This volume contains the papers presented at the inaugural workshop on Data Mining and Bioinformatics at the 32nd International Conference on Very Large Data Bases (VLDB). The purpose of this workshop was to begin bringing - gether researchersfrom database, data mining, and bioinformatics areas to help leverage respective successes in each to the others. We also hope to expose the richness, complexity, and challenges in this area that involves mining very large complex biological data that will only grow in size and complexity as geno- scale high-throughput techniques become more routine. The problems are s- ?ciently di?erent enough from traditional data mining problems (outside of life sciences) that novel approaches must be taken to data mine in this area. The workshop was held in Seoul, Korea, on September 11, 2006. We received 30 submissions in response to the call for papers. Each subm- sion was assigned to at least three members of the Program Committee. The Program Committee discussed the submission electronically, judging them on their importance, originality, clarity, relevance, and appropriateness to the - pected audience. The Program Committee selected 15 papers for presentation. These papers arein the areasof microarraydata analysis, bioinformaticssystem and text retrieval, application of gene expression data, and sequence analysis. Because of the format of the workshop and the high number of submissions, many good papers could not be included.

Inhalt
Bioinformatics at Microsoft Research.- A Novel Approach for Effective Learning of Cluster Structures with Biological Data Applications.- Subspace Clustering of Microarray Data Based on Domain Transformation.- Bayesian Hierarchical Models for Serial Analysis of Gene Expression.- Applying Gaussian Distribution-Dependent Criteria to Decision Trees for High-Dimensional Microarray Data.- A Biological Text Retrieval System Based on Background Knowledge and User Feedback.- Automatic Annotation of Protein Functional Class from Sparse and Imbalanced Data Sets.- Bioinformatics Data Source Integration Based on Semantic Relationships Across Species.- An Efficient Storage Model for the SBML Documents Using Object Databases.- Identification of Phenotype-Defining Gene Signatures Using the Gene-Pair Matrix Based Clustering.- TP+Close: Mining Frequent Closed Patterns in Gene Expression Datasets.- Exploring Essential Attributes for Detecting MicroRNA Precursors from Background Sequences.- A Gene Structure Prediction Program Using Duration HMM.- An Approximate de Bruijn Graph Approach to Multiple Local Alignment and Motif Discovery in Protein Sequences.- Discovering Consensus Patterns in Biological Databases.- Comparison of Modularization Methods in Application to Different Biological Networks.