Created by Pangaea Data Limited

Making Data Findable and Usable

Helping life science companies determine 'what data exists' and organising it in specific scientific or clinical contexts, so they are able to analyse and interpret it effectively and thereby make the most from their investment in such data .

Organise Biomedical Data

Automate mandatory but currently manual processes for knowing what data exists so it is findable and usable

Due to rising data volumes there is growing need to automate mandatory but currently manual processes for organising biomedical data, which includes harmonisation (clean, curate, structure) and classification (catalogue) so data is findable, accessible, meaningful and therefore usable for analysis and interpretation. Pangaea enables such automation through its machine learning based software product which increases the speed and accuracy of the overarching scientific research or clinical diagnosis by at least 75%, resulting in time and cost savings for life science companies.


The different data types for which Pangaea’s capabilities are built include data from Lab devices, Clinical data from Electronic Health Record (EHR) systems, Clinical trial data, Genomic data, Transcriptomic data (microarray and RNA-seq), Microbiomic data, Real-world evidence data and Imaging data. Additional data types are being added to this list as Pangaea engages with more customers.

Analyse, Interpret and Share Knowledge

Easily execute analytical workflows, interpret output and visualise data

Scientists, clinicians and researchers with little or no IT expertise are able to find relevant data and execute their end-to-end analysis through a single web based portal regardless of the number of underlying tools and applications. As a result, the company’s resources can be focused on analysis and interpretation as opposed to data organisation. 

Pangaea's software operates with a high accuracy rendered by machine learning algorithms which are trained with the help of supervised and unsupervised approaches coupled with expert input from users.

Break Data Silos and Assurance Compliance

Without investing heavily in large data integration projects or the need to expend additional effort for security and compliance


Data can be integrated from various proprietary and public sources, without the need of investing in building large data warehouses. Pangaea's product is installed in a customer's environment (enterprise or cloud) and therefore does not require additional effort to comply with IT security and data governance rules.


Pangaea's output helps assure further compliance as organisations are able to determine 'what data exists' in their ecosystem and therefore are able to legislate its usage per prescribed internal (audit) policies and external regulations such as the General Data Protection Regulation (GDPR).