Structured flexibility

Structured Flexibility

“Structured flexibility” encapsulates our philosophy and approach to developing a great product which enables scientists to make the highest quality data-driven decisions. We believe in taking the best from the plasticity of ‘flexibility’ and the solidity of ‘structure’. We’re also acutely aware of the disadvantage of being too flexible, where any option is on the table, or too structured, where every decision is made and there is no room for exploration or experimentation or innovation.

Within the Aigenpulse Platform

This means enabling users to focus on the data they really need by providing options and hiding what they don’t. Of course, additional options and modules can be added at any time without requiring any significant changes to the overall structure of the Platform. Therefore, Structured Flexibility allows the Aigenpulse Platform to simultaneously maintain the structures of security, performance and properly managed data with the flexibility of dynamically adding new data types, modules and machine learning algorithms.

To Control Complexity, the Aigenpulse Platform has three core structural elements namely Entities, Experiments and Processes described as follows.

Want to know more about Aigenpulse?

Contact us to learn more

Get in Contact


The ability to carry out contextually relevant machine learning analyses of biological data from multiple experimental workflows necessitates the standardisation of terms, definitions and entities. At the most fundamental level this means enterprise-wide use of the same vocabulary to annotate metadata for experiments and patient sample descriptions. Consistent language and ontologies also reduces miscommunication, and represents good basic data husbanding. The management of entities means that they can be linked across the Aigenpulse Platform and throughout the whole organisation, with no ambiguity. This standardisation is a key requisite for labs that are driving to automate experiments and for the ability to make full contextual analysis of data. Further, this enables feeding machine learning models with high-quality input for high-quality output.


Experiments are the core activity of scientific research. As such the protocols, parameters, the entities which are subjected to experimentation, and output data are stored in the Aigenpulse Platform – to ensure the efficient linking of experimental information to the output data. The raw data acquired from laboratory instrumentation and the processing steps, see below, executed to generate results (including summarised or aggregated values) are also recorded. Standard representations of experimental data on the front-end are displayed as tables, along with experiment-type specific visualisations – e.g. 96-well plate viewer for ELISA, concentration curves for SPR. Experiment descriptions are linked to Entities to ensure that single point-of-truth for definitions are cascaded throughout the Aigenpulse Platform.


Within the Aigenpulse Platform, processes describe the input entities and data, a transformation (be it annotation, conversion, statistical, summarising, aggregation or modelling), and the resultant output. Each process carried out is automatically retrievable along with the inputs and outputs, even after data sources have been updated. This enables comparability over time which also leads to far more accurate data/results reproduction and provides gains in efficiency because all parameters are stored in a single location.