“
Myroslav Trynko Graduate news editor at “Mezhy”. A geek, a programmer by profession, but a journalist by profession. Rider, tennis player and Formula 1 fan. I write about technology, smartphones and electric cars.
This AI helped discover a mechanism that makes “cold” tumors visible to the immune system. Usually, such tumors avoid recognition by the immune system, which complicates treatment, in particular immunotherapy. The new discovery could open the way to combination treatments that were previously impossible.
C2S-Scale 27B analyzed more than 4,000 drugs in patient tumor samples and in laboratory cells. The model was able to identify substances that selectively enhance the immune response, rather than affecting all cells indiscriminately.
Among the most interesting finds — CK2 kinase inhibitor silmitasertib (CX-4945). The AI predicted that the drug only works if there is a small amount of interferon in the cells. One drug or interferon alone had almost no effect on the cells, and their combination increased the activity of the immune system by 50%, “warming up” the tumors and making them visible to the body’s protective cells.
The AI prediction was confirmed in the laboratory on human neuroendocrine cells, which the model had not seen before. This demonstrates that the system can not only process data, but also make inferences based on the context of the cells.
According to scientists, large AI models can become “virtual laboratories” that run thousands of simulations and discover unknown connections between drugs, cells and the immune system.
“This discovery could be a new way to develop cancer treatments,” said Google’s CEO Sundar Pichai.
Success C2S-Scale 27B shows that AI can accelerate science and help create effective treatments much faster than traditional approaches.
It will be recalled that recently researchers from New York University Abu Dhabi (NYUAD) presented a new type of brain implant capable of delivering drugs simultaneously to several areas of the brain with high precision.
”, — write: www.pravda.com.ua
Myroslav Trynko Graduate news editor at “Mezhy”. A geek, a programmer by profession, but a journalist by profession. Rider, tennis player and Formula 1 fan. I write about technology, smartphones and electric cars.
This AI helped discover a mechanism that makes “cold” tumors visible to the immune system. Usually, such tumors avoid recognition by the immune system, which complicates treatment, in particular immunotherapy. The new discovery could open the way to combination treatments that were previously impossible.
C2S-Scale 27B analyzed more than 4,000 drugs in patient tumor samples and in laboratory cells. The model was able to identify substances that selectively enhance the immune response, rather than affecting all cells indiscriminately.
Among the most interesting finds — CK2 kinase inhibitor silmitasertib (CX-4945). The AI predicted that the drug only works if there is a small amount of interferon in the cells. One drug or interferon alone had almost no effect on the cells, and their combination increased the activity of the immune system by 50%, “warming up” the tumors and making them visible to the body’s protective cells.
The AI prediction was confirmed in the laboratory on human neuroendocrine cells, which the model had not seen before. This demonstrates that the system can not only process data, but also make inferences based on the context of the cells.
According to scientists, large AI models can become “virtual laboratories” that run thousands of simulations and discover unknown connections between drugs, cells and the immune system.
“This discovery could be a new way to develop cancer treatments,” said Google’s CEO Sundar Pichai.
Success C2S-Scale 27B shows that AI can accelerate science and help create effective treatments much faster than traditional approaches.
It will be recalled that recently researchers from New York University Abu Dhabi (NYUAD) presented a new type of brain implant capable of delivering drugs simultaneously to several areas of the brain with high precision.