Artificial Neural Networks for the Resolution of Dopamine and Serotonin Complex Mixtures Using a Graphene-Modified Carbon Electrode

Machine learning toward high-performance electrochemical sensors

The so-coined fourth paradigm in science has reached the sensing area, with the use of machine learning (ML) toward data-driven improvements in sensitivity, reproducibility, and accuracy, along with the determination of multiple targets from a single measurement using multi-output regression models. Particularly, the use of supervised ML models trained on large data sets produced by electrical and electrochemical bio/sensors has emerged as an impacting trend in the literature by allowing accurate analyses even in the presence of usual issues such as electrode fouling, poor signal-to-noise ratio, chemical interferences, and matrix effects. In this trend article, apart from an outlook for the coming years, we present examples from the literature that demonstrate how helpful ML algorithms can be for dispensing the adoption of experimental methods to address the aforesaid interfering issues, ultimately contributing to translate testing technologies into on-site, practical, and daily applications.

Application and Progress of Chemometrics in Voltammetric Biosensing

The voltammetric electrochemical sensing method combined with biosensors and multi-sensor systems can quickly, accurately, and reliably analyze the concentration of the main analyte and the overall characteristics of complex samples. Simultaneously, the high-dimensional voltammogram contains the rich electrochemical features of the detected substances. Chemometric methods are important tools for mining valuable information from voltammetric data. Chemometrics can aid voltammetric biosensor calibration and multi-element detection in complex matrix conditions. This review introduces the voltammetric analysis techniques commonly used in the research of voltammetric biosensor and electronic tongues. Then, the research on optimizing voltammetric biosensor results using classical chemometrics is summarized. At the same time, the incorporation of machine learning and deep learning has brought new opportunities to further improve the detection performance of biosensors in complex samples. Finally, smartphones connected with miniaturized voltammetric biosensors and chemometric methods provide a high-quality portable analysis platform that shows great potential in point-of-care testing.

Machine learning and chemometrics for electrochemical sensors: moving forward to the future of analytical chemistry

Electrochemical sensors and biosensors have been successfully used in a wide range of applications, but systematic optimization and nonlinear relationships have been compromised for electrode fabrication and data analysis. Machine learning and experimental designs are chemometric tools that have been proved to be useful in method development and data analysis. This minireview summarizes recent applications of machine learning and experimental designs in electroanalytical chemistry. First, experimental designs, e.g., full factorial, central composite, and Box-Behnken are discussed as systematic approaches to optimize electrode fabrication to consider the effects from individual variables and their interactions. Then, the principles of machine learning algorithms, including linear and logistic regressions, neural network, and support vector machine, are introduced. These machine learning models have been implemented to extract complex relationships between chemical structures and their electrochemical properties and to analyze complicated electrochemical data to improve calibration and analyte classification, such as in electronic tongues. Lastly, the future of machine learning and experimental designs in electrochemical sensors is outlined. These chemometric strategies will accelerate the development and enhance the performance of electrochemical devices for point-of-care diagnostics and commercialization.

Graphene for the Building of Electroanalytical Enzyme-Based Biosensors. Application to the Inhibitory Detection of Emerging Pollutants

Graphene and its derivates offer a wide range of possibilities in the electroanalysis field, mainly owing to their biocompatibility, low-cost, and easy tuning. This work reports the development of an enzymatic biosensor using reduced graphene oxide (RGO) as a key nanomaterial for the detection of contaminants of emerging concern (CECs). RGO was obtained from the electrochemical reduction of graphene oxide (GO), an intermediate previously synthesized in the laboratory by a wet chemistry top-down approach. The extensive characterization of this material was carried out to evaluate its proper inclusion in the biosensor arrangement. The results demonstrated the presence of GO or RGO and their correct integration on the sensor surface. The detection of CECs was carried out by modifying the graphene platform with a laccase enzyme, turning the sensor into a more selective and sensitive device. Laccase was linked covalently to RGO using the remaining carboxylic groups of the reduction step and the carbodiimide reaction. After the calibration and characterization of the biosensor versus catechol, a standard laccase substrate, EDTA and benzoic acid were detected satisfactorily as inhibiting agents of the enzyme catalysis obtaining inhibition constants for EDTA and benzoic acid of 25 and 17 mmol·L⁻¹, respectively, and a maximum inhibition percentage of the 25% for the EDTA and 60% for the benzoic acid.

Determination of Chemical Oxygen Demand (COD) Using Nanoparticle-Modified Voltammetric Sensors and Electronic Tongue Principles

This manuscript reports the use of nanoparticle-modified voltammetric sensors for the rapid and green determination of chemical oxygen demand in river waters and waters from agricultural waste. Four different variants of modified electrodes have been prepared: CuO nanoparticles electrogenerated over Cu and covered with Nafion film (CuO/Cu-Nf), and graphite–epoxy composites modified with Cu, CuO, and Cu–Ni alloy nanoparticles. The response features of these electrodes were assessed by calibrating them vs. glucose, glycine, ethyleneglycol, and hydrogenphtalate in alkaline media, as samples providing different difficulty in their (bio)degradation characteristics. The most sensitive electrode was demonstrated to be the (CuO/Cu-Nf) electrode, with an LOD of 12.3 mg O2·L−1. The joint information provided by the sensor array showed the ability of estimating both the organic load and the type of sample in terms of difficulty of degradation, in what can be named an intelligent sensor assembly.

Modification of electrodes with N-and S-doped carbon dots. Evaluation of the electrochemical response

Nitrogen and sulphur-doped Carbons Dots (N-CDs and S-CDs) were synthesized by a hydrothermal method and incorporated as surface electrode modifiers to evaluate their properties for electrochemical sensing. The first task was to characterize the synthesized materials, for which different spectroscopies, scanning microscopes, mass spectrometry and elementary analysis were performed. Next, a glassy carbon electrode (GCE) was surface-modified with the doped CDs and applied to check the electrochemical signal of different organic compounds corresponding to different families. Water solubility of the doped carbon dots forced us to incorporate them in a graphite-polystyrene ink to complete the modification of electrodes. This modification needed a first activation to obtain a properly conductive surface. The organic compounds examined were salicylic acid, cysteine and ascorbic acid. The modified GCEs exhibited an enhanced sensitivity, probably caused by the increase of active surface, but in addition, signals of salicylic acid were shifted ca. 200 mV to lower potentials, what is a proof of the increase of the heterogeneous electron transfer rate, and a demonstration of an enhanced catalytic response.