SERS Chip Multiplex Probe ML Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional surface-enhanced Raman scattering (SERS) techniques face limitations in detecting small gaseous molecules like SO2, NO2, and volatile organic compounds (VOCs) due to weak Raman cross-sections and interference from complex matrices, making on-site applications challenging, especially in multiplex analysis and disease diagnosis.
Innovation Solution
A SERS chip with multiple molecular probes configured on a substrate, combined with machine learning for automated spectral analysis, enhances detection accuracy by inducing interaction-induced peak shifts and generating multiple SERS profiles for seamless classification and quantification of target analytes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional direct SERS detection is used for small gaseous molecules, then the detection method is simple, but the Raman cross-section is too weak to achieve reliable detection
Solution Approach 1:
The patent introduces molecular probes as intermediary substances that specifically bind to target analytes. These probes act as mediators between the analyte and the SERS substrate, transferring and amplifying the analytical signal. The probe-analyte complex generates enhanced SERS signals that are much stronger than direct detection, enabling sensitive detection of small gaseous molecules with weak Raman cross-sections.
Solution Approach 2:
The patent changes the detection parameter from direct molecular vibration detection to probe vibration detection. By monitoring the vibrational modes of the molecular probes (which have strong Raman activity) rather than the weakly scattering analyte molecules directly, the system achieves enhanced sensitivity. The binding of analytes to probes induces measurable shifts in probe vibration frequencies, providing a amplified detection signal.
2Measurement precision
If multiple molecular probes are used for multiplex detection, then the classification accuracy improves to 100%, but the device complexity increases
Solution Approach 1:
The patent divides the detection system into multiple independent probe units, each functionalized with a specific molecular probe type. Each probe segment targets different analytes or provides different spectral information. This segmentation allows the system to detect and classify multiple analytes simultaneously by combining the spectral information from each probe segment, achieving 100% classification accuracy through ensemble analysis.
Solution Approach 2:
The patent employs a universal SERS substrate platform that can support multiple different molecular probes. The substrate provides a common enhanced Raman scattering environment that works with various probe types. This multi-functional platform allows the same base system to detect different analytes by simply changing or combining probe configurations, achieving versatility without requiring completely separate detection systems for each analyte.
3Measurement precision
If machine learning algorithms are used for automated spectral analysis, then the objectivity and accuracy improve, but the risk of overfitting increases
Solution Approach 1:
The patent performs preliminary feature extraction and selection from the SERS spectral data before applying machine learning classification algorithms. By pre-processing the spectral data to identify and extract the most discriminative features (such as peak positions, intensities, and ratios), the system reduces the dimensionality and complexity of the input data. This preliminary action helps prevent overfitting by focusing the ML model on the most relevant information while reducing the risk of learning noise or spurious patterns.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The solution achieves 100% classification accuracy and precise quantification of small gas molecules in complex environments, enabling on-site detection and multiplex analysis, and has been demonstrated in identifying COVID-19 from breath samples with high sensitivity and specificity.
Implementation Method 1
Surface-enhanced raman scattering (SERS) has attracted emerging attention as an ultrasensitive sensing technique
Implementation Method 2
the functional group interacts with the one or more analytes to induce a change in molecular vibration of the receptor molecule which is identifiable by surface-enhanced Raman scattering
Data Source
AI summary
Herein disclosed is a surface-enhanced Raman scattering (SERS) chip for generating multiple SERS profiles simultaneously from one or more analytes suspected to be in a sample. The SERS chip includes one or more substrates, and one or more Raman probes formed on the one or more substrates, wherein each of the one or more Raman probes includes a SERS-active nanoparticle grafted with a receptor molecule, (i) wherein the receptor molecule on each of the one or more Raman probes on one substrate is different from the receptor molecule of the one or more Raman probes on another substrate, and/or (ii) wherein the one or more Raman probes include two or more Raman probes and wherein the receptor molecule on each of the two or more Raman probes on one substrate is different, wherein the receptor molecule includes a thiol group proximal to the SERS-active nanoparticle and a functional group distal to the SERS-active nanoparticle, wherein the functional group interacts with the one or more analytes to induce a change in molecular vibration of the receptor molecule which is identifiable by surface-enhanced Raman scattering for generating the multiple SERS profiles. Herein also discloses a method of identifying one or more analytes suspected to be in a sample, the method includes contacting the surface-enhanced Raman scattering (SERS) chip described in various embodiments of the first aspect with a sample suspected to contain the one or more analytes, collecting SERS signals from the surface-enhanced Raman scattering (SERS) chip which has contacted the sample, constructing a combined-SERS profile from the SERS signals, and providing the combined-SERS profile to a device configured with a model trained to identify the one or more analytes from the combined-SERS profile.