Biomedical Data Translator - Connecting the Dots
summary
A cloud of connected knowledge graphs built by 14 teams answers three templated queries today and exposes an alpha release (Sept 2023) user interface that returns ranked paths, provenance and PubMed snippets. Autonomous relay agents (ARAs) query domain knowledge providers and exchange JSON messages over the Translator Reasoner API (TRAPI/BioLink). Examples include valproic acid→FRAS1 paths and a clinician-used guanosine suggestion that showed measurable patient improvement after about five months. Plans add APIs, user data upload and pathway‑figure OCR.
AI-written summary · about
chapters (7)
- 0:00Introduction
- 3:55Biomedical Data Translator overview
- 12:20Translator development history
- 17:58Demo of Translator UI
- 23:31Clinical use cases
- 27:03Future plans and AI integration
- 31:17Audience questions and next steps
related talks
16mMedQGraph: TMKGs for AI-Driven Healthcare Insights
15mGraphRAG-Powered AI Agents: Transforming Corporate Metadata into Intelligent Knowledge
22mThe Nexus of Innovation: How Knowledge Graphs Fuel AI Scientific Breakthroughs
33mAI Context Engineering for R&D Knowledge Using a Multi-Model Database
44mBuilding Knowledge Graphs
33mSmarter Industrial Fault Diagnosis with Knowledge Graphs and Large Language Models
24mUnleashing the power of FHIR data with knowledge graphs
36mVibing with Data -- Multi-Agent Data Modeling and Constructi...