Machine-learning-assisted SERS nanosensor platform toward chemical fingerprinting of Baijiu flavors.

A novel fingerprinting platform for multiplex detection of flavor molecules in Baijiu was developed by using a surface-enhanced Raman scattering (SERS) nanosensor array in combination with machine learning. The SERS sensors were constructed by core-shell Fe3O4@Ag nanoparticles modified with molecules carrying end-groups of hydroxyl, pyridyl, methyl, and amino, respectively, which interacted with flavors and led to changes in the sensors' spectra. All the Raman spectra acquired from the nanosensor array contacting with the sample were concatenated into a single SERS super-spectrum, representing the flavor fingerprint which was recognized through machine learning. Principal component analysis, support vector machine, and partial least squares were utilized to build classification and quantitation models for predictive analyses. The SERS nanosensor array was successfully used for fingerprinting ten typical flavors in Baijiu including four esters, three alcohols, and three acids, with an accuracy of 100%, linear detection ranges over two orders of magnitude, and limits of detection ranging from 3.45 × 10-3 mg/L of phenylethyl acetate to 1.21 × 10-2 mg/L of ethyl hexanoate. It was also demonstrated that satisfactory accuracies (recoveries) ranging from 96.2 to 104% and relative standard deviations ranging from 0.65 to 2.78% were obtained for the simultaneous quantification of 3-methylbutyl acetate and phenylethyl acetate in eighteen Baijiu samples of three flavor types including sauce flavor, strong flavor, and light flavor. Compared with the existing detection techniques, this chemical fingerprinting platform is easy to use, highly sensitive, and can perform multiplex detection, which has great potential for practical applications.

An all-in-one magnetic SERS nanosensor for ratiometric detection of Escherichia coli in foods.

An all-in-one nanosensor was developed for the magnetic enrichment and ratiometric surface-enhanced Raman scattering (SERS) detection of Escherichia coli (E. coli). The all-in-one nanosensor was constructed through the chemical integration of four components into a single nanoparticle, which include a manganese ferrite nanoparticle serving as the magnetic core, a thin silver shell as the SERS substrate, a self-assembled layer of 4-mercaptobenzoic acid (MBA) molecules as the SERS internal standard, and a MBA-conjugated layer of aptamer sequences as the capture probe of E. coli. In the detection of E. coli in food, the target cells were first captured by the nanosensors and magnetically enriched in a short time of 15 min, and then the ratiometric SERS was performed through the Raman intensity ratio between two specific SERS peaks produced by the captured E. coli and the internal MBA. The pre-concentration and ratiometry enabled the nanosensor to detect E. coli with a detection limit down to 10 CFU/mL. The all-in-one nanosensor was successfully applied for the detection of E. coli in various liquid foods including milk, juice, tea, and coffee, with recoveries ranging from 89 to 110% and relative standard deviation lower than 1.7%. In comparison with the previous sandwich strategy adopted by most SERS sensors, this nanosensor endowed with an easier use and a lower cost is more sensitive and reproducible, leading to a great potential in practical applications.