Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “Neural Networks, Computer”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 recordsLinked to original sources
PubMed1990

Improvements in protein secondary structure prediction by an enhanced neural network.

Computational neural networks have recently been used to predict the mapping between protein sequence and secondary structure. They have proven adequate for determining the first-order dependence between these two sets, but have, until now, been unable to garner higher-order information that helps determine secondary structure. By adding neural network units that detect periodicities in the input sequence, we have modestly increased the secondary structure prediction accuracy. The use of tertiary structural class causes a marked increase in accuracy. The best case prediction was 79% for the class of all-alpha proteins. A scheme for employing neural networks to validate and refine structural hypotheses is proposed. The operational difficulties of applying a learning algorithm to a dataset where sequence heterogeneity is under-represented and where local and global effects are inadequately partitioned are discussed.

Artificial Intelligence↗
PubMed1997

Computational neural networks for predictive microbiology. II. Application to microbial growth.

The growth of a specific microorganism on a certain food is influenced by a number of environmental factors such as temperature, pH, and salt concentration. Methods that delineate the history of the growth of microorganisms are always subject to a considerable debate and scrutiny in the field of predictive microbiology. Regardless of its types, a growth model (e.g., modified Gompertz model) contains several parameters that vary depending on the microorganisms/food combination and the associated prevailing environmental conditions. The growth model parameters for a set of operating conditions are commonly determined from expressions developed via multiple linear regressions. In the present study, a substitute for the nonlinear regression-based equations is developed using computational neural networks. Computational neural networks are applied herein on experimental data pertaining to the anaerobic growth of Shigella flexneri. Results have indicated that predictions by neural networks offer better agreement with experimental data as compared to predictions obtained via corresponding regression equations.

Neural Networks, Computer↗
PubMedDate not supplied

Correction of temperature variations in kinetic-based determinations by use of pruning computational neural networks in conjunction with genetic algorithms.

The joint use of genetic algorithms and pruning computational neural networks is shown to be an effective means for selecting the number of inputs required to correct temperature variations in kinetic-based determinations. The genetic algorithm uses a pruning procedure based on Bayesian regularization and is highly efficient as a feature selector; it provides quite good results in the generalization process without the need to use a validation set. The fitness function is defined as the sum of two subfunctions: one controls the learning ability of the network and the other its complexity. The training, pruning, and generalization processes were initially tested with simulated data in order to acquire preliminary information for the ensuing work with real data. The performance of the proposed method was assessed by applying it to the determination of the amino acid L-glycine by its classical spectrophotometric reaction with ninhydrin. A straightforward network topology including temperature as input (40+T:2:1 with 19 connections after the pruning process) was used to estimate the L-glycine concentration from kinetic curves affected by temperature variations over the range 60-75 degrees C, using kinetic data acquired up to only 1.5 half-lives. The trained network estimates this concentration with a standard error of prediction for the testing set of ca. 8%, which is much smaller than those provided by a classical parametric method such as nonlinear regression (even if kinetic data acquired at longer half-lives are used). Finally, a kinetic interpretation of the pruning process is provided in order to better demonstrate its potential for kinetic analysis.

Algorithms↗
PubMed1998

Neural network computer program to determine photorefractive keratectomy nomograms.

