基于GEP的露天矿台阶爆破块度预测模型

针对爆破块度难以预测的问题,选用基因表达式编程(GEP)算法,以MyEclipse为开发工具,建立基于GEP的爆破块度预测模型。选取一组实测数据进行预测,并与库兹列佐夫法(Kuznetsov),多重回归分析法(MVRA),人工神经网络法(ANN)预测的结果进行对比。通过比较,GEP模型预测结果的相关系数最高,平均绝对误差、平方根误差最低,分别是0.957、0.008、0.078。预测结果表明GEP模型在爆破块度预测方面是可行的,为爆破块度预测提供了一种新的方法。     

Lung cancer prediction from microarray data by gene expression programming

Lung cancer is a leading cause of cancer‐related death worldwide. The early diagnosis of cancer has demonstrated to be greatly helpful for curing the disease effectively. Microarray technology provides a promising approach of exploiting gene profiles for cancer diagnosis. In this study, the authors propose a gene expression programming (GEP)‐based model to predict lung cancer from microarray data. The authors use two gene selection methods to extract the significant lung cancer related genes, and accordingly propose different GEP‐based prediction models. Prediction performance evaluations and comparisons between the authors’ GEP models and three representative machine learning methods, support vector machine, multi‐layer perceptron and radial basis function neural network, were conducted thoroughly on real microarray lung cancer datasets. Reliability was assessed by the cross‐data set validation. The experimental results show that the GEP model using fewer feature genes outperformed other models in terms of accuracy, sensitivity, specificity and area under the receiver operating characteristic curve. It is concluded that GEP model is a better solution to lung cancer prediction problems.Inspec keywords: lung, cancer, medical diagnostic computing, patient diagnosis, genetic algorithms, feature selection, learning (artificial intelligence), support vector machines, multilayer perceptrons, radial basis function networks, reliability, sensitivity analysisOther keywords: lung cancer prediction, cancer‐related death, cancer diagnosis, gene profiles, gene expression programming‐based model, gene selection, GEP‐based prediction models, prediction performance evaluations, representative machine learning methods, support vector machine, multilayer perceptron, radial basis function neural network, real microarray lung cancer datasets, cross‐data set validation, reliability, receiver operating characteristic curve     

Robust ANOVA for microarray data

Analysis of Variance (ANOVA) separates the effects of different factors in a dataset. Typical examples for gene microarray data are the factors time and treatment. This separation can improve the interpretability of the results. However, the main effects and interactions, calculated in ANOVA, can be heavily influenced by outliers, large numbers of non-expressed genes with noise, and the heavy-tailedness of the distribution of expression values. Robust methods are less affected by these and will improve the analysis.In this paper, several methods to perform robust nonparametric ANOVA are applied to a large multi-treatment time series dataset. The results are compared with the results obtained with parametric ANOVA using Procrustes analysis. A further comparison is made by Gene Ontology (GO) enrichment analysis of groups of genes identified as significant by inspection of the interaction terms in ANOVA. It is shown that there are significant differences in the estimates of main effects and gene–treatment interactions. ROC curves show an improved representation of current biological knowledge for one particular robust form of ANOVA, using a combination of rank transformed data, with the median as location parameter.     

Resampling-based multiple testing for microarray data analysis

The burgeoning field of genomics has revived interest in multiple testing procedures by raising new methodological and computational challenges. For example, microarray experiments generate large multiplicity problems in which thousands of hypotheses are tested simultaneously. Westfall and Young (1993) propose resampling-basedp-value adjustment procedures which are highly relevant to microarray experiments. This article discusses different criteria for error control in resampling-based multiple testing, including (a) the family wise error rate of West-fall and Young (1993) and (b) the false discovery rate developed by Benjamini and Hochberg (1995), both from a frequentist viewpoint; and (c) the positive false discovery rate of Storey (2002a), which has a Bayesian motivation. We also introduce our recently developed fast algorithm for implementing the minP adjustment to control family-wise error rate. Adjustedp-values for different approaches are applied to gene expression data from two recently published microarray studies. The properties of these procedures for multiple testing are compared.     

