Google’s new AI finds promising approach for cancer treatment, Pg16

Key Highlights:

• Google unveiled new AI tools that proposed a novel drug combination for detecting cancer.
• The AI, named Cell2Sentence-Scale 27B (C2S-Scale), identified a drug effective in laboratory conditions that human experts were unaware of.
• C2S-Scale is a 27-billion-parameter foundation model designed to understand the language of individual cells.
• The AI model zeroed in on a chemical drug called silmitasertib that boosts the immune system when it suspects a tumour.

Detailed Insights:

• The C2S-Scale 27B model was tasked to find a drug that boosts immune signals only if low levels of interferon are present.
• Researchers exposed the 27-billion parameter model to real-world patient samples with tumour-immune interactions plus low-level interferon signalling and cell-line data with no immune context.
• The model simulated the effect of over 4,000 drugs and noted how many of them worked in situations where interferon levels were low even as the tumours grew.
• The discovery may reveal a promising new pathway for developing therapies to fight cancer, pending more pre-clinical and clinical tests.
• The strategy was to force nascent tumours to display immune-triggering signals through a process called antigen presentation.

Scientific/Technical Concepts Involved:

• Antigen presentation: A process where cells display antigens on their surface to trigger an immune response.
• Interferon: Proteins produced by the body that act as frontline defenders against infections and tumours.
• AI: The theory and development of computer systems able to perform tasks that normally require human intelligence.