BioDM 2010 - Workshop Biological Data Mining and its Applications in Healthcare

Scientists in biology and healthcare are facing a growing flood of biological and clinical data, such as DNA microarrays, protein sequences, protein-protein interactions, biological pathways, bio-images, electronic medical records, and biomedical literatures that they need to digest in their research. As the life sciences scientists begin to translate their genomic research from bench to bedside, meaningful observations and discoveries will have to be drawn from a wider array of diverse data with high degrees of data heterogeneity and hierarchy spanning from molecular biology to pharmaceutical and clinical domains. However, their ability to generate large amounts of biological and clinical data may soon surpass their ability to analyze and make sense of the data generated in a timely fashion.

Data mining is well positioned to help the biologists and clinicians draw meaningful observations and discoveries from the vast array of biomedical data that are now available for analysis. However, there are challenges to be addressed; for example, the algorithms need to be able to handle a high level of noise and incompleteness in the data (e.g. protein interactions have high false positive and false negative rates), process computationally intensive tasks effectively (e.g. large scale graph mining), address privacy issues (e.g. patients medical records), and integrate heterogeneous data sources.

The mission of this workshop is to disseminate the latest research challenges, results, and practice of the data mining approaches in biology and healthcare. We encourage submissions of cross-disciplinary research works using data mining and machine learning techniques (data cleansing, data integration, data selection, data transformation, knowledge representation, association mining, clustering, classification, semi-supervised learning, regression, graph mining, text mining, outlier detections, and visualization) to address the challenging issues in biological and clinical data analysis. In addition to bioinformatics applications for computational biology problems, we also seek submissions which apply data mining techniques in healthcare related applications, such as disease diagnosis & prognostics, drug targets identification, biological markers detection, bio-image analysis, disease pathway analysis, as well as medical data mining. We especially welcome submissions that highlight new data mining problems and algorithms that are inspired by the emerging trend of translational research in post-genome computational biology and healthcare.