Benchmarking of the Vaxi-DL pathogen models with other existing PVC prediction tools. The four pathogen models of the Vaxi-DL namely bacterial, protozoan, and viral were benchmarked against known PVC prediction tools such as Vaxign-ML [1] and VaxiJen [2]. The independent datasets used for benchmarking consisted of 57 known bacterial antigens (25 Gram+ and 32 Gram-), 14 protozoan, 7 viral antigens that were manually curated.
The dataset used for benchmarking consisted of 7 known viral PVCs that were manually curated.
References
Ong, E., Wang, H., Wong, M.U., Seetharaman, M., Valdez, N. and He, Y., 2020. Vaxign-ML: supervised machine learning reverse vaccinology model for improved prediction of bacterial protective antigens. Bioinformatics, 36(10), pp.3185-3191.
Doytchinova, I.A. and Flower, D.R., 2007. VaxiJen: a server for prediction of protective antigens, tumour antigens and subunit vaccines. BMC bioinformatics, 8(1), p.4.