Amazon’s cloud unit, Amazon Web Services (AWS), launched Amazon Bio Discovery on Tuesday, an artificial intelligence application designed to accelerate drug discovery at an early stage by allowing scientists to execute complex computational workflows without writing code.
Drug manufacturers and technology companies have intensified their efforts to use AI to speed up drug development.
Amazon Web Services stated in a blog post that Amazon Bio Discovery allows researchers to access a library of specialized biological models capable of generating and evaluating potential drug molecules, along with an AI agent that assists users in selecting models, defining parameters, and interpreting results.
Researchers can send preselected candidates to integrated lab partners for synthesis and testing, with the results being fed back into the system to guide the next design cycle.
Rajiv Chopra, vice president of Healthcare AI and life sciences at AWS, told Reuters that the rapid increase in drug discovery models has created a bottleneck for computational biologists who can translate lab objectives into machine learning pipelines.
AWS mentioned that Bayer, the Broad Institute, Voyager Therapeutics, and 19 of the top 20 global pharmaceutical companies are already using their cloud services.
In collaboration with the Memorial Sloan Kettering Cancer Center, AWS stated that the platform used multiple models to generate nearly 300,000 new antibody molecules and reduce them to 100,000 candidates for laboratory testing by partner Twist Bioscience, compressing work that could take months into just a few weeks.
Mr. Chopra emphasized that the service is meant to complement, not replace, scientists and contract research organizations.
Jefferies analyst Tycho Peterson stated that fears of AI reducing the need for research instruments in drug research are exaggerated, pointing out that expenses on tools can be increased as the pace and output of research programs grow.
AWS, Boston Consulting Group, and Merck will also unveil an AI platform at AWS’s life sciences symposium aimed at improving the selection of clinical trial sites, a common bottleneck in drug development.
