Google’s AI for Drug Discovery
Why in the News?
Google’s launch of a suite of artificial intelligence (AI) tools, which not only suggested a new drug combination for cancer therapy but even stood up to early tests in the laboratory, is a signal that research scientists ought to be integrating Al into the process of scientific discovery.
UPSC Relevance
Latest technological developments are often asked in Prelims
PYQ
2025 Prelims
Consider the following statements:
I. It is expected that the Majorana 1 chip will enable quantum computing.
II. Majorana 1 chip has been introduced by Amazon Web Services (AWS).
III. Deep learning is a subset of machine learning.
Which of the statements given above are correct?
(a) I and II only
(b) II and III only
(c) I and III only
(d) I, II and III
C2S-Scale Model
- C2S-Scale Model: Google launched a suite of AI tools featuring the Cell2Sentence-Scale 27B (C2S-Scale), a 27-billion-parameter foundation model.
- Built on Gemma: The C2S-Scale model is based on the open-source Gemma family of models.
- “Cell Whisperer”: It is designed to “understand” the molecular language of individual cells.
- Training: It was trained on a large dataset of real-world patients and cell-line data.
- Autonomous Learning: Developers contend these models can learn biological rules autonomously by rewarding successes and penalizing failures, rather than being explicitly trained on the rules.
Drug Discovery Success
- Novel Hypothesis: C2S-Scale generated a novel hypothesis about cancer cellular behavior that was later confirmed with experimental validation in living cells.
- Drug Suggestion: The model suggested a new use for the drug silmitasertib (CX-4945).
- New Use Case: It proposed that silmitasertib could improve the immune system’s ability to identify early-stage cancerous tumors.
- Novelty: The key achievement was scanning the vast cancer biology literature to suggest a novel use for an existing drug candidate, a process that typically takes pharmaceutical companies and researchers months and billions of dollars.
- Time Saver: Experts noted the result was a “nice result” because the model significantly shortened the time needed to suggest such a drug use.