Can Fleming Initiative and AWS Defeat AMR with Gen AI?

Medical science is turning to AI to outsmart mutating pathogens that cause antimicrobial resistance (AMR), a condition where changing microorganisms render standard treatments ineffective.

In a global response to drug-resistant infections, Fleming Initiative, a partnership between Imperial College London and Imperial College Healthcare NHS Trust, is receiving technical support from Amazon Web Services (AWS) to tackle the threat associated with AMR. 

This includes up to several million pounds worth of cloud and gen AI technology, as well as technical support, for a global AMR intelligence platform which the Initiative is building. 

The support will supercharge the efforts of the organisation to better connect data, researchers, clinicians and public health stakeholders to combat what is predicted to cause 39 million deaths between 2025 to 2050. 

Despite being one of the biggest global public health challenges, the progress in tackling AMR remains slow due to fragmented surveillance systems and siloed research efforts. 

Healthcare systems also face limited access to integrated, real-world data across healthcare, laboratory and community settings.

Speaking at the One Health Summit in Lyon, held under France’s G7 presidency, Professor the Lord Darzi of Denham, Executive Chair of the Fleming Initiative, described the AMR landscape as “a vast, interconnected ecosystem of data; millions, even billions, of signals”.

He says: “Medicine and public health are increasingly driven by data. The opportunity now is not simply to gather more of it but to turn it into action; at the speed and scale this threat demands. 

“By pairing world-leading scientific expertise with the most advanced technology available, we can build a new generation of intelligence for AMR: one that allows countries, researchers and health systems to anticipate threats rather than react to them. That is the ambition this moment requires.” 

Unifying global AMR data in cloud

Leveraging the latest gen AI and cloud services from AWS, the Fleming Initiative is pioneering in bringing together some of the world’s fragmented AMR datasets to build a cloud-based platform. 

This marks the first time these disparate datasets, including compound libraries and surveillance signals, will be unified.

The platform aims to reveal previously invisible patterns that are hidden across institutional silos and national boundaries.

By connecting these networks, global research insights will no longer be limited to whatever one laboratory happens to hold, further accelerating the pipeline from data to discovery. 

Professor Alison Holmes, Director of the Fleming Initiative, says: “Antimicrobial resistance is a global challenge that no single institution, country or dataset can solve alone. The support from AWS could help us unlock new opportunities to bring together expertise, data and technology in ways that were not previously possible. 

“By supporting more connected and accessible data ecosystems, researchers and public health leaders could collaborate more effectively, move faster and generate new insights at the scale and pace that matches the urgency of the AMR crisis.” 

Together, these capabilities create the infrastructure for a living, global AMR intelligence platform which grows more powerful as more institutions contribute data. It supports researchers, healthcare organisations, industry and policymakers to collaborate across borders to accelerate research and development.

This shared infrastructure also builds vital local and regional capacity for AMR surveillance, preparedness and response.

Securing data across borders

AI is shifting the healthcare landscape from a reactive model to an efficiently predictive one. 

Dr Rowland Illing, Chief Medical Officer and Director of Global Healthcare and Life Sciences at AWS, highlights how the technology helps in compressing years of laboratory research into weeks.

He says: “AWS’ generative and agentic AI services allow siloed organisations to bring together compound libraries, clinical data and genomic sequences in a secure fashion while respecting regional data sovereignty concerns, to find new treatments and enhance surveillance for new resistance patterns.”

Talking about the impact of these digital tools on underserved areas, he adds: “Because AMR disproportionately impacts regions with less technology, AWS’ AI services can accelerate data collection from these regions by transforming paper-based content into usable data, reducing or eliminating manual data entry processes through AI and agents and improving access to computational capacity.”

Dr Rowland talks about the Initiative, saying: “In the case of our work with Fleming, AWS creates a single, secure, cloud-based research environment that unifies these disparate datasets for the first time, enabling real-time access, AI-powered analysis at scale and multi-institutional collaboration without the constraints of physical infrastructure or jurisdictional barriers, to improve health outcomes for all. 

“For researchers, a big part of what we are supporting is silico drug discovery. Now, generative AI is being used to screen the Initiative’s library of over 100,000 compounds and generate novel molecular candidates that may be effective against drug-resistant pathogens, compressing what previously took years of laboratory work into weeks. 

“Additionally, our AI tools are being used for resistance pattern prediction – training foundation models on global genomic and surveillance data to forecast where and when new resistance patterns are likely to emerge, giving public health agencies an early warning system.”