PURPOSE: To evaluate a commercially available neural network program for calculation of photorefractive keratectomy treatment nomograms. SETTING: University referral refractive surgery clinic. METHODS: PRK/LASIK Brain, a commercial neural network computer program, was trained using the demographics, preoperative clinical data, surgical parameters, and 1 year postoperative clinical data of 44 patients treated with a Summit Technology excimer laser using a 5.0 mm optical zone. The neural-network derived nomogram was compared with the standard treatment nomogram for each patient. The relative contribution of age, sex, keratometry, and intraocular pressure (IOP) to the predicted nomograms was also assessed. RESULTS: Nomograms produced by the neural network were qualitatively similar to the standard nomogram. The sequence of data entry during training affected the network's predictions. Entry ordered by outcome (as opposed to entry by chronological order) yielded a nomogram that was more consistent with the standard nomogram. However, both outcome- and chronologically ordered network-derived nomograms diverged from the standard nomogram in individual patients, including a subset for whom use of the standard nomogram yielded desired refractive results (within 0.25 diopter of emmetropia). Further analysis of the neural-network-derived nomograms revealed marked sensitivity to sex, age, keratometry readings, and IOP. CONCLUSIONS: Neural networks offer a potential means of individualizing treatment nomograms, to account for patient demographics, preoperative examination, surgeon style, and equipment bias. However, a data set of 44 patients was not sufficient to train the PRK/LASIK Brain network to accurately predict treatment parameters in individual cases in the training set. A larger training set or a different learning algorithm may be required to improve the neural network's performance.

Adult↗
PubMed1997

Computational neural networks for predictive microbiology: I. Methodology.

Artificial neural networks are mathematical tools inspired by what is known about the physical structure and mechanism of the biological cognition and learning. Neural networks have attracted considerable attention due to their efficacy to model wide spectrum of challenging problems. In this paper, we present one of the most popular networks, the backpropagation, and discuss its learning algorithm and analyze several issues necessary for designating optimal networks that can generalize after being trained on examples. As an application in the area of predictive microbiology, modeling of microorganism growth by neural networks will be presented in a second paper of this series.

Algorithms↗
PubMedDate not supplied

Interpreting computational neural network QSAR models: a measure of descriptor importance.

We present a method to measure the relative importance of the descriptors present in a QSAR model developed with a computational neural network (CNN). The approach is based on a sensitivity analysis of the descriptors. We tested the method on three published data sets for which linear and CNN models were previously built. The original work reported interpretations for the linear models, and we compare the results of the new method to the importance of descriptors in the linear models as described by a PLS technique. The results indicate that the proposed method is able to rank descriptors such that important descriptors in the CNN model correspond to the important descriptors in the linear model.

Models, Molecular↗
PubMedDate not supplied

Interpreting computational neural network quantitative structure-activity relationship models: a detailed interpretation of the weights and biases.

In this work, we present a methodology to interpret the weights and biases of a computational neural network (CNN) quantitative structure-activity relationship model. The methodology allows one to understand how an input descriptor is correlated to the predicted output by the network. The method consists of two parts. First, the nonlinear transform for a given neuron is linearized. This allows us to determine how a given neuron affects the downstream output. Next, a ranking scheme for neurons in a layer is developed. This allows us to develop interpretations of a CNN model similar in manner to the partial least squares (PLS) interpretation method for linear models described by Stanton. The method is tested on three datasets covering both physical and biological properties. The results of this interpretation method correspond well to PLS interpretations for linear models using the same descriptors as the CNN models, and they are consistent with the generally accepted physical interpretations for these properties.

Algorithms↗
PubMed2001

Linear regression and computational neural network prediction of tetrahymena acute toxicity for aromatic compounds from molecular structure.

A quantitative structure toxicity relationship (QSTR) has been derived for a diverse set of 448 industrially important aromatic solvents. Toxicity was expressed as the 50% growth impairment concentration (ICG(50)) for the ciliated protozoa Tetrahymena and spans the range -1.46 to 3.36 log units. Molecular descriptors that encode topological, geometrical, electronic, and hybrid geometrical-electronic structural features were calculated for each compound. Subsets of molecular descriptors were selected via a simulated annealing technique and a genetic algorithm. From this reduced pool of descriptors, multiple linear regression models and nonlinear models using computational neural networks (CNNs) were derived and then used to predict the ICG(50) values for an external set of representative compounds. An average of 10 nonlinear CNN models with 11-5-1 architecture was found to best describe the system with root-mean-square errors of 0.28, 0.29, and 0.34 log units for the training, cross validation, and prediction sets, respectively.

