Chat with Open Targets genetics database leveraging text-to-graphQL capabilities of OpenAI Codex.
-
Updated
May 16, 2025 - Python
Chat with Open Targets genetics database leveraging text-to-graphQL capabilities of OpenAI Codex.
MCP server for Open Targets data
GeneticsGPT is an intuitive application that leverages OpenAI's GPT-3.5-turbo model to provide insights and answers to genetic and disease-related questions. By integrating with the Open Targets genetics database and translating natural language queries into GraphQL, it empowers users to easily explore and extract valuable information.
Analyze human genetic knockouts to predict drug efficacy and side effects
Falsifiable drug-target validation: a content-addressed audit engine for direction of effect (inhibit vs. activate), built on Open Targets colocalization and benchmarked against approved drug–target pairs. SHA-locked rules; allowed to refuse.
Powerful Model Context Protocol (MCP) server for therapeutic discovery and drug repurposing using the Open Targets Platform GraphQL API.
Prescribing genes, not just drugs. ETL + dashboard pipeline that cross-references Open Targets, ChEMBL and UniProt to rank therapeutic targets by disease.
Fixture-backed biomedical evidence atlas for browsing neuroplasticity and receptor pharmacology research, with a FastAPI backend and a React frontend.
Disease-target knowledge graph: Open Targets ETL into Neo4j, FastAPI REST, and a React explorer with ranked associations and provenance.
Local research-only AI agent for evidence-grounded therapeutic target discovery with PubTator3, Open Targets, Neo4j, ChEMBL/RDKit, and FastAPI.
Forensic post-mortems for clinical trials. Give it an NCT ID, drug, or target: it classifies why a trial stopped, links the biology across ClinicalTrials.gov, openFDA, Open Targets, and ChEMBL, and returns an evidence-graded report, or refuses to speculate when the stop was not scientific.
Deterministic knowledge graph engine that finds multi-hop drug-to-disease paths across 50 rare diseases. Zero LLM calls. Built on NetworkX, RDKit, DuckDB, and live biological databases (ChEMBL, Open Targets, UniProt, Reactome)
Ranks schizophrenia GWAS genes on genetic association, druggability and brain cell-type specificity at once. A triage tool for shortlisting candidates, not a claim to have found drug targets.
TargetIntel-IO is an explainable, rule-based tool that ranks and classifies candidate targets in anti-PD-1-resistant melanoma by therapeutic intent: antibody/IO-combination, biomarker, or small-molecule strategy, with evidence-based reasoning and benchmark-checked accuracy behind every call.
AI-powered drug repurposing pipeline that federates live data across 8 biomedical databases in real time, ranks candidates via DeepSeek V4 LLM analysis, and visualizes target–drug–protein networks in an interactive 3D knowledge graph.
Add a description, image, and links to the open-targets topic page so that developers can more easily learn about it.
To associate your repository with the open-targets topic, visit your repo's landing page and select "manage topics."