Docs | BioBox Platform
GuideAPIRelease NotesLog In
  • Welcome to BioBox!
  • Framework
    • Overview
    • Why Graph?
    • Core Concepts
  • Data Packages
    • Data Packages
    • External Ontologies
      • Gene Ontology
      • Tissue
      • Disease
      • Cell Ontology
      • Phenotype
  • How To
    • 🧭Configure your Knowledge Graph Schema
      • πŸ—‚οΈFormat Internal Data For Uploading
      • ‴️Upload Internal Data
    • βš–οΈCreate Prioritization Graph Models
      • πŸ—’οΈGenerate Reports
      • πŸ›£οΈPathway Enrichment
    • πŸ—ΊοΈUse the Graph Explorer
      • βš™οΈRunning Graph Algorithms
      • πŸ’ΎSave Graph Explorer Sessions
    • πŸ”—Use the Query Language
      • Customize the data table returned with your query
      • 🧭Explore and understand your results
      • πŸ“ŠVisualize data returned in Query Language
      • ✏️Modify Queries using the Query Editor
    • Ask questions with Natural Language (GraphRAG)
      • Use Agent Orion to generate a query with Natural Language
      • Use Agent Iris to converse with your data
  • πŸ“ŠVisualize data on the Legacy Platform
    • πŸ“„Create a Genomic Sequencing Dashboard (Legacy Platform)
    • 🍭Create a Stacked Lollipop Plot (Legacy Platform)
    • ↕️Upload raw data (Legacy Platform)
    • πŸ“«Invite Users to Your Organization
  • Release Notes
Powered by GitBook
On this page
  • Tips for Natural Language Prompts
  • Editing the Query Generated
  1. How To
  2. Ask questions with Natural Language (GraphRAG)

Use Agent Orion to generate a query with Natural Language

How to use natural language to generate complex biological queries with Agent Orion

PreviousAsk questions with Natural Language (GraphRAG)NextUse Agent Iris to converse with your data

Last updated 6 months ago

The is an intuitive way to write complex multi-omic queries designed to retrieve information from your graph. We make this even easier though the use of AI Agent Orion. Agent Orion converts your natural language question into a Query Language Query. Agent Orion is accessible from the Query Language page. Select "Natural Language Query Generator" to use the agent.

Check out Agent Orion in action below

To use the agent, type in a very descriptive prompt.

For example

Which genes are upregualted in differential expression datasets where the experimental group is pathologically confirmed to be "endometrium adenocarcinoma"?

Select "Generate Query" and this will generate the corresponding Query Language query.

Once a query has been generated you can launch the query and explore your results. A detailed breakdown explaining the results returned from the query language can be accessed here.

Tips for Natural Language Prompts

Editing the Query Generated

Multiple natural language prompts can be attempted to ensure the correct query is generated. The generated query itself can also be edited or expanded on prior to it's submission. You may want to adjust the direction of the relationships, the data properties identified or add more to the query. The Query Language query that is returned can be edited within the dialog.

In the example above the initial prompt was "Which genes are upregulated in differential expression datasets where the experimental group is pathologically confirmed to be "adenocarcinoma"

Which genes are upreugulated in differential expression datasets where the experimental group is pathologically confirmed to be "adenocarcinoma"?

This natural language prompt generated the following query

(dataset:DifferentialExpressionDataset)-> upregulates ->(gene:Gene) + (dataset:DifferentialExpressionDataset)-> experimental group includes ->(Sample)-> pathologically confirmed to be ->(Disease { displayName="adenocarcinoma" })

The query was edited to update the display name of the disease to be "endometrium adenocarcinoma"

Resulting in the following query

(dataset:DifferentialExpressionDataset)-> upregulates ->(gene:Gene) + (dataset:DifferentialExpressionDataset)-> experimental group includes ->(Sample)-> pathologically confirmed to be ->(Disease { displayName="endometrium adenocarcinoma" })

Using quotations around data properties can help Agent Orion better understand the query that you would like to generate. For example, if you would like to filter on a specific disease put the disease in quotations. Throughly describing your query using terminology in your custom knowledge graph schema will improve query accuracy. Your knowledge graph schema can be reviewed in the .

Foundry
Query Language