Describing Sequential Association Patterns from Longitudinal Microarray Data Sets in Humans

High throughput gene expression analysis using qPCR is commonly used to identify molecular markers of complex cellular processes. However, statistical analysis of multi-dimensional, temporal gene expression data is complicated by limited biological replicates and large number of measurements. Moreover, many available statistical tools for analysis of time series data assume that the data sequence is static and does not evolve over time. With this assumption, the parameters used to model the time series are fixed and thus, can be estimated by pooling data together. However, in many cases, dynamic processes of biological systems involve abrupt changes at unknown time points, making the assumption of stationary time series break down. We addressed this problem using a combination of statistical methods including hierarchical clustering, change point detection, and multiple testing. We applied this multi-step method to multi-dimensional, temporal gene expression data that resulted from our study of colony size-dependent neural cell differentiation of stem cells. The gene expression data were time series as the observations were recorded sequentially over time. Hierarchical clustering segregated the genes into three distinct clusters based on their temporal expression profiles; change point detection identified specific time points at which the entire dataset was divided into several homogenous subsets to allow a separate analysis of each subset; and multiple testing procedure identified the differentially expressed genes in each cluster within each subset of data. We established that our multi-step approach pinpoints specific sets of genes that underlie colony size-mediated neural differentiation of stem cells and demonstrated its advantages over conventional parametric and non-parametric tests that do not take into account temporal dynamics of the data. Importantly, our proposed approach is broadly applicable to any multivariate data sets of limited sample size from high throughput and high content screening such as in drug and biomarker discovery studies.

Temporal gene expression data is of particular interest to researchers as it can be used to create regulatory gene networks. Such gene networks represent the regulatory relationships between genes over time and provide insight into how genes up- and down-regulate each other from one time-point to the next (the Biological Motherboard). Reverse engineering gene networks from temporal gene expression data is considered an important step in the study of complex biological systems. This paper introduces sensitivity analysis of trained perceptions to reverse engineer the gene networks from temporal gene expression data. It is shown that a trained neural network, with pruning (gene silencing), can also be described as a gene network with minimal re-interpretation, where the sensitivity between nodes reflects the probability of one gene affecting another gene in time. The methodology is known as the Neural Network System Biology Approach with Gene Silencing Simulations (NNSBAGSS). The methodology was applied to artificial temporal data and rat CNS development time-course data.

Analysis of temporal gene expression data poses a significant challenge due to the combination of high dimensionality and low sample size. The purpose of this paper is to present a methodology for classification, modelling, and analysis of short time-series gene expression data using spiking neural networks (SNN) and to uncover temporal expression patterns for knowledge discovery. The classification is based on the NeuCube SNN model. Time-series gene expression data of mouse primary cortical neurons is examined as a case study. The results of the analysis are promising, indicating that SNN methodologies can be effectively used to model and analyse temporal gene expression data with surpassing performance over traditional machine learning algorithms. Additionally, a gene interaction network is constructed from the temporal gene activity modelled using the NeuCube architecture offering a new way of knowledge discovery. Future work will be directed towards using gene interactions networks to help guide pharmacological research for dementia.

Gene expression time course data can be used not only to detect differentially expressed genes but also to find temporal associations among genes. The problem of reconstructing generalized logical networks to account for temporal dependencies among genes and environmental stimuli from transcriptomic data is addressed. A network reconstruction algorithm was developed that uses statistical significance as a criterion for network selection to avoid false-positive interactions arising from pure chance. The multinomial hypothesis testing-based network reconstruction allows for explicit specification of the false-positive rate, unique from all extant network inference algorithms. The method is superior to dynamic Bayesian network modeling in a simulation study. Temporal gene expression data from the brains of alcohol-treated mice in an analysis of the molecular response to alcohol are used for modeling. Genes from major neuronal pathways are identified as putative components of the alcohol response mechanism. Nine of these genes have associations with alcohol reported in literature. Several other potentially relevant genes, compatible with independent results from literature mining, may play a role in the response to alcohol. Additional, previously unknown gene interactions were discovered that, subject to biological verification, may offer new clues in the search for the elusive molecular mechanisms of alcoholism.

Within 0/1 data, co-clustering provides a collection of bi-clusters, i.e., linked clusters for both objects and Boolean properties. Beside the classical need for grouping quality optimization, one can also use user-defined constraints to capture subjective interestingness aspects and thus to improve bi-cluster relevancy. We consider the case of 0/1 data where at least one dimension is ordered, e.g., objects denotes time points, and we introduce co-clustering constrained by interval constraints. Exploiting such constraints during the intrinsically heuristic clustering process is challenging. We propose one major step in this direction where bi-clusters are computed from collections of local patterns. We provide an experimental validation on two temporal gene expression data sets.KeywordsLocal PatternRand IndexGene Expression Data AnalysisInterval ConstraintBoolean PropertyThese 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.

