An Efficient Approach in Analysis of DNA Base Calling Using Neural Fuzzy Model

In this paper, a reconfiguration approach using fuzzy logic algorithm and neural network modelling is proposed. When failure has been detected, the state of the degraded system is evaluated by comparing the output of the system with the estimation provided by a neural model. Therefore, we propose to use the neural network in order to cover all the operating zone of the faulty system. By combining neural network capabilities and fuzzy logic for fault evaluation, a new control law is determined taking into account the impact of the failure on the system. Its potentialities are illustrated through simulation studies on a thermal plant presenting bilinear characteristics. >

Furfural production from Eucalyptus globulus: Optimizing by using neural fuzzy models

This paper analyzes the three-level inclusion relationship of high-level innovative talents and combs the structure of high-level scientific and technological talent evaluation models based on big data technology. Aiming at the evaluation problems of high-level scientific and technological talents, a fuzzy neural network model is constructed, and at the same time, the R&D middle school effect is utilized to evaluate the innovation achievements of high-level scientific and technological talents. Construct the evaluation index system of high-level scientific and technological innovative talents by utilizing 6 first-level indexes, 14 second-level indexes and 48 third-level indexes. Create a hierarchical analysis structure model, evaluate the indicator data through a judgment matrix and consistency test, and output the indicator weights. Analyze the relevance of the indicator model for different input layer neurons in fuzzy hierarchical analysis through comparative experiments. Use empirical analysis to analyze the innovative evaluation scores of high-level scientific and technological talents in Group A. The experimental results show that when the input layer contains 48 neurons, the loss value ranges from [0.132,1.765], the loss decreases the fastest, the stronger the indicator correlation, the stronger the generalization ability of the fuzzy neural network regression model. The overall scores of the evaluation of high-level scientific and technological talents of Group A for the first and second-level indicators are 3.54 and 3.869, respectively, and the overall view of Group A’s high-level scientific and technological talent innovative ability is better. Good.

Anaerobic biological wastewater treatment systems are difficult to model because their performance is complex and varies significantly with different reactor configurations, influent characteristics, and operational conditions. Instead of conventional kinetic modeling, advanced neural fuzzy technology was employed to develop a conceptual adaptive model for anaerobic treatment systems. The conceptual neural fuzzy model contains the robustness of fuzzy systems, the learning ability of neural networks, and can adapt to various situations. The conceptual model was used to simulate the daily performance of two high-rate anaerobic wastewater treatment systems with satisfactory results obtained.

Comparison of polynomial and neural fuzzy models as applied to the ethanolamine pulping of vine shoots

In this study, using a model reference adaptation law, a stable fuzzy neural control system is developed. Despite the advantages of Model reference control design technique, which is mainly its power to exactly set trajectories of the system under control, this method is designed for linear system. In this study using fuzzy neural systems, a stable model reference controller for nonlinear systems is developed, Lyapunov method is used to guarantee the stability of fuzzy neural training algorithm and model following of the system under control.

Characterization of Mutant MUTYH Proteins Associated With Familial Colorectal Cancer

BACKGROUND: dtxR gene is a global regulator that can be used as a marker for detection of Corynebacterium diphtheriae (C. diphtheriae) and it is also a representative tool for mapping purpose (molecular typing) of this bacteria. The aim of this study was to analyze the DNA sequences of partial dtxR gene of C. diphtheriae causing diphtheria in some region of Indonesia. DNA sequence analysis was used to verify the accuracy of the in-house multiplex polymerase chain reaction (PCR) method that used for detection of C. diphtheriae in the clinical specimen as well as a preliminary study to determine the strain diversity of C. diphtheriae circulating in Indonesia.METHODS:Ten PCR products targeting the dtxR gene that have been detected as positive C. diphtheriae previously by in-house multiplex PCR used as samples in this study. The DNA sequencing carried out by Sanger method and the sequence data was analyzed by Bioedit software offline and basic local alignment sequence typing (BLAST) online.RESULTS: All of DNA sequence analyzed in this study were similar or identical to the dtxR gene sequence data of C. diphtheriae registered in GenBank. Within the 162 nucleotides (base 150-311) of dtxR gene that analyzed, at least 2 clonals were found among 10 samples. Substitutions of 2 nucleotides (base 225 and 273) was detected, both were silent mutation.CONCLUSION:Ten partial DNA sequences of dtxR genes in this study verify the accuracy of in-house multiplex PCR which used to identify the bacteria causing diphtheria in the clinical specimen. The DNA sequences also represent the existing diversity of the bacteria causing diphtheria circulating in Indonesia.KEYWORDS: dtxR, C. diphtheriae, diphtheria, Indonesia

