LIMS & Lab Automation


How can laboratories solve our greatest challenges? Mikael Hagstroem, CEO, LabVantage Solutions


From fi ghting pandemics to ensuring a safe and reliable food supply, or meeting unmet medical needs and generating clean energy, the laboratory will be at the heart of solving humankind’s greatest challenges.


Too many of today’s labs, however, are disconnected from the larger digital transformation of the enterprise, leaving them isolated and reliant on what could be considered analogue systems. To an industry outsider, it could be surprising to fi nd paper laboratory notebooks, word processing software and spreadsheets, or homegrown solutions as the data management tools of today’s scientists.


Of course, many labs are using laboratory informatic solutions - LIMS platforms, electronic notebooks, scientifi c data management systems, etc. - and amassing troves of digital data. But we know that data management, storage, use, accessibility, analytics, integrity, and security all need to be transformed to meet the demands of tomorrow. The question is, what does the lab of the future look like? And who will decide?


The value of data Data


Laboratories have always been data factories, as everything from instruments to experiments to the lab or manufacturing environment itself produce data and metadata that should be captured and analysed for maximum benefi t. But more often than not, that data, even if captured electronically, sits isolated and unmined. Experiments are repeated to avoid time wasted looking to fi nd if anyone had done them previously. Supporting details and documents that could explain a dataset aren’t part of the record, leaving more questions. Opportunities to leverage data to speed products to market, lower costs, reduce risk, or improve outcomes go untaken.


Yet, as the volume, velocity, and variety of data exponentially grows, so does the realisation of its untapped value. This has launched efforts to democratise data, unleashing its potential with new software solutions in the cloud or via software-as-a- service. Artifi cial intelligence and machine learning start moving into the lab. And while self-service drove IT from the lab, that skill set must re-engage to connect the lab to the internet-of-things and the greater enterprise as AI takes centre stage.


With great intentions, everyone from lab managers to the C-suite and vendors are working to gain maximum value from the vast data stores being created within labs. That led to what I call the fi rst phase of Digital Transformation - generally where most of us are now, making sure our labs are digitally enabled and less siloed.


Continuing the digital transformation


The next phase of digital transformation is a bit harder to achieve, but more rewarding. With such things as digital twins and automation, we’re able to create computer models or simulations that mirror physical lab activities to predict future results or recommend future next-best steps.


From there, we move into the third phase, where the digital native lab is designed with data at the forefront. It’s enabled by augmentation, AI, ML, and algorithms to analyse data collected in an all-encompassing data mesh for far greater insights and informed decision-making than possible today. That will enable fully integrated labs to serve as both a producer and consumer of data to benefi t the overall organisation, not to mention humankind.


Seeing the potential


Having spent decades in the fi elds of analytics, digital transformation, and AI, it is quite exciting to imagine how laboratories can benefi t from these solutions. Labs are the source of innovation, and nothing of signifi cance happens without a laboratory being somehow involved. Since solving the greatest challenges of our time will start with scientifi c discovery, we need to equip our labs and enterprises to take full advantage of the data produced there – and everywhere else.


Digital native labs – powered by AI and machine learning – enable us to shift from using limited data for descriptive analytics (what happened?) to accessing unlimited data for predictive and prescriptive analytics, helping to us to know what could happen, or how we can make something happen. Such transformation will certainly open doors.


Sources


This does require a strategy for your data, supported by a new data architecture (see Figure 1). This architecture will defi ne the boundaries and components for implementing a robust framework necessary for a data lake, or mesh. It covers everything from your sources of data to its ingestion, the reservoir holding the data and preparing it for analytics, to data access and delivery and the application of analytics. An information portal provides a single point of entry to the analytics ecosystem, assisting users with navigation. The architecture also supports the workfl ows, data management, technical governance, and systems management for the lab.


Architecture Overview


Streaming Data Reservoir


Data Ingestion


Base Data


Semantic Data


Analytic Persistence


Information Portal


Shared Operational Data


Systems Management Technical Governance Data Management Workflow


Data Access & Delivery


Analytic Applications


Figure 1: A modern big data and analytics reference architecture defi nes the boundaries and components for implementing a robust framework required for a data lake.


The immediate benefi ts of such a data strategy and architecture, as well as the deployment of advanced analytics in the digital lab, include speed to market and more informed decision-making. The effective and thorough analysis of a broader dataset enables organisations to quickly determine which options have the best chance of success. Once data are in a centrally hosted platform serving the enterprise, that data is now accessible to view and subject to algorithms for analysis. AI and machine learning only accelerate the ability to make critical decisions.


That’s because systems can be taught to quickly spot previously undiscoverable patterns in data, allowing for additional investigation to fi nd which are lowest risk, highest reward. As our current informatics solutions - such as ELNs and LIMS - grow in their capacity to track and store ever larger volumes and variety of data, advanced analytics will be needed to make the most of those assets. Not only for scientifi c advancement, but also lab productivity. AI and ML can monitor lab operations to optimise work plans, or predict process or system failures so preventive and corrective actions can be taken to reduce waste and downtime. It’s hard to imagine areas of the lab that won’t be enhanced by a complete digital transformation.


In fact, we’re already seeing glimpses of the positive effect that AI is having - helping gas refi ners to discover new revenue streams; or consumer packaged goods companies advance their carbon tracking beyond manufacturing out to product use - earning Level 4 carbon designations; while pharmaceutical companies are better able to sustain production documentation for regulatory requirements and diagnostic applications enable next-best-test decision-making.


Making the commitment


None of the benefi ts of digital transformation will be realised without a true commitment to AI and the process. We have seen many organisations ‘play’ in AI but few that have gone all in. It’s understandable to a degree because so much is unknown. That saying of ‘fl ying the plane while building it’ can feel familiar in this instance.


That is why partnership is so important. Working with partners who can help you navigate this transformative journey is essential to its success. Vendors like


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72