Personalised modelling with spiking neural networks integrating temporal and static information

We have performed a systematic temporal and spatial expression profiling of the developing mouse kidney using Compugen long-oligonucleotide microarrays. The activity of 18,000 genes was monitored at 24-h intervals from 10.5-day-postcoitum (dpc) metanephric mesenchyme (MM) through to neonatal kidney, and a cohort of 3,600 dynamically expressed genes was identified. Early metanephric development was further surveyed by directly comparing RNA from 10.5 vs. 11.5 vs. 13.5dpc kidneys. These data showed high concordance with the previously published dynamic profile of rat kidney development (Stuart RO, Bush KT, and Nigam SK. Proc Natl Acad Sci USA 98: 5649-5654, 2001) and our own temporal data. Cluster analyses were used to identify gene ontological terms, functional annotations, and pathways associated with temporal expression profiles. Genetic network analysis was also used to identify biological networks that have maximal transcriptional activity during early metanephric development, highlighting the involvement of proliferation and differentiation. Differential gene expression was validated using whole mount and section in situ hybridization of staged embryonic kidneys. Two spatial profiling experiments were also undertaken. MM (10.5dpc) was compared with adjacent intermediate mesenchyme to further define metanephric commitment. To define the genes involved in branching and in the induction of nephrogenesis, expression profiling was performed on ureteric bud (GFP+) FACS sorted from HoxB7-GFP transgenic mice at 15.5dpc vs. the GFP- mesenchymal derivatives. Comparisons between temporal and spatial data enhanced the ability to predict function for genes and networks. This study provides the most comprehensive temporal and spatial survey of kidney development to date, and the compilation of these transcriptional surveys provides important insights into metanephric development that can now be functionally tested.

Spatio-temporal data mining is an emerging area with increasing importance in a variety of applications, such as homeland security, mobile services, surveillance systems, and health monitoring applications. However, mining in spatio-temporal databases is still in its infancy. Existing work on spatio-temporal data mining has mainly focused on three types of patterns: evolution patterns of natural phenomena, frequent movements of objects over time, and space-time clusters. While there has been much research on association rule mining on transactional, spatial, and temporal data, there is little literature on finding interesting associations in spatio-temporal data. In this chapter, we introduce the early attempts at spatio-temporal data mining and review the techniques to discover various interesting spatio-temporal patterns. This is followed by a review of the traditional association rules mining algorithms and their variants on transactional data, temporal data, and spatial data.

The real-time system of the JT-60 has a cascade structure with the major and the minor control loops. The multi-variable feedback control is adopted in the major control loop in order to adjust non-linear effects which will appear in the high-/beta/region. By applying the concept of 'phase shift control' to the control program of the major control loop, a flexible tokamak discharge control is expected to be performed with taking account of machine protection.

In biology, cell-fate decisions are controlled by complex gene regulation. Although gene expression data may be collected at multiple time points, it remains difficult to construct the continuous dynamics from the data. In this work, we developed a data-driven approach, NeuralGene, a model based on neural ordinary differential equations (ODEs), to reconstruct continuous dynamical systems governing gene regulation from temporal gene expression data. In addition, NeuralGene has the flexibility of incorporating partial prior biological information in the model to further improve its accuracy. For a given cell at a static time point, the NeuralGene model can impute its continuous gene expression dynamics and predict its cell fate. We applied NeuralGene to a simulation toggle-switch model to verify its utility in modeling and reconstructing temporal dynamics. In addition, NeuralGene was applied to experimental single-cell qPCR data to show its ability for gene expression imputation and cell-fate prediction.

Reverse-engineering transcriptional networks from longitudinal expression profiles is a crucial step towards the study of gene regulatory mechanisms. Genes dynamically orchestrate to each other, the stationarity assumption made by existing methods of transcriptional interaction inference is no longer adequate. As such, we need a new approach to handle the nonstationary behavior in gene expression. On the other hand, microarrays for human studies are equipped with a large number of probe sets, leading the inference of dynamic networks to a computationally intensive task. Hence, there is a need to design the inference algorithm in a tractable manner. This paper develops a Bayesian network approach to inferring the nonstationary transcriptional interactions. The applications of our approach to a clinical study of mechanical periodontal therapy demonstrates a significant improvement over stationary models. Our nonstationary network model also explains the anti-inflammatory effect of mechanical periodontal therapy.

This research demonstrates the application of association rule mining to spatio‐temporal data. Association rule mining seeks to discover associations among transactions encoded in a database. An association rule takes the form A→B where A (the antecedent) and B (the consequent) are sets of predicates. A spatio‐temporal association rule occurs when there is a spatio‐temporal relationship in the antecedent or consequent of the rule. As a case study, association rule mining is used to explore the spatial and temporal relationships among a set of variables that characterize socioeconomic and land cover change in the Denver, Colorado, USA region from 1970–1990. Geographic Information Systems (GIS)‐based data pre‐processing is used to integrate diverse data sets, extract spatio‐temporal relationships, classify numeric data into ordinal categories, and encode spatio‐temporal relationship data in tabular format for use by conventional (non‐spatio‐temporal) association rule mining software. Multiple level association rule mining is supported by the development of a hierarchical classification scheme (concept hierarchy) for each variable. Further research in spatio‐temporal association rule mining should address issues of data integration, data classification, the representation and calculation of spatial relationships, and strategies for finding ‘interesting’ rules.

