Machine Learning Enhances the Performance of Bioreceptor-Free Biosensors

Abstract

Since their inception, biosensors have frequently employed simple regression models to calculate analyte composition based on the biosensor’s signal magnitude. Traditionally, bioreceptors provide excellent sensitivity and specificity to the biosensor. Increasingly, however, bioreceptor-free biosensors have been developed for a wide range of applications. Without a bioreceptor, maintaining strong specificity and a low limit of detection have become the major challenge. Machine learning (ML) has been introduced to improve the performance of these biosensors, effectively replacing the bioreceptor with modeling to gain specificity. Here, we present how ML has been used to enhance the performance of these bioreceptor-free biosensors. Particularly, we discuss how ML has been used for imaging, Enose and Etongue, and surface-enhanced Raman spectroscopy (SERS) biosensors. Notably, principal component analysis (PCA) combined with support vector machine (SVM) and various artificial neural network (ANN) algorithms have shown outstanding performance in a variety of tasks. We anticipate that ML will continue to improve the performance of bioreceptor-free biosensors, especially with the prospects of sharing trained models and cloud computing for mobile computation. To facilitate this, the biosensing community would benefit from increased contributions to open-access data repositories for biosensor data.

Machine Learning-Based Quantification of (−)-trans-Δ-Tetrahydrocannabinol from Human Saliva Samples on a Smartphone-Based Paper Microfluidic Platform

“… 35 We tested k -nearest neighbor ( k -NN), decision tree, and support vector machine (SVM), which have popularly been used to make classifications. 36 Multidimensional data set was used to build a training data set, consisting of four different dilutions (10, 100, 1000, and 10,000; i.e., 10, 1, 0.1, and 0.01%), with three different saliva samples ( Figure S9 ). As the concentrations of spiked THC were varied from 0 to 30 pg/mL, these four dilutions would cover a wide range of THC concentrations and subsequently the varied linear ranges of the assay.…”

“…We sought to use machine learning (ML)-based classification to address this problem . We tested k -nearest neighbor ( k -NN), decision tree, and support vector machine (SVM), which have popularly been used to make classifications . Multidimensional data set was used to build a training data set, consisting of four different dilutions (10, 100, 1000, and 10,000; i.e., 10, 1, 0.1, and 0.01%), with three different saliva samples (Figure S9).…”

Machine Learning Methods of Regression for Plasmonic Nanoantenna Glucose Sensing

“…[ 34 ] successfully employed an ANN as multivariate calibration model for an amperometric biosensor, while Ref. [ 35 ] reported highly promising results by combining surface-enhanced Raman spectroscopy biosensors with neural network algorithms. To estimate the glucose levels in human blood by processing the measurement signal of a non-invasive near-infrared spectroscopy (NIRS) sensing system, Ref.…”

Rational Design of Field-Effect Sensors Using Partial Differential Equations, Bayesian Inversion, and Artificial Neural Networks

“…Furthermore, the sensors are developed to detect specific biological species with the highest sensitivity. In the design process, using neural networks enables us to optimize the design parameters to enhance the sensor performance [27][28][29][30][31][32].…”