The full process took about 2.5 months, plus another half month for human chemists to write up the results.
OpenAI's GPT-5.4 model has been instrumental in advancing a medicinal chemistry project, assisting in tasks from literature review to experimental validation. The AI helped identify an improved method for Chan-Lam coupling, a crucial reaction in drug discovery, particularly for challenging substrates like primary sulfonamides. Human chemists guided the process, validating the AI's proposals and confirming significant yield improvements in 88% of tested boronic acids and 83% of sulfonamides. AI
IMPACT Demonstrates AI's capability to accelerate scientific discovery by optimizing complex chemical reactions and improving experimental yields in drug development.