Building Predictive Models to Efficiently Generate New Nanomaterials with Antimicrobial Activity Book in Scopus uri icon

abstract

  • A current problem related to the treatment of some bacterial diseases is that some bacteria have developed resistance to some of the most common antibiotics. To address this threat, research is being conducted on the generation of new nanomaterials that can inhibit the growth of pathogenic bacteria. The normal process to develop a new nanomaterial and test its effectiveness as an antimicrobial is long and costly, so one alternative is to rely on artificial intelligence tools to make the process more efficient. This chapter briefly describes how a multidisciplinary group has been collaborating in this direction with promising results. Nanomaterials based on the doping of zinc oxide with rare earth elements, such as erbium, ytterbium, cesium, samarium, and neodymium, have been tested and have shown inhibitory properties on Escherichia coli and Staphylococcus aureus. The data generated from these experiments have allowed the training of models based on neural networks that have shown the ability to predict the antimicrobial activity of the material under certain conditions. As more data have been added, the model has been generalized, and it is expected that in the medium term, it will be able to predict with a reasonable accuracy this effect even for materials that are not yet synthesized in the laboratory, thus helping in a better planning of the experiments and obtaining a significant reduction in time and cost of this process. © 2024 selection and editorial matter, Manuel Cebral-Loureda, Elvira G. Rincón-Flores and Gildardo Sanchez-Ante.

publication date

  • January 1, 2023