Prediction of the Antibacterial Activity of the Green Synthesized Silver Nanoparticles against Gram Negative and Positive Bacteria by using Machine Learning Algorithms

Abstract

With the appearance and growth of microbial organisms resistant to various antibiotics, as well as the need to reduce the cost of care of health, the production of antimicrobials at lower costs has become an inescapable necessity for today’s human societies. Recently, the interdisciplinary field of nanotechnology has developed widely. One of the applications of nanobiotechnology is the use of silver nanoparticles (AgNPs) for new solutions in the treatment of microbial infections. AgNPs have unique properties which help in molecular diagnostics, therapies, and also in devices that are used in several medical procedures. In this field, machine learning algorithms have been used with hopeful results. One of the branches of artificial intelligence (AI) is machine learning (ML) that focuses on data and shows the power of the data. Machine learning techniques are taking considerable attention because of their obvious successes in a broad range of predictive tasks. In this work, we studied machine learning technique to predict the antibacterial activity of AgNPs against Escherichia coli, Pseudomonas aeruginosa, Staphylococcus aureus, and Klebsiella pneumoniae. Here, we reviewed 100 articles for completing the data, highlighting the recently used different plants for the synthesis of highly efficient antimicrobial green AgNPs, which consist of key experimental conditions (amount of plant extract, volume of plant extract, volume of solvent, volume of AgNO3 solution, reaction temperature, reaction time, concentration of precursors, and nanoparticle size). The results showed that nanoparticles size and concentration of AgNPs are key factors in predicting the antibacterial effect of AgNPs.