Excitation-emission fluorescence matrix acquired from glutathione capped CdSeS/ZnS quantum dots in combination with chemometric tools for pattern-based sensing of neurotransmitters

Deep convolutional neural network-based 3D fluorescence sensor array for sugar identification in serum based on the oxidase-mimicking property of CuO nanoparticles

Developing sensor arrays capturing comprehensive fluorescence (FL) spectra from a single probe is crucial for understanding sugar structures with very high similarity in biofluids. Therefore, the analysis of highly similar sugar' structures in biofluids based on the entire FL of a single nanozyme probe needs more concern, which makes the development of novel alternative approaches highly wanted for biomedical and other applications. Herein, a well-designed deep learning model with intrinsic information of 3D FL of CuO nanoparticles (NPs)' oxidase-like activity was developed to classify and predict the concentration of a group of sugars with very similar chemical structures in different media. The findings presented that the overall accuracy of the developed model in classifying the nine selected sugars was (99-100 %), which prompted us to transfer the developed model to predict the concentration of the selected sugars at a concentration range of (1-100 μM). The transferred model also gave excellent results (R2 = 97-100 %). Therefore, the model was extended to other more complex applications, namely the identification of mixtures of sugars in serum and the detection of polysaccharides in different media such as serum and lake water. Notably, LOD for fructose was determined at 4.23 nM, marking a 120-fold decrease compared to previous studies. Our developed model was also compared with other deep learning-based models, and the results have demonstrated remarkable progress. Moreover, the identification of other possible coexisting interference substances in lake water samples was considered. This work marks a significant advancement, opening avenues for the widespread application of sensor arrays integrating nanozymes and deep learning techniques in biomedical and other diverse fields.

Identification and Removal of Pollen Spectral Interference in the Classification of Hazardous Substances Based on Excitation Emission Matrix Fluorescence Spectroscopy

Sensitively detecting hazardous and suspected bioaerosols is crucial for safeguarding public health. The potential impact of pollen on identifying bacterial species through fluorescence spectra should not be overlooked. Before the analysis, the spectrum underwent preprocessing steps, including normalization, multivariate scattering correction, and Savitzky-Golay smoothing. Additionally, the spectrum was transformed using difference, standard normal variable, and fast Fourier transform techniques. A random forest algorithm was employed for the classification and identification of 31 different types of samples. The fast Fourier transform improved the classification accuracy of the sample excitation-emission matrix fluorescence spectrum data by 9.2%, resulting in an accuracy of 89.24%. The harmful substances, including Staphylococcus aureus, ricin, beta-bungarotoxin, and Staphylococcal enterotoxin B, were clearly distinguished. The spectral data transformation and classification algorithm effectively eliminated the interference of pollen on other components. Furthermore, a classification and recognition model based on spectral feature transformation was established, demonstrating excellent application potential in detecting hazardous substances and protecting public health. This study provided a solid foundation for the application of rapid detection methods for harmful bioaerosols.

Quantum dots-based "chemical tongue" for the discrimination of short-length Aβ peptides

A "chemical tongue" is proposed based on thiomalic acid-capped quantum dots (QDs) with signal enrichment provided by excitation-emission matrix (EEM) fluorescence spectroscopy for the determination of close structural analogs-short-length amyloid β (Aβ) peptides related to Alzheimer's disease. Excellent discrimination is obtained by principal component analysis (PCA) for seven derivatives: Aβ1-16, Aβ4-16, Aβ4-9, Aβ5-16, Aβ5-12, Aβ5-9, Aβ12-16. Detection of Aβ4-16, Aβ4-16, and Aβ5-9 in binary and ternary mixtures performed by QDs-based chemical tongue using partial least squares-discriminant analysis (PLS-DA) provided perfect 100% accuracy for the two studied peptides (Aβ4-16 and Aβ4-16), while for the third one (Aβ5-9) it was slightly lower (97.9%). Successful detection of Aβ4-16 at 1 pmol/mL (1.6 ng/mL) suggests that the detection limit of the proposed method for short-length Aβ peptides can span nanomolar concentrations. This result is highly promising for the development of simple and efficient methods for sequence recognition in short-length peptides and better understanding of mechanisms at the QD-analyte interface.

Kinetic Determination of Acetylsalicylic Acid Using a CdTe/AgInS2 Photoluminescence Probe and Different Chemometric Models

The combination of multiple quantum dots (QDs) in a multi-emitter nanoprobe can be envisaged as a promising sensing scheme, as it enables obtaining a collective response of individual emitters towards a given analyte and allows for achieving specific analyte-response profiles. The processing of these profiles using adequate chemometric methods empowers a more sensitive, reliable and selective determination of the target analyte. In this work, we developed a kinetic fluorometric method consisting of a dual CdTe/AgInS₂ quantum dots photoluminescence probe for the determination of acetylsalicylic acid (ASA). The fluorometric response was acquired as second-order time-based excitation/emission matrices that were subsequently processed using chemometric methods seeking to assure the second-order advantage. The data obtained in this work are considered second-order data as they have a three-dimensional size, I × J × K (where I represents the samples' number, J the fluorescence emission wavelength while K represents the time). In order to select the most adequate chemometric method regarding the obtained data structure, different chemometric models were tested, namely unfolded partial least squares (U-PLS), N-way partial least squares (N-PLS), multilayer feed-forward neural networks (MLF-NNs) and radial basis function neural networks (RBF-NNs).

