A Machine Learning Tool to Predict the Antibacterial Capacity of Nanoparticles

Abstract

The emergence and rapid spread of multidrug-resistant bacteria strains are a public health concern. This emergence is caused by the overuse and misuse of antibiotics leading to the evolution of antibiotic-resistant strains. Nanoparticles (NPs) are objects with all three external dimensions in the nanoscale that varies from 1 to 100 nm. Research on NPs with enhanced antimicrobial activity as alternatives to antibiotics has grown due to the increased incidence of nosocomial and community acquired infections caused by pathogens. Machine learning (ML) tools have been used in the field of nanoinformatics with promising results. As a consequence of evident achievements on a wide range of predictive tasks, ML techniques are attracting significant interest across a variety of stakeholders. In this article, we present an ML tool that successfully predicts the antibacterial capacity of NPs while the model’s validation demonstrates encouraging results (R2 = 0.78). The data were compiled after a literature review of 60 articles and consist of key physico-chemical (p-chem) properties and experimental conditions (exposure variables and bacterial clustering) from in vitro studies. Following data homogenization and pre-processing, we trained various regression algorithms and we validated them using diverse performance metrics. Finally, an important attribute evaluation, which ranks the attributes that are most important in predicting the outcome, was performed. The attribute importance revealed that NP core size, the exposure dose, and the species of bacterium are key variables in predicting the antibacterial effect of NPs. This tool assists various stakeholders and scientists in predicting the antibacterial effects of NPs based on their p-chem properties and diverse exposure settings. This concept also aids the safe-by-design paradigm by incorporating functionality tools.

Data Shepherding in Nanotechnology: An Antimicrobial Functionality Data Capture Template

“…Standard processes should be followed while creating reliable datasets, datasets should be sufficiently large and values should be appropriate for in silico usage. There is still a long way to go to analytically address the key antibacterial properties of NMs that characterize their efficacy without a consensus on standard characterization methods, or reference microorganisms and standardized assays [23]. In addition to the standardization of methods, further harmonized outlines should be developed on how to report the p-chem properties of NMs or experimental environments and how to make these measurements analogous.…”

“…Among the diverse data that are available, we did not find any dataset containing antimicrobial capacity data, signifying the importance of initiating the capturing of these data in a systematic way. For the moment, antimicrobial data is not yet in a format that is suitable for reusable purposes (available only scattered in literature), and tremendous efforts are needed to be put into extracting data (Mirzaei et al [23]).…”

“…Unfortunately, the antimicrobial data of NMs are not as readily available as data related to toxicological endpoints. In a study conducted by Mirzaei et al [23], information from studies was manually extracted following a literature review regarding NMs that were introduced to diverse bacteria to measure the NMs' antimicrobial capacity. The aforementioned study revealed that very little information is included in the original studies, specifically the characterization data that reveal the key properties that enhance the antimicrobial capacity of NMs.…”

Biomaterials by design: Harnessing data for future development

“…With a diverse selection of nanoparticles created, it is then possible to probe for biological functionalities with the assistance of machine learning. Metal nanoparticles were investigated to determine and predict the antibacterial properties, with nanoparticle core size being the key physicochemical feature [ 122 ]. Gold nanoparticles were also monitored for their fate in vivo by the combination of the tools of mass spectroscopy and supervised machine learning [ 59 ].…”

A Supervised Machine-Learning Prediction of Textile’s Antimicrobial Capacity Coated with Nanomaterials

“…There are many studies that have employed ML models to primarily forecast NM's safety and toxicity [69][70][71]. Mirzaei, et al [72] developed a tool to predict the antimicrobial capacity expressed as zone of inhibition of various NMs using regression models. The authors used data from in vitro experimental set-ups.…”