Researchers make neural networks successfully detect DNA damage caused by UV radiation

October 24, 2019

According to the authors, the ways the UV could affect the DNA structure, especially with the short-term irradiation, remain practically unstudied. The UV radiation is also known to cause cancer. However, it is almost impossible to detect minor changes in the DNA structure.

"In the article Label-free surface-enhanced Raman spectroscopy with artificial neural network technique for recognition photoinduced DNA damage, we offer an alternative to well-known techniques. We used model samples such as oligonucleotides of various sequences. Some of them were irradiated with UV for different periods of time. Then, we used highly sensitive sensor systems developed by the research team based on plasmon-polariton gold gratings. The oligonucleotides were immobilized on the sensor surface. They subsequently were hybridized with the irradiated oligonucleotides. Then, the changes in the DNA structure were analyzed using a Raman spectrometer, " Pavel Postnikov, Associate Prof. of the TPU Research School of Chemistry & Applied Biomedical Sciences, says.

He also noticed that the obtained spectra were used to train artificial neural networks. The analysis and interpretation of the oligonucleotide sequence spectra is quite a complex task, especially if it is large-scale and performed with a high level of statistics processing.

"Using neural networks enabled to avoid the numerical processing of a huge number of spectra and it freed us from the optimization of measurement procedure. Besides, the neural networks both reveal the damages and effectively predict changes in the DNA structure caused by UV radiation.

Moreover, the neural network in combination with the surface-enhanced Raman spectroscopy can detect changes with high accuracy, where traditional methods fail", - Pavel Postnikov says.

The researchers believe that the neural networks and Raman spectroscopy can be successfully used for medical diagnostics in the future. Moreover, this technique can be further improved.

"Analysis of biological objects by Raman spectroscopy methods is still an extremely difficult, but interesting and promising issue. In this regard, DNA damages caused by the UV radiation was an extremely interesting model for us. This concept provides the detecting of minor changes in the DNA structure. It can be expanded and improved, " - Pavel Postnikov underlines. He also specifies, that the studies are supported by a grant under the TPU Competitiveness Improvement Program and conducted under the scientific supervision of Prof. Marina Trusova, the Research School of Chemistry & Applied Biomedical Sciences.

The Research School of Chemistry & Applied Biomedical Sciences implements more than ten various projects on the development of hybrid materials, combining different properties. One of these areas is the development of highly sensitive sensor systems. Sensors are a multilayer construction: they are based on a thin, wavy gold film 1x0.5 cm in size, which is modified with diazonium salts, special organic compounds.

Due to the developments of the TPU research team, the sensor can detect toxic substances, heavy metals, and some diseases and defects in the DNA structure. The advantages of hybrid sensors are hypersensitivity, the speed of analysis and the ability to analyze at the sampling site.
-end-


Tomsk Polytechnic University

Related Neural Networks Articles from Brightsurf:

Deep neural networks show promise for predicting future self-harm based on clinical notes
Medical University of South Carolina researchers report in JMIR Medical Informatics that they have developed deep learning models to predict intentional self-harm based on information in clinical notes.

Researchers develop new model of the brain's real-life neural networks
Researchers at the Cyber-Physical Systems Group at the USC Viterbi School of Engineering, in conjunction with the University of Illinois at Urbana-Champaign, have developed a new model of how information deep in the brain could flow from one network to another and how these neuronal network clusters self-optimize over time.

The brain's memory abilities inspire AI experts in making neural networks less 'forgetful'
Artificial intelligence (AI) experts at the University of Massachusetts Amherst and the Baylor College of Medicine report that they have successfully addressed what they call a ''major, long-standing obstacle to increasing AI capabilities'' by drawing inspiration from a human brain memory mechanism known as ''replay.''

New data processing module makes deep neural networks smarter
Artificial intelligence researchers have improved the performance of deep neural networks by combining feature normalization and feature attention modules into a single module that they call attentive normalization.

Neural cartography
A new x-ray microscopy technique could help accelerate efforts to map neural circuits and ultimately the brain itself.

Researchers study why neural networks are efficient in their predictions
A study has tested the predictions of a neural network to check whether they coincide with actual results.

Optimizing neural networks on a brain-inspired computer
Neural networks in both biological settings and artificial intelligence distribute computation across their neurons to solve complex tasks.

Teaching physics to neural networks removes 'chaos blindness'
Teaching physics to neural networks enables those networks to better adapt to chaos within their environment.

A clique away from more efficient networks
An old branch of mathematics finds a fertile new field of application.

Unravelling complex brain networks with automated 3D neural mapping
KAIST researchers developed a new algorithm for brain imaging data analysis that enables the precise and quantitative mapping of complex neural circuits onto a standardized 3D reference atlas.

Read More: Neural Networks News and Neural Networks Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.