Leveraging machine learning has been shown to improve the accuracy of structure-based virtual screening. Furthermore, a tremendous amount of empirical data is publicly available, which further enhances the performance of the machine learning approach. In this proof-of-concept study, the 3CL^pro enzyme of SARS-CoV-2 was used. Structure-based virtual screening relies heavily on scoring functions. It is widely accepted that target-specific scoring functions may perform more effectively than universal scoring functions in real-world drug research and development processes. It would be beneficial to drug discovery to develop a method that can effectively build target-specific scoring functions. In the current study, the bindingDB database was used to retrieve experimental data. Smina was utilized to generate protein-ligand complexes for the extraction of InteractionFingerPrint (IFP) and SimpleInteractionFingerPrint SIFP fingerprints via the open drug discovery tool (oddt). The present study found that randomforestClassifier and randomforestRegressor performed well when used with the above fingerprints along the Molecular ACCess System (MACCS), Extended Connectivity Fingerprint (ECFP4), and ECFP6. It was found that the area under the precision-recall curve was 0.80, which is considered a satisfactory level of accuracy. In addition, our enrichment factor analysis indicated that our trained scoring function ranked molecules correctly compared to smina’s generic scoring function. Further molecular dynamics simulations indicated that the top-ranked molecules identified by our developed scoring function were highly stable in the active site, supporting the validity of our developed process. This research may provide a template for developing target-specific scoring functions against specific enzyme targets.

Usutu virus is an emerging mosquito-borne flavivirus with an expanding geographic distribution and increasing public health relevance, yet no licensed vaccine is currently available. This study used an integrated reverse vaccinology strategy to identify conserved immunogenic regions from the Envelope protein and NS5 protein, and construct a multi-epitope vaccine. Following sequential computational screening, the retained T-cell and B-cell epitopes satisfied the predefined selection criteria, while selected T-cell epitopes achieved an estimated 96.41% global population coverage. The final vaccine consisted of 240 amino acids and incorporated an adjuvant together with peptide linkers. Computational characterization indicated favorable physicochemical features and a refined three-dimensional model with improved stereochemical characteristics. Receptor-binding analyses predicted favorable interactions with TLR2 and TLR4, producing weighted docking scores of −1326.1 and −1230.2, respectively. Molecular dynamics simulation further characterized the temporal behavior of the vaccine–TLR2 complex, while MM-GBSA analysis yielded an estimated binding energy of −74.78 kcal/mol. C-ImmSim predicted enhanced humoral and cellular immune-response patterns following repeated antigen administration, including increased simulated antibody levels and changes in immune-cell populations. All findings in this study are based on in silico analyses and represent computational predictions rather than experimentally confirmed results. Further experimental validation is required to verify the predicted properties, immunogenicity, and protective potential of the proposed vaccine candidate.