How GPT-5 helped immunologist Derya Unutmaz solve a 3-year-old mystery

Immunologist Derya Unutmaz used GPT-5 Pro to crack a puzzle about T cells that had remained unsolved for three years, according to the OpenAI Blog. The mystery involved how certain T cells behave, a question that had stymied conventional research. By feeding the model experimental data and asking it to generate and test hypotheses, Unutmaz was able to identify a mechanism that had eluded manual analysis. The findings could have implications for cancer immunotherapy and autoimmune disease treatment, as T cells are central to both. For developers and solopreneurs building AI workflows, this showcases how large language models can serve as research assistants, not just for text generation but for pattern discovery in scientific data. The case highlights a growing trend: domain experts leveraging generative AI to accelerate hypothesis generation and validation, turning years of work into weeks. While GPT-5 Pro is not yet widely available, the approach of combining structured reasoning with natural language interaction points toward new possibilities for AI-accelerated discovery in specialized fields.