Effects of atmospheric ozone on microarray data quality

A data anomaly was observed that affected the uniformity and reproducibility of fluorescent signal across DNA microarrays. Results from experimental sets designed to identify potential causes (from microarray production to array scanning) indicated that the anomaly was linked to a batch process; further work allowed us to localize the effect to the posthybridization array stringency washes. Ozone levels were monitored and highly correlated with the batch effect. Controlled exposures of microarrays to ozone confirmed this factor as the root cause, and we present data that show susceptibility of a class of cyanine dyes (e.g., Cy5, Alexa 647) to ozone levels as low as 5-10 ppb for periods as short as 10-30 s. Other cyanine dyes (e.g., Cy3, Alexa 555) were not significantly affected until higher ozone levels (> 100 ppb). To address this environmental effect, laboratory ozone levels should be kept below 2 ppb (e.g., with filters in HVAC) to achieve high quality microarray data.     

Performance analysis of classifiers for colon cancer detection from dimensionality reduced microarray gene data

Cancer disease is accountable for many deaths that are over 9.6 million in 2018 and roughly one out of six deaths occur because of cancer worldwide. The colon cancer is the second prominent source of death of around 1.8 million cases. This research is inclined to detect the colon cancer from microarray dataset. It will aids the experts to distinguish the cancer cells from normal cells for appropriate determination and treatment of cancer at earlier stages that leads to increase the survival rate of the patients. The high dimensionality in microarray dataset with less samples and more attributes creates lag in the detection capability of the classifier. Hence there is a need for dimensionality reduction techniques to preserve the significant genes that are prominent in the disease classification. In this article, at first ANOVA method used to select the best genes and then principal component analysis (PCA) and fuzzy C-means clustering (FCM) techniques are further employed to choose relevant genes. The PCA and FCM features are classified using model, discriminant, regression, hybrid, and heuristic-based classifiers. The attained results show that the heuristic classifier with PCA features is encapsulated an average classification accuracy of 97.92% for classifying both the colon cancer and normal samples. Also, for FCM features, the Heuristic classifier is maintained at an average classification accuracy of 99.48% and 97.92% for classifying the colon cancer and normal samples, respectively. The Heuristic classifier outperforms with high accuracy than all other classifiers in the classification of colon cancer.     

Prediction of fracture characteristics of metals from high-frequency test data

A method is proposed for the prediction of cyclic crack resistance characteristics of metallic materials under low-frequency loading from high-frequency test data, which is based on a model of development of local plastic deformation regions during the accumulation of fatigue damages and fatigue crack growth with allowance for cyclic loading rate. We performed a comparative analysis of the results of prediction of fatigue fracture diagrams with test data for VT22, VT18U, VNS-25, and AMg6N alloys in a frequency range of 20 Hz–10 kHz. Report on International Conference “Dynamics, Strength, and Life of Machines and Structures” (1–4 November 2005, Kiev, Ukraine). __________ Translated from Problemy Prochnosti, No. 2, pp. 121–128, March–April, 2007.     

Gene networks reconstruction and time-series prediction from microarray data using recurrent neural fuzzy networks

Reverse engineering problems concerning the reconstruction and identification of gene regulatory networks through gene expression data are central issues in computational molecular biology and have become the focus of much research in the last few years. An approach has been proposed for inferring the complex causal relationships among genes from microarray experimental data, which is based on a novel neural fuzzy recurrent network. The method derives information on the gene interactions in a highly interpretable form (fuzzy rules) and takes into account the dynamical aspects of gene regulation through its recurrent structure. To determine the efficiency of the proposed approach, microarray data from two experiments relating to Saccharomyces cerevisiae and Escherichia coli have been used and experiments concerning gene expression time course prediction have been conducted. The interactions that have been retrieved among a set of genes known to be highly regulated during the yeast cell-cycle are validated by previous biological studies. The method surpasses other computational techniques, which have attempted genetic network reconstruction, by being able to recover significantly more biologically valid relationships among genes     

