In 2022, Agilent announced its acquisition of advanced artificial intelligence (AI) technology developed by Virtual Control, an AI and machine learning software developer that creates innovative analysis solutions in lab testing. Agilent will integrate the software, known as ACIES, into its industry-leading gas chromatography and mass spectrometry (GS/MS) platforms to improve the productivity, efficiency and accuracy of high-throughput labs the company serves around the world.
ACIES automates the labor-intensive task of gas chromatography/mass spectrometry data analysis improving efficiency in the laboratory workflow, from sampling to reporting. Agilent will integrate the technology into its MassHunter software package for LC/MS and GC/MS instruments.
This move by Agilent signals that the digital age is very much here for laboratories. Science has always driven the world forward and now it will do the same for laboratories. The lab of the future is a concept built on the foundation of digitalized labs. It encompasses smart technological workflow systems that are connected and capable of collecting vast amounts of data via integrated automation.
A digitalised lab should be considered a more advanced lab as it has more access to data. With data being key to transforming science, increasing amounts of data generated in any lab, let alone a digitally connected lab, could be a game-changer – but only if it’s collected and synthesised into information and knowledge that is useful.
The digital environment (i.e., paperless work in an electronic format) capitalises on digitalisation. It incorporates all of the necessary instrumentation for complete data analysis, and enables the full value of the data for decision making. The ability to monitor operations and provide more sophisticated insights is a core reasoning for introducing AI into the operational lab environment.
Artificial intelligence (AI) is often defined as the ability of a machine to learn how to solve cognitive challenges. However, in the context of scientific methodology and laboratory interconnectivity, AI is starting to be used for capturing data to model human observation and decision-making processes. Taken forward, connecting all instruments in a lab via AI enables the opportunity for an even more astute understanding of the interactions between technology and also users, potentially providing an all-inclusive view of all laboratory operations.
Accessing this powerful source of information will become a necessary component of scientific productivity. This is an inevitable next step in creating lab management systems that are so efficient and provide knowledge that is so valuable that only AI will be able to produce them.
AI, coupled with universal sensing capabilities to detect and monitor a range of variables, e.g., an instrument’s power draw, enables companies to realize certain operational and financial benefits to their business and plan for the future. Through high-quality and readily available insights, AI enables the simultaneous monitoring of all equipment usage in the lab and holistic capacity tracking.
Globally, scientific innovation is accelerating, so labs need to consider the technology investments required to become digitally enabled in order to keep up and stay competitive. We live in a data-driven world, so scientific laboratories must fundamentally transform how they create, manage, and effectively use all the data that is generated in their lab ecosystem. Achieving and sustaining a competitive edge in a world of constant change will require the continual transformation of lab operations and scientific data management. This will be the first and most important step toward becoming a truly digitalised lab.
Although previous work has been done developing case studies for fingerprinting foodstuffs, including honey, the approaches among laboratories have been different regarding sample preparation and instrumental condition. There are also differences in terms of data processing and analysis. As a result, two laboratories analyzing the same sample may obtain slightly different results. Ideally, developing a standardized fingerprinting method that could be used across all LC/MS-based workflows, enabling the same testing technique to be used across multiple laboratories, would be optimal and where future work is aimed.
When addressing the issues of food safety, product quality, and authenticity, each may be governed by separate sets of regulations. For example, looking at the residues of contaminants in honey, such as pesticides, there may be differences globally. Countries may have their own restrictions for the maximum limit for specific compounds. Contaminants are a part of the picture when considering fingerprinting for honey, but permitted levels may vary between countries.
Additionally, as samples come from the field to the lab for testing, there is potential interest in reversing this and bringing the lab out into the field instead. This interesting but not yet recognised capability would enable regulators and the global food industry to respond more quickly to honey contamination and food fraud.