Four Things to Consider when Preparing your Laboratory Data for Artificial Intelligence and Machine Learning ?

Background 

The delivery of informatics systems within lab-based companies has always been a very active space. Traditionally this was focused on single systems or multiple connected systems covering a specific set of workflows. Most labs now operate at least some form of LIMS, ELN, LES, SDMS, CDS etc. The current “Big Thing” is how to use those same laboratory informatics systems to deliver data that supports Artificial Intelligence and Machine Learning (AI/ML) to derive more value and to predict outcomes of changes to the workflow to achieve specific goals. 

What do you want from AI/ML? 

This may seem like an obvious, but important point to consider. Before embarking on your AI/ML journey, make sure you have some specific and prioritized targets in mind, for example moving to environmentally friendly raw materials, reduced toxicity effects for a class of drugs, lower costs of production by optimising process conditions and so on.  This helps you to: 

    • Prioritize where to focus your efforts 

    • Estimate potential costs and expected benefits 

    • Know who in your organisation will need to be involved 

    • Know who will be impacted by the program 

    • Understand where funding is coming from 

Holding workshops with stakeholders to capture and prioritize areas of focus is a useful activity in mapping out your AI/ML journey and gathering all these attributes. It will also help you to decide where to invest in preparing your data and lab applications for the journey ahead. 

Is Digital Transformation a Necessary Step to AL/ML? 

We