Classification of antibiotics by neural network analysis of optical resonance data of whispering gallery modes in dielectric microspheres

Abstract

A novel emerging technique for the label-free analysis of nanoparticles and biomolecules in liquid fluids using optical micro cavity resonance of whispering-gallery-type modes is being developed.A scheme based on polymer microspheres fixed by adhesive on the evanescence wave coupling element has been used. We demonstrated that the only spectral shift can't be used for identification of biological agents by developed approach. So neural network classifier for biological agents and micro/nano particles classification has been developed. The developed technique is the following. While tuning the laser wavelength images were recorded as avi-file. All sequences were broken into single frames and the location of the resonance was allocated in each frame. The image was filtered for noise reduction and integrated over two coordinates for evaluation of integrated energy of a measured signal. As input data normalized resonance shift of whispering-gallery modes and the relative efficiency of whispering-gallery modes excitation were used. Other parameters such as polarization of excited light, "center of gravity" of a resonance spectra etc. are also tested as input data for probabilistic neural network. After network designing and training we estimated the accuracy of classification. The classification of antibiotics such as penicillin and cephasolin have been performed with the accuracy of not less 97 %. Developed techniques can be used for lab-on-chip sensor based diagnostic tools as for identification of different biological molecules, e.g. proteins, oligonucleotides, oligosaccharides, lipids, small molecules, viral particles, cells and for dynamics of a delivery of medicines to bodies.

Diagnostics of biomedical agents by whispering gallery mode optical resonance based sensor

“…Introducing controlled amount of nano particles (50 nm in diameter glass gel solution) into microsphere surrounding was accompanied also by correlative resonance shift. The most attention was concentrated on development of a technique for recognition and identification of nanoparticles and biomolecules in liquid fluids [8][9][10][11][12]. We demonstrated that the only spectral shift is not sufficient for identification of biological agents by developed approach.…”

“…Several schemes of experimental realization of the method have been tested [13][14][15][16]. The most promising looks a scheme based on polymer microspheres fixed by adhesive on the evanescence wave coupling element [12]. The sensitivity of the developed scheme has been tested by monitoring the whispering gallery mode spectral shift.…”

“…Here the newer version of the scheme has been developed [12]. It uses thin adhesive layer on the surface being in the field of evanescence wave.…”

“…A novel emerging method for the label-free analysis of nanoparticles and biomolecules in liquid fluids using optical micro cavity resonance of whispering-gallery-type modes is being developed [9][10][11][12]. Several schemes of experimental realization of the method have been tested [13][14][15][16].…”

“…We demonstrated that the only spectral shift is not sufficient for identification of biological agents by developed approach. So classifier based on probabilistic neural network for biological agents and micro/nano particles classification has been developed [8][9][10][11][12]. It was tested on solutions of different biological agents.…”