Bioinformatics and Biomedical Data Sciences: Semantics, Analytics and Knowledge provides an overview of the approaches used in semantic systems biology, introduces novel areas of its application and describes step-wise protocols for transforming heterogeneous data into useful knowledge that can influence healthcare and biomedical research. Given the astronomical increase in the number of published reports, papers, and datasets over the last few decades, the ability to curate this data has become a new field of biomedical and healthcare research. However, this kind of data cannot be handled by the same approaches traditionally used by biomedical scientists and epidemiologist, and it requires high-throughput approaches of semantic and text analysis to curate, understand and disseminate the knowledge hidden in this big data. This book discusses big data text-based mining in order to understand molecular architecture of diseases and to guide health care decision. Additionally, it presents actual research examples to be used as a practical tutorial. The book is a valuable resource for bioinformaticians and members of several areas of biomedical field who are interested in understanding more about how to process and apply great amount of data to improve their research.
Part I Understanding Molecular Architecture of Disease Using Big Data 1. Curation of molecular data pertaining to human cancer and the Cancer Genome Atlas Initiative 2. Merging data from published literature to understand the sequence of disease pathology 3. Predicting potential therapeutic targets using drug-gene and gene-disease associations 4. Combination of graph theory and big data analysis in genomics and proteomics 5. Challenges in sharing, standardization and dissemination of molecular big data Part II Guiding Health Care Decisions Using Big Data 6. Towards a unified version of EMR corpora and data systems 7. Natural language processing and computational linguistics in EMR analysis 8. Orienting infectious disease management using Big Data 9. Modeling disease burden using big data 10. Automated diagnosis and risk factor prediction based on natural language processing Part III Online Repositories and In-Silico Research in the Era of Big Data 11. Curating a brain connectome using Big Data 12. Genotype and phenotype associations using online clinical repositories - a step-wise approach 13. In-silico pharmacology and cost- and time- effective approaches in drug discovery 14. Guided and semi-automatic approaches for clinical meta-analyses 15. Towards a unified language in molecular big data