An Australian research team has developed a large language model (LLM) designed to speed up scientific discovery in molecular property prediction.

Lead co-author, PhD candidate Yizhen Zheng, from Monash University’s Faculty of Information Technology, said the team’s ‘LLM4SD’ artificial intelligence tool reads decades of scientific literature and analyses lab data to predict how molecules behave. “It can answer questions like, ‘Can this drug cross the brain’s protective barrier?’ or ‘Will this compound dissolve in water?’ It has the potential to make the drug discovery process easier, faster and more accurate and become a supercharged research support for scientists in every field all across the world.”

Apart from outperforming current validation tools that operate like a ’black box’, this new AI system can also explain its analysis, predictions and results using simple rules which could help scientists trust and act on its insights, said Zheng. “We foresee LLM4SD providing interpretable and potentially new insights, aiding scientific discovery in molecular property prediction.”

The team’s research was published in Nature Machine Intelligence.