At the World Economic Forum, Google DeepMind CEO Demis Hassabis announced that drugs designed by artificial intelligence are expected to enter clinical trials by 2025. This news marks a major breakthrough of artificial intelligence in the field of drug research and development, and heralds the innovation of future drug research and development models. Isomorphic Labs, a company under DeepMind that focuses on drug research and development, is actively promoting this process, aiming to use machine learning technology to shorten the drug development cycle, reduce costs, and ultimately achieve personalized medicine. This technology can not only significantly improve the efficiency of drug research and development, but also save pharmaceutical companies huge amounts of money and alleviate the current dilemma of high costs and low success rates in new drug research and development.
At the World Economic Forum held in Davos recently, Demis Hassabis, CEO of Google DeepMind, said that the first drugs designed with the help of artificial intelligence may begin clinical trials by 2025. . Hassabis is also the head of Isomorphic Labs, a drug development company owned by DeepMind. "Our plan is to have some AI-designed drugs enter clinical trials by the end of this year," he said.
Since 2021, Isomorphic Labs has been working to accelerate drug development using machine learning. Hassabis mentioned that personalized medicine is expected to be realized in the future, and AI systems can optimize drugs for each person's metabolic profile in a short period of time. He emphasized that pharmaceutical companies are increasingly interested in AI because it has the potential to save them a lot of time and money.
According to an article in the journal Nature Medicine, the development and approval process for new drugs typically takes 12 to 15 years and costs up to $2.6 billion. Moreover, more than 90% of clinical trials fail. Therefore, any technology that reduces costs, speeds development, or improves success rates will have a significant impact on a pharmaceutical company's financial health.
Hassabis noted that machine learning models can improve the drug discovery process in multiple ways. He believes there is huge potential for time and cost savings. However, he also reminded that obtaining high-quality training data still faces challenges due to factors such as privacy regulations, data sharing policies, and data acquisition costs. Still, he doesn't think the challenges are insurmountable. Gaps in public data can be filled by collaborating with clinical research organizations or using synthetic data.
However, Hassabis emphasized that the application of AI in scientific research does not mean that scientists will be replaced. He pointed out that true innovation is still beyond the reach of AI, which cannot come up with new hypotheses or theories. Although AI can solve complex mathematical conjectures, it essentially relies on the wisdom and creativity of human scientists.
In addition, companies such as Nvidia are also actively exploring the application of AI in drug discovery. Nvidia has even open sourced the BioNeMo machine learning framework for drug development and cooperated with multiple pharmaceutical companies to accelerate research progress.
Highlight:
AI-designed drugs are expected to enter clinical trials by 2025, demonstrating the huge potential of AI in drug development.
The pharmaceutical industry faces challenges of high costs and low success rates, and AI has the potential to significantly reduce the impact of these issues.
Hassabis said that AI cannot replace the creative thinking of scientists, and real scientific discoveries still need to rely on humans.
All in all, artificial intelligence has broad prospects for application in the field of drug research and development. Although challenges still exist, the efficiency improvements and cost reductions it brings cannot be ignored. AI will become a powerful tool for scientists, rather than a substitute, pushing the pharmaceutical industry into a new stage of development.