Animals↗
PubMedDate not supplied

Use of pruned computational neural networks for processing the response of oscillating chemical reactions with a view to analyzing nonlinear multicomponent mixtures.

The suitability of pruned computational neural networks (CNNs) for resolving nonlinear multicomponent systems involving synergistic effects by use of oscillating chemical reaction-based methods implemented using the analyte pulse perturbation technique is demonstrated. The CNN input data used for this purpose are estimates provided by the Levenberg-Marquardt method in the form of a three-parameter Gaussian curve associated with the singular profile obtained when the oscillating system is perturbed by an analyte mixture. The performance of the proposed method was assessed by applying it to the resolution of mixtures of pyrogallol and gallic acid based on their perturbating effect on a classical oscillating chemical system, viz. the Belousov-Zhabotinskyi reaction. A straightforward network topology (3:3:2, with 18 connections after pruning) allowed the resolution of mixtures of the two analytes in concentration ratios from 1:7 to 6:2 with a standard error of prediction for the testing set of 4.01 and 8.98% for pyrogallol and gallic acid, respectively. The reduced dimensions of the selected CNN architecture allowed a mathematical transformation of the input vector into the output one that can be easily implemented via software. Finally, the suitability of response surface analysis as an alternative to CNNs was also tested. The results were poor (relative errors were high), which confirms that properly selected pruned CNNs are effective tools for solving the analytical problem addressed in this work.

Journal Article↗
PubMed2003

Prediction of dihydrofolate reductase inhibition and selectivity using computational neural networks and linear discriminant analysis.

A data set of 345 dihydrofolate reductase inhibitors was used to build QSAR models that correlate chemical structure and inhibition potency for three types of dihydrofolate reductase (DHFR): rat liver (rl), Pneumocystis carinii (pc), and Toxoplasma gondii (tg). Quantitative models were built using subsets of molecular structure descriptors being analyzed by computational neural networks. Neural network models were able to accurately predict log IC(50) values for the three types of DHFR to within +/-0.65 log units (data sets ranged approximately 5.5 log units) of the experimentally determined values. Classification models were also constructed using linear discriminant analysis to identify compounds as selective or nonselective inhibitors of bacterial DHFR (pcDHFR and tgDHFR) relative to mammalian DHFR (rlDHFR). A leave-N-out training procedure was used to add robustness to the models and to prove that consistent results could be obtained using different training and prediction set splits. The best linear discriminant analysis (LDA) models were able to correctly predict DHFR selectivity for approximately 70% of the external prediction set compounds. A set of new nitrogen and oxygen-specific descriptors were developed especially for this data set to better encode structural features, which are believed to directly influence DHFR inhibition and selectivity.

Animals↗
PubMed1996

Neural network computer simulation of medical aerosols.

Preliminary investigations have been conducted to assess the potential for using artificial neural networks to simulate aerosol behaviour, with a view to employing this type of methodology in the evaluation and design of pulmonary drug-delivery systems. Details are presented of the general purpose software developed for these tasks; it implements a feed-forward back-propagation algorithm with weight decay and connection pruning, the user having complete run-time control of the network architecture and mode of training. A series of exploratory investigations is then reported in which different network structures and training strategies are assessed in terms of their ability to simulate known patterns of fluid flow in simple model systems. The first of these involves simulations of cellular automata-generated data for fluid flow through a partially obstructed two-dimensional pipe. The artificial neural networks are shown to be highly successful in simulating the behaviour of this simple linear system, but with important provisos relating to the information content of the training data and the criteria used to judge when the network is properly trained. A second set of investigations is then reported in which similar networks are used to simulate patterns of fluid flow through aerosol generation devices, using training data furnished through rigorous computational fluid dynamics modelling. These more complex three-dimensional systems are modelled with equal success. It is concluded that carefully tailored, well trained networks could provide valuable tools not just for predicting but also for analysing the spatial dynamics of pharmaceutical aerosols.

