Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “network analysis”

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 1,675 records · Page 93Linked to original sources
PubMed1991

On the rate of convergence in topology preserving neural networks.

A formal analysis of the neighborhood interaction function selection in the topology preserving unsupervised neural network is presented in this paper. The definition of the neighborhood interaction function is motivated by anatomical evidence as opposed to what is currently used, which is a uniform neighborhood interaction set. By selecting a neighborhood interaction function with a neighborhood amplitude of interaction which is decreasing in spatial domain the topological order is always enforced and the rate of self-organization to final equilibrium state is improved. Several simulations are carried out to show the improvement in rate between using a neighborhood interaction function vs. using a neighborhood interaction set. An error measure functional is further defined to compare the two approaches quantitatively.

Animals↗
PubMed1994

Application of an artificial neural network in epiluminescence microscopy pattern analysis of pigmented skin lesions: a pilot study.

In vivo epiluminescence microscopy (ELM) is a non-invasive technique which improves the clinical diagnosis of naevi and malignant melanoma by providing diagnostic criteria that cannot be appreciated by the naked eye. The present study investigated whether ELM criteria pattern analysis can be employed in an objective, observer-trained, computer-aided diagnostic system, and whether artificial neural networks (ANN) can be applied to the diagnosis of pigmented skin lesions (PSL). The ELM criteria patterns of 200 PSL oil immersion images (60 common naevi, 60 dysplastic naevi, and 80 malignant melanomas) were analysed using a standardized questionnaire. One hundred randomly assigned PSL were used as a training set for an ANN, the remaining 100 PSL serving as the test set. The ANN was trained by backward propagation according to the histological diagnosis, and its performance was compared with that of human investigators. Out of the test set the human investigators correctly diagnosed 88% of PSL and the ANN 86%. In a dichotomized model comparing common, compound, and dysplastic naevi vs. malignant melanoma, i.e. benign vs. malignant PSL, the sensitivity and specificity of human diagnosis was 95 and 90%, respectively, whereas the sensitivity and specificity of the ANN diagnosis was 95 and 88%. Our data indicate that artificial neural networks can be trained to diagnose PSL at a human expert level, based on patterns provided by ELM criteria. We suggest that this technique offers a new approach to the diagnosis of PSL.

Diagnosis, Computer-Assisted↗
PubMed2003

Application of a data-mining method based on Bayesian networks to lesion-deficit analysis.

Although lesion-deficit analysis (LDA) has provided extensive information about structure-function associations in the human brain, LDA has suffered from the difficulties inherent to the analysis of spatial data, i.e., there are many more variables than subjects, and data may be difficult to model using standard distributions, such as the normal distribution. We herein describe a Bayesian method for LDA; this method is based on data-mining techniques that employ Bayesian networks to represent structure-function associations. These methods are computationally tractable, and can represent complex, nonlinear structure-function associations. When applied to the evaluation of data obtained from a study of the psychiatric sequelae of traumatic brain injury in children, this method generates a Bayesian network that demonstrates complex, nonlinear associations among lesions in the left caudate, right globus pallidus, right side of the corpus callosum, right caudate, and left thalamus, and subsequent development of attention-deficit hyperactivity disorder, confirming and extending our previous statistical analysis of these data. Furthermore, analysis of simulated data indicates that methods based on Bayesian networks may be more sensitive and specific for detecting associations among categorical variables than methods based on chi-square and Fisher exact statistics.

Algorithms↗
PubMedDate not supplied

Morphometric analysis of the anastomosing arteriolar network in cat sartorius muscle.

