Exscientia wanted to shrink the time, cost, and failure rate of drug discovery, where conventional methods can take up to 15 years, cost over 2 billion dollars, and still fail 90–96 percent of the time.
Reported impact
Exscientia makes 10 times fewer compounds than the industry average, has accelerated drug design by up to 70 percent, decreased capital cost by 80 percent, and has already advanced six AI-designed molecules into clinical trials.
Exscientia built a design-make-test-learn platform on AWS that combines generative AI, active learning, and robotic lab automation to accelerate drug discovery. The company starts with target product profiles, then uses algorithms trained on public pharmacology data plus proprietary patient tissue samples, genomics, single-cell transcriptomics, and medical literature to generate candidate compounds in the cloud. Active learning narrows those candidates to the most promising molecules, and automated robots synthesize and test them in a lab orchestrated by AWS microservices. The resulting experimental data feeds back into future DMTL cycles so Exscientia can improve predictions, reduce the number of compounds it has to make, and move candidates to the clinic faster.
Public pharmacology data, patient tissue samples, genomics, single-cell transcriptomics, and medical literature train Exscientia’s generative models; active learning narrows the candidate list, robots synthesize and test compounds, and the resulting data feeds future design-make-test-learn cycles.
Built on Amazon Web Services (AWS), Exscientia’s innovative DMTL solution incorporates in silico design—using generative AI algorithms to design compounds in the cloud—and automated robots that make drug candidates in a lab.
Exscientia has accelerated drug design by up to 70 percent while decreasing capital cost by 80 percent, compared with industry benchmarks.
Six molecules that Exscientia designed using AI have entered clinical trials.
Thus, its lab—orchestrated by AWS microservices—can operate 24/7 with minimal human supervision.
Using this synthesis-aware, iterative approach built on AWS, Exscientia makes 10 times fewer compounds than the industry average.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
AWS Sample Feb 27, 2025 Availity In spring 2023, Michael Privat, chief architect and chief data officer at healthcare technology company Availity , started exploring how artificial intelligence (AI) could transform software development. 20 years Amazon Bedrock · Amazon Q Business · Amazon Q Developer AWS Sample Feb 14, 2025 NHS Midlands and Lancashire NHS ML helps to support general practitioners (GPs), hospital trusts, and other healthcare providers with services for patient communication and engagement. 67% of patients served with automated calls Amazon Connect · Amazon Lex AWS Sample Jan 8, 2025 Natera In the case of Brent, a young husband and father sought care following a mountain bike accident that caused pain and discomfort. Natera nearly doubled data extraction, from 25 to 46 elements per test, enabling more accurate patient care,… AWS HealthOmics · AWS Step Functions · Amazon Bedrock 