Leptospirosis vaccine candidates still need to be identified, which was a challenge. One such candidate, however, is OmpL37, a potential surface-exposed antigen with the highest elastin-binding capacity yet observed, indicating that it likely contributes significantly to host colonization. Cell viability is frequently evaluated using high throughput metabolic viability assays like MTT and MTS. Utilizing genomic, proteomic data, and computational methods, particularly deep learning systems, can be crucial in identifying vaccine targets. A new computational method for identifying and evaluating novel vaccination targets, which paves the way for the creation of a multi-epitope subunit vaccine candidate was using Vax-Elan. In order to uncover prospective vaccine candidates, the system screens genomic and proteomic datasets of multiple diseases, including leptospirosis species, using reverse vaccination and immuno-informatics. It uses supervised machine learning-based methods for vaccine discovery and an immuno-informatics approach. To computationally analyze and assess the pathogenic proteomes that were developed followed by narrowing down proteins that exhibit particular traits in order to rank them as prospective vaccination candidates. In this study, we developed new leptospirosis vaccine targets. Where the protein sequence of ligA [Id-ach98094.1] was extracted from the NCBI protein database. And the predicted amino acid sequence for LigA is a set of 90-amino-acid tandem repeats encoded by a 3,675-bp open reading frame. By using the Vax-Elan server to evaluate important properties, to check the suitability of this protein as a potential vaccine candidate. As per VaxElan, the protein is predicted to be 1 for Target p, if it is a signal peptide ligA is predicted to be a signal peptide and hence scored 1 as being a signal peptide is a criterion for a potential vaccine candidate. In the case of mTP and cTP, VaxElan gives a score of 0 and for 1TP VaxElan gives 0.05 which is followed by various research studies.