Application of probabilistic neural network in the clinical diagnosis of cancers based on clinical chemistry data

As a recently developed and powerful classification tool, probabilistic neural network was used to distinguish cancer patients from healthy persons according to the levels of nucleosides in human urine. Two datasets (containing 32 and 50 patterns, respectively) were investigated and the total consistency rate obtained was 100% for dataset 1 and 94% for dataset 2. To evaluate the performance of probabilistic neural network, linear discriminant analysis and learning vector quantization network, were also applied to the classification problem. The results showed that the predictive ability of the probabilistic neural network is stronger than the others in this study. Moreover, the recognition rate for dataset 2 can achieve to 100% if combining, these three methods together, which indicated the promising potential of clinical diagnosis by combining different methods. (C) 2002 Elsevier Science B.V. All rights reserved.

Artificial neural network classification based on high-performance liquid chromatography of urinary and serum nucleosides for the clinical diagnosis of cancer

Nucleosides in human urine and serum have frequently been studied as a possible biomedical marker for cancer, acquired immune deficiency syndrome (AIDS) and the whole-body turnover of RNAs. Fifteen normal and modified nucleosides were determined in 69 urine and 42 serum samples using high-performance liquid chromatography (HPLC). Artificial neural networks have been used as a powerful pattern recognition tool to distinguish cancer patients from healthy persons. The recognition rate for the training set reached 100%. In the validating set, 95.8 and 92.9% of people were correctly classified into cancer patients and healthy persons when urine and serum were used as the sample for measuring the nucleosides. The results show that the artificial neural network technique is better than principal component analysis for the classification of healthy persons and cancer patients based on nucleoside data. (C) 2002 Elsevier Science B.V. All rights reserved.

Preparation and Characterization of Interpenetration Polymer Network Films Based on Poly(vinyl alcohol) and Poly(acrylic acid) for Drug Delivery

A series of full interpenetrating polymer network (full-IPN) films of poly(acrylic acid) (PAA)/poly (vinyl alcohol) (PVA) were prepared by radical solution polymerization and sequential IPN technology. Attenuated total reflectance-Fourier transform infrared spectroscopy, swelling properties, mechanical properties, morphology, and glass transition temperature of the films were investigated. FTIR spectra analysis showed that new interaction hydrogen bonds between PVA and PAA were formed. Swelling property of the films in distilled water and different pH buffer solution was studied. Swelling ratio increased with increasing PAA content of IPN films in all media, and swelling ratio decreased with increasing PVA crosslink degree. Tensile strength and elongation at break related not only to the constitution of IPNs but also to the swelling ratio of IPNs.

Construction of coordination networks with high connectivity: a new 8-connected self-penetrating network based on tetranuclear metal clusters

Two highly connected cobalt(II) and zinc(II) coordination polymers with tetranuclear metal clusters as the nodes of network have been prepared, being the first example of an 8-connected self-penetrating net based on a cross-linked alpha-Po subnet.

Glucose biosensor based on gold nanoparticle-catalyzed luminol electrochemiluminescence on a three-dimensional sol-gel network

An electrochemiluminescent glucose biosensor was proposed based on gold nanoparticle-catalyzed luminol electrochemiluminescence (ECL). Gold nanoparticles were self-assembled onto silica sol-gel network, and then glucose oxidase was adsorbed on the surface of gold nanoparticles. The surface assembly process and the electrochemistry and ECL behaviors of the biosensor were investigated. The assembled gold nanoparticles could efficiently electrocatalyze luminol ECL ECL intensity of the biosensor depended on scan rate, luminol concentration, and size of gold nanoparticles.

Electrochemiluminescence detection of NADH and ethanol based on partial sulfonation of sol-gel network with gold nanoparticles

We developed a stable, sensitive electrochemiluminescence (ECL) biosensor based on the synthesis of a new sol-gel material with the ion-exchange capacity sol-gel to coimmobilize the Ru(bpy)(3)(2+) and enzyme. The partial sulfonated (3-mercaptopropyl)-trimethoxysilane sol-gel (PSSG) film acted as both an ion exchanger for the immobilization of Ru(bpy)(3)(2+) and a matrix to immobilize gold nanoparticles (AuNPs). The AuNPs/PSSG/Ru(bpy)(3)(2+) film modified electrode allowed sensitive the ECL detection of NADH as low as 1 nM. Such an ability of AuNPs/PSSG/Ru(bpy)(3)(2+) film to promote the electron transfer between Ru(bpy)(3)(2+) and the electrode suggested a new, promising biocompatible platform for the development of dehydrogenase-based ECL biosensors. With alcohol dehydrogenase (ADH) as a model, we then constructed an ethanol biosensor, which had a linear range of 5 mu M to 5.2 mM with a detection limit of 12 nM.