Topological and geometrical characteristics of the anastomotic arteriolar network in cat sartorius muscle were studied. The vessels were dilated and filled with gelatin-ink solution and the muscle cleared with methylsalicylate. The analysis was done on 11 muscles and included 2297 vascular segments and 772 vascular loops classified according to their position within the network. On average, each muscle had 644 transverse arterioles arising from the anastomotic vessels. The length of vascular segments close to feeding arteries was greater than those located in the central region, while the number of transverse arterioles per unit length of arcade vessel showed an opposite tendency. Most vessel orders had similar diameters, except for the segments at the periphery of the muscle, which were significantly larger. No correlation was found between vessel length and diameter. Vascular loops located in the central part of the network were smaller, as assessed by area, perimeter, number of segments, segment length and number of branches. The variability of the parameters between muscles was smaller than variability within each muscle. We concluded that, in addition to the parameters previously reported, quantitative descriptions of anastomotic networks may be enhanced by considering certain topological aspects of microvessels. The separation of segments and loops according to the position in the network may reveal differences between muscles of different sizes and functions which would not be detected if the vessels were considered as a single group.

Animals↗
PubMed1978

Burst generation by electrically coupled network in the snail helisoma: analysis using computer simulation.

The effectiveness of electrical coupling between neurons as a mechanism for mediating single and repetitive bursts is investigated here using computer simulation. The cyberchron network in the snail Helisoma generates repetitive bursts controlling the animal's feeding behavior and served as the basic model for the simulation studies described in this paper. The action potential properties of individual neurons were modeled by the Rall equations describing generalized action potentials. Several properties of electrical coupling and its role in burst generation were demonstrated, including: (1) A neuron in an electrically coupled network can generate action potentials at a higher frequency than an isolated neuron with similar membrane properties due to the loading through the electrical junctions. However, the ability of electrically coupled neurons to generate high-frequency bursts of action potentials requires a concomitantly greater amount of driving current to overcome the junctional loading. (2) Temporal and spatial summation of synaptic input onto a neuron is maintained at its most effective level because the postsynaptic current is integrated across the long postsynaptic membrane time constant. (3) Initial simulations concentrated on a pair of electrically coupled neurons which were below threshold. Stimulation of one of the two neurons with a short pulse resulted in a reverberation or regenerative excitation between the two neurons. The reverberation terminated after a number of action potentials dependent on the specific model parameters. Similar results were obtained with a network containing a greater number (20) of model neurons if approximately one-half of the neurons were stimulated simultaneously. However, none of the cases studied produced more than a single discrete burst. (4) Simulations were also conducted on 20-neuron networks containing two subpopulations of model neurons differing in their values of coupling resistance and excitability. Some networks of this type required stimulation of only one cell to make the two subpopulations of model neurons reverberate with one another. Such simulations suggest the possibility that 'preferred' input pathways involving a small number of neurons would be capable of 'turning on' the activity of the entire network.

Animals↗
PubMed2000

Networking and expert-system analysis: next frontier in biomonitoring.

The extensive use of biomarkers in environment biomonitoring programmes has raised the problem of data management and intercomparison. A research project (Pollution Effect Network, PEN) is proposed here, consisting of the realisation of an on-line warehouse for biomarker data (http://www.muf.unipmn.it/pen). The web site will contain repository sections and expert system procedures able to integrate information from different biomarkers and provide ranking of the organism health status in terms of synthetic stress syndrome indexes. Researchers accessing the site will be able to submit and process their own data. This will allow common criteria in the evaluation of the biological effects of pollutants, and an intercomparison of biomonitoring data among different geographic areas and sentinel species.

Animals↗
PubMedDate not supplied

Diagnosis of sensorineural hearing loss with neural networks versus logistic regression modeling of distortion product otoacoustic emissions.

