From Platform to Knowledge Graph: Evolution of Laboratory Automation

Abstract

High-fidelity computer-aided experimentation is becoming more accessible with the development of computing power and artificial intelligence tools. The advancement of experimental hardware also empowers researchers to reach a level of accuracy that was not possible in the past. Marching toward the next generation of self-driving laboratories, the orchestration of both resources lies at the focal point of autonomous discovery in chemical science. To achieve such a goal, algorithmically accessible data representations and standardized communication protocols are indispensable. In this perspective, we recategorize the recently introduced approach based on Materials Acceleration Platforms into five functional components and discuss recent case studies that focus on the data representation and exchange scheme between different components. Emerging technologies for interoperable data representation and multi-agent systems are also discussed with their recent applications in chemical automation. We hypothesize that knowledge graph technology, orchestrating semantic web technologies and multi-agent systems, will be the driving force to bring data to knowledge, evolving our way of automating the laboratory.

Figure 1

Functional components of a platform-based approach toward chemical discovery, annotated with the communications between each component.

Figure 2

Community landscape toward better data representation and exchange in chemical digitalization. The focus of each category: (a) Molecule: chemical structure, physicochemical properties, and spectral information on a given species; (b) Reaction: chemical reaction scheme, conditions, description of procedures, and statistic summary of the reaction outcome; (c) Analytical data and method: analytical data collected and the methods applied within the experimentation (this is distinct from the spectral information on a given species as this focuses on the data collection process); (d) Procedure and hardware: the operational procedure in an experiment in the format that can be directly executed by hardware; (e) Holistic data capture and exchange: the initiatives to capture all the experimental information generated within the experiment and the exchange of data between different hardware/software. For those on the fence between two categories, we meant they cover both areas. Chemical Markup Language (CML) was labeled as both semantic and non-semantic since it preserves hard-coded and rule-based semantics but not ontologies following semantic web standards. Basic Formal Ontology (BFO) is an upper-level ontology as the basis of other ontologies, and it does not capture any domain-specific information.

Figure 3

Dynamic knowledge-graph-based approach toward automated closed-loop optimization. The real world layer demonstrates the existing physical entities, adapting from the experimentation setup of Jeraal et al. The dynamic knowledge graph layer hosts all the data generated during the experimentation and a digital twin of the experimentation apparatus. This layer is dynamic as it reflects and influences the status of the real world in real time. This synchronization is enforced by the agents in the active agents layer, which are instantiated from their ontological representation in the knowledge graph.