ABSTRACT
Candida auris is a kind of fungus that causes severe illness in humans. Candida auris belongs to the Candida genus which is a group of infectious yeast species. Both enzymes Peptidyl-prolyl isomerases (PPIases) and Dihydrofolate Reductase (DHFR) plays an important role in life cycle of Candida auris. Inhibiting activity of both enzymes i.e. PPIases & DHFR disrupts the normal functioning of fungal cell and helps to fight against Candida auris infection. The fungus Candida auris infests on the skin cells and displays aversion to antifungal agents. Molecular docking is a conventional approach used for exploring chemicals as antifungal agents to fight against fungal infections. Exploring vast library of molecules through conventional drug discovery process to discover effective drugs against the resistant strains of fungus is a very difficult process. Hence, there is a need for alternative techniques such as ML to develop drugs against pathogens such as Candida auris. Identifying diseases caused by fungi is often challenging because the fungal pathogens may exist asymptomatically leading to difficulty in tracking the chain of spread, deficiency in availability of tools. Candida auris is one such disease-causing fungus that have been selected for present study. Hence, there is need to develop a robust ML algorithm to create user friendly environment to increase speed and quality of process of molecular docking.
