Khuan Y. Lee

Classification of salivary based NS1 from Raman Spectroscopy with support vector machine

Non-Structural Protein 1 (NS1) antigen has been recognized as a biomarker for diagnosis of flavivirus viral infections at early stage. Surface Enhanced Raman Spectroscopy (SERS) is an optical technique capable of detecting up to a single molecule. Our previous work has established the Raman fingerprint of NS1 with gold as substrate. Our current study aims to classify NS1 infected saliva samples from healthy samples, a first ever attempt. Saliva samples from healthy subjects, NS1 protein and NS1-saliva mixture samples were analyzed using SERS. The SERS spectra were then pre-processed prior to classification with support vector machine (SVM). NS1-saliva mixture at concentration of 10ppm, 50ppm and 100ppm were examined. Performance of SVM classifier with linear, polynomial and radial basis function (RBF) kernels were compared, in term of accuracy, sensitivity, and specificity. From the results, it can be concluded that SVM classifier is able to classify the samples into NS1 infected samples and normal saliva samples. Of the three kernels, performance in using polynomial and RBF kernel is found surpassing the linear kernel. The best performance is attained with RBF kernel with accuracy of [97.1% 93.4% 81.5%] for 100ppm, 50ppm and 10ppm respectively.

Raman molecular fingerprint of non-structural protein 1 in phosphate buffer saline with gold substrate

SERS is a form of Raman spectroscopy that is enhanced with nano-sensing chip as substrate. It can yield distinct biochemical fingerprint for molecule of solids, liquids and gases. Vice versa, it can be used to identify unknown molecule. It has further advantage of being non-invasive, non-contact and cheap, as compared to other existing laboratory based techniques. NS1 has been clinically accepted as an alternative biomarker to IgM in diagnosing viral diseases carried by virus of flaviviridae. Its presence in the blood serum at febrile stage of the flavivirus infection has been proven. Being an antigen, it allows early detection that can help to reduce the mortality rate. This paper proposes SERS as a technique for detection of NS1 from its scattering spectrum. Contribution from our work so far has never been reported. From our experiments, it is found that NS1 protein is Raman active. Its spectrum exhibits five prominent peaks at Raman shift of 548, 1012, 1180, 1540 and 1650cm-1. Of these, peak at 1012cm-1 scales the highest intensity. It is singled out as the peak to fingerprint the NS1 protein. This is because its presence is verified by the ring breathing vibration of the benzene ring structure side chain molecule. The characteristic peak is found to vary in proportion to concentration. It is found that for a 99% change in concentration, a 96.7% change in intensity is incurred. This yields a high sensitivity of about one a.u. per ppm. Further investigation from the characterization graph shows a correlation coefficient of 0.9978 and a standard error estimation of 0.02782, which strongly suggests a linear relationship between the concentration and characteristic peak intensity of NS1. Our finding produces favorable evidence to the use of SERS technique for detection of NS1 protein for early detection of flavivirus infected diseases with gold substrate.

Optimization of Savitzky-Golay smoothing filter for salivary surface enhanced Raman spectra of non structural protein 1

Raman spectroscopy is a vibration based spectroscopic technique for identifying chemical constituent. The Raman signal can be enhanced by binding with metal nanostructures, resulting in so-called surface-enhanced Raman scattering (SERS). Non-structural protein 1 (NS1), a biomarker for flavivirus origin diseases, is found to present in saliva in low concentration. SERS is promising as an early detection method for NS1 in saliva. However, unwanted features are found to embed in the SERS spectrum, making the characteristic features undetected with visual or automated means. In particular, at low concentration of NS1, the intensity at characteristic peak (Imax) and its signal-to-noise ratio (SNR) is so low that the noisy features actually bury the fingerprint characteristics. In addition to background subtraction and baseline removal, spectrum smoothing using suitable filter is found to improve the spectra SNR. In this study, NS1 dilution dataset from the UiTM-NMRR-12868-NS1-DENV spectral database is used. It is found that SG smoothing filter optimized with a span of 13 and a polynomial degree of order 3 produces the most intense smoothing effect while preserving most of the characteristics of the original spectral waveform, with SNR of 3.76, %RMSE of 33.49% and maximum intensity (Imax) of 98%.

Nonstructural protein 1 characteristic peak from NS1-saliva mixture with Surface-Enhanced Raman spectroscopy

Surface Enhanced Raman spectroscopy (SERS) is an enhanced technique of Raman spectroscopy, which amplifies the intensity of Raman scattering to a practical range with adsorption of analyte onto nano-size plasmonic material such as gold, silver or copper. This feature of SERS has given it a niche in tracing molecular structure, especially useful for marking diseases specific biomarker. NS1 protein has been clinically accepted as an alternative biomarker for diseases caused by flavivirus. Detection of Nonstructural Protein 1 (NS1) will allow early diagnosis of the diseases. Its presence in the blood serum has been reported as early as first day of infection. With gold substrate, our work here intends to explore if SERS is suitable to detect NS1 from saliva, with saliva becoming the most favored alternative to blood as diagnostic fluid due to its advantages in sample collection. Our experimental results find both gold coated slide (GS) and saliva being Raman inactive, but the molecular fingerprint of NS1 protein at Raman shift 1012cm-1, which has never been reported before. The distinct peak is discovered to be attributed by breathing vibration of the benzene ring structure of NS1 side chain molecule. The characteristic peak is also found to vary in direct proportion to concentration of the NS1-saliva mixture, with a correlation coefficient of +0.96118 and a standard error estimation of 0.11382.