Feature Selection Assists BLSTM for the Ultrasensitive Detection of Bioflavonoids in Different Biological Matrices Based on the 3D Fluorescence Spectra of Gold Nanoclusters

Rapid and on-site qualitative and quantitative analysis of small molecules (including bioflavonoids) in biofluids are of great importance in biomedical applications. Herein, we have developed two deep learning models based on the 3D fluorescence spectra of gold nanoclusters as a single probe for rapid qualitative and quantitative analysis of eight bioflavonoids in serum. The results proved the efficiency and stability of the random forest-bidirectional long short-term memory (RF-BLSTM) model, which was used only with the most important features after deleting the unimportant features that might hinder the performance of the model in identifying the selected bioflavonoids in serum at very low concentrations. The optimized model achieves excellent overall accuracy (98-100%) in the qualitative analysis of the selected bioflavonoids. Next, the optimized model was transferred to quantify the selected bioflavonoids in serum at nanoscale concentrations. The transferred model achieved excellent accuracy, and the overall determination coefficient (R²) value range was 99-100%. Furthermore, the optimized model achieved excellent accuracies in other applications, including multiplex detection in serum and model applicability in urine. Also, LOD in serum at nanoscale concentration was considered. Therefore, this approach opens the window for qualitative and quantitative analysis of small molecules in biofluids at nanoscale concentrations, which may help in the rapid inclusion of sensor arrays in biomedical and other applications.

New Trends in Fluorescent Nanomaterials-Based Bio/Chemical Sensors for Neurohormones Detection-A Review

The study of neurotransmitters and stress hormones allows the determination of indicators of the current stress load in the body. These species also create a proper strategy of stress protection. Nowadays, stress is a general factor that affects the population, and it may cause a wide range of serious disorders. Abnormalities in the level of neurohormones, caused by chronic psychological stress, can occur in, for instance, corporate employees, health care workers, shift workers, policemen, or firefighters. Here we present a new nanomaterials-based sensors technology development for the determination of neurohormones. We focus on fluorescent sensors/biosensors that utilize nanomaterials, such as quantum dots or carbon nanomaterials. Nanomaterials, owing to their diversity in size and shape, have been attracting increasing attention in sensing or bioimaging. They possess unique properties, such as fluorescent, electronic, or photoluminescent features. In this Review, we summarize new trends in adopting nanomaterials for applications in fluorescent sensors for neurohormone monitoring.

Deep Learning-Based Sensor Array: 3D Fluorescence Spectra of Gold Nanoclusters for Qualitative and Quantitative Analysis of Vitamin B6 Derivatives

Vitamin B₆ derivatives (VB6Ds) are of great importance for all living organisms to complete their physiological processes. However, their excess in the body can cause serious problems. What is more, the qualitative and quantitative analysis of different VB6Ds may present significant challenges due to the high similarity of their chemical structures. Also, the transfer of deep learning model from one task to a similar task needs to be present more in the fluorescence-based biosensor. Therefore, to address these problems, two deep learning models based on the intrinsic fingerprint of 3D fluorescence spectra have been developed to identify five VB6Ds. The accuracy ranges of a deep neural network (DNN) and a convolutional neural network (CNN) were 94.44-97.77% and 97.77-100%, respectively. After that, the developed models were transferred for quantitative analysis of the selected VB6Ds at a broad concentration range (1-100 μM). The determination coefficient (R²) values of the test set for DNN and CNN were 93.28 and 97.01%, respectively, which also represents the outperformance of CNN over DNN. Therefore, our approach opens new avenues for qualitative and quantitative sensing of small molecules, which will enrich fields related to deep learning, analytical chemistry, and especially sensor array chemistry.

A tutorial on multi-way data processing of excitation-emission fluorescence matrices acquired from semiconductor quantum dots sensing platforms

This tutorial demonstrates how to exploit the second-order advantage on excitation-emission fluorescence matrices (EEFMs) acquired from sensing platforms based on analyte-triggered semiconductor quantum dots (QDs) fluorescence modulation (quenching/enhancing). The advantage in processing such second-order EEFMs data from complex samples, seeking successful quantification, is comprehensively addressed. It is worth emphasizing that, aiming to exploit the second-order advantage, the selection of the most appropriate advanced chemometric model should rely on the matching between the data structure and the physicochemical chemometric model assumption. In this sense, the achievement of second-order advantage after EEFMs' processing is extensively addressed throughout this tutorial taking into consideration three different analytical situations, each involving a specific data structure: i) parallel factor analysis (PARAFAC), which is applied in a real dataset stacked in a three-way data array containing a trilinear data structure acquired from QDs-based detection with non-selective species; ii) multivariate curve resolution - alternating least-squares (MCR-ALS), which is also employed in a real dataset arranged in an augmented data matrix containing non-trilinear data structure acquired from QDs-based detection with a single breaking mode caused by background signals; iii) unfolded partial least-squares with residual bilinearization (U-PLS/RBL), which is applied in a dataset containing non-trilinear data acquired from a classical fluorescence system with two breaking modes caused by inner filter effect (IFE) in both instrumental modes (excitation and emission). The latter challenging data structure can be acquired via fluorescence quenching from IFE-based sensing platforms and chemometrically handled in two main steps. First, a set of calibration EEFMs data is converted into an unfolded data matrix during the unfolding process, followed by applying U-PLS model. Second, a post-calibration procedure using RBL analysis is applied to a test sample of EEFM maintained in its matrix form, in order to handle potential interferents. In the last section, the state-of-the-art of second-order EEFMs data acquired from semiconductor QDs-based sensing platforms and coupled to multi-way fluorescence data processing to accomplish a successful quantification, even with substantial interfering species, is critically reviewed.