DNA network structures on various solid substrates investigated by atomic force microscopy

We have fabricated DNA network structures on glass and sapphire substrates. As a comparison, we also formed the network structure on mica substrate. For titanate strontium substrate, however, DNA network can not be obtained even if it is wet-treated by Na2HPO4 solution to make it hydrophilic. We also discuss the factors that affect the DNA networks formed on various substrates.

Amplification of antigen-antibody interactions based on biotin labeled protein-streptavidin network complex using impedance spectroscopy

Antibody was covalently immobilized by amine coupling method to gold surfaces modified with a self-assembled monolayer of thioctic acid. The electrochemical measurements of cyclic voltammetry and impedance spectroscopy showed that the hexacyanoferrate redox reactions on the gold surface were blocked due to the procedures of self-assembly of thioctic acid and antibody immobilization. The binding of a specific antigen to antibody recognition layer could be detected by measurements of the impedance change. A new amplification strategy was introduced for improving the sensitivity of impedance measurements using biotin labeled protein- streptavidin network complex. This amplification strategy is based on the construction of a molecular complex between streptavidin and biotin labeled protein. This complex can be formed in a cross-linking network of molecules so that the amplification of response signal will be realized due to the big molecular size of complex. The results show that this amplification strategy causes dramatic improvement of the detection sensitivity of hIgG and has good correlation for detection of hIgG in the range of 2-10 mug/ml. (C) 2001 Elsevier Science B.V. All rights reserved.

Self-organization of interlaced network lamellar crystals of trans-1,4-polybutadiene (TPBD) on an amorphous surface

A novel morphology of TPBD crystals consisting of a three-dimensional interlaced network was obtained by casting the self-seeded 0.1% benzene solution onto carbon-boated mica. Both the transmission electron microscopy (TEM) and electron diffraction (ED) analyses showed that the network was composed of well-developed lamellae. It is imagined this interesting morphology is the results of asymmetrical growth of the original TPBD lamellae on the amorphous interface, and that their preferred orientation changed when they encountered each other.

Study on Phenol Compounds Using Multiple Regression and Neural Network Methods

In this paper, the molecular connectivity indices and the electronic charge parameters of forty-eight phenol compounds nave been calculated. and applied for studying the relationship between partition coefficients and structure of phenol compounds. The results demonstrate that the properties of compounds can be described better with selective parameters, and the results obtained by neural network are superior to that by multiplle regression.

A Parallel Crossbar Routing Chip for a Shared Memory Multiprocessor

This thesis describes the design and implementation of an integrated circuit and associated packaging to be used as the building block for the data routing network of a large scale shared memory multiprocessor system. A general purpose multiprocessor depends on high-bandwidth, low-latency communications between computing elements. This thesis describes the design and construction of RN1, a novel self-routing, enhanced crossbar switch as a CMOS VLSI chip. This chip provides the basic building block for a scalable pipelined routing network with byte-wide data channels. A series of RN1 chips can be cascaded with no additional internal network components to form a multistage fault-tolerant routing switch. The chip is designed to operate at clock frequencies up to 100Mhz using Hewlett-Packard's HP34 $1.2\\mu$ process. This aggressive performance goal demands that special attention be paid to optimization of the logic architecture and circuit design.

An in silico approach for screening flavonoids as P-glycoprotein inhibitors based on a Bayesian-regularized neural network

P-glycoprotein (P-gp), an ATP-binding cassette (ABC) transporter, functions as a biological barrier by extruding cytotoxic agents out of cells, resulting in an obstacle in chemotherapeutic treatment of cancer. In order to aid in the development of potential P-gp inhibitors, we constructed a quantitative structure-activity relationship (QSAR) model of flavonoids as P-gp inhibitors based on Bayesian-regularized neural network (BRNN). A dataset of 57 flavonoids collected from a literature binding to the C-terminal nucleotide-binding domain of mouse P-gp was compiled. The predictive ability of the model was assessed using a test set that was independent of the training set, which showed a standard error of prediction of 0.146 +/- 0.006 (data scaled from 0 to 1). Meanwhile, two other mathematical tools, back-propagation neural network (BPNN) and partial least squares (PLS) were also attempted to build QSAR models. The BRNN provided slightly better results for the test set compared to BPNN, but the difference was not significant according to F-statistic at p = 0.05. The PLS failed to build a reliable model in the present study. Our study indicates that the BRNN-based in silico model has good potential in facilitating the prediction of P-gp flavonoid inhibitors and might be applied in further drug design.

A Framework for the Scoring of Operators on the Search Space of Equivalence Classes of Bayesian Network Structures

R. Daly and Q. Shen. A Framework for the Scoring of Operators on the Search Space of Equivalence Classes of Bayesian Network Structures. Proceedings of the 2005 UK Workshop on Computational Intelligence, pages 67-74.