Healthcare is generating more biomedical data than ever before. Yet, turning that data into insights to inform new treatments remains a significant challenge. Right now, despite decades of research with significant investment into drug discovery, just 6% of drugs that enter clinical trials reach patients. It’s an unsustainable model that acutely affects rare disease management, with just 5% of these conditions in the UK having an approved treatment.
Faced with these odds, researchers and healthcare organisations are increasingly turning to drug repurposing: identifying new applications for medicines that already exist. It is a pragmatic response that is already showing results, but scaling it further requires complete visibility across the drug discovery lifecycle. Healthcare professionals need to clearly see the connections between genes, diseases, pathways, and existing medicines to improve the chances of finding rare disease treatments.
Importantly, advancements in artificial intelligence can help organisations get to these insights faster. But it relies upon a robust, structured data environment that is often missing. Data is the bedrock that gives AI context and a means to produce reliable, actionable outcomes. Graph database technology has emerged as a unique means of connecting disparate data to make it AI-ready, enabling researchers to uncover hidden links, generate new hypotheses, and accelerate drug discovery for patients in need.
Turning raw data into usable knowledge
Graph technology works by connecting isolated or siloed data, revealing the relationships and providing greater context. Instead of storing information in tables with rows and columns, it links data within a network – a ‘knowledge graph’ – that captures how all insights interrelate. This means professionals can see how a specific gene connects to a disease, which pathway links to which drug, and how confident that link really is. It’s a web of relationships that gives AI the vital context it needs to accelerate drug discovery.
Explaining this in more detail, this moves the industry beyond research and development that is based on simple facts such as “Gene A causes disease B”. Instead, a knowledge graph captures connections across different data sets, for example: “Gene A could cause disease B according to a study, based on specific experimental results, with a confidence score of 0.7”. It transforms isolated data into actionable knowledge, enabling AI to discover insights that would otherwise remain hidden.
Putting graph intelligence to work
Organisations now applying graph intelligence at scale are seeing results that would have been impossible through traditional research methods alone.
For example, the RARE Hopes organisation has an initiative to map billions of relationships between genomic information, signalling pathways, and drug data to surface treatment hypotheses. The system can identify when a drug affects a biological pathway central to a rare disease, even one it was never designed to treat. In one instance, this revealed that a drug developed for bone marrow cancer may also be effective against Carney complex – a rare disease that, until that point, had no viable treatment pathway.
The science behind the discovery
When repurposing medicines, knowledge graphs, graph data science, machine learning, and AI all work together across every stage of the discovery process. The PageRank algorithm, for example, was originally developed to rank web pages but is now widely applied across complex network analysis. In drug discovery, it identifies and ranks the genes most strongly associated with certain diseases – bringing statistical rigour to what was previously a manual and incomplete process.
The implications for safety testing are just as significant. By mapping relationships between drug candidates and potential side effects, graph technology can mathematically identify safety risks before a single animal or human experiment takes place – compressing timelines and reducing costly late-stage failures.
At the Dr. von Hauner Children’s Hospital in Munich, the Care-for-Rare Foundation uses a clinical knowledge graph to connect 2,500 paediatric patients to more than 8,000 rare diseases. By applying algorithmic analysis to cross-reference genomic, proteomic, and clinical data – a feat that would be impossible to join in a traditional database – the system can mathematically surface the causal links that lead to a diagnosis. For children, where every month without a diagnosis matters, that is the difference between timely treatment and irreversible decline.
Ultimately, the knowledge graph serves as a grounded layer of truth for AI, anchoring its outputs in verified, contextualised data that substantially reduces the risk of hallucinations. In a field where a single erroneous connection could send researchers down a wrong path, that reliability is fundamental.
A new foundation for medical discovery
The data needed to transform rare disease treatment has always existed – what has been missing is the ability to make sense of it at scale. Graph intelligence doesn’t create new data – it transforms disconnected datasets into a coherent knowledge structure that AI can interrogate far more effectively. The result is insights that researchers can act on. A drug developed for one disease may unlock treatment pathways in another; a trial that fell short of its original goal may contain exactly the hypothesis researchers have been looking for.
For the hundreds of millions living with a rare disease and without adequate treatment options, this is a meaningful shift in what is possible – and it starts with finally putting the data to work.
By Dr. Alexander Jarasch, Global Head of Pharma & Life Sciences, Neo4j