ARAX: a graph-based modular reasoning tool for translational biomedicine

Area of Science:

• Biomedical Informatics
• Computational Biology
• Translational Medicine

Background:

• Increasing biomedical data necessitates advanced computational reasoning methods.
• Existing tools lack an expressive workflow language and a federated reasoning engine for translational research.

Purpose of the Study:

• Introduce ARAX, a new reasoning system for translational biomedicine.
• Enable encoding of translational questions and integration of knowledge across diverse sources.

Main Methods:

• Developed novel approaches for query planning, knowledge gathering, reasoning, and result ranking.
• Dynamically integrated knowledge providers for comprehensive biomedical question answering.
• Created a web browser user interface and an application programming interface (API).

Main Results:

• ARAX provides a system for encoding and answering translational biomedical questions.
• Demonstrated ARAX's utility through several disease-specific use-case examples.
• Successfully integrated knowledge across multiple sources to facilitate query answering and result exploration.

Conclusions:

• ARAX offers a powerful new tool for computational reasoning in translational biomedicine.
• The system's design supports dynamic knowledge integration and user-friendly exploration of results.
• ARAX has the potential to accelerate biomedical research by improving knowledge discovery.