turingdb-graph

Builds, queries, and analyzes biomedical knowledge graphs in TuringDB.

Updated May 10, 2026
One-click install
npx skills add https://github.com/MubasherMohammed/opencode-BioInfo --skill turingdb-graph
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: turingdb-graph
Source: https://github.com/MubasherMohammed/opencode-BioInfo/tree/main/python/skills/turingdb-graph
Command: npx skills add https://github.com/MubasherMohammed/opencode-BioInfo --skill turingdb-graph

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires turingdb, pandas, fastapi, uvicorn, pydantic, tabulate, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows users to build, query, and analyze biomedical knowledge graphs using TuringDB, a columnar graph database with git-like versioning.

Core Features & Use Cases

  • Graph Building: Ingest CSV/TSV/GML/JSONL files into a TuringDB graph.
  • Querying: Run arbitrary Cypher queries against a graph.
  • Cohort Analysis: Perform fixed cohort analyses on a patient-centric graph.
  • Demo: Run end-to-end examples with synthetic datasets.
  • Use Case: A researcher wants to build a knowledge graph from a patient cohort and analyze the most common conditions and medications. They can use this Skill to build the graph, query it for specific information, and perform cohort analyses.

Quick Start

Use the turingdb-graph skill to build a graph from the attached CSV file 'patient_data.csv' and analyze the cohort.

Frequently Asked Questions about turingdb-graph

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a biomedical knowledge graph from CSV files?

To build a biomedical knowledge graph from CSV files, you ingest CSV/TSV/GML/JSONL data into TuringDB, a columnar graph database. This process structures your raw patient or biomedical data into a queriable graph format.

Can I run Cypher queries on biomedical data in TuringDB?

Yes, you can run arbitrary Cypher queries directly against your biomedical knowledge graph in TuringDB. This allows you to retrieve specific conditions, medications, and patient relationships from the ingested data.

How do I perform cohort analysis on a patient-centric graph?

You perform cohort analysis on a patient-centric graph by applying fixed analytical functions provided by the TuringDB graph workflow. This identifies common conditions and medications within a specific patient cohort.

Does TuringDB support ingesting JSONL and GML file formats?

Yes, TuringDB supports ingesting JSONL and GML file formats, alongside CSV and TSV files. This allows flexible integration of diverse biomedical datasets into your knowledge graph.

What is the best way to analyze common conditions in a patient cohort?

The best way to analyze common conditions in a patient cohort is to build a knowledge graph in TuringDB and run fixed cohort analyses. This workflow processes patient data to surface frequent medical conditions.

Do I need FastAPI and Uvicorn to query a knowledge graph in TuringDB?

Yes, querying and analyzing knowledge graphs in TuringDB requires FastAPI and Uvicorn alongside pandas, pydantic, and tabulate. These dependencies support the API server and data manipulation capabilities.