NERVE 2.0: boosting the new enhanced reverse vaccinology environment via artificial intelligence and a user-friendly web interface

Abstract

Background: Vaccines development in this millennium started by the milestone work on Neisseria meningitidis B, reporting the invention of Reverse Vaccinology (RV), which allows to identify vaccine candidates (VCs) by screening bacterial pathogens genome or proteome through computational analyses. When NERVE (New Enhanced RV Environment), the first RV software integrating tools to perform the selection of VCs, was released, it prompted further development in the field. However, the problem-solving potential of most, if not all, RV programs is still largely unexploited by experimental vaccinologists that impaired by somehow difficult interfaces, requiring bioinformatic skills.

Results: We report here on the development and release of NERVE 2.0 (available at: https://nerve-bio.org ) which keeps the original integrative and modular approach of NERVE, while showing higher predictive performance than its previous version and other web-RV programs (Vaxign and Vaxijen). We renewed some of its modules and added innovative ones, such as Loop-Razor, to recover fragments of promising vaccine candidates or Epitope Prediction for the epitope prediction binding affinities and population coverage. Along with two newly built AI (Artificial Intelligence)-based models: ESPAAN and Virulent. To improve user-friendliness, NERVE was shifted to a tutored, web-based interface, with a noSQL-database to consent the user to submit, obtain and retrieve analysis results at any moment.

Conclusions: With its redesigned and updated environment, NERVE 2.0 allows customisable and refinable bacterial protein vaccine analyses to all different kinds of users.

Keywords: Artificial intelligence; Machine learning; Modular software; Reverse vaccinology; User-friendly website; Vaccine candidates.

Fig. 1

NERVE 2.0 working structure. Bacterial protein sequences are provided as an input FASTA proteome and undergo eight analytical steps: A Subcelloc predicts protein subcellular localization, B Adhesin returns the probability of a protein to be an adhesin, C Tmhelices predicts protein topology, D Loop Razor rescues membrane proteins reduced to their extracellular fragments, E Autoimmunity and Mouse Immunity which find respectively matches between the pathogen under analysis and human or mice proteomes F Conservation which detects conserved proteins between two input bacterial strains, G Virulent to infer presence of virulence factors and H Annotation to predict protein function. Then, the Select module I filters out PVCs, which meet specific requirements. Output results can be downloaded in .json, .csv, or.xlsx format. Epitope prediction J is performed after the Select module. Created with BioRender.com

Fig. 2

ESPAAN confusion matrix. A 2 × 2 matrix has been considered for this binary classification problem (adhesin/non-adhesin), setting PAD (probability of being adhesin) = 0.5 as threshold

Fig. 3

Snapshot taken from the IEDB.org home page. All settings applied to create mhcpep-sapiens are shown. “MHC Restriction” is for MHC class I and II

Fig. 4

Virulent confusion matrix. Similarly to ESPAAN, here is a 2 × 2 matrix considering PVR (probability of being a virulence factor) = 0.50 as threshold

Fig. 5

Snapshot from the NERVE 2.0 homepage, with menu header, main benefits, and the dedicated tutorial video

Fig. 6

Snapshot from NERVE 2.0 website (Create new job section)

Fig. 7

Snapshot from NERVE 2.0 website. Results with PVCs filtered from the proteome of Neisseria meningitidis group B (MC58)

Fig. 8

A detail of Epitope prediction results and TMHMM sequence (at the bottom) of UniprotKB: Q9K0K9 extracted from the proteome of Neisseria meningitidis group B (MC58)

Fig. 9

Epitope prediction results for UniprotKB: P17739 from the proteome of Borrelia burgdorferi (strain ATCC 35210). Here are highlighted the MHC-I and II binders for multiple alleles to identify promiscuous linear epitopes