Webinar  /  June 22, 2026, 12 - 1 pm

Data Heterogeneity and Lack of Interoperability – From Data Landscaping to Full Data Integration

As AI leaves its traces everywhere in the pharmaceutical R&D process, the rapid generation of overviews on published and proprietary data ("data landscapes") used in a defined context becomes an essential challenge. Finding data, qualifying them as “semantically interoperable” to other data and making them interoperable by e.g. mapping is as tedious as it was in the pre-AI era.

However, AI helps us to speed up the process of finding data, FAIRifying data, qualifying them for a purpose (e.g. to serve as test- or validation data sets). In our webinar we will demonstrate approaches to data landscaping and data integration.

Research aimed at unraveling disease mechanisms relies heavily on cohort studies, but these datasets are often highly heterogeneous, difficult to compare, and not fully interoperable. Differences in variable definitions, data structures, and accessibility create major barriers for cross-cohort analyses and limit the reproducibility and scalability of research findings.

In our webinar, we present approaches for data landscaping, semantic harmonization, and semi-automatic interoperability assessment across specific disease cohorts. We demonstrate tools and web applications designed to improve dataset findability, support FAIR data principles, compare cohort characteristics, and facilitate the creation of common data models for harmonized analyses. By combining semantic mapping with semi-automatic integration workflows, these approaches aim to accelerate data integration and promote more reusable and interoperable research infrastructures in disease-centric, translational research.