Integrated structure selection and parameter optimisation for eng-genes neural models

The eng-genes concept involves the use of fundamental known system functions as activation functions in a neural model to create a 'grey-box' neural network. One of the main issues in eng-genes modelling is to produce a parsimonious model given a model construction criterion. The challenges are that (1) the eng-genes model in most cases is a heterogenous network consisting of more than one type of nonlinear basis functions, and each basis function may have different set of parameters to be optimised; (2) the number of hidden nodes has to be chosen based on a model selection criterion. This is a mixed integer hard problem and this paper investigates the use of a forward selection algorithm to optimise both the network structure and the parameters of the system-derived activation functions. Results are included from case studies performed on a simulated continuously stirred tank reactor process, and using actual data from a pH neutralisation plant. The resulting eng-genes networks demonstrate superior simulation performance and transparency over a range of network sizes when compared to conventional neural models. (c) 2007 Elsevier B.V. All rights reserved.

Hierarchical coordination of periodic genes in the cell cycle of Saccharomyces cerevisiae

Background: Gene networks are a representation of molecular interactions among genes or products thereof and, hence, are forming causal networks. Despite intense studies during the last years most investigations focus so far on inferential methods to reconstruct gene networks from experimental data or on their structural properties, e.g., degree distributions. Their structural analysis to gain functional insights into organizational principles of, e.g., pathways remains so far under appreciated.

Predicting Cell Cycle Regulated Genes by Causal Interactions

The fundamental difference between classic and modern biology is that technological innovations allow to generate high-throughput data to get insights into molecular interactions on a genomic scale. These high-throughput data can be used to infer gene networks, e. g., the transcriptional regulatory or signaling network, representing a blue print of the current dynamical state of the cellular system. However, gene networks do not provide direct answers to biological questions, instead, they need to be analyzed to reveal functional information of molecular working mechanisms. In this paper we propose a new approach to analyze the transcriptional regulatory network of yeast to predict cell cycle regulated genes. The novelty of our approach is that, in contrast to all other approaches aiming to predict cell cycle regulated genes, we do not use time series data but base our analysis on the prior information of causal interactions among genes. The major purpose of the present paper is to predict cell cycle regulated genes in S. cerevisiae. Our analysis is based on the transcriptional regulatory network, representing causal interactions between genes, and a list of known periodic genes. No further data are used. Our approach utilizes the causal membership of genes and the hierarchical organization of the transcriptional regulatory network leading to two groups of periodic genes with a well defined direction of information flow. We predict genes as periodic if they appear on unique shortest paths connecting two periodic genes from different hierarchy levels. Our results demonstrate that a classical problem as the prediction of cell cycle regulated genes can be seen in a new light if the concept of a causal membership of a gene is applied consequently. This also shows that there is a wealth of information buried in the transcriptional regulatory network whose unraveling may require more elaborate concepts than it might seem at first.

Evaluation of Five Interleukin Genes for Association with End-Stage Renal Disease in White Europeans

Background: Genetic variation within interleukin genes has been reported to be associated with end-stage renal disease (ESRD). These findings have not been consistently replicated. No study has yet reported the comprehensive investigation of IL1A, IL1B, IL1RN, IL6 and IL10 genes. Methods: 664 kidney transplant recipients (cases) and 577 kidney donors (controls) were genotyped to establish if common variants in interleukin genes are associated with ESRD. Single nucleotide polymorphism (SNP) genotype data for each gene were downloaded for a northern and western European population from the International HapMap Project. Haploview was used to visualize linkage disequilibrium and select tag SNPs. Thirty SNPs were genotyped using MassARRAY (R) iPLEX Gold technology and data were analyzed using the chi(2) test for trend. Independent replication was conducted in 1,269 individuals with similar phenotypic characteristics. Results: Investigating all common variants in IL1A, IL1B, IL1RN, IL6 and IL10 genes revealed a statistically significant association (rs452204 p(empirical) = 0.02) with one IL1RN variant and ESRD. This IL1RN SNP tags three other variants, none of which have previously been reported to be associated with renal disease. Independent replication in a separate transplant population of comparable size did not confirm the original observation. Conclusions: Common variants in these five candidate interleukin genes are not major risk factors for ESRD in white Europeans. Copyright (C) 2010 S. Karger AG, Basel