Microsoft Unveils Quine: AI System Tackles Complexity of Biology
Microsoft Research has introduced Quine, an AI research system designed to tackle the complexity of biology. The system is intended for researchers and not for clinical or medical use, and its outputs may be incomplete or inaccurate. Quine aims to connect knowledge across different biological modalities and scales, reason about experiments and evidence, and participate in the iterative process of scientific discovery.
The system brings together a world model of biology with an interactive harness that connects models, scientific tools, literature, and researchers. The world model learns shared representations across biological modalities and scales, including sequence, structure, function, cellular state, and imaging data. This multimodal design reflects the reality of biology, where understanding any one level requires context from others.
Quine has been tested in cancer biology, specifically pancreatic ductal adenocarcinoma (PDAC). Researchers used Quine to predict and prioritize thousands of compounds based on their potential to shift tumor cells between therapeutically relevant states. The results showed that Quine's highest-ranked compounds produced the largest intended shifts across experimental assays.