| Amar Das, MD, PhD., Associate Professor of Biomedical Data Science, Associate Professor of Psychiatry, Director of Biomedical Informatics, Dartmouth College, USA Bio: Amar Das is Associate Professor of Biomedical Data Science, Psychiatry and the Dartmouth Institute at the Geisel School of Medicine. He is the founding Director of Biomedical Informatics at Dartmouth, where he established the Informatics Collaboratory for Design, Development, and Dissemination and heads the Social Computing & Health Informatics Lab. His research focuses on temporal database mining and intelligent systems in healthcare and biomedical research. He received his M.D. degree and Ph.D. in Biomedical Informatics from Stanford, where he was also Assistant Professor of Medicine (Biomedical Informatics) and Psychiatry and Behavioral Sciences. He is a recipient of the PhRMA Research Foundation Starter Award in Informatics and has received several best paper awards for his research. Talk Title: Incorporating Semantic Similarity into Machine Learning Approaches for Big Biomedical Data Abstract: Biomedical researchers are inundated with vast amounts of digital information, ranging from electronic medical records to genomic experiments. There is a need for machine learning approaches that can assist in making sense of patterns within such complex data sets. Semantic similarity measures, based on ontologies or concept hierarchies, quantify the relatedness of concepts within complex data sets, and can be used computationally in cluster analysis and information retrieval. In this talk, I discuss the use of semantic similarity in handling two big data challenges: (1) finding distinct patterns of care in a longitudinal clinical database of treatment events, and (2) finding published articles, or snippets within the publications, that match encoded definitions of disease categories. Our research indicates that incorporating background domain knowledge into machine learning approaches improves the relevance of the results. |
| Ulf Leser, PhD., Professor, Director of Knowledge Management in Bioinformatics, Humboldt-Universität in Berlin, Germany Bio: Ulf Leser studied computer science at the Technische Universität München and did his PhD at the Technische Universität Berlin. After positions in research institutes and in the private sector, be became a professor for Knowledge Management in Bioinformatics at Humboldt-Universität zu Berlin. His research focuses on scientific data management, statistical Bioinformatics, biomedical text mining and infrastructures for large-scale Bioinformatics analysis, topics he typically approaches in interdisciplinary projects with biologists and medical doctors. He is speaker of the graduate school SOAMED (Service-oriented architectures for medical applications) and a board member of the Berlin School for Integrative Oncology (BSIO). Title: Storing, Sharing, and Processing of Large Biomedical Data Sets Abstract: Biobanks store and catalog human biological material that is increasingly being digitized using next generation sequencing. There is, however, a computational bottleneck, as existing software systems are not scalable and secure enough to store and process the incoming wave of genomic data. In the BiobankCloud project, we are building a platform for the secure storage, sharing, and parallel processing of genomic data. The system builds on top of Hadoop and includes a scalable scientific workflow engine, a work flow definition language, adaptive scheduling, and support for iterative dataflows. The platform also supports the secure sharing of data across diff erent, distributed Hadoop clusters. The entire system is open-source and includes predefined workflows for popular tasks in biomedical data analysis, such as variant identification, differential transcriptome analysis, and analysis of ChIP-Seq data. |
|
|
