Derived Information Framework
What is it?
The derived information framework, developed by the 4Cs, is a framework which extends the capabilities of dynamic knowledge graphs.
It records provenance, tracking when and how pieces of information are obtained from others, instilling confidence in the validity of data and ensuring values are up-to-date.
Knowledge graphs have rapidly gained popularity in both enterprise applications and research fields. They are highly useful for integrating diverse information sources and building common understanding. Dynamic knowledge graphs, with rapidly changing data, build upon this capability. However, there is a serious need for robust methods to deal with complex interdependencies and information provenance.
The derived information framework handles these issues, combining knowledge graphs with software agents, allowing for autonomous workflows which propagate changes/updates to data through the knowledge graph.
What are the benefits?
Live
Data is kept up to date, avoiding issues with mismatched caching in complex dynamic knowledge graphs.
Autonomous
Software agents autonomously cascade and integrate data, managed via an overarching architecture.
Tracked
Records of data provenance are automatically generated and marked up by agents via an ontology.
Case Study - Self Driving Labs
Self-Driving Laboratories are a rapidly growing field that could potentially unlock rapid advances in material design, drug discovery and more. By combining artificial intelligence with automated robotic platforms, experiments can be planned and carried out with far greater speed than before, releasing highly-skilled researchers from repetitive tasks.
However, challenges with scaling the technology have so far hindered progress and limited potential. The immediate need for vaccines during the Covid pandemic highlighted the need for research to be more agile than ever.
The World Avatar™ and the Derived Information Framework are ideally placed to tackle this challenge, and were applied to connect physical labs in Cambridge and Singapore. The connected laboratories were able to collaborate and rapidly move towards a combined set of results. This work has been published in a paper in Nature Communications, and adjacent work in lab management was published here.
Modern laboratories are complex facilities, requiring a highly skilled team to function.
They represent cross-sector sites, where complex supply chains, deep chemical expertise and the built environment must work together in perfect harmony.
Managers and researchers within the labs are required to have multi-domain expertise, which takes years to accumulate.
An assessment of existing roles and responsibilities within laboratories
Comparing the existing approach in research to The World Avatar™
The World Avatar™ uses autonomous software agents to move between human inputs, design of experiments, experiment actuation, result gathering and data presentation.
The process connects lab hardware and software to BIM models, and tracks reagent volumes, equipment usage, temperature, humidity and more.
Information is cascaded across the knowledge graph, with agents recording provenance via ontologies.
Autonomously moving from a human-defined goal to experimental results
Cascading experimental data via the derived information framework
As experiments were carried out and results gathered, a Design of Experiment (DoE) agent autonomously identified new experimental inputs and passed those parameters to the labs. These points can be seen in the far right chart.
In this case study, the linked labs were able to rapidly (<3 days) generate a Pareto front displaying cost-yield optimisation, a common goal across industry.
An example of agents suggesting and executing experiments across linked labs to generate a combined Pareto front
Still interested in learning more about the framework? Read more via this paper, or contact us directly.