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%.

[1]  Robert Tibshirani,et al.  Discriminant Adaptive Nearest Neighbor Classification , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Jialei Bai,et al.  Application of suspension array for simultaneous detection of four different mycotoxins in corn and peanut. , 2013, Biosensors & bioelectronics.

[3]  S. Nie,et al.  Novel surface-enhanced Raman scattering-based assays for ultra-sensitive detection of human pluripotent stem cells. , 2016, Biomaterials.

[4]  Yonghong He,et al.  Dual-wavelength digital holographic phase and fluorescence microscopy combining with Raman spectroscopy for micro-quartz pieces-based dual-channel encoded suspension array. , 2019, Optics express.

[5]  Vladimir V. Tsukruk,et al.  Electrostatic Deposition of Polyionic Monolayers on Charged Surfaces , 1997 .

[6]  Zhouyi Guo,et al.  Characterization and noninvasive diagnosis of bladder cancer with serum surface enhanced Raman spectroscopy and genetic algorithms , 2015, Scientific Reports.

[7]  Nan Liu,et al.  Highly specific detection of thrombin using an aptamer-based suspension array and the interaction analysis via microscale thermophoresis. , 2015, The Analyst.

[8]  Edgar Guevara,et al.  Use of Raman spectroscopy to screen diabetes mellitus with machine learning tools. , 2018, Biomedical optics express.

[9]  Michael Walsh,et al.  Deep learning for FTIR histology: leveraging spatial and spectral features with convolutional neural networks. , 2019, The Analyst.

[10]  Jea Ho Park,et al.  High throughput differential identification of TMPRSS2-ERG fusion genes in prostate cancer patient urine. , 2017, Biomaterials.

[11]  Sailing He,et al.  Raman reporter-coated gold nanorods and their applications in multimodal optical imaging of cancer cells , 2011, Analytical and bioanalytical chemistry.

[12]  Minseok S Kim,et al.  A microchip filter device incorporating slit arrays and 3-D flow for detection of circulating tumor cells using CAV1-EpCAM conjugated microbeads. , 2014, Biomaterials.

[13]  Naoki Kuwata,et al.  Deep-learning-based data page classification for holographic memory , 2017, Applied optics.

[14]  Eriko Watanabe,et al.  Optical correlation-based cross-domain image retrieval system. , 2017, Optics letters.

[15]  D. Spiller,et al.  A simple method for preparing spectrally encoded magnetic beads for multiplexed detection. , 2007, ACS nano.

[16]  Wang Li,et al.  SERS-fluorescence joint spectral encoding using organic-metal-QD hybrid nanoparticles with a huge encoding capacity for high-throughput biodetection: putting theory into practice. , 2012, Journal of the American Chemical Society.

[17]  Asifullah Khan,et al.  Analysis of hepatitis B virus infection in blood sera using Raman spectroscopy and machine learning. , 2018, Photodiagnosis and photodynamic therapy.

[18]  Homan Kang,et al.  Encoding peptide sequences with surface-enhanced Raman spectroscopic nanoparticles. , 2011, Chemical communications.

[19]  Zhimin Zhang,et al.  Deep learning-based component identification for the Raman spectra of mixtures. , 2019, The Analyst.

[20]  Margarita Osadchy,et al.  Deep Convolutional Neural Networks for Raman Spectrum Recognition: A Unified Solution , 2017, The Analyst.

[21]  M. Amin,et al.  Phenol Photocatalytic Degradation by Advanced Oxidation Process under Ultraviolet Radiation Using Titanium Dioxide , 2013, Journal of environmental and public health.

[22]  D. Pang,et al.  Multiple optical trapping assisted bead-array based fluorescence assay of free and total prostate-specific antigen in serum , 2018, Sensors and Actuators B: Chemical.

[23]  Jian Sun,et al.  Object Detection Networks on Convolutional Feature Maps , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  J. Xu,et al.  Ultrasensitive low-background multiplex mycotoxin chemiluminescence immunoassay by silica-hydrogel photonic crystal microsphere suspension arrays in cereal samples , 2016 .

[25]  Kevin Dhaliwal,et al.  Surface-enhanced Raman scattering in cancer detection and imaging. , 2013, Trends in biotechnology.

[26]  Zhi Huang,et al.  A SERS-based immunoassay with highly increased sensitivity using gold/silver core-shell nanorods. , 2012, Biosensors & bioelectronics.

[27]  Paul Mulvaney,et al.  Tunable whispering gallery mode emission from quantum-dot-doped microspheres. , 2005, Small.

[28]  Xiebing Wang,et al.  Highly efficient preparation of multiscaled quantum dot barcodes for multiplexed hepatitis B detection. , 2013, ACS nano.

[29]  Qinlin Gu,et al.  Tribological behaviors of self-assembled 3-aminopropyltriethoxysilane films on silicon , 2008 .

[30]  Yonghong He,et al.  Dual-digital encoded suspension array based on Raman spectroscopy and laser induced breakdown spectroscopy for multiplexed biodetection , 2019, Sensors and Actuators B: Chemical.