We investigated whether modeling with artificial neural networks or logistic regression of distortion product otoacoustic emissions (DPOAE), across diverse frequencies, may achieve an accurate diagnosis of sensorineural hearing loss (SNHL) of cochlear origin. 256 ears (90 with SNHL and 166 with normal hearing) were evaluated with pure-tone audiometry, impedance audiometry, speech audiometry and DPOAE. Ears were split into training (n = 176) and validation (n = 80) sets. Input variables included gender, age, examination time, DPOAE intensity at F(2) frequencies 593, 937, 1906, 3812 and 6031 Hz, and respective values corrected for noise levels. In the validation data set, an average network had an area under the receiver operating characteristic curve (AUC) of 0.86 (accuracy 84%). Logistic regressions including all these variables or those selected by backward elimination had AUC values of 0.91 and 0.92, respectively (accuracy 85% both). Eleven of 12 trained networks had better specificity than the backward elimination logistic regression, and the backward elimination logistic regression had a better sensitivity than 11 of the 12 networks. Both modeling approaches correctly identified all ears with sudden hearing loss, congenital hearing loss, head trauma, nuclear jaundice and ototoxicity, and 2-3 of 5 ears with acoustic trauma, but missed 1-3 of 3 ears with Ménière's disease and 4-6 of 8 ears with abnormal pure-tone thresholds on audiometry which had no accompanying findings. For SNHL exceeding 45 dB HL on a pure-tone threshold, sensitivity was 83% (15/18) by neural networks and 84 or 94% (16/18 or 17/18) by logistic regression. Both neural-network-based analysis and logistic regression modeling of the DPOAE pattern across a range of frequencies offer promising approaches for the objective diagnosis of moderate and severe SNHL.

Adult↗
PubMed2004

[Medulloblastoma presenting as an extra-axial tumor in the cerebellopontine angle].

Differences in the imaging characteristic of adult medulloblastomas have been reported, including involvement of lateral cerebellar hemispheres with an extra-axial appearance. We present a case report of this rare circumstance: a 40 year old man presented with a 3 weeks history of headache, morning vomiting and left hearing difficulties. Magnetic resonance imaging revealed a left cerebellopontine angle (CPA) tumor, like a well circumscribed homogeneously enhancing mass. Through a left suboccipital craniectomy the tumor was totally removed. It presented as a cerebellopontine angle tumor, like a meningioma, and not as an intra-axial tumor. Histological analysis revealed that the tumor was composed of densely packed with highly proliferative cells that produce a dense intercellular reticulin fiber network. Inmunohistochemical analysis showed positive expression to synaptophysin, specific neuronal enolase and cromogranin. Histological diagnosis was crucial to define it as a desmoplastic medulloblastoma the present case and to perform postoperative adjuvant therapy. Neurosurgeons should be aware of the possibility that a CPA tumor is of intraaxial origin, because this increase the variability on pathological diagnosis.

Adult↗
PubMed2004

On the neurobiological investigation of language understanding in context.

There are two significant problems in using functional neuroimaging methods to study language. Improving the state of functional brain imaging will depend on understanding how the dependent measure of brain imaging differs from behavioral dependent measures (the "dependent measure problem") and how the activation of the motor system may be confounded with non-motor aspects of processing in certain experimental designs (the "motor output problem"). To address these problems, it may be necessary to shift the focus of language research from the study of linguistic competence to the understanding of language use. This will require investigations of language processing in full multi-modal and environmental context, monitoring of natural behaviors, novel experimental design, and network-based analysis. Such a combined naturalistic approach could lead to tremendous new insights into language and the brain.

Brain Mapping↗
PubMed1999

Global stability analysis in delayed cellular neural networks.

In this paper, the author analyzes further problems of global stability for a class of cellular neural networks with delays by means of the Lyapunov functional method, inequalities a(2)+b(2)> or =2ab and a(3)+b(3)+c(3)> or =3abc (a,b,c > or =0) analysis technique, some stability criteria are obtained under more general conditions. These criteria can be applied to design globally stable networks and thus have important significance in both theory and applications.

Biophysical Phenomena↗
PubMed1992

Predicting protein secondary structure content. A tandem neural network approach.

