Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

MicroRNAs

MicroRNAs

MicroRNA (miRNA) are short, regulatory RNA transcribed from introns (non-coding regions of a gene) or intergenic regions (stretches of DNA present between genes). Several processing steps are required to form biologically active, mature miRNA. The initial transcript, called primary miRNA (pri-mRNA), base-pairs with itself, forming a stem-loop structure. Within the nucleus, an endonuclease enzyme, called Drosha, shortens the stem-loop structure into hairpin-shaped pre-miRNA. After the pre-miRNA...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Noninvasive whole-brain imaging of glymphatic dynamics.

Science advances·2026

Same author

Machine-learning-based tumor segmentation and classification using dynamic optical contrast imaging for thyroid cancer.

Biophotonics discovery·2026

Same author

Magneto-Plasmonics-Enhanced Colorimetric Lateral Flow Immunoassay Using Magnetic-Gold Nanostars.

ACS applied materials & interfaces·2026

Same author

Direct, Pretreatment-Free Surface-Enhanced Raman Scattering (SERS) Detection of Uric Acid in Urine Facilitated by Efficient Hydrogen Bonding-Driven Capture.

Analytical chemistry·2026

Same author

Association between autoimmune thyroid disease and presence of CagA and gastric intestinal metaplasia among patients with H. pylori: a cross-sectional endoscopic study.

BMC endocrine disorders·2026

Same author

<i>Helicobacter pylori</i> Eradication Rates among Patients Undergoing Endoscopy Remain Stagnant Despite Evolving Clinical Practice Patterns.

Southern medical journal·2026

Search research articles

Related Experiment Video

Updated: Jul 12, 2025

MicroRNA Based Liquid Biopsy: The Experience of the Plasma miRNA Signature Classifier MSC for Lung Cancer Screening

MicroRNA Based Liquid Biopsy: The Experience of the Plasma miRNA Signature Classifier MSC for Lung Cancer Screening

Published on: October 26, 2017

Surface-Enhanced Raman Spectroscopy-Based Detection of Micro-RNA Biomarkers for Biomedical Diagnosis Using a

Joy Q Li^1,2, Hsin Neng-Wang^1,2, Aidan J Canning^1,2

¹Fitzpatrick Institute for Photonics, Durham, North Carolina, USA.

Applied Spectroscopy

|November 1, 2023

Summary

Machine learning, specifically convolutional neural networks (CNNs), excels at analyzing complex surface-enhanced Raman spectroscopy (SERS) data for micro-RNA detection. Combining CNNs with non-negative matrix factorization (NMF) improves efficiency without compromising accuracy in spectral unmixing for diagnostics.

Keywords:

CNN NMF SERS Surface-enhanced Raman spectroscopy convolutional neural network machine learning miRNA micro-RNA nanoparticle non-negative matrix factorization

More Related Videos

Author Spotlight: Advancing SERS Technology: Au@Carbon Dot Nanoprobes for Label-Free Analysis and Imaging

Author Spotlight: Advancing SERS Technology: Au@Carbon Dot Nanoprobes for Label-Free Analysis and Imaging

Published on: June 9, 2023

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Related Experiment Videos

Last Updated: Jul 12, 2025

MicroRNA Based Liquid Biopsy: The Experience of the Plasma miRNA Signature Classifier MSC for Lung Cancer Screening

MicroRNA Based Liquid Biopsy: The Experience of the Plasma miRNA Signature Classifier MSC for Lung Cancer Screening

Published on: October 26, 2017

Author Spotlight: Advancing SERS Technology: Au@Carbon Dot Nanoprobes for Label-Free Analysis and Imaging

Author Spotlight: Advancing SERS Technology: Au@Carbon Dot Nanoprobes for Label-Free Analysis and Imaging

Published on: June 9, 2023

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Area of Science:

Spectroscopy and Analytical Chemistry
Biomedical Diagnostics
Machine Learning Applications

Background:

Surface-enhanced Raman spectroscopy (SERS) offers multiplex analysis capabilities for diagnostics due to its narrow spectral features.
Inverse molecular sentinel (iMS) nanosensors enable multiplexed micro-RNA (miRNA) detection using SERS.
High dimensionality of SERS data challenges traditional machine learning (ML) methods, leading to overfitting and poor generalization.

Purpose of the Study:

To compare the performance of various ML algorithms for spectral unmixing of multiplexed SERS data from iMS assays.
To evaluate the impact of dimensionality reduction using non-negative matrix factorization (NMF) on ML model performance and efficiency.
To analyze clinical SERS data from tissue biopsies using the developed ML models.

Main Methods:

Compared ML methods: convolutional neural network (CNN), support vector regression, and extreme gradient boosting.
Investigated the efficacy of combining ML methods with non-negative matrix factorization (NMF) for dimensionality reduction.
Utilized gradient class activation maps and partial dependency plots for model interpretability.

Main Results:

Convolutional neural network (CNN) demonstrated high accuracy in spectral unmixing of multiplexed SERS data.
Integrating NMF prior to CNN significantly reduced memory and training demands without compromising performance.
CNN and CNN-NMF models achieved high accuracy (RMSE ~0.101 and 0.0968, respectively) when analyzing clinical SERS data.

Conclusions:

CNN-based ML approaches show significant promise for spectral unmixing in multiplexed SERS applications.
Dimensionality reduction using NMF is effective in enhancing the efficiency of ML models for SERS data analysis.
The developed models accurately analyzed clinical SERS data, highlighting their potential for diagnostic applications.