Forbes - Recursion Thinks AI Can Lower The High Failure Rate Of New Pharmaceutical Drugs
Chris Gibson, co-founder and CEO of Recursion, discusses the company's mission to tackle the high failure rate of drugs in clinical trials, which stands at 90%. Recursion aims to address this by integrating AI and machine learning into biology and chemistry, fields known for their complexity. The company was founded in 2013, initially using basic machine learning classifiers, and has since advanced to using convolutional neural networks and AI tools. Recursion operates the fastest supercomputer in the bio-pharma industry to train these AI models. The company emphasizes the importance of data, having built a vast biological dataset through millions of experiments involving human cells and chemical compounds. This data enables Recursion to quickly identify new disease targets, akin to performing a web search, significantly accelerating drug discovery projects. Gibson highlights the transformative potential of AI in drug discovery and urges other enterprises to adopt AI to stay competitive, suggesting that AI can alleviate repetitive tasks and drive innovation.
Key Points:
- Recursion uses AI to reduce the 90% failure rate of drugs in clinical trials.
- The company has built a vast dataset from millions of biological experiments.
- AI tools at Recursion can quickly identify new disease targets, speeding up drug discovery.
- Recursion operates the fastest supercomputer in the bio-pharma industry for AI training.
- Chris Gibson advises companies to adopt AI to remain competitive and innovate.
Details:
1. 🎯 The Challenge of Drug Development
- 90% of drugs entering clinical trials fail before reaching patients, emphasizing the complexity involved.
- Biological challenges include targeting the right mechanisms, understanding disease biology, and predicting human responses.
- Chemical challenges involve optimizing drug properties such as solubility, stability, and bioavailability.
- To improve success rates, integrating AI for predictive modeling and personalized medicine approaches shows promise.
2. 🤖 Leveraging AI in Biotech
- The biotech company integrated AI and machine learning from its inception, beginning with basic classifiers derived from academic research.
- Founded in 2013, the company quickly advanced to experimenting with convolutional neural networks and advanced AI technologies by 2015-2016.
- AI technologies have been applied to enhance research and development processes, improving efficiency and outcomes in biotech projects.
- Specific AI applications include optimizing drug discovery processes and personalizing treatment approaches, leading to accelerated development timelines.
- The integration of AI has significantly impacted the company's strategic goals, allowing them to stay competitive in the evolving biotech landscape.
3. 🔬 Innovating with Data-Driven Biology
- Recursion runs the fastest supercomputer in the bio-pharma industry, allowing it to train massive convolutional neural networks and other AI tools to tackle biological challenges.
- A significant focus was placed on building a comprehensive biology data set, as AI requires robust data to be effective.
- Robotics were developed to conduct millions of experiments weekly with real human cells, chemicals, and biological perturbations.
- Utilizing CRISPR-Cas9, every gene in the human genome has been knocked out in multiple human cell types.
- Millions of chemical compounds have been profiled across various human cell types, generating extensive data accessible for machine learning and AI.
- The process of targeting a new disease at Recursion begins with a search through this vast dataset, aided by trained large language models.
4. 🚀 Revolutionizing Drug Discovery
- AI accelerates drug discovery projects by multiple years, representing a fundamental shift in the process and offering a competitive edge.
- Companies not implementing AI are at a significant disadvantage, potentially losing out on efficiency and innovation.
- Existing AI tools can be deployed to reduce manual toil, enhancing productivity and operational efficiency.
- It is crucial for businesses to hire talent capable of identifying and leveraging next-generation AI use cases to maintain competitiveness.
- The integration of AI in industries is comparable to a new industrial revolution, significantly transforming work methodologies and productivity.