A priori knowledge of secondary structure content can be of great use in theoretical and experimental determination of protein structure. We present a method that uses two computer-simulated neural networks placed in "tandem" to predict the secondary structure content of water-soluble, globular proteins. The first of the two networks, NET1, predicts a protein's helix and strand content given information about the protein's amino acid composition, molecular weight and heme presence. Because NET1 contained more adjustable parameters (network weights) than learning examples, this network experienced problems with memorization, which is the inability to generalize onto new, never-seen-before examples. To overcome this problem, we designed a second network, NET2, which learned to determine when NET1 was in a state of generalization. Together, these two networks produce prediction errors as low as 5.0% and 5.6% for helix and strand content, respectively, on a set of protein crystal structures bearing little homology to those used in network training. A comparison between three other methods including a multiple linear regression analysis, a non-hidden-node network analysis and a secondary structure assignment analysis reveals that our tandem neural network scheme is, indeed, the best method for predicting secondary structure content. The results of our analysis suggest that the knowledge of sequence information is not necessary for highly accurate predictions of protein secondary structure content.

Databases, Bibliographic↗
PubMed2003

Quantitative chiral analysis in capillary electrophoresis from unresolved peaks using derivative electropherograms, experimental design, and artificial neural networks.

Quantitative capillary electrophoretic analysis of chiral compounds might be difficult or even impossible when baseline separation is not reached. In this work, the use of n-th derivative of the electropherogram was studied and examined on model and experimental data. The electropherograms should be first smoothed using Savitzky-Golay method and the quantitative analysis is then possible using either a graphical method or multivariate calibration applying a combination of experimental design (ED) and artificial neural networks (ANNs). The best results were obtained for the first derivative, higher derivatives are not suitable because of noise accumulation. The method was applied to real experimental data to quantify chiral amino acids from unresolved peaks, but it is applicable for quantitative analysis of any other chiral analytes from poorly resolved peaks. Precision of analysis from partially resolved peaks reached was about +/- 3.2% relative standard deviation.

Amino Acids↗
PubMed1996

Self-organizing neural networks--an alternative way of cluster analysis in clinical chemistry.

Supervised learning schemes have been employed by several workers for training neural networks designed to solve clinical problems. We demonstrate that unsupervised techniques can also produce interesting and meaningful results. Using a data set on the chemical composition of milk from 22 different mammals, we demonstrate that self-organizing feature maps (Kohonen networks) as well as a modified version of error backpropagation technique yield results mimicking conventional cluster analysis. Both techniques are able to project a potentially multi-dimensional input vector onto a two-dimensional space whereby neighborhood relationships remain conserved. Thus, these techniques can be used for reducing dimensionality of complicated data sets and for enhancing comprehensibility of features hidden in the data matrix.

Animals↗
PubMed2001

Quality control in mutation analysis: the European Molecular Genetics Quality Network (EMQN).

UNLABELLED: The demand for clinical molecular genetics testing has steadily grown since its introduction in the 1980s. In order to reach and maintain the agreed quality standards of laboratory medicine, the same internal and external quality assurance (IQA/EQA) criteria have to be applied as for "conventional" clinical chemistry or pathology. In 1996 the European Molecular Genetics Quality Network (EMQN) was established in order to spread QA standards across Europe and to harmonise the existing national activities. EMQN is operated by a central co-ordinator and 17 national partners from 15 EU countries; since 1998 it is being funded by the EU commission for a 3-year period. EMQN promotes QA by two tools: by providing disease-specific best practice meetings (BPM) and EQA schemes. A typical BPM is focussed on one disease or group of related disorders. International experts report on the latest news of gene characterisation and function and the state-of-the-art techniques for mutation detection. Disease-specific EQA schemes are provided by experts in the field. DNA samples are sent out together with mock clinical referrals and a diagnostic question is asked. Written reports must be returned which are marked for genotyping and interpretation. So far, three BPMs have been held and six EQA schemes are in operation at various stages. Although mutation types and diagnostic techniques varied considerably between schemes, the overall technical performance showed a high diagnostic standard. Nevertheless, serious genotyping errors have been occurred in some schemes which underline the necessity of quality assurance efforts. CONCLUSION: The European Molecular Genetics Quality Network provides a necessary platform for the internal and external quality assurance of molecular genetic testing.

Benchmarking↗
PubMed1998

Fourier analysis of the generalized CMAC neural network.

