Amazon introduces an AI Bio platform aimed at speeding up the process of early-stage drug discovery.
Amazon Web Services (AWS) announced the launch of its AI bio tool, Amazon Bio Discovery, this Tuesday, aiming to expedite the early stages of drug discovery in the pharmaceutical sector. This application is designed to assist scientists in swiftly and securely creating and testing new drugs.
Amazon Bio Discovery allows researchers to execute intricate computational workflows utilizing over 40 foundational models specialized in AI, which have been trained on a diverse array of biological datasets. These models identify and assess potential drug molecules, while AI agents assist scientists in choosing models, optimizing inputs, and evaluating candidates based on their research.
Scientists can forward the shortlisted candidates to partnered labs for synthesis and testing, with the results subsequently returned to the application for further analysis and model enhancement, establishing what AWS refers to as a lab-in-the-loop.
As the demand for AI biological models rises, each possessing distinct features, computational biologists tasked with implementing these models face challenges, while bench scientists with specialized knowledge struggle with slow research or experimentation processes due to limited direct access to computational resources. Amazon Bio Discovery seeks to address this issue by providing a platform that integrates computational design with wet-lab validation.
The Memorial Sloan Kettering Cancer Center, which has recently collaborated with Amazon Bio Discovery, reports the creation of nearly 300,000 new antibody molecules, from which they identified 100,000 top candidates for testing, significantly reducing the workflow timeframe from a year to mere weeks.
Rajiv Chopra, vice president of healthcare AI and life sciences at AWS, stated that the service is designed to enhance the capabilities of scientists and contract research organizations rather than replace them. Furthermore, Tycho Peterson, an analyst at Jefferies, commented that fears regarding AI diminishing the need for instruments in drug research are exaggerated, as there remain opportunities for greater investment and returns as research initiatives expand.
AWS indicated that early adopters of Amazon Bio Discovery include Bayer, the Broad Institute, and Voyager Therapeutics, alongside endorsements of its cloud services by 19 out of the top 20 global pharmaceutical companies.
Additionally, AWS and the Gray Lab at Johns Hopkins Engineering have introduced the Antibody Developability Benchmark dataset, one of the largest and most diverse databases for AI-driven antibody design. This new dataset is part of Amazon Bio Discovery, with plans for additional benchmarks to be integrated over time.
Other articles
Amazon introduces an AI Bio platform aimed at speeding up the process of early-stage drug discovery.
AWS has unveiled its AI biological tool, Amazon Bio Discovery, aimed at speeding up the initial stages of drug discovery.
