluation, Preclinical - methods; Engineering and Technology; Ethics; Experiments; Humans; Immune response; In vivo methods and tests; Laboratories; Language processing; Learning algorithms; Machine Learning; Medical research; Medicine and health sciences; Methods; Natural language interfaces; Neural networks; Pathogens; Protective Agents - therapeutic use; Proteins; Proteome - metabolism; Proteomes; Representations; Research and Analysis Methods; Subject Headings; Testing; Vaccine Development - methods; Vaccines; Vaccines, Subunit - therapeutic use; Vaccinology; Italy
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0323895

Identifying protective antigens (PAs), i.e., targets for bacterial vaccines, is challenging as conducting in-vivo tests at the proteome scale is impractical. Reverse Vaccinology (RV) aids in narrowing down the pool of candidates through computational screening of proteomes. Within RV, one prominent approach is to train Machine Learning (ML) models to classify PAs. These models can be used to predict unseen protein sequences and assist researchers in selecting promising candidates. Traditionally, proteins are fed into these models as vectors of biological and physico-chemical descriptors derived from their residue sequences. However, this method relies on multiple third-party software packages, which may be unreliable, difficult to use, or no longer maintained. Furthermore, selecting descriptors is susceptible to biases. Hence, Protein Sequence Embeddings (PSEs)—high-dimensional vectorial representations of protein sequences obtained from pretrained deep neural networks—have emerged as an alternative to descriptors, offering data-driven feature extraction and a streamlined computational pipeline. We introduce PSEs as a descriptor-free representation of protein sequences for ML in RV. We conducted a thorough comparison of PSE-based and descriptor-based pipelines for PA classification across 10 bacterial species evaluated independently. Our results show that the PSE-based pipeline, which leverages the FAIR ESM-2 protein language model, outperformed the descriptor-based pipeline in 9 out of 10 species, with a mean Area Under the Receiver Operating Characteristics curve (AUROC) of 0.875 versus 0.855. Additionally, it achieved superior performance on the iBPA benchmark (0.86 AUROC vs. 0.82) compared to other methods in the literature. Lastly, we applied the pipeline to rank unseen proteomes based on protective potential to guide candidate selection for pre-clinical testing. Compared to the standard RV practice of ranking candidates according to their biological descriptors, our approach reduces the number of pre-clinical tests needed to identify PAs by up to 83% on average.