Dozens of Seattle biotech companies are using artificial intelligence to design new medical treatments. But at a conference of industry leaders and investors this week, scientists delivered a nuanced message: AI holds enormous promise, but expectations must remain grounded in reality.
The trade association Life Sciences Washington and investment company Madrona hosted the one-day forum in downtown Seattle delving into biotechnology, pharmaceuticals and AI.
“There is some hype about the breadth and depth of the capabilities of some of these AI models,” he said. Jamie LazarovitsCEO and co-founder of Archon Biosciences. Researchers need to “be very cautious” when drawing conclusions from the data generated by the models, he said.
And there’s still a lot to be excited about.
“What was science fiction 15 years ago is now reality,” said Erik Procko, chief scientist at the Cyrus Biotechnology. “So yes, there has been enthusiasm. But there is still enormous potential, and sometimes the progress being made is just dizzying.”
Lazarovits and Procko were part of a panel that included four Seattle startups leveraging AI. Each company is facing different challenges in drug development:
- Archona company that emerged from secrecy more than a year ago with $20 million in funding, is using AI to design proprietary protein structures, known as Antibody Cages or AbCs, that are intended to help antibodies bind to target cells and avoid other cells.
- Ciro is developing medicines that focus on identifying and removing areas that will trigger an immune system response – a challenge called immunogenicity. The 10-year-old company has raised $36.6 million according to PitchBook.
- Outpace Biographya startup founded in 2021 that raised $200 million is designing proteins that aim to boost T-cell therapies for solid tumors, which make up 90% of cancers. Tumors are disappointingly good at deflecting current T-cell treatments, which often stop working within a month.
- Talus Bioscienceslaunched in 2020 and worth almost US$20 million, it targets transcription factors – proteins that are part of the “regulome” that turns genes on and off. The company targets transcription factors that activate genes that cause specific cancers.
In addition to discussing their own work, the panelists identified key principles for how AI should — and shouldn’t — be used in biotech research:
Increasing researchers, not replacing them
Marc Lajoieco-founder and CEO of Outpace, compared the AI tools to the robotic exoskeleton used by Ripley and others in the sci-fi film Aliens to carry heavy loads – and fight the ET Xenomorph Queen.
“It makes the researcher better,” he said. “We are not trying to replace the researcher.”
Models must meet reality
Lazarovits noted that while AI can generate interesting clues and information, it doesn’t mean much until it’s tested in real experiments with cells and organisms.
“Whenever we try to adopt new models, new AI methods, you can get incredibly excited about that silicon validation,” he said. “But the reality is: what do you actually validate in the wet lab?”
The real bottleneck: clinical trials
AI is great for developing new therapies, but the most expensive and labor-intensive part of the drug development process is seeing how they work in patients.
“The most impactful place for AI to truly change the game in drug development would be to conduct smaller, better-powered clinical studies,” Lajoie said. The way to do this, he added, would be to find better drug candidates that perform multiple functions.
Still searching for AI’s breakthrough moment
Procko still hopes that AI will go further to spur advances in biotechnology and pharmacology.
“AI is currently fantastic for predicting, say, a protein structure, but for creating new medicines it hasn’t yet found its killer application,” Procko said. “What does AI allow us to do now to produce new medicines that were previously simply impossible to manufacture? How could this be a game changer?”
The question captures a central tension discussed on the panel and at the conference: While AI has transformed the way Seattle biotech companies approach drug design, the industry is still navigating the gap between computational promise and clinical proof.
Leave a Reply