Improved processing of microarray data using image reconstruction techniques

Spotted cDNA microarray data analysis suffers from various problems such as noise from a variety of sources, missing data, inconsistency, and, of course, the presence of outliers. This paper introduces a new method that dramatically reduces the noise when processing the original image data. The proposed approach recreates the microarray slide image, as it would have been with all the genes removed. By subtracting this background recreation from the original, the gene ratios can be calculated with more precision and less influence from outliers and other artifacts that would normally make the analysis of this data more difficult. The new technique is also beneficial, as it does not rely on the accurate fitting of a region to each gene, with its only requirement being an approximate coordinate. In experiments conducted, the new method was tested against one of the mainstream methods of processing spotted microarray images. Our method is shown to produce much less variation in gene measurements. This evidence is supported by clustering results that show a marked improvement in accuracy.     

Increased cross-platform microarray data set correlation via substrate-independent nanofilms

Recently developed substrate-independent nanofilms were utilized to generate highly concordant cross-platform microarray data sets on a diverse set of materials such as glass, mica, silicon, and polymer. Using model DNA and protein dose-response assays, the number of cross-platform data sets exhibiting high correlation (>0.98) increased from 33% to 86% when utilizing platforms coated with substrate-independent nanofilms as opposed to traditional surface coatings such as aminosilane and poly-L-lysine. Furthermore, it is shown how the surface properties of the substrate-independent nanofilms can be tailored through secondary modifications to improve assay performance, demonstrating a viable approach for standardized and rapid biochip development through common, yet upgradable, cross-platform interfaces.     

Comparative analysis of genomic signal processing for microarray data clustering

Genomic signal processing is a new area of research that combines advanced digital signal processing methodologies for enhanced genetic data analysis. It has many promising applications in bioinformatics and next generation of healthcare systems, in particular, in the field of microarray data clustering. In this paper we present a comparative performance analysis of enhanced digital spectral analysis methods for robust clustering of gene expression across multiple microarray data samples. Three digital signal processing methods: linear predictive coding, wavelet decomposition, and fractal dimension are studied to provide a comparative evaluation of the clustering performance of these methods on several microarray datasets. The results of this study show that the fractal approach provides the best clustering accuracy compared to other digital signal processing and well known statistical methods.     

Prediction of constant amplitude fatigue lives of precracked specimens from accelerated fatigue data

The feasibility of using an accelerated fatigue test programme to predict constant amplitude fatigue lives of precracked specimens was examined. An analytical basis for the fracture mechanics approach was developed by modifying earlier work that had been applied to unnotched specimens. A load programme involving a linearly increasing load with cycle number was used for the accelerated tests. The predicted curves from the accelerated test data were found to provide a good fit for the constant amplitude results in 2024-T3 and 7075-T6 aluminium alloys. These results indicate that the accelerated test data can be effectively employed to predict constant amplitude fatigue lives, while also providing a considerable reduction in testing time.     

Prediction of environmental degradation of closed adhesive joints using data from open-faced specimens

A framework was established to predict the fracture toughness of degraded closed DCB (CDCB) joints of a toughened adhesive-aluminum system using fracture data obtained from accelerated degradation tests on open-faced joints. The exposure index (EI), the time integral of water concentration, was calculated at all points in the closed joints using the water diffusion properties of the adhesive. The fracture toughness of the closed joints was then predicted from these calculated EIs by making reference to previously reported fracture toughness data from open-faced DCB (ODCB) specimens degraded to various EI levels. To verify the predictions, fracture experiments and analyses were carried out for closed DCB joints degraded at 60 °C-95% relative humidity (RH) and 60 °C-82% RH conditions. The failure mode of both closed and open DCBs was cohesive in the adhesive layer. Good agreement was observed between the predicted steady-state critical strain energy release rate (G_cs) values and the experimentally measured G_cs values for the degraded closed DCB joints. The results showed that the accelerated open-faced methodology, which significantly reduces the exposure time to reach a given level of degradation, can be used to predict the durability of degraded closed joints used in service conditions. It was also shown that at a given temperature, the knowledge of the degradation behavior at one RH level could be extended to other levels of RH with an acceptable accuracy using the fact that fracture degradation at a given temperature is a unique function of EI, independent of the RH exposure history that gives rise to EI. The results are applicable to other laminated systems where degradation of the bonding layer is a failure mode of concern.     

Investigation of self-organizing oscillator networks for use in clustering microarray data

The self-organizing oscillator network (SOON) is a comparatively new clustering algorithm that does not require the knowledge of the number of clusters. The SOON is distance based, and its clustering behavior is different to density-based algorithms in a number of ways. This paper examines the effect of adjusting the control parameters of the SOON with four different datasets; the first is a (communications) modulation dataset representing one modulation scheme under a variety of noise conditions. This allows the assessment of the behavior of the algorithm with data varying between highly separable and nonseparable cases. The main thrust of this paper is to evaluate its efficacy in biological datasets. The second is taken from microarray experiments on the cell cycle of yeast, while the third and the fourth represent two microarray cancer datasets, i.e., the lymphoma and the liver cancer datasets. The paper demonstrates that the SOON is a viable tool to analyze these problems, and can add many useful insights to the biological data that may not always be available using other clustering methods.     

Prediction of fat oxidation capacity using H-NMR and LC-MS lipid metabolomic data combined with phenotypic data

There is evidence from clinical trials that a low capacity to oxidize dietary fats may predispose human individuals to weight gain, obesity, and weight regain following weight loss. These observations have led to a need to identify plasma markers of fat oxidation capacity in order to avoid time consuming direct measurements by indirect calorimetry. The aim of this study was to investigate whether prediction of fat oxidation capacity in an obese population is possible, using ¹H-NMR and LC-MS-based metabolic profiling of blood plasma samples collected before and after a high fat test meal from 100 obese women, who represented the extremes of fat oxidizing capacity. Subject characteristics (baseline anthropometrics, body composition and dietary records) and clinical data (blood values and derived measures for insulin resistance) were recorded into a phenotypic dataset. Filtering by orthogonal signal correction, variable reduction by spectra segmentation, Mann–Whitney U tests and genetic algorithms were applied to spectral data together with partial least squares regression models for prediction. Our findings suggested that only a small fraction of subject variation contained in metabolic profiles is related to fat oxidation capacity and variable reduction methods improved fat oxidation capacity predictability. The LC-MS dataset led to higher specificity (fasting: 86%; postprandial: 73%) and sensitivity (fasting: 75%; postprandial: 75%) than classification using the ¹H-NMR dataset (specificity: fasting: 50%; postprandial: 60%; sensitivity: fasting: 67%; postprandial: 62%). Inclusion of phenotypic variables increased specificity and sensitivity values in both fasting and postprandial time points. However, the moderate specificity and sensitivity values indicated that fat oxidation capacity may only be reflected in subtle differences in the metabolic profiles analyzed. In future studies, metabolomics data may be supplemented with gene variation and gene expression data to caption the properties of fat oxidation capacity more precisely.     

An optimal choice of window width for LOWESS normalization of microarray data

The purpose of normalization in microarray data analysis is to minimize systematic variations in the measured gene expression levels of two co-hybridized mRNA samples so that biological differences can be more easily distinguished. The most commonly and widely used normalization procedure for spotted arrays is probably the intensity dependent and print-tip LOWESS normalization. It is well known that the choices of different parameter values greatly affect the quality of the normalization results, and thus poor quality of the normalization results could be due to the arbitrary choice of the smoothing parameters for LOWESS normalization. In many normalization studies, however, LOWESS has been simply used without rigorous consideration of the parameters. In this article, we propose a bootstrap method to find the optimal window width in print-tip normalization by applying the cross validation technique. We also compare through simulation studies the normalization results by using the proposed method with those by fixing the window width.     

Prediction of the cushioning properties of corrugated fibreboard from static and quasi-dynamic compression data

The relation between static and quasi-dynamic stress-strain compression data and the peak acceleration observed in the impact test for cushioning pads made of corrugated fibreboard is discussed. As a result, a predictive model of cushioning properties of such pads based on static and quasi-dynamic compression data obtained from experiment has been developed. The model represents an original approach to the presentation of cushioning data. © 1997 John Wiley & Sons, Ltd.