Surface-Enhanced Raman Spectroscopy-Based Detection of Micro-RNA Biomarkers for Biomedical Diagnosis Using a Comparative Study of Interpretable Machine Learning Algorithms.

Surface-enhanced Raman spectroscopy (SERS) has wide diagnostic applications due to narrow spectral features that allow multiplex analysis. We have previously developed a multiplexed, SERS-based nanosensor for micro-RNA (miRNA) detection called the inverse molecular sentinel (iMS). Machine learning (ML) algorithms have been increasingly adopted for spectral analysis due to their ability to discover underlying patterns and relationships within large and complex data sets. However, the high dimensionality of SERS data poses a challenge for traditional ML techniques, which can be prone to overfitting and poor generalization. Non-negative matrix factorization (NMF) reduces the dimensionality of SERS data while preserving information content. In this paper, we compared the performance of ML methods including convolutional neural network (CNN), support vector regression, and extreme gradient boosting combined with and without NMF for spectral unmixing of four-way multiplexed SERS spectra from iMS assays used for miRNA detection. CNN achieved high accuracy in spectral unmixing. Incorporating NMF before CNN drastically decreased memory and training demands without sacrificing model performance on SERS spectral unmixing. Additionally, models were interpreted using gradient class activation maps and partial dependency plots to understand predictions. These models were used to analyze clinical SERS data from single-plexed iMS in RNA extracted from 17 endoscopic tissue biopsies. CNN and CNN-NMF, trained on multiplexed data, performed most accurately with RMSElabel = 0.101 and 9.68 × 10-2, respectively. We demonstrated that CNN-based ML shows great promise in spectral unmixing of multiplexed SERS spectra, and the effect of dimensionality reduction on performance and training speed.

Plasmonic nanorod probes' journey inside plant cells for in vivo SERS sensing and multimodal imaging.

Nanoparticle-based platforms are gaining strong interest in plant biology and bioenergy research to monitor and control biological processes in whole plants. However, in vivo monitoring of biomolecules using nanoparticles inside plant cells remains challenging due to the impenetrability of the plant cell wall to nanoparticles beyond the exclusion limits (5-20 nm). To overcome this physical barrier, we have designed unique bimetallic silver-coated gold nanorods (AuNR@Ag) capable of entering plant cells, while conserving key plasmonic properties in the near-infrared (NIR). To demonstrate cellular internalization and tracking of the nanorods inside plant tissue, we used a comprehensive multimodal imaging approach that included transmission electron microscopy (TEM), confocal fluorescence microscopy, two-photon luminescence (TPL), X-ray fluorescence microscopy (XRF), and photoacoustics imaging (PAI). We successfully acquired SERS signals of nanorods in vivo inside plant cells of tobacco leaves. On the same leaf samples, we applied orthogonal imaging methods, TPL and PAI techniques for in vivo imaging of the nanorods. This study first demonstrates the intracellular internalization of AuNR@Ag inside whole plant systems for in vivo SERS analysis in tobacco cells. This work demonstrates the potential of this nanoplatform as a new nanotool for intracellular in vivo biosensing for plant biology.

miRNA probe integrated biosensor platform using bimetallic nanostars for amplification-free multiplexed detection of circulating colorectal cancer biomarkers in clinical samples.

There is a critical need for sensitive and rapid detection technologies utilizing molecular biotargets such as microRNAs (miRNAs), which regulate gene expression and are a promising class of diagnostic biomarkers for disease detection. Here, we present the development and fabrication of a highly reproducible and robust plasmonic bimetallic nanostar biosensing platform to detect miRNA targets using surfaced-enhanced Raman scattering (SERS)-based gene probes called the inverse Molecular Sentinel (iMS). We investigated and optimized the integration of iMS gene probes onto this SERS substrate, achieving ultra-sensitive detection with limits of detection of 6.8 and 16.7 zmol within the sensing region for two miRNA sequences of interest. Finally, we demonstrated the biomedical usefulness of this nanobiosensor platform with the multiplexed detection of upregulated miRNA targets, miR21 and miR221, from colorectal cancer patient plasma. The resulting SERS data are in excellent agreement with PCR data obtained from patient samples and can distinguish between healthy and cancerous patient samples. These results underline the potential of the iMS-integrated substrate nanobiosensing platform for rapid and sensitive diagnostics of cancer biomarkers for point-of-care applications.