[논문]잡음이 포함된 측정 자료에 대한 신경망의 DNA 용액 조성비 예측

강경희; 김민지; 이효민

doi:10.9713/kcer.2024.62.1.118

잡음이 포함된 측정 자료에 대한 신경망의 DNA 용액 조성비 예측
Prediction of Composition Ratio of DNA Solution from Measurement Data with White Noise Using Neural Network 원문보기

Korean chemical engineering research = 화학공학, v.62 no.1, 2024년, pp.118 - 124

강경희 (제주대학교 화학공학과) , 김민지 (제주대학교 화학공학과) , 이효민 (제주대학교 화학공학과)

초록
AI-Helper

신경망은 심전도 신호, 망막 영상, 지진파 등 잡음이 포함된 자료의 전처리 작업에 활용되고 있다. 그러나, 잡음의 전처리는 전산시간 증가, 원본 신호의 왜곡등의 문제점을 내포하고 있다. 본 연구에서는 잡음의 전처리 없이 측정 자료를 분석할 수 있는 신경망 구조를 연구하였다. 신경망의 학습 자료로써 잡음이 포함된 DNA 용액의 동역학적 거동을 선정하여, 해당 자료로부터 DNA 용액의 조성비를 예측하고자 하였다. DNA의 동역학 자료에 인위적으로 백색 잡음을 추가하여, 신경망의 예측에 대한 잡음의 영향을 알아보았다. 결과적으로, 잡음의 전처리 없이 O(1)의 신호 대 잡음비 자료로부터 O(0.01)의 오차로 용액의 조성비를 예측할 수 있었다. 이러한 연구 결과는 측정 잡음에 민감하게 영향 받을 수 있는 극미량의 유전병 또는 암세포와 관련된 DNA를 분석을 위한 핵심 인공지능 기술로 활용할 수 있다.

Abstract ▼ AI-Helper

A neural network is utilized for preprocessing of de-noizing in electrocardiogram signals, retinal images, seismic waves, etc. However, the de-noizing process could provoke increase of computational time and distortion of the original signals. In this study, we investigated a neural network architecture to analyze measurement data without additional de-noizing process. From the dynamical behaviors of DNA in aqueous solution, our neural network model aimed to predict the mole fraction of each DNA in the solution. By adding white noise to the dynamics data of DNA artificially, we investigated the effect of the noise to neural network's predictions. As a result, our model was able to predict the DNA mole fraction with an error of O(0.01) when signal-to-noise ratio was O(1). This work can be applied as a efficient artificial intelligence methodology for analyzing DNA related to genetic disease or cancer cells which would be sensitive to background measuring noise.

주제어

표/그림 (6)

$Fig. 1. (a) Schematic of microfluidic platform for DNA manipulation. (b) Concentration profiles for DNA solution of c10bpbulk:c1000bpbulk =1:9. (c) Spatiotemporal map for DNA solution of . (d) Concentration profiles for DNA solution of c10bpbulk:c1000bpbulk =9:1. (e) Spatiotemporal map for DNA solution of c10bpbulk:c1000bpbulk = 9:1. In (b) and (d), each colored solid line corresponded with $\widetilde{t}$ = 0.001 (black), 0.0025 (blue), 0.005 (green), respectively.$ 그림 Fig. 1. (a) Schematic of microfluidic platform for DNA manipulation. (b) Concentration profiles for DNA solution of c_10bp^bulk:c_1000bp^bulk =1:9. (c) Spatiotemporal map for DNA solution of . (d) Concentration profiles for DNA solution of c_10bp^bulk:c_1000bp^bulk =9:1. (e) Spatiotemporal map for DNA solution of c_10bp^bulk:c_1000bp^bulk = 9:1. In (b) and (d), each colored solid line corresponded with $\widetilde{t}$ = 0.001 (black), 0.0025 (blue), 0.005 (green), respectively.
그림 Fig. 2. (a) Configuration of deep neural network structures. (b) Root-mean-squared-error for train and validation data as a function of number of epochs. Red dashed line and green solid line correspond with train and validation data, respectively. (c) Root-mean-squared-error affected by number of train data. Symbols and error bars represent average and standard deviation at the given number of train data, respectively. Red solid line is regression for data point of symbols. The shaded region shows appropriate number of train data.
표 Table 1. Used characteristic scale for non-dimensional variables
그림 Fig. 3. The spatiotemporal map of the DNA dynamics when dimensionless applied current density was 20 at (a) SNR = 0.01, (b) 1, (c) 100. The represented colors in the map were the total concentration of the DNA solution. (d) Root-mean-squared-error with respect to signal-to-noise ratio for validation data. SNR_lim was 1.775. When the signal-to-noise-ratio exceeds the SNR_lim, the performance of neural network is independent of the white noise.
$Fig. 4. Confusion matrices with respect to SNR and $\widetilde{t}$app.$ 그림 Fig. 4. Confusion matrices with respect to SNR and $\widetilde{t}$_app.
그림 Fig. 5. (a) Root-mean-squared-error with respect to signal-to-noise ratio for each applied current density. (b) SNR_lim as a function of applied current density.

참고문헌 (29)

Brunton, S. L., Noack, B. R. and Koumoutsakos, P., "Machine？Learning for Fluid Mechanics," Annu. Rev. Fluid Mech., 52, 477-508(2020).

상세보기
Ghavipour, M., Ghavipour, M., Chitsazan, M., Najibi, S. H. and？Ghidary, S. S., "Experimental Study of Natural Gas Hydrates？and a Novel Use of Neural Network to Predict Hydrate Formation Conditions," Chemical Engineering Research and Design,？91, 264-273(2013).

