Fast and accurate decoding of Raman spectra-encoded suspension arrays using deep learning.

08:00 EDT 12th June 2019 | BioPortfolio

Summary of "Fast and accurate decoding of Raman spectra-encoded suspension arrays using deep learning."

A deep learning network called "residual neural network" (ResNet) was used to decode Raman spectra-encoded suspension arrays (SAs). With narrow bandwidths and stable signals, Raman spectra have ideal encoding properties. The different Raman reporter molecules assembled micro-quartz pieces (MQPs) were grafted with various biomolecule probes, which enabled simultaneous detection of numerous target analytes in a single sample. Multiple types of mixed MQPs were measured by Raman spectroscopy and then decoded by ResNet to acquire the type information of analytes. The good classification performance of ResNet was verified by a t-distributed stochastic neighbor embedding (t-SNE) diagram. Compared with other machine learning models, these experiments showed that ResNet was obviously superior in terms of classification stability and training convergence to different datasets. This method simplified the decoding process and the classification accuracy reached 100%.


Journal Details

This article was published in the following journal.

Name: The Analyst
ISSN: 1364-5528


DeepDyve research library

PubMed Articles [8513 Associated PubMed Articles listed on BioPortfolio]

Graphically encoded suspension array for multiplex immunoassay and quantification of autoimmune biomarkers in patient sera.

In precision medicine, clinical decisions and pharmaceutical evaluations tends to be made upon parallel analysis of multiple protein biomarkers. Currently, the growing needs of high-throughput multipl...

Fast Raman Chemical Imaging of Tablets with Non-Flat Surfaces.

A curved area with embossment on an analgesic tablet with three APIs is imaged with a Raman instrument equipped with hardware options that allow for continuous focus adjustment and very fast acquisiti...

A probabilistic recurrent neural network for decoding hind limb kinematics from multi-segment recordings of the dorsal horn neurons.

Providing accurate and robust estimates of limb kinematics from recorded neural activities is prominent in closed-loop control of functional electrical stimulation (FES). A major issue in providing ac...

Raman spectra study hydrogen bonds network in ice Ih with cooling.

The Raman spectra of ice Ih (HO and HDO) in the temperatures range from 253 to 83 K are measured. The results show that Raman peaks shift to low- or high-wavenumber due to the influence of temperatu...

Raman spectroscopic evaluation of human serum using metal plate and 785- and 1064-nm excitation lasers.

In this study, we utilized a stainless steel (SUS304) plate for measuring the Raman scattering spectra of body fluid samples. Using this stainless steel plate, we recorded the Raman scattering spectra...

Clinical Trials [2166 Associated Clinical Trials listed on BioPortfolio]

Intraoperative Detection of Residual BCC by Fast Raman

The main objective of this research is to develop a new scanning technology called the Fast Raman device, to accurately check the skin removed by the surgeon and detect any residual cancer...

A Study to Look at Performance of MICRUSFRAME and GALAXY Coils for the Treatment of Intracranial Aneurysms

A post-market registry evaluating ruptured/unruptured aneurysms treated exclusively with Spectra Galaxy and Spectra Micrusframe coils

Confocal Raman Spectroscopy: in Vivo Measurement of Physiological Skin Parameters

The purpose of this study is to I. determine several skin parameters, for example natural moisturizing factor (NMF) and cholesterol, with Raman spectroscopy in vivo and II. compare...

An Evaluation of the Spectra Optia CMNC Collection Procedure

The purpose of this prospective, randomized, cross-over, multi-center study is to evaluate the performance of the Spectra Optia Apheresis System's CMNC Collection Procedure, compared to th...

Diagnosing Melanoma, Squamous Cell Carcinoma and Basal Cell Carcinoma Using the Spectra-Scope

The primary objective is to collect emission spectra of normal tissue, pigmented normal lesion, benign lesion, SCC, BCC and melanoma to construct the database and validate the classifying ...

Medical and Biotech [MESH] Definitions

A mass spectrometric technique that is used for the analysis of a wide range of biomolecules, such as glycoalkaloids, glycoproteins, polysaccharides, and peptides. Positive and negative fast atom bombardment spectra are recorded on a mass spectrometer fitted with an atom gun with xenon as the customary beam. The mass spectra obtained contain molecular weight recognition as well as sequence information.

Analysis of the intensity of Raman scattering of monochromatic light as a function of frequency of the scattered light.

An AAA ATPase that binds and severs MICROTUBULES. It specifically recognizes and cuts polyglutamylated microtubules with short polyglutamate tails to promote reorganization of cellular microtubule arrays and the release of microtubules from the CENTROSOME following nucleation. It is critical for the biogenesis and maintenance of complex microtubule arrays in AXONS; SPINDLE APPARATUS; and CILIA. Mutations in the spastin gene (SPAST) are associated with type 4 of HEREDITARY SPASTIC PARAPLEGIA.

Skeletal muscle fibers characterized by their expression of the Type II MYOSIN HEAVY CHAIN isoforms which have high ATPase activity and effect several other functional properties - shortening velocity, power output, rate of tension redevelopment. Several fast types have been identified.

Cell surface proteins that bind amino acids and trigger changes which influence the behavior of cells. Glutamate receptors are the most common receptors for fast excitatory synaptic transmission in the vertebrate central nervous system, and GAMMA-AMINOBUTYRIC ACID and glycine receptors are the most common receptors for fast inhibition.

Quick Search


DeepDyve research library

Searches Linking to this Article