Label-free surface-enhanced Raman spectroscopy with artificial neural network technique for recognition photoinduced DNA damage

O. Guselnikova, A. Trelin, A. Skvortsova, P. Ulbrich, P. Postnikov, A. Pershina, D. Sykora, V. Svorcik, O. Lyutakov

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Taking advantage of surface-enhanced Raman scattering (SERS) methodology with its unique ability to collect abundant intrinsic fingerprint information and noninvasive data acquisition we set up a SERS-based approach for recognition of physically induced DNA damage with further incorporation of artificial neural network (ANN). As a proof-of-concept application, we used the DNA molecules, where the one oligonucleotide (OND) was grafted to the plasmonic surface while complimentary OND was exposed to UV illumination with various exposure doses and further hybridized with the grafted counterpart. All SERS spectra of entrapped DNA were collected by several operators using the portable spectrometer, without any optimization of measurements procedure (e.g., optimization of acquisition time, laser intensity, finding of optimal place on substrate, manual baseline correction, etc.) which usually takes a significant amount of operator's time. The SERS spectra were employed as input data for ANN training, and the performance of the system was verified by predicting the class labels for SERS validation data, using a spectra dataset, which has not been involved in the training process. During that phase, accuracy higher than 98% was achieved with a level of confidence exceeding 95%. It should be noted that utilization of the proposed functional-SERS/ANN approach allows identifying even the minor DNA damage, almost invisible by control measurements, performed with common analytical procedures. Moreover, we introduce the advanced ANN design, which allows not only classifying the samples but also providing the ANN analysis feedback, which associates the spectral changes and chemical transformations of DNA structure.

Original languageEnglish
Article number111718
JournalBiosensors and Bioelectronics
Volume145
DOIs
Publication statusPublished - 1 Dec 2019

Fingerprint

Raman Spectrum Analysis
DNA Damage
Raman spectroscopy
Labels
DNA
Raman scattering
Neural networks
Oligonucleotides
Dermatoglyphics
Lighting
Electric network analysis
Lasers
Spectrometers
Mathematical operators
Data acquisition
Feedback
Molecules
Substrates

Keywords

  • Artificial neural network
  • Detection and recognition
  • DNA
  • Photo-damage
  • SERS

ASJC Scopus subject areas

  • Biotechnology
  • Biophysics
  • Biomedical Engineering
  • Electrochemistry

Cite this

Label-free surface-enhanced Raman spectroscopy with artificial neural network technique for recognition photoinduced DNA damage. / Guselnikova, O.; Trelin, A.; Skvortsova, A.; Ulbrich, P.; Postnikov, P.; Pershina, A.; Sykora, D.; Svorcik, V.; Lyutakov, O.

In: Biosensors and Bioelectronics, Vol. 145, 111718, 01.12.2019.

Research output: Contribution to journalArticle

@article{8fb9899cb33b46a4994f970f9cede02f,
title = "Label-free surface-enhanced Raman spectroscopy with artificial neural network technique for recognition photoinduced DNA damage",
abstract = "Taking advantage of surface-enhanced Raman scattering (SERS) methodology with its unique ability to collect abundant intrinsic fingerprint information and noninvasive data acquisition we set up a SERS-based approach for recognition of physically induced DNA damage with further incorporation of artificial neural network (ANN). As a proof-of-concept application, we used the DNA molecules, where the one oligonucleotide (OND) was grafted to the plasmonic surface while complimentary OND was exposed to UV illumination with various exposure doses and further hybridized with the grafted counterpart. All SERS spectra of entrapped DNA were collected by several operators using the portable spectrometer, without any optimization of measurements procedure (e.g., optimization of acquisition time, laser intensity, finding of optimal place on substrate, manual baseline correction, etc.) which usually takes a significant amount of operator's time. The SERS spectra were employed as input data for ANN training, and the performance of the system was verified by predicting the class labels for SERS validation data, using a spectra dataset, which has not been involved in the training process. During that phase, accuracy higher than 98{\%} was achieved with a level of confidence exceeding 95{\%}. It should be noted that utilization of the proposed functional-SERS/ANN approach allows identifying even the minor DNA damage, almost invisible by control measurements, performed with common analytical procedures. Moreover, we introduce the advanced ANN design, which allows not only classifying the samples but also providing the ANN analysis feedback, which associates the spectral changes and chemical transformations of DNA structure.",
keywords = "Artificial neural network, Detection and recognition, DNA, Photo-damage, SERS",
author = "O. Guselnikova and A. Trelin and A. Skvortsova and P. Ulbrich and P. Postnikov and A. Pershina and D. Sykora and V. Svorcik and O. Lyutakov",
year = "2019",
month = "12",
day = "1",
doi = "10.1016/j.bios.2019.111718",
language = "English",
volume = "145",
journal = "Biosensors and Bioelectronics",
issn = "0956-5663",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Label-free surface-enhanced Raman spectroscopy with artificial neural network technique for recognition photoinduced DNA damage

