Amazon Enters Drug Discovery Race with AI Platform for Faster Molecule Design
Bengaluru: Amazon's cloud unit on Tuesday launched Amazon Bio Discovery, an artificial intelligence application designed to speed early-stage drug discovery by allowing scientists to run complex computational workflows without writing code.
Drugmakers and technology companies have stepped up efforts to use AI to accelerate drug development.
Amazon Web Services said in a blog post that Amazon Bio Discovery gives researchers access to a library of specialized biological foundation models that can generate and evaluate potential drug molecules, along with an AI agent that helps users select models, set parameters and interpret results.
Researchers can send shortlisted candidates to integrated lab partners for synthesis and testing, with results routed back into the system to guide the next round of design.
Rajiv Chopra, vice president of healthcare AI and life sciences at AWS told Reuters the rapid rise of drug-discovery models has turned computational biologists who can translate lab goals into machine-learning pipelines into a bottleneck.
AWS said Bayer, the Broad Institute and Voyager Therapeutics are among early adopters, and 19 of the top 20 global pharmaceutical companies already use its cloud services.
In a collaboration with Memorial Sloan Kettering Cancer Center, AWS said the platform used multiple models to generate nearly 300,000 novel antibody molecules and narrow them to 100,000 candidates for lab testing by partner Twist Bioscience, compressing work that can take months into weeks.
Chopra said the service is intended to augment, not replace, scientists and contract research organizations.
Jefferies analyst Tycho Peterson said that the fears of AI reducing the need for instruments for drug research are largely overblown. He added there is scope to increase the spending on tools as the pace and returns for research programs go up.
AWS, Boston Consulting Group and Merck will also unveil an AI platform at AWS's Life Science Symposium aimed at improving clinical trial site selection, a common bottleneck in drug development.
