Explainable Deep Learning-Assisted Self-Calibrating Colorimetric Patches for In Situ Sweat Analysis

Sweat has emerged as a compelling analyte for noninvasive biosensing technology because it contains a wealth of important biomarkers in hormones, organic biomacromolecules, and various ionic mixtures. These components offer valuable insights and can reflect an individual's physiological conditions. Here, we introduced an explainable deep learning (DL)-assisted wearable self-calibrating colorimetric biosensing analysis platform to efficiently and precisely detect the biomarker's concentration in sweat. Specifically, we have integrated the advantages of the colorimetric sensing method, adsorbing-swelling hydrogel, and explainable DL algorithms to develop an enzyme/indicator-immobilized colorimetric patch, which has reliable colorimetric sensing ability and excellent adsorbing-swelling function. A total of 5625 colorimetric images were collected as the analysis data set and assessed two DL algorithms and seven machine learning (ML) algorithms. Zn2+, glucose, and Ca2+ in human sweats could be facilely classified and quantified with 100% accuracy via the convolutional neural network (CNN) model, and the testing results of actual sweats via the DL-assisted colorimetric approach are 91.7-97.2% matching with the classical UV-vis spectrum. Class activation mapping (CAM) was utilized to visualize the inner working mechanism of CNN operation, which contributes to verify and explicate the design rationality of the noninvasive biosensing technology. An "end-to-end" model was established to ascertain the black box of the DL algorithm, promoted software design or principium optimization, and contributed facile indicators for health monitoring, disease prevention, and clinical diagnosis.

Highly-accurate solvent identification using dynamic evaporation reflection spectra from an inverse opal sensor combined with a deep learning model

Developing a low-cost, rapid, and highly accurate method for detecting solvents with similar structures and properties is highly demanded. In recent years, methods based on dynamic reflection spectroscopy have been developed to distinguish isomers and homologues. However, these methods heavily rely on responsive photonic crystals that can interact intricately with the solvent. In this work, we propose a deep learning approach for direct solvent identification from dynamic evaporative reflection spectra (DERS) obtained on a simple inverse opal (IO) sensor. The sensor was prepared using co-assembly and sacrificial template methods. Then, a dataset was constructed with 985 DERS obtained from 14 different solvents. Different classical machine learning and deep learning algorithms were employed for classifying these DERS. The results showed that ResNet18-CBAM, an improved convolutional neural network, outperformed all other algorithms, achieving 97.7 ± 0.9% on the 5-fold cross-validation set and 100% accuracy on the test set. This strategy presents not only a simple, efficient, and repeatable method for solvent detection but also, more importantly, by integrating the deep learning model, it allows an automatic, rapid, and accurate analysis of DERS data without the need for human intervention. It holds great application prospects in the field of solvent detection.

Semi-Selective Array for the Classification of Purines with Surface Plasmon Resonance Imaging and Deep Learning Data Analysis

In process analytics or environmental monitoring, the real-time recording of the composition of complex samples over a long period of time presents a great challenge. Promising solutions are label-free techniques such as surface plasmon resonance (SPR) spectroscopy. They are, however, often limited due to poor reversibility of analyte binding. In this work, we introduce how SPR imaging in combination with a semi-selective functional surface and smart data analysis can identify small and chemically similar molecules. Our sensor uses individual functional spots made from different ratios of graphene oxide and reduced graphene oxide, which generate a unique signal pattern depending on the analyte due to different binding affinities. These patterns allow four purine bases to be distinguished after classification using a convolutional neural network (CNN) at concentrations as low as 50 μM. The validation and test set classification accuracies were constant across multiple measurements on multiple sensors using a standard CNN, which promises to serve as a future method for developing online sensors in complex mixtures.

Explainable Deep Learning-Assisted Photochromic Sensor for β-Lactam Antibiotic Identification

Photochromic sensors have the advantages of diverse isomers for multi-analysis, providing more sensing information and possessing more recognition units and more sensitivity to external stimulations, but they present enormous complexity with various stimulations as well. Deep learning (DL) algorithms contribute a huge advantage at analyzing nonlinear and multidimensional data, but they suffer from nontransparent inner networks, "black-boxes". In this work, we employed the explainable DL approach to process and explicate photochromic sensing. Spirooxazine metallic complexes were adopted to prepare a multi-state analysis array for β-Lactams identification and quantitation. A dataset of 2520 unduplicated fluorescence intensity images was collected for convolutional neural network (CNN) operation. The method clearly discriminated six β-Lactams with 97.98% prediction accuracy and allowed rapid quantification with a concentration range from 1 to 100 mg/L. The photochromic sensing mechanism was verified via molecular simulation and class activation mapping, which explicated how the CNN model assesses the importance of photochromic sensor states and makes a discrimination decision. The explainable DL-assisted analysis method establishes an end-to-end strategy to ascertain and verify the complicated sensing mechanism for device optimization and even new scientific discovery.

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.

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.

Image learning to accurately identify complex mixture components

The study of complex mixtures is very important for exploring the evolution of natural phenomena, but the complexity of the mixtures greatly increases the difficulty of material information extraction. Image perception-based machine-learning techniques have the ability to cope with this problem in a data-driven way. Herein, we report a 2D-spectral imaging method to collect matter information from mixture components, and the obtained feature images can be easily provided to deep convolutional neural networks (CNNs) for establishing a spectral network. The results demonstrated that a single CNN trained end-to-end from the proposed images can directly accomplish synchronous measurement of multi-component samples using only raw pixels as inputs. Our strategy has some innate advantages, such as fast data acquisition, low cost, and simple chemical treatment, suggesting that it can be extensively applied in many fields, including environmental science, biology, medicine, and chemistry.

Advancing Biosensors with Machine Learning

Chemometrics play a critical role in biosensors-based detection, analysis, and diagnosis. Nowadays, as a branch of artificial intelligence (AI), machine learning (ML) have achieved impressive advances. However, novel advanced ML methods, especially deep learning, which is famous for image analysis, facial recognition, and speech recognition, has remained relatively elusive to the biosensor community. Herein, how ML can be beneficial to biosensors is systematically discussed. The advantages and drawbacks of most popular ML algorithms are summarized on the basis of sensing data analysis. Specially, deep learning methods such as convolutional neural network (CNN) and recurrent neural network (RNN) are emphasized. Diverse ML-assisted electrochemical biosensors, wearable electronics, SERS and other spectra-based biosensors, fluorescence biosensors and colorimetric biosensors are comprehensively discussed. Furthermore, biosensor networks and multibiosensor data fusion are introduced. This review will nicely bridge ML with biosensors, and greatly expand chemometrics for detection, analysis, and diagnosis.