AU - Guselnikova, O.

AU - Trelin, A.

AU - Skvortsova, A.

AU - Ulbrich, P.

AU - Postnikov, P.

AU - Pershina, A.

AU - Sykora, D.

AU - Svorcik, V.

AU - Lyutakov, O.

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Taking advantage of surface-enhanced Raman scattering (SERS) methodology with its unique ability to collect abundant intrinsic fingerprint information and noninvasive data acquisition we set up a SERS-based approach for recognition of physically induced DNA damage with further incorporation of artificial neural network (ANN). As a proof-of-concept application, we used the DNA molecules, where the one oligonucleotide (OND) was grafted to the plasmonic surface while complimentary OND was exposed to UV illumination with various exposure doses and further hybridized with the grafted counterpart. All SERS spectra of entrapped DNA were collected by several operators using the portable spectrometer, without any optimization of measurements procedure (e.g., optimization of acquisition time, laser intensity, finding of optimal place on substrate, manual baseline correction, etc.) which usually takes a significant amount of operator's time. The SERS spectra were employed as input data for ANN training, and the performance of the system was verified by predicting the class labels for SERS validation data, using a spectra dataset, which has not been involved in the training process. During that phase, accuracy higher than 98% was achieved with a level of confidence exceeding 95%. It should be noted that utilization of the proposed functional-SERS/ANN approach allows identifying even the minor DNA damage, almost invisible by control measurements, performed with common analytical procedures. Moreover, we introduce the advanced ANN design, which allows not only classifying the samples but also providing the ANN analysis feedback, which associates the spectral changes and chemical transformations of DNA structure.

AB - Taking advantage of surface-enhanced Raman scattering (SERS) methodology with its unique ability to collect abundant intrinsic fingerprint information and noninvasive data acquisition we set up a SERS-based approach for recognition of physically induced DNA damage with further incorporation of artificial neural network (ANN). As a proof-of-concept application, we used the DNA molecules, where the one oligonucleotide (OND) was grafted to the plasmonic surface while complimentary OND was exposed to UV illumination with various exposure doses and further hybridized with the grafted counterpart. All SERS spectra of entrapped DNA were collected by several operators using the portable spectrometer, without any optimization of measurements procedure (e.g., optimization of acquisition time, laser intensity, finding of optimal place on substrate, manual baseline correction, etc.) which usually takes a significant amount of operator's time. The SERS spectra were employed as input data for ANN training, and the performance of the system was verified by predicting the class labels for SERS validation data, using a spectra dataset, which has not been involved in the training process. During that phase, accuracy higher than 98% was achieved with a level of confidence exceeding 95%. It should be noted that utilization of the proposed functional-SERS/ANN approach allows identifying even the minor DNA damage, almost invisible by control measurements, performed with common analytical procedures. Moreover, we introduce the advanced ANN design, which allows not only classifying the samples but also providing the ANN analysis feedback, which associates the spectral changes and chemical transformations of DNA structure.

KW - Artificial neural network

KW - Detection and recognition

KW - DNA

KW - Photo-damage

KW - SERS

UR - http://www.scopus.com/inward/record.url?scp=85072553820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072553820&partnerID=8YFLogxK

U2 - 10.1016/j.bios.2019.111718

DO - 10.1016/j.bios.2019.111718

M3 - Article

AN - SCOPUS:85072553820

VL - 145

JO - Biosensors and Bioelectronics

JF - Biosensors and Bioelectronics

SN - 0956-5663

M1 - 111718

ER -