Resumen de Predicting prokaryotic and eukaryotic gene networks by fusing domain knowledge with conceptual clustering algorithms

Oscar Marcos Harari

• PREDICTING PROKARYOTIC AND EUKARYOTIC GENE NETWORKS BY FUSING DOMAIN KNOWLEDGE WITH CONCEPTUAL CLUSTERING ALGORITHMS SHORT SUMMARY The PhD dissertation is product of an interdisciplinary work, which includes system and molecular biology, medicine, bioinformatics and computer science, I address the employment of machine learning techniques [2,3,4,5], to identify and predict genetic networks. I propose a methodology able to find novel genetic profiles (i.e., set of genes sharing a subset of attributes) that infers phenotype-genotype relationships.

  Gene expression is central to these relationship [6]; thus I study the regulatory network governed by the PhoP-PhoQ two-component system in the enteric bacteria Escherichia coli and Salmonella enterica. The work uncovers cis-elements relevant to differential gene expression, and by decomposing binding sites from a transcription factor into families of motifs, it enhances their prediction, helps discerning functional from non-functional binding sites in messy genome-wide analysis (e.g., microarray, ChIP-chip); uncovers physical constraints imposed by the DNA-binding protein interaction [7,8]; and establishes a model of evolution along the enterobacteria [9,10].

  Schizophrenia is a highly heritable disorder, although the identification of individual genes has remained elusive [11]. I employ a conceptual clustering methodology to study the liability to this disorder by independently generating clinical and SNPs profiles, and learning relationships among them that allow modeling and predicting a risk function [12] corresponding to the studied subjects REFERENCES 2. Mitchell T (1997) Machine Learning. New York: McGraw-Hill.

  3. Bezdek JC (1998) Pattern Analysis. In: Pedrycz W, Bonissone PP, Ruspini EH, editors. Handbook of Fuzzy Computation. Bristol: Institute of Physics. pp. F6.1.1-F6.6.20.

  4. Zhang NL (2004) Hierarchical Latent Class Models for Cluster Analysis. Journal of Machine Learning Research 5: 697-723.

  5. Deb K (2001) Multi-objective optimization using evolutionary algorithms. Chichester ; New York: John Wiley & Sons. xix, 497 p.

  6. Wray GA, Hahn MW, Abouheif E, Balhoff JP, Pizer M, et al. (2003) The evolution of transcriptional regulation in eukaryotes. Mol Biol Evol 20: 1377-1419.

  7. Pedersen AG, Jensen LJ, Brunak S, Staerfeldt HH, Ussery DW (2000) A DNA structural atlas for Escherichia coli. J Mol Biol 299: 907-930.

  8. Goni JR, Perez A, Torrents D, Orozco M (2007) Determining promoter location based on DNA structure first-principles calculations. Genome Biol 8: R263.

  9. Alm E, Huang K, Arkin A (2006) The evolution of two-component systems in bacteria reveals different strategies for niche adaptation. PLoS Comput Biol 2: e143.

  10. Moses AM, Pollard DA, Nix DA, Iyer VN, Li XY, et al. (2006) Large-scale turnover of functional transcription factor binding sites in Drosophila. PLoS Comput Biol 2: e130.

  11. Harrison PJ, Weinberger DR (2005) Schizophrenia genes, gene expression, and neuropathology: on the matter of their convergence. Mol Psychiatry 10: 40-68; image 45.

  12. Braff DL, Freedman R, Schork NJ, Gottesman, II (2007) Deconstructing schizophrenia: an overview of the use of endophenotypes in order to understand a complex disorder. Schizophr Bull 33: 21-32.