Document Oriented Graphical Analysis and Prediction.

Area of Science:

• Bioinformatics
• Data Science
• Clinical Informatics

Background:

• Small to mid-size research labs face challenges managing diverse clinical and secondary datasets.
• Efficient data dissemination, correlation, and prediction from these datasets remain a significant bottleneck.

Purpose of the Study:

• To introduce Document Oriented Graphical Analysis and Prediction (DO-GAP), a novel hybrid tool designed to address data management challenges in research laboratories.
• To demonstrate DO-GAP's capability in integrating heterogeneous data sources and facilitating knowledge discovery.

Main Methods:

• Developed DO-GAP, a hybrid tool merging strengths of NoSQL document-oriented and graph databases.
• Utilized document databases for flexible data integration and graph databases for data visualization and knowledge discovery.
• Integrated genomic lab findings and Electronic Health Record (EHR) clinical data.

Main Results:

• DO-GAP provides a flexible and simple mechanism for integrating data from heterogeneous sources.
• The tool enables straightforward querying, data visualization, and knowledge discovery.
• Demonstrated successful integration of genomic and EHR data.

Conclusions:

• DO-GAP offers a robust solution for managing and analyzing complex datasets in research settings.
• The tool's application can extend to various clinical studies, aiding in diagnosis validation and comparison with molecular genetic analysis.