THE CEREBELLAR MODEL ARTICULATION CONTROLLER (CMAC) IS A SIMPLE AND FAST NEURAL NETWORK: these characteristics have extended its successful applications, while the analysis of its representation capabilities, as for many other neural networks, did not follow a similar development.IN THIS ARTICLE WE DISCOVER THE CLOSE PARALLELISM BETWEEN THE REPRESENTATION OF A FUNCTION BY A GENERALIZED CMAC (GCMAC) AND NYQUIST SAMPLING THEORY: discussing the role of different parameters and components of the network according to this similarity. The consideration of a representative example shows how the parallelism can be used to design a GCMAC adapted to its particular application.

Journal Article↗
PubMedDate not supplied

Analysis of the internal representations developed by neural networks for structures applied to quantitative structure--activity relationship studies of benzodiazepines.

An application of recursive cascade correlation (CC) neural networks to quantitative structure-activity relationship (QSAR) studies is presented, with emphasis on the study of the internal representations developed by the neural networks. Recursive CC is a neural network model recently proposed for the processing of structured data. It allows the direct handling of chemical compounds as labeled ordered directed graphs, and constitutes a novel approach to QSAR. The adopted representation of molecular structure captures, in a quite general and flexible way, significant topological aspects and chemical functionalities for each specific class of molecules showing a particular chemical reactivity or biological activity. A class of 1,4-benzodiazepin-2-ones is analyzed by the proposed approach. It compares favorably versus the traditional QSAR treatment based on equations. To show the ability of the model in capturing most of the structural features that account for the biological activity, the internal representations developed by the networks are analyzed by principal component analysis. This analysis shows that the networks are able to discover relevant structural features just on the basis of the association between the molecular morphology and the target property (affinity).

Benzodiazepines↗
PubMed2004

Mutational analysis and biochemical characterization of the Burkholderia thailandensis DW503 quorum-sensing network.

Numerous gram-negative bacteria communicate and regulate gene expression through a cell density-responsive mechanism termed quorum sensing (QS), which involves the synthesis and perception of diffusible N-acyl-homoserine lactones (AHL). In this study we genetically and physiologically characterized the Burkholderia thailandensis DW503 QS network. In silico analysis of the B. thailandensis genome revealed the presence of at least three AHL synthases (AHS) and five transcriptional regulators belonging to the LuxIR family of proteins. Mass spectrometry demonstrated that wild-type B. thailandensis synthesizes N-hexanoyl-homoserine lactone (C6-HSL), N-octanoyl-homoserine lactone (C8-HSL), and N-decanoyl-homoserine lactone (C10-HSL). Mutation of the btaI1 (luxI) AHS gene prevented accumulation of C8-HSL in culture supernatants, enhanced beta-hemolysis of sheep erythrocytes, increased lipase production, and altered colony morphology on swarming and twitching motility plates. Disruption of the btaI3 (luxI) AHS prevented biosynthesis of C6-HSL and increased lipase production and beta-hemolysis, whereas mutagenesis of the btaI2 (luxI) allele eliminated C10-HSL accumulation and reduced lipase production. Complementation of the btaI1 and btaI3 mutants fully restored the synthesis of C8-HSL and C6-HSL to parental levels. In contrast, mutagenesis of the btaR1, btaR3, btaR4, and btaR5 (luxR) transcriptional regulators had no effect on AHL accumulation, enhanced lipase production, and resulted in extensive beta-hemolysis on sheep blood agar plates. Furthermore, interruption of the btaI1, btaR1, and btaR3 genes altered colony morphology on twitching and swarming motility plates and induced pigmentation. Additionally, phenotypic microarray analysis indicated that QS in B. thailandensis both positively and negatively affects the metabolism of numerous substrates, including citric acid, formic acid, glucose 6-phosphate, capric acid, gamma-hydroxybutyric acid, and d-arabinose. These results demonstrate that mutagenesis of the B. thailandensis QS system affects various cellular processes, including lipase production, swarming and twitching motility, beta-hemolysis of sheep erythrocytes, and carbon metabolism and/or transport.

4-Butyrolactone↗