Ad Astra per Aspirin
This project is an AI-powered drug-protein visualizer that fetches real 3D structures from RCSB PDB, renders them interactively with multiple view modes, and uses GPT-6 Astra to analyze binding sites, molecular interacti
Core trick
Fetches RCSB PDB 3D structures and PubChem drug molecules, then renders them interactively with an LLM analysis of binding sites.
Description
This project is an AI-powered drug-protein visualizer that fetches real 3D structures from RCSB PDB, renders them interactively with multiple view modes, and uses GPT-6 Astra to analyze binding sites, molecular interactions, and clinical relevance thereby giving biologists a tool that makes drug discovery more visual and intuitive.
README excerpt
# MolSight — AI Drug-Protein Visualizer > **Team: Ad Astra Per Aspirin** · Hackathon 2026 MolSight is an AI-powered drug-protein visualizer that fetches real 3D molecular structures from the Protein Data Bank, renders them interactively in the browser, and uses GPT-6 Astra to analyze binding sites, molecular interactions, and clinical relevance — giving biologists a tool that makes drug discovery more visual and intuitive. ## Features - **Real 3D protein structures** — Fetches authentic PDB data from [RCSB Protein Data Bank](https://www.rcsb.org) - **Drug molecule overlay** — Retrieves 3D drug structures from [PubChem](https://pubchem.ncbi.nlm.nih.gov) and renders them alongside the protein - **Multiple render modes** — Cartoon (ribbon), Stick, Sphere, and Surface views with one-click toggling - **AI interaction analysis** — GPT-6 Astra identifies binding sites, key residues, hydrogen bonds, hydrophobic contacts, and clinical relevance - **Interactive 3D viewer** — Rotate, zoom, pan, spin animation, and drug visibility toggle - **Pre-loaded examples** — 6 well-known protein-drug pairs ready to demo (SARS-CoV-2 + Paxlovid, Abl Kinase + Gleevec, HER2 + Herceptin, and more) ## Quick Start ```bash # Install dependencies npm install # Copy env file and add your OpenAI API key cp .env.example .env.local # Edit .env.local and set OPENAI_API_KEY=sk-... # Run dev server npm run dev ``` Open [http://localhost:3000](http://localhost:3000). ## How It Works 1. **Enter a protein