Applications of Statistical and Machine Learning Methods in Bioinformatics

Statistical and machine learning approaches play an increasingly important role in biomedical research. In the absence of fundamental (first principle-based) models, or because of the computational complexity of such models, statistical and machine learning approaches are being used to identify interesting structures in the data (e.g. patterns in gene expression profiles), correlate these patterns and other «input» attributes with (e.g. medically) relevant outcomes, and to develop predictors that can generalize from known data and make predictions for new data instances. Examples of important applications include structural bioinformatics, in which one of the goals is to predict elements of protein structure from amino acid sequence, or microarray gene expression profiling, in which the goal is to discover interesting patterns in gene expression data and correlate them with clinically relevant phenotypes. This volume includes papers submitted to the BIT 2005 workshop on the Applications of Machine and Statistical Learning Methods in Bioinformatics that took place in September 2005 in Torun, Poland.

Autorentext

The Editors: Jaroslaw Meller worked at Hebrew University (Israel), Kyoto University (Japan) and Cornell University (USA). At present, he is an Associate Professor in the Division of Biomedical Informatics, Cincinnati Children's Hospital Research Foundation, focusing his research on protein structure and function prediction.
Wieslaw Nowak is a Professor of the Nicholas Copernicus University in Torun (Poland), where he conducts research in the fields of computational biology and chemistry.

Inhalt
Contents: Baoqiang Cao/Mario Medvedovic/Jaroslaw Meller: Prediction of Transmembrane Domains and Pore-facing Residues in Beta-barrel Membrane Proteins Rafa Adamczak/ukasz Pepowski/Wiesaw Nowak: Performance of Neural Networks Based Transmembrane Helix Prediction Methods Applied to Mosquito Anopheles Gambiae G-Protein Coupled Odorant Receptors Frank Emmert-Streib/Matthias Dehmer: A Systems Biology approach for the classification of DNA Microarray Data Isabelle Rivals/Léon Personnaz: A procedure for the evaluation of the discriminatory power of differentially expressed genes Davide Anguita/Dario Sterpi: Multiclass SVM for the Classification of Microarray Data Shiro Usui: Modeling approach and neuroinformatics in vision science Zvi Boger: Experience in the Applications of Artificial Neural Networks in Bio-Informatics Jaroslaw Meller/Rafa Adamczak/Michael P. Scola/Michael Barnes/Susan D. Thompson/Murray H. Passo/Hermine I. Brunner/David N. Glass/Alexei A. Grom: Machine Learning Analysis of Expression Profiles of Synovial Tissue Cytokines Helps Identify Patients with Systemic Onset Juvenile Rheumatoid Arthritis Anil G. Jegga/Jing Chen/Sivakumar Gowrisankar/Mrunal A. Deshmukhl/Bruce J. Aronow: GenomeTrafac: A Wohle-Genome Resource for the Detection of Conserved Transcription Factor Binding Site Motifs and Clusters in Promoters and Flanking Regions of Known Human-Mouse Gene Orthologs.