Aerosols↗
PubMedDate not supplied

Prediction of glass transition temperatures from monomer and repeat unit structure using computational neural networks.

Quantitative structure-property relationships (QSPR) are developed to correlate glass transition temperatures and chemical structure. Both monomer and repeat unit structures are used to build several QSPR models for Parts 1 and 2 of this study, respectively. Models are developed using numerical descriptors, which encode important information about chemical structure (topological, electronic, and geometric). Multiple linear regression analysis (MLRA) and computational neural networks (CNNs) are used to generate the models after descriptor generation. Optimization routines (simulated annealing and genetic algorithm) are utilized to find information-rich subsets of descriptors for prediction. A 10-descriptor CNN model was found to be optimal in predicting T(g) values using the monomer structure (Part 1) for 165 polymers. A committee of 10 CNNs produced a training set rms error of 10.1K (r2 = 0.98) and a prediction set rms error of 21.7 K (r2 = 0.92). An 11-descriptor CNN model was developed for 251 polymers using the repeat unit structure (Part 2). A committee of CNNs produced a training set rms error of 21.1K (r2 = 0.96) and a prediction set rms error of 21.9 K (r2 = 0.96).

Journal Article↗
PubMed1998

Neural Network Computer Analysis of Fetal Heart Rate.

> Objective: A nonsubjective evaluation of intrapartum fetal heart rate (FHR) with a neural network (NNW) computer system and its clinical application. Methods: Eight simple FHR data were input into the NNW computer after 16-step normalizations. The computer was composed of 40 units in the input layer, 30 in intermediate layer, and 3 in the output layer, and the probabilities to be normal, suspicious, and pathological were obtained at the output. Before use, the computer was trained 10,000 times by 50-min teacher FHR data of 20 cases with known outcomes. The trained NNW computer was tested by FHRs of another 29 cases. The outcome probabilities in 15 min were calculated every 5 min in another 10 cases, and the bar graphs of the probabilities were displayed in sequence in the trendgrams. Results: The trained NNW computer was 100% accurate in the internal check; in the external check 86% of the results were evaluated correctly with the cardiotocogram, Apgar score, and umbilical arterial pH of the 29 test cases. The FHR scores of our conventional computer FHR analysis were higher in the suspicious and pathological groups than the normal group, and the fetal distress index was high in the pathological group. The trendgrams were simply accurate in typically normal or abnormal cases, transitory abnormal probabilities were shown in intermediate cases, and mixed suspicious and pathological probabilities suggested pathological outcome. Conclusions: The outcome probabilities and their trendgrams in the NNW FHR analysis are promising in objective decision making in the intrapartum stage.

Journal Article↗
PubMed1993

Introduction to backpropagation neural network computation.

Neurocomputing is computer modeling based, in part, upon simulation of the structure and function of the brain. Neural networks excel in pattern recognition, that is, the ability to recognize a set of previously learned data. Although their use is rapidly growing in engineering, they are new to the pharmaceutical community. This article introduces neurocomputing using the backpropagation network (BPN).

Animals↗
PubMed2000

[Use of neural network computer technology in the determination of therapeutic strategy in patients with stomach and duodenal ulcer].

The authors present the expert neural network programmed complex "Axon" allowing the prognosis of the course of ulcer disease of the stomach and duodenum to be made. On the basis of the prognosis obtained certain medical strategy can be recommended. The neural network in which the data of treatment of 909 patients with ulcer disease of the stomach and duodenum had been introduced was taken as a basis of the complex. The program is registered in the Russian copyright agency for PC programs, data base and topologies of integrated circuits. The authors consider that the approach proposed will allow the correct medical policy to be chosen which can lead to better results of treatment of patients with ulcer disease and thus the 100 years long contradictions between different specialists in determining medical policy for such category of patients will be overcome.

Duodenal Ulcer↗