Amazon Web Services (AWS) has launched Amazon Bio Discovery, a new AI-powered application aimed at speeding up how scientists design, test, and refine potential new drugs.

 

The platform brings together a curated set of specialized AI systems—known as biological foundation models (bioFMs)—trained on large-scale biological datasets. These models generate and assess candidate drug molecules, including those used in antibody therapies, targeting a faster and more efficient early-stage discovery process.

 

But AWS is positioning the product as more than just model access. Amazon Bio Discovery is designed as an end-to-end scientific workspace where researchers can interact with AI using natural language, automate complex experimental design tasks, and continuously refine results through real-world lab feedback.

 

Scientists can “talk” to an AI agent using familiar scientific terminology to choose appropriate models, optimize inputs, and evaluate drug candidates. They can also fine-tune models using their own experimental data, improving prediction accuracy over time. Once promising candidates are identified, they can be sent directly to physical labs for synthesis and testing, with results fed back into the system to drive iterative improvement.

 

The company says the goal is to remove major friction points that have slowed down AI adoption in life sciences. While generative AI has rapidly expanded across domains—from protein structure prediction to chemical property analysis—many of these tools still require advanced coding skills, infrastructure management, and benchmarking expertise. With dozens of competing models available, even selecting the right one can be a major hurdle.

 

Amazon Bio Discovery addresses this with three core components: a benchmarked library of AI models and analysis tools, an AI agent that helps design and manage experiments, and integrated lab partners that handle physical testing and return results directly into the platform. Together, these elements create a continuous “lab-in-the-loop” system for faster iteration.

 

“AWS is also aiming to solve another long-standing bottleneck: fragmented lab workflows and disconnected data systems that make it difficult to move from computational design to real-world testing.”

 

“AI agents make powerful scientific capabilities accessible to all drug researchers, not just those with computational expertise," said Rajiv Chopra, vice president of AWS Healthcare AI and Life Sciences. 

 

"These AI systems can help scientists design drug molecules, coordinate testing, learn from results, and get smarter with each experiment. This combination of cutting-edge AI and the robust, secure infrastructure AWS has built for regulated industries allows scientists to accelerate antibody discovery in ways that weren't possible before.”

 

With Amazon Bio Discovery, AWS is betting that tightly integrated AI agents, models, and lab automation can compress drug discovery timelines—and lower the barrier for scientists who have traditionally lacked access to advanced computational tools.