Explanatory Agent

Back to Home

Description

The explanatory autonomous relay agent (xARA) utilizes a case-based reasoning (CBR) approach to execute ARS queries by obtaining results from multiple knowledge providers (KPs) and relies on natural language understanding models to seek explanations in the biomedical literature to rank KP’s results.
The xARA executes five steps to answer queries: query analysis, KP selection, results in ranking, results grouping, and response.

The current Explanatory Agent Workflow consists of:

• Analogical reasoning engine
• Ranking results through explanations
  • Explanatory evidence via NLU model
  • Explanatory evidence via other methods
• User-centered working group
• Translator Quality Management System (QMS)

Team Contact:

• Rosina Weber ([email protected])
• Eugene Hinderer ([email protected])

Translator Reasoner API

• TRAPI Compatible Link

Knowledge Providers Accessed

• Genetic Knowledge Provider
• Molecular Data Knowledge Provider
• Clinical Data Knowledge Provider
  • [Clinical Open Health Data] (https://github.com/WengLab-InformaticsResearch/cohd_api)
  • [OpenPredict API] (https://openpredict.semanticscience.org/)
  • [Translator Knowledge Collaboratory API] (https://smart-api.info/ui/89054eff6ee6d91641d278d9ffdb3993)
• Multiomics Knowledge Provider
  • [Wellness Knowledge Provider API] (https://smart-api.info/ui/02af7d098ab304e80d6f4806c3527027)
  • [Drug Response Knowledge Provider API] (https://smart-api.info/ui/adf20dd6ff23dfe18e8e012bde686e31)
  • [TCGA Mutation Knowledge Provider API] (https://smart-api.info/ui/5219cefb9d2b8d5df08c3a956fdd20f3)
  • [Clinical Risk Knowledge Provider API] (https://smart-api.info/ui/1bef5ecbb0b9aee90023ce9faa2c8974)

Source Code

• Jupyter Notebook Implementation
• Explanatory Agent

Deployment Pipeline

External Documentation

T.B.D.