Amazon Web Services (AWS) announced this Tuesday the launch of Amazon Bio Discovery, an AI bio tool to accelerate early-stage drug discovery in the pharmaceutical industry. The app aims to help scientists design and test new drugs quickly and safely.
Amazon Bio Discovery enables scientists to drive complex computational workflows through more than 40 AI-qualified foundational models trained on a wide variety of biological datasets.
These models generate and evaluate potential drug molecules alongside AI agents that help scientists select models, optimize inputs, and evaluate suitable candidates for their research.
Researchers can send a shortlist of selected candidates to integrated lab partners for synthesis and testing, and the results are sent back to the application for analysis and model refinement, creating what AWS calls a loop-in-the-loop.
With the proliferation of artificial intelligence biological models, each with distinct characteristics, computational biologists responsible for developing these models face bottlenecks, while bench scientists with deep expertise face slow processes for research or experimentation due to lack of direct access to computational tools.
Amazon Bio Discovery aims to solve this challenge by providing access to a platform that brings computational design and wet-lab validation.
Memorial Sloan Kettering Cancer Center, which recently partnered with Amazon Bio Discovery, reports that they have developed approximately 300,000 new antibody molecules and sent the best 100,000 candidates for testing, increasing their workflow from a year to a few weeks.
Rajiv Chopra, vice president of healthcare AI and life sciences at AWS, reported said the service aims to augment rather than replace scientists and contract research organizations. Additionally, Tycho Peterson, an analyst at Jefferies, said fears that AI will reduce the need for tools in drug research are overblown, as there are opportunities for increased investment and revenue as research programs grow.
AWS noted that early adopters of Amazon Bio Discovery include Bayer, the Broad Institute and Voyager Therapeutics, as well as 19 of the top 20 global pharmaceutical companies in cloud services.
Additionally, AWS and Gray Lab at Johns Hopkins Engineering Antibody Development Benchmark DatabaseIt is one of the most diverse and large-scale databases for AI-informed antibody design. This new database is part of Amazon Bio Discovery, and additional benchmarks will be added over time.