상세보기
Landgrebe, M. K. B. and Nkazi, D., "Toward a Robust, Universal Predictor of Gas Hydrate Equilibria by Means of a Deep？Learning Regression," ACS Omega, 4, 22399-22417(2019).

상세보기
Poort, J. P., Ramdin, M., van Kranendonk, J. and Vlugt, T. J. H.,？"Solving Vapor-liquid Flash Problems Using Artificial Neural？Networks," Fluid Phase Equilibria, 490, 39-47(2019).
Sun, G. et al., "Vapor-liquid Phase Equilibria Behavior Prediction？of Binary Mixtures Using Machine Learning," Chemical Engineering Science, 282, 119358(2023).
Hamilton, S. J. and Hauptmann, A., "Deep D-Bar: Real-Time？Electrical Impedance Tomography Imaging With Deep Neural？Networks," IEEE Transactions on Medical Imaging, 37, 2367-2377(2018).
Kwon, O., Leejieun, Hwan, K. J., Seongjun, L. and Yoo, S. K.,？"Design of Deep De-nosing Network for Power Line Artifact in？Electrocardiogram," Journal of Korea Multimedia Society, 23,？402-411(2020).
Badar, M., Haris, M. and Fatima, A., "Application of Deep Learning？for Retinal Image Analysis: A Review," Computer Science Review,？35, 100203(2020).

상세보기
Zhang, J. et al. in 2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring). 1-5.
Li, Y. and Ma, Z., "Deep Learning-based Noise Reduction for？Seismic Data," Journal of Physics: Conference Series, 1861,？012011(2021).

상세보기
Hong, H., Hong, Q., Liu, J., Tong, W. and Shi, L., "Estimating？Relative Noise to Signal in DNA Microarray Data," International Journal of Bioinformatics Research and Applications, 9, 433-448(2013).

상세보기
Sorkhi, M., Jahed-Motlagh, M. R., Minaei-Bidgoli, B. and Daliri,？M. R., "Hybrid Fuzzy Deep Neural Network Toward Temporalspatial-frequency Features Learning of Motor Imagery Signals,"？Sci. Rep., 12, 22334(2022).

상세보기
C, A. et al., "Noise Reduction in CT Images Using a Selective？Mean Filter," Journal of Biomedical Physics & Engineering, 10,？623-634(2020).

상세보기
Huang, T., Yang, G. and Tang, G., "A Fast Two-dimensional Median？Filtering Algorithm," IEEE Transactions on Acoustics, Speech,？and Signal Processing, 27, 13-18(1979).

상세보기
Haddad, R. A. and Akansu, A. N., "A Class of Fast Gaussian？Binomial Filters for Speech and Image Processing," IEEE Transactions on Signal Processing, 39, 723-727(1991).

상세보기
Lee, H., "Analysis of Preconcentration Dynamics inside Dead-end？Microchannel," Korean Chem. Eng. Res., 61, 155-161(2023).
Kim, S. J., Wang, Y.-C., Lee, J. H., Jang, H. and Han, J., "Concentration Polarization and Nonlinear Electrokinetic Flow near a？Nanofluidic Channel," Phys. Rev. Lett., 99, 044501(2007).

상세보기
Kim, S. J., Li, L. D. and Han, J., "Amplified Electrokinetic？Response by Concentration Polarization near Nanofluidic Channel," Langmuir, 25, 7759-7765(2009).

상세보기
Kim, J., Kim, H.-Y., Lee, H. and Kim, S. J., "Pseudo 1-D Micro/Nanofluidic Device for Exact Electrokinetic Responses," Langmuir, 32, 6478-6485(2016).

상세보기
Choi, J. et al., "Selective Preconcentration and Online Collection of？Charged Molecules Using Ion Concentration Polarization," RSC？Adv., 5, 66178-66184(2015).

상세보기
Choi, J. et al., "Nanoelectrokinetic Selective Preconcentration？Based on Ion Concentration Polarization," BIOCHIP J., 14, 100-109(2020).

상세보기
Kim, J., Cho, I., Lee, H. and Kim, S. J., "Ion Concentration？Polarization by Bifurcated Current Path," Sci. Rep., 7, 5091(2017).

상세보기
Dydek, E. V. and Bazant, M. Z., "Nonlinear Dynamics of Ion？Concentration Polarization in Porous Media: The Leaky Membrane？Model," AIChE Journal, 59, 3539-3555(2013).

상세보기
Robertson, R. M., Laib, S. and Smith, D. E., "Diffusion of Isolated DNA Molecules: Dependence on Length and Topology,"？Proc. Natl. Acad. Sci. U.S.A., 103, 7310-7314(2006).

상세보기
Salieb-Beugelaar, G. B., Dorfman, K. D., van den Berg, A. and？Eijkel, J. C. T., "Electrophoretic Separation of DNA in Gels and？Nanostructures," Lab Chip, 9, 2508-2523(2009).

상세보기
Yap, K. K., Fukuda, K., Vail, J. R., Wong, J. and Masen, M. A.,？"Spatiotemporal Mapping for In-situ and Real-time Tribological？Analysis in Polymer-metal Contacts," Tribology International,？171, 107533(2022).

상세보기
Posner, J. D., Perez, C. L. and Santiago, J. G., "Electric Fields？Yield Chaos in Microflows," Proc. Natl. Acad. Sci. U.S.A., 109,？14353-14356(2012).

상세보기
Kwak, R., Pham, V. S. and Han, J., "Sheltering the Perturbed？Vortical Layer of Electroconvection Under Shear Flow," J. Fluid？Mech., 813, 799-823(2017).

상세보기
Cho, S.-Y. et al., "Finding Hidden Signals in Chemical Sensors？Using Deep Learning," Anal. Chem., 92, 6529-6537(2020).

상세보기

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증