Slideshow Image

Leibniz Institute of Plant Genetics and Crop Plant Research, Departament of Molecular Genetics, Data Inspection Research Group. Gatersleben, Germany.


Environmental and biomedical sciences share major properties that push utilization of state-of-the-art analysis tools from computational intelligence and machine learning research. Common properties are large numbers of data attributes, attribute correlations caused by spatio-temporal dependencies, and the presence of uncertainty induced by noise and missing values. We plan to combine the learning metrics principle with genetic algorithms for a uniform approach to retrieve relevant subsets of data attributes, and to minimalistic models of associations between different data sets. This way, robust mappings of physico-chemical substance properties to octanol-water partitioning coefficients shall be generated, which are essential building blocks in models of compound transport, e.g. PCB, in the environment. Using the same computational framework, modelling and understanding metabolic processes shall be enhanced by mapping gene- and protein-expression levels to phenotypic properties - a first essential step towards systems biology of stress tolerance in crop plants. The joint development of the new computational methods will allow addressing these and upcoming analytical challenges.


Centro de Investigaciones Príncipe Felipe, Bioinformatics and Genomics Department. Valencia, Spain.

Systems Biology discipline focus the study of biology as the compendium of molecular systems that operate in an interconnected and coordinated way. The development of high-throughput omics technologies such as DNA microarrays enabled genome-wide measurements of the activity of cellular elements and provide the first analytical resources for the establishment of the Systems Biology orientation. Thus, analysis and interpretation of microarray gene expression data has evolved from the gene to the pathway and interaction level, i.e. from the detection of differentially expressed genes, to the establishment of gene interaction networks and the identification of enriched functional categories. Still, the understanding of the biological systems requires a higher level of study, which would be characterized by the interaction between functional modules. In this sense, the main goal of our cooperation research activities is focused in the development of a novel methodological approach to data analysis in Systems Biology which enables the definition of networks of relationships between molecular pathways and the study of their changes across experimental situations. Our proposal has been developed for gene expression data but could be easily extended to other types of molecular high-throughput measurements.

Centro de Química Farmacéutica. Havana, Cuba.

Prediction of physicochemical properties is of major concern for pharmaceutical research. In this context, machine learning methods are of great importance due to their contribution to the development of a plethora of models. In particular, we are working on a novel framework for physicochemical property prediction, where training data is first clustered according to their structural similarity, and a classifier is trained for each conformed cluster. In this regard, the property prediction of a novel candidate drug is modeled by the classifier associated with the cluster that has more structurally-similar compounds with regard to the new putative drug.

School of Computing and Mathematics, University of Ulster. Jordanstown, United Kingdom.

This research line consists in the study of artificial intelligence techniques to infer gene regulatory networks from gene expression data, and to apply software engineering tools to visualize and model such networks. In particular, we are working in the inference of time delay association rules among genes combining adaptive discretization of microarray data with intelligent classification methods, in order to infer complex functional regulation associations. We are also working in the incorporation of another type of biological data sources to the inference process. As a second phase of this research, we will work in the adaptation of model checking techniques for the verification and evaluation of biological hypothesis about the networks behaviors. Our long-term objective is the development of an integrative bioinformatic tool for the inference, modelling and study of gene regulatory mechanism.

Grant Code: 24/N026.
Project Leader:Dra. Nélida B. Brignole.
Supporting Organization: SGCyT-UNS.
Period: 01/01/2009 al 31/12/2011.

The general purpose of this research line consists in the development of new computational methods to efficiently solve complex problems of properties’ prediction, simulation and instrumentation design, which commonly arise in the area of Industrial Process’ Engineering.
The re-engineering of our Decision Support System for instrumentation design will be carried on. The main work will be performed on the standardization of simulation modules of industrial pieces of equipment, and on the prediction of properties according to the CAPE-Open specifications.
With respect to the bioinformatics area, machine learning techniques (including genetic programming and neural networks), and scientific computation for the prediction of ADME-Tox parameters, will be applied.