Streamline Cancer Data Standardization with mCodeGPT

Enhance the efficiency and effectiveness of your data standardization process with mCodeGPT - the cutting-edge solution that combines mCODE™ and large language model (LLM) to extract cancer concepts based on ontology. 

Try our Hugging Face demo:

Welcome to mCodeGPT

At mCodeGPT, we offer a revolutionary approach to cancer data standardization. Our integrated solution leverages the power of mCODE™ and LLMs to streamline the process, ensuring accurate extraction of cancer concepts based on ontology.

Comprehensive Data Standardization

Our advanced technology combines mCODE™ and LLMs to provide comprehensive data standardization for cancer-related information, enabling better analysis and decision-making.


mCodeGPT is a fully open-source project, designed to empower contributors from all backgrounds. We welcome and value your contributions.

Download Cancer Ontology Example File to see the cancer ontology.

Contact us to help build other disease ontology.

This project is partially supported by NCI U01CA274576, CPRIT RR180012, and UTHealth internal funding