Enter your team name
Type a cancer problem.
Core trick
Maps a cancer research prompt to oncology terms, searches live literature and protein databases, and attaches accession-backed structure previews.
Description
Type a cancer problem. The AI searches live oncology literature and public protein databases, then stocks the shelf with accession-backed proteins, NIH/NCBI 3D structure previews, source papers, and usefulness notes.
README excerpt
# Pramazon Pramazon is a cancer-only AI protein research marketplace built for a healthcare hackathon. A user types a cancer research prompt, and the app turns it into oncology terminology, live literature results, accession-backed protein cards, NIH/NCBI iCn3D structure previews, and a copyable research packet. ## Screenshots The first screen behaves like a research marketplace: search a cancer problem, review protein candidates, inspect source papers, and add proteins to a research cart.  The structure viewer embeds NIH/NCBI iCn3D so public PDB/CIF structure files can be inspected directly in the app.  The evidence section keeps the literature and model-routing context visible, so users can see why a protein was selected.  ## What It Does - Accepts cancer-focused prompts such as `blood cancer for human`, `skin cancer for my dog`, or `breast cancer for humans`. - Normalizes the prompt into oncology terminology with an LLM when `OPENAI_API_KEY` is configured. - Searches trusted biomedical sources for recent literature, accession records, and public structure files. - Displays proteins as research cards with accession IDs, source links, paper summaries, usefulness notes, and iCn3D previews when st