- AWS reveals new AI drug discovery tool
- Amazon Bio Discovery removes technical barriers to highly computational AI experiments
- Tool can significantly reduce drug testing times
Amazon Web Services (AWS) has launched a new AI-powered drug discovery tool.
The Amazon Bio Discovery tool helps researchers accelerate the discovery of new drugs by giving them the ability to run complex computational loads without the need for technical expertise.
Amazon’s cloud platform touts the tools as capable of reducing the work time of an antibody design workflow from 12 months to just weeks.
Article continues below.
AI accelerates drug discovery
Amazon Bio Discovery offers a catalog of fundamental models specialized for drug discovery, with the option for scientists to upload third-party models. Of course, the tool would not be complete without an AI agent, which can guide users in selecting the right models and parameters for their research.
When the experiment is ready to begin, the AI agent begins searching through data sources and fundamental biological factors, and even provides scientific references and rationale for its predictions and suggestions.
The tool then filters the results down to the top selection of results which can then be sent to one of Amazon’s integrated partner laboratories for synthesis and testing without the need for manual delivery that can cause delays. Lab test results are automatically sent to Amazon Bio Discovery for further analysis.
Continuous feedback between integrated laboratories and researchers allows rapid adjustment of results, accelerating the time between design, testing and synthesis.
In collaborative testing with Memorial Sloan Kettering Cancer Center, Amazon Bio Discovery helped narrow a selection of 300,000 antibody candidates to the top 100,000 and sent them for testing “in weeks instead of up to a year using traditional design methods.”
AWS also collaborated with Gray Lab at Johns Hopkins Whiting School of Engineering to produce the ‘Antibody Development Bank,’ the “largest and most diverse” antibody data set designed to help evaluate AI-guided antibody design.
Luca Giancardo, an applied scientist at Amazon Web Services, said: “This data set will allow researchers to be able to answer with confidence: ‘Which model is best for our purposes?’. There are many computational models today that are mainly evaluated with proprietary data or public data sets, which are not representative of the heterogeneity of antibodies. That means that deciding what is better or worse is very, very difficult, if not impossible.”
Follow TechRadar on Google News and add us as a preferred source to receive news, reviews and opinions from our experts in your feeds. Be sure to click the Follow button!
And of course you can also follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp also.