Principal component analysis for detection of NS1 molecules from Raman spectra of saliva

NS1 is an early biomarker for detection of flavivirus related diseases such as Japanese Encephalitis, Murray Valley Encephalitis, Tick-borne Encephalitis, West Nile Encephalitis, Dengue Fever and Yellow Fever. At present, it is detected in the infected blood serum through ELISA and immune-chromatographic lateral flow test. As a preliminary study, we are using PCA to extract NS1 feature from SERS spectra of NS1 adulterated saliva. NS1 characteristic peak at about 1000cm-1 is extracted by the most significant principal component, PC1. Using PCA adhoc stopping rules, data dimension is significantly reduced to more than 90% without losing important features from the original data. Furthermore, PCA score plots of the dataset is also showing clear separation between NS1 adulterated saliva and healthy saliva. This encouraging finding is suggesting the possibility to develop a SERS based automatic classification algorithm for detection of NS1 in saliva. Being a salivary based technique, this will lead to a novel, rapid, non-invasive and non-infectious detection method, dispense of problem arising from blood sampling.

Wavelet packet analysis of EEG signals from dyslexic children with writing disability

This paper describes Wavelet Packet Analysis of EEG signal of dyslexic children with writing disability. Two activities were carried out during EEG recordings; relax and and writing letters. EEG signals were collected using biosignal gMobilab system and analysed using Wavelet Packet Decomposition to extract alpha and beta brainwave rhythm. Statistical data such as log energy entropy and standard deviation were used to compare the characteristic of EEG signals from dyslexic and normal children. Result showed that the dyslexic children consumed higher energy at left parietal lobe during writing activity especially those who write incorrectly. The alpha band shows higher log energy entropy for dyslexic children compare to normal children at most channel during relax.

Raman spectra of drop coating deposition Raman for melamine solution

Melamine is an organic compound that is often combined with formaldehyde (chemical compound) to produce melamine resin, a synthetic polymer that is fire resistant and heat tolerant. Melamine can be easily molded while warm but will set into a fixed form, which makes it suitable for certain industrial applications. This compound is considered safe for its normal uses, but food products that are contaminated with it can be unsafe for consumption. Routine consumption can cause acute renal failure, kidneys damage and death. Focusing on the milk with melamine in the market, a rapid and easy method is needed to detect melamine from the milk. Now with Surface Enhanced Raman Spectroscopy (SERS), which is capable of detection up to a single molecule, this problem can be surmounted. This paper describes the characterization of dried melamine sample prepared via drop coating deposition Raman (DCDR) method for Raman analysis. Two chosen substrates were used for sample deposition. The samples were analyzed using Dispersive Raman Spectrometer to observe the Raman spectra for different concentration of diluted melamine solution. Using statistical analysis, our results demonstrate that the melamine peak intensity is linearly proportional to the melamine solution concentration. In addition, the SERS detection method proves to be a fast, highly sensitive and quantitative detection for melamine.

Comparison between characteristics of EEG signal generated from dyslexic and normal children

Electroencephalogram (EEG) is one of the methods to detect dyslexia in children. Dyslexia has to be detected at an early stage to help the children to excel in their study and later be successful in life. In this study, the EEG signals generated from dyslexic and normal children during relax and writing words were processed, analysed and compared. Four electrodes; C3, C4, P3 and P4 were used in the recording of the EEG signals. The recorded EEG signals were filtered using a band pass filter with frequency range of 8 - 30 Hz. The signal was then analyzed using Fast Fourier Transform. Analysis of EEG signals showed that the range of frequency of EEG signals during writing for dyslexic was greater than that of normal children for each electrode placement at beta sub band frequency. The range of frequency of EEG signals for dyslexics is 22-28 Hz whereas for normal children is 14-22 Hz.

Automatic Non-Structural Protien 1 recognition based on LDA classifier

This paper discusses the possibilities of Non Structural Protein 1 (NS1) fingerprint can be classified from Raman spectra of saliva using Linear Discriminant Analysis (LDA). LDA is a supervised statistical method that can be used to classify two or more groups of data. In this research, Raman spectra of saliva and NS1-saliva mixture are obtained using Surface Enhanced Raman Spectroscopy (SERS) technique where gold coated slides (GS) are used as substrates. The NS1-saliva mixtures are prepared into different concentration of 10ppm, 50ppm and 100ppm. After applying simple LDA algorithm, the transformed data of saliva and NS1-saliva mixture are overlapping. However the overlapped data is reduced as the concentration of the mixture increase. It indicate that the algorithm is more suitable for samples with higher amount of NS1. Integration of LDA with other algorithm need to be considered for better classification.

Frequency analysis of EEG signal generated from dyslexic children

Dyslexia is a neurological disorder which needs to be detected at an early stage to know their specific needs and to help them cope with the problem. One of the ways to detect dyslexia is by using Electroencephalogram (EEG). In this study, the EEG signals recorded from dyslexics children while performing writing activities were analyzed. The EEG signals were recorded from 4 channels; C3, C4, P3 and P4 and filtered using band pass filter with frequency range 8 Hz to 30 Hz. The signal was analyzed using Fast Fourier Transform. Analysis of EEG signals showed that the range of frequency for dyslexic children during writing is 22-28 Hz which is considered high and indicates that they are trying hard to write a correct word.