Scientists in fields ranging from evolution to medicine compare protein or DNA sequences from several biological sources. DNA is a long molecule, deoxyribonucleic acid, that contains genetic codes that control biological processes. The DNA molecule most often consists of two strands of nucleotides each consisting of a deoxyribose residue, a phosphate group, and a nucleotide base. The four nucleotide bases (or bases for short) are denoted A, C, G, T corresponding to adenine, cytosine, guanine, and thymine. The deoxyribose residues linked by phosphate bonds are like the backbone of a single strand of a long necklace with the bases being attached beads. The two strands are linked by hydrogen bonds between pairs of bases, where an A on one strand links with T on the other strand, and a C on one strand links with a G on the other strand. Knowing the sequence of bases in one strand automatically gives the sequence in the complementary strand.KeywordsPerfect MatchCommon WordIndependent SequenceProtein Sequence AnalysisPoisson ApproximationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Hepatocellular carcinoma (HCC) is the sixth most common cancer worldwide and the third leading cause of cancer-related deaths. Patient derived xenografts (PDX), generated by direct engraftment of tumor samples from the patients into immunocompromised mice can be used as an in vivo platform that provides the opportunity to test proposed personalized medicine strategies. In this study, comprehensive molecular characterizations of 28 Chinese HCC PDX models were done by both whole genome sequencing (WGS) and RNAseq technology. After removing contaminated murine DNA/RNA reads by a proprietary algorithm (unpublished) to eliminate homology bias, more than 35 million reads per sample were analyzed in the RNAseq experiment, and at least average 40X coverage at each base of DNA in the WGS experiment. In order to find meaningful targets with high confidence, we integrated multiple lines of evidences from both DNA and RNA levels. Out of 346 gene fusion events were identified in 28 HCC PDXs, 51 occurred in more than one sample and 13 were supported by structural variation evidence from WGS dataset. The same passages (between p3-p5) of 24 PDX tissues were also treated with Sorafenib in the efficacy studies and showed differential responses. The expression of 482 genes (2%) is statistically significantly correlated with drug sensitivity (p-value <0.05), 198 of them (41%) are positively correlated. In the single nucleotide variation (SNV) and indel analysis of WGS dataset, 162 genes were identified as highly mutated genes (p-value <0.05), including classical cancer driver gene TP53. Total 27401 novel SNVs in these 162 genes were identified, 991 (3.6%) of them are nonsynonymous. 557 (2%) SNVs are statistically significantly correlated with drug sensitivity status (p-value<0.05), 28 are nonsynonymous. Pathway analysis shows that these drug responses related genes are enriched in focal adhension formation, induction of apoptosis, P53 signaling pathway, DNA damage response and cell cycle checkpoint. Comparing to other similar studies, our approach of integrative analysis of WGS (vs. Whole exome sequencing) and RNAseq (vs. microarray) provided the most comprehensive genetic insights/landscapes of HCC patients and genetic alterations’ relationship to the drug responses. It also demonstrated that PDX models provide rich information for preclinical studies of experimental therapeutics, and an excellent resource for biomarker discovery and translational research. Citation Format: Hui Zhou, Haisong Lu, Yujian Shi, Gang Hu, He Zhou, Xueyan Yang, Limei Ouyang, Xiaolong Zhu, Zhuolin Gong, Weikang Tao. Integrative pharmacogenomic analysis of patient-derived xenografts of Chinese hepatocellular carcinoma. [abstract]. In: Proceedings of the 105th Annual Meeting of the American Association for Cancer Research; 2014 Apr 5-9; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2014;74(19 Suppl):Abstract nr LB-226. doi:10.1158/1538-7445.AM2014-LB-226

This DOI is not currently attached to any metadata records. DOIs can’t actually ever be deleted (they’re persistent), but sometimes our members create DOIs in error. We do have a process to approximate deletion which we follow only in rare cases where the DOI has been genuinely created in error, and most crucially, if the DOI has never been published anywhere online or in print and never otherwise distributed to or communicated with anyone (authors, readers, reviewers, etc.

In general, fuzzy neural networks cannot match nonlinear systems exactly. Unmodeled dynamic can lead parameters drive and even instability problem. Some robust modifications must be contained, in order to guarantee Lyapunov stability. In this paper input-to-state stability is applied to access robust training algorithm of the fuzzy neural networks. We state that the normal gradient descent law with a time-varying learning rate is stable in the sense of L/sub /spl infin//. The fuzzy neural networks approximation, which is suggested in this paper, needs no robust modification and is robust to any bounded uncertainty.

This paper has investigated a new model based on the brain emotional learning to forecast chaotic series. The proposed model is based on the Moren model which is a model of the emotional part of the brain of mammals. In this paper, we have extended the Moren model based on the actual inputs to the thalamus of mammalian brain, i.e., the number of entries to the thalamus is considered to be more than one. A better performance in chaotic time series forecasting has been achieved in simulations. The results show that in comparison with other methods such as neural network based models and fuzzy neural models, the proposed model has less MSE in both short-term and long-term forecasting for the chaotic time series.

As one of the most important characteristics of structural steels, toughness is assessed by the Charpy V-notch impact test. The absorbed impact energy and the transition temperature defined at a given Charpy energy level are regarded as the common criteria for toughness assessment. This paper aims at establishing generic toughness prediction models which link materials compositions and processing conditions with Charpy impact properties. Hybrid knowledge-based neural-fuzzy modeling techniques which incorporate linguistic knowledge into data-driven neural-fuzzy models have been used to develop the Charpy properties prediction models for thermomechanically controlled rolled (TMCR) steels. Two basic ways of knowledge incorporation are introduced to improve the performance of the obtained fuzzy models. Simulation experiments show that both numeric data and linguistic information can be combined in a unified framework and that both Charpy impact energy and the impact transition temperature (ITT) can be predicted by the same model.

DNA microarray analysis for the detection of mutations in hemophilia A.