Plattner H., Schapranow M.-P. (Ed.) High-Performance In-Memory Genome Data Analysis. How In-Memory Database Technology Accelerates Personalized Medicine

Springer International Publishing Switzerland, 2014. - 239 с.
ISBN: 978-3-319-03034-0We wrote this book to provide details about innovative approaches to process, combine, and analyze data required in the course of personalized treatment. It contains latest research results of applying in-memory database technology to process and analyze big genomic data. Furthermore, we share how to design and develop specific research tools that require real-time analysis of scientific data.
With this book, we contribute by bridging the gap between medical experts, such as physician, clinicians, and biological researchers, and technology experts, such as software developers, database specialists, and statisticians. As a result, we designed a specific structure of the book to support the individual audiences.QuotesHasso Plattner, Matthieu-P. Schapranow and Franziska Häger Innovations for Personalized Medicine
Requirements for Personalized Medicine
Researchers
Clinicians
Patients
Interdisciplinary Teams
Trends in Hardware
In-memory Technology Building Blocks
Combined Column and Row Store
Complete History
Lightweight Compression
Partitioning
Multi-core and Parallelization
Active and Passive Data Store
Reduction of Layers
High-performance In-memory Genome Platform
Application Layer with Micro Applications
Platform Layer
Data Layer
Structure of the WorkData Processing in Personalized Medicine
Marie Schäffer Modeling Genome Data Processing PipelinesRelated Work
Modeling of Genome Data Processing Pipelines
Requirements Engineering
Modeling of Execution Semantics
Machine Readable Model Representation
Application Example
Pipeline Configuration User Interface
Data Format for Pipelines
Evaluation and Discussion
Conclusion and OutlookCornelius Bock Scheduling and Execution of Genome Data Processing PipelinesRelated Work
Method
Requirements of the Execution Environment
In-memory Database as Scheduler
Real-time Scheduling
Application Example
Architecture
Application of Design Patterns
Implementations of Scheduling Policies
Evaluation and Discussion
Conclusion and OutlookFranz Liedke Exchanging Medical KnowledgeRelated Work
In-memory Databases
Sharing Medical Knowledge
Requirements
Application Example
Use Case
System Requirements
Installing Applications
Configuring Applications
Cohort Analysis
Benchmarks
Method
Results
Evaluation and Discussion
Predicate Scan
Aggregation
Join
Conclusion and OutlookJoseph Bethge Billing Processes in Personalized MedicineRelated Work
Requirements Engineering
Entity Definition
Free Price System
Calculation of Usage Fees
In-memory Database Technology
Application Example
Database Schema
Database Functionality
User Interface
Billing Process
Benchmarks
Evaluation
Impact of Transaction Log Size
Impact of Data Partitioning
Conclusion and Outlook
AppendixReal-Time Data Analysis in Personalized Medicine
Ricarda Schüler Real-time Analysis of Patient CohortsRelated Work
Cohort Analysis
K-Means Clustering
Hierarchical Clustering
In-memory Technology Building Blocks
Application Example
Architecture
Application
Benchmarks
Benchmark Data
Benchmarks for In-memory Technology
Benchmarks for R
Impact of Selected Variables
est Procedure and Technical Environment
Results and Discussion
Data Size
Number of Genes
Conclusion and OutlookDominik Müller Ad-hoc Analysis of Genetic PathwaysRelated Work
Pathway Analysis
Existing Analysis Possibilities
Storing a Graph
NoSQL
In-memory Database Technology
Creating an Integrated Pathway Database
Application Example
Benchmarks
Occurrences of Analyzed Genes
Genes in Input Set
Integrated Pathways
Results and Discussion
Occurrences of Analyzed Genes
Genes in Input Set
Integrated Pathways
Conclusion and Outlook
AppendixDavid Heller Combined Search in Structured and Unstructured Medical DataRelated Work
In-memory Database Text Analysis Features
Application Example
Customized Biomedical Dictionaries
Customized Extraction Rules
Post-processing of Text Analysis Results
Trial Filtering
User Interface
Benchmarks
Genes
Partitioning the Text Analysis Result Table
Indexed Trials
Discussion
Conclusion and Outlook
AppendixHasso Plattner and Matthieu-P. Schapranow Real-time Collaboration in the Course of Personalized Medicine
Real-time Combination of Oncology Data
Holistic Patient View
Search in Structured and Unstructured Data
Real-time Analysis of Patient Cohorts
Building Research Hypotheses
Pharmaceutical Feedback Loop
Federal Bureau of Statistics
Health Insurance Companies
Tumor Board of the FutureList of Abbreviations
Index