Key Takeaways:
- The development of artificial-intelligence-designed antibodies is a rapidly advancing field, with some companies expected to claim the first AI-designed antibody in the clinic within the next year or two.
- There is a divide in the industry on what "AI-designed" means, with some considering an antibody to be AI-designed if a computer generates the basic sequence that is later tweaked by scientists, while others believe it requires the antibody to be ready for clinical use directly from the computer.
- Researchers have made progress in using AI to design antibodies, but there is skepticism about the ability of AI models to meet or beat traditional techniques.
- The development of AI-designed antibodies has attracted significant investment, with AI-native biotechs receiving higher valuations than traditional biotech startups.
Introduction to AI-Designed Antibodies
The use of artificial intelligence (AI) in the design of antibodies is a rapidly advancing field, with some companies expected to claim the first AI-designed antibody in the clinic within the next year or two. However, the industry is divided on what "AI-designed" really means, and how close we are to the technology truly being able to design a medicine. As one researcher noted, "if a computer designs the basic antibody sequence that scientists later tweak to make a clinical candidate, that counts as ‘AI-designed.’" However, others argue that to be truly AI-designed, an antibody should be ready to go straight into the clinic from the computer, with no further lab work needed.
Defining AI-Designed Antibodies
There are two schools of thought among antibody and protein AI researchers on what it means for an antibody to be designed by AI. Some consider an antibody to be AI-designed if a computer generates the basic sequence that is later tweaked by scientists to make a clinical candidate. This definition is considered the easier of the two, and researchers have already made progress in using AI to design antibodies that meet this criteria. As noted in the article, "in 2025, researchers made it clear that AI can meet the first, easier definition of making an ‘AI-designed’ antibody." However, others argue that to be truly AI-designed, an antibody should be ready for clinical use directly from the computer, with no further lab work needed. This is a much higher bar to clear, and many experts are skeptical about the ability of AI models to meet or beat traditional techniques.
Progress and Challenges
Despite the challenges, some startups claim to be making antibodies that are ready to go straight into the clinic, and investors are taking notice. AI-native biotechs are receiving higher valuations than traditional biotech startups, and many experts believe that AI has the potential to revolutionize the field of antibody design. However, as noted in the article, "even pharma and antibody experts embracing AI find it hard to believe that de novo protein design AI models can meet or beat traditional techniques." This skepticism is driven by the complexity of antibody design, which requires a deep understanding of the underlying biology and chemistry. While AI models have made significant progress in recent years, they still have a long way to go before they can truly design a medicine.
Investment and Valuations
The development of AI-designed antibodies has attracted significant investment, with AI-native biotechs receiving higher valuations than traditional biotech startups. This is driven by the potential of AI to revolutionize the field of antibody design, and the potential for significant returns on investment. As noted in the article, "investors are shoveling more money into AI-native biotechs at higher valuations compared to traditional biotech startups." However, this investment is not without risk, and many experts are cautious about the ability of AI models to deliver on their promise. As one expert noted, "it’s still early days for AI in antibody design, and we need to be careful not to get ahead of ourselves."
Conclusion
In conclusion, the development of AI-designed antibodies is a rapidly advancing field, with significant potential for revolutionizing the field of medicine. However, there is still much work to be done, and many challenges to overcome. As noted in the article, "the industry is divided on what ‘AI-designed’ really means, and how close we are to the technology truly being able to design a medicine." Despite these challenges, many experts believe that AI has the potential to make a significant impact in the field of antibody design, and investors are taking notice. As the field continues to evolve, it will be important to carefully evaluate the progress of AI models, and to separate the hype from the reality.
AI has finally started making drug-like antibodies. When will it revolutionize biopharma?