Guest Editorial-Introduction to the Special Issue

Biotechnology and Bioengineering, 2003

The application of DNA microarray technology for analysis of gene expression creates enormous opportunities to accelerate the pace in understanding living systems and identification of target genes and pathways for drug development and therapeutic intervention. Parallel monitoring of the expression profiles of thousands of genes seems particularly promising for a deeper understanding of cancer biology and the identification of molecular signatures supporting the histological classification schemes of neoplastic specimens. However, the increasing volume of data generated by microarray experiments poses the challenge of developing equally efficient methods and analysis procedures to extract, interpret, and upgrade the information content of these databases. Herein, a computational procedure for pattern identification, feature extraction, and classification of gene expression data through the analysis of an autoassociative neural network model is described. The identified patterns and features contain critical information about gene-phenotype relationships observed during changes in cell physiology. They represent a rational and dimensionally reduced base for understanding the basic biology of the onset of diseases, defining targets of therapeutic intervention, and developing diagnostic tools for the identification and classification of pathological states. The proposed method has been tested on two different microarray datasets-Golub's analysis of acute human leukemia [Golub et al. (1999) Science 286:531-537], and the human colon adenocarcinoma study presented by Alon et al. [1999; Proc Natl Acad Sci USA 97:10101-10106]. The analysis of the neural network internal structure allows the identification of specific phenotype markers and the extraction of peculiar associations among genes and physiological states. At the same time, the neural network outputs provide assignment to multiple classes, such as different pathological conditions or tissue samples, for previously unseen instances.

2015

Artificial Neural Network (ANN) is an information-processing archetype that draws inspiration from biological nervous systems, like the brain, in order to process information. The key unit of this information processing system is the large number of highly interconnected processing elements called neurons. Research activities started as early as in 1943 to simulate neural behavior upon building mathematical models. A neural network model is based on the nature of the problem, characteristics of the application domain and the learning procedure of the selected model. Currently, many neural network models have been built, each with distinct performance features. An attempt is made to study the various ANN suitable for clustering with an accuracy similar to the best statistical methods and which are characterized by parallel processing, a distributed architecture, and a large number of nodes, at the same time capable of proposing an optimal number of groups into which the patterns may ...

The emergence of DNA microarray technologies leads to significant advances in molecular biology. Time-course gene expression data are often measured in order to study dynamic biological systems and gene regulatory networks. It is believed that genes demonstrating similar expression profiles over time might give an informative insight into how underlying biological mechanisms work. This importance leads that in microarray gene research, statistical and intelligent models have received considerable attention to analyze complex time-course gene expression data. Recently, various classification models have been applied in order to find genes which show similar periodic pattern expression. In this paper, we consider the classification of gene expression in temporal expression patterns; then propose an Intelligent hybrid classification model, in which an artificial neural network is combined with a multiple linear regression model to classify genes data. Empirical results show that the proposed model can yield more accurate results than other well-known statistical and intelligent classification models. Therefore, it can be applied as an appropriate approach for classification of gene expression data.

1997

Abstract Artificial neural networks are being used with increasing frequency for high dimensional problems of regression or classification. This article provides a tutorial overview of neural networks, focusing on back propagation networks as a method for approximating nonlinear multivariable functions. We explain, from a statistician's vantage point, why neural networks might be attractive and how they compare to other modern regression techniques. KEYWORDS: neural networks function approximation backpropagation.

The correct inference of gene regulatory networks (GRN) remains as a fascinating task for researchers to understand the detailed process of complex biological regulations and functions. With availability of large dimensional microarray data, relationships among thousands of genes can be extracted simultaneously that is a reverse engineering problem. Among the different popular models to infer GRN, Recurrent Neural Networks (RNN) are considered as most popular and promising mathematical tool to model the dynamics of, as well as to infer the correct dependencies among genes from, biological data like time series microarray. RNN is closed loop Neural Network with a delay feedback. By observing the weights of RNN model, it is possible to extract the regulations among genes. Several metaheuristics or optimization techniques were already proposed to search the optimal value of RNN model parameters. In this review, we illustrate different problems regarding reverse engineering of GRN and how different proposed models can overcome these problems. It is observed that finding out the most suitable and efficient optimization techniques for the accurate inference of small artificial, large artificial, Dream4 Network, and real world GRNs with less computational complexity are still an open research problem to all.

Gene array studies can assess the global expression patterns of thousands of genes under multiple conditions. The paper demonstrates the application of large-scale artificial neural networks (ANNs) for gene array analysis and cancer cell identification by training an ANN model on data generated by gene array experiments involving four different small round blue-cell tumors. Recursive input pruning of the ANN model and re-training techniques were used to identify the more relevant genes. Out of the original list of 2308 genes, an ANN model with 9 gene inputs and 5 neurons in the hidden layer correctly classified the four cancer cell types in the training set with only two possible misclassifications in the validation set. These misclassifications were identified as questionable by pattern analysis of the outputs of the ANN hidden neurons. Causal index evaluation shows the influence of each of the identified most relevant genes on the cancer cell classification; this constitutes impor...

Folate metabolism, also known as one-carbon metabolism, is required for several cellular processes including DNA synthesis, repair and methylation. Impairments of this pathway have been often linked to Alzheimer's disease (AD). In addition, increasing evidence from large scale case-control studies, genome-wide association studies, and metaanalyses of the literature suggest that polymorphisms of genes involved in one-carbon metabolism influence the levels of folate, homocysteine and vitamin B12, and might be among AD risk factors. We analyzed a dataset of 30 genetic and biochemical variables (folate, homocysteine, vitamin B12, and 27 genotypes generated by nine common biallelic polymorphisms of genes involved in folate metabolism) obtained from 40 late-onset AD patients and 40 matched controls to assess the predictive capacity of Artificial Neural Networks (ANNs) in distinguish consistently these two different conditions and to identify the variables expressing the maximal amount of relevant information to the condition of being affected by dementia of Alzheimer's type. Moreover, we constructed a semantic connectivity map to offer some insight regarding the complex biological connections among the studied variables and the two conditions (being AD or control). TWIST system, an evolutionary algorithm able to remove redundant and noisy information from complex data sets, selected 16 variables that allowed specialized ANNs to discriminate between AD and control subjects with over 90% accuracy. The semantic connectivity map provided important information on the complex biological connections among one-carbon metabolic variables highlighting those most closely linked to the AD condition.

IEEE Transactions on Neural Networks, 1996

In this paper a general class of fast learning algorithms for feedforward neural networks is introduced and described. The approach exploits the separability of each layer into linear and nonlinear blocks and consists of two steps. The first step is the descent of the error functional in the space of the outputs of the linear blocks (descent in the neuron space), which can be performed using any preferred optimization strategy. In the second step, each linear block is optimized separately by using a Least Squares (LS) criterion.