In this study, new add-on bands in a multispectral dataset of WorldView-2, DigitalGlobe's second next-generation satellite, have been evaluated. For extraction of a specific agriculture crop at a time, WorldView-2 multispectral single, as well as two-date data sets, were used. For this purpose, a class-based sensor independent spectral band ratio normalized difference vegetation index (NDVI) (CBSI-NDVI) and its possibilistice fuzzy classification approach was used. Different agriculture crops selected for the study were sugarcane, late wheat, cauliflower, berseem (fodder), early wheat and ratoon. It is found that bands four and eight with temporal data are good for extracting sugarcane, while bands four, eight and five, seven with temporal data are suitable for late wheat and bands four and eight work well for cauliflower. Similarly, bands five, seven and five, eight with temporal data are good for extracting berseem (fodder), bands four, eight work for early wheat with temporal data and for ratoon four, six single date or four, six and four, eight temporal data. This suitability of bands has been observed with respect to a maximum membership value difference, as well as maximum entropy difference, between the two closest agriculture crops. Thus, it can be concluded that existing bands five, seven and new bands four, six, eight in WorldView-2 are important for identifying and mapping crops mentioned in this study. This indicates new bands, especially four, six, eight introduced in WorldView-2, are more effective than existing bands in QuickBird for mapping specific crops.

Privacy is very important in Data Mining. Association rule mining, is a important technique, has already been applied in a wide range of areas. Large databases cannot be secured by encryption or other techniques because of complexities. These security issues can be divided into two categories: data hiding and knowledge hiding. This paper deals with the problem of association rule mining which preserves the confidentiality of each database i.e. Knowledge hiding. Knowledge hiding is concerned with the sanitization of confidential knowledge from the data. There are many methods to solve this problem. The one, presented in the paper is called support-based and confidence-based blocking schemes. Apriori algorithm is used for mining rule from database. Knowledge hiding is achieved using ISL and DSR. The improvement over sensitive rule hiding is proposed to offer more accuracy and security with smaller negative impact. In ever changing business environment like enterprises e-businesses, the old fashioned disclosure and database inference protection techniques are not capable to ensure complete data privacy. Privacy is important for the on line disclosure of private information Organizations should be able to evaluate the risk of disclosing information and should adopt new more efficient approaches for information disclosure control, in order to maintain their competitive edge in the market. Not only the data but also the hidden knowledge in the data should be made secure. The sensitive information can be extracted in the form of association rules with association rule mining tools. But this can jeopardize the privacy of the customers. Some other rule could be very critical for the company itself such as buying patterns of very rich customers. For example, an Internet based company may give up selling hardware and may concentrate on selling books and videos. Therefore a rule relating the customer buying patterns of hardware may no longer be sensitive for that company. It is desirable to apply a trivial algorithm that hides data by deleting it randomly. Data Mining is the process of discovering new patterns from large data sets involving methods from statistics and artificial intelligence but also database management. Privacy has become an important issue in Data Mining. Many methods have been brought out to solve this problem. This paper focuses on the problem of association rule mining, which hides the knowledge from each database. This paper reviews the major method of knowledge hiding. Association rule mining, as a very important technique, has already been applied in a wide range of areas. Knowledge hiding is concerned with the sanitization of confidential knowledge from the data. As a result of association rule mining, many useful association rules will be discovered, but at the same time, many privacy rules will also be exposed which do not want others to know. To solve this, limit the mining process, in order to keep these sensitive rules being hidden. There are so many methods to solve this problem. The one that is covered in the paper is just one kind of them, called support-based and confidence-based blocking schemes. Algorithm used For Knowledge Hiding is ISL algorithm or DSR algorithm (2). The main disadvantage of a block in algorithm is the fact that the dataset, apart from the blocked values, is not distorted. Thus, an adversary can disclose the hidden rules by identifying those generating item sets that contain question marks and lead to rules with a maximum confidence that lies above the minimum confidence threshold. If the number of these rules is small then the probability of identifying the sensitive ones among them becomes high. To avoid this problem, a method for selectively removing individual values from a database is introduced to prevent the discovery of a set of rules, while preserving the data for other applications. The problem of building privacy preserving algorithms is considered for one category of data mining techniques, the association rule mining. New metrics is introduced in order to demonstrate how security issues can be taken into consideration in the general framework of association rule mining (1).

Coronary Heart Disease (CHD) is a ordinary cardiovascular disease which does gravely harm to humans' health. It belongs to the category of chest stuffiness and pains on usual Indian Medicine. Many more researcher work on the association improvement is a very important research field in data mining. The mining association rule recurrently has been adopting numerous replica support, confidence, interestingness. But this model can't accurate determine the correlative degree between the precursor and the major of the rule by allocation. So we proposed a new mining algorithm of association rules. Proposed a new system based SVM,fuzzy Discriminant support. Our propose Coronary Heart Disease prediction system quantitatively estimate the correlation of rules and reduce many rules that have low support or have no correlation or have negative correlation. In our work we conduct experiments on large real time rural and urban data set and to predict the diseases like Medication in Coronary Heart Disease.