Drug discovery teams are working across more modalities, disciplines, systems, and external partners than ever. That creates a practical challenge: how do you keep scientific data connected and meaningful as it moves between people, laboratories, and organizations?
In a new article for Drug Discovery World, Janice Darlington, Director of Customer Engagement at Collaborative Drug Discovery, explores why strong data foundations matter as research becomes increasingly multimodal and AI enabled.
The article makes an important distinction: organized data is not necessarily structured data. Files and spreadsheets may be neatly named, but inconsistent terminology, missing metadata, and disconnected records can make it difficult for researchers and computational tools to recognize relationships between experiments and scientific entities.
FAIR principles—making data findable, accessible, interoperable, and reusable—offer a framework for addressing that challenge. In practice, this means building shared terminology, preserving provenance, and capturing enough experimental context to understand not only what a result was, but how it was generated and why it matters. That context also helps teams learn from unsuccessful experiments and avoid repeating work.
These foundations become especially important as AI enters more drug discovery workflows. AI can help process large datasets, but it cannot fill in missing context or reliably reconcile inconsistent records. Scientists still need to evaluate model outputs and determine whether they make sense in the context of the research.
Building a stronger foundation does not have to start with replacing every existing system. It starts with understanding what the data needs to support, identifying where information moves through a workflow, and involving subject matter experts in decisions about standards and terminology.
Read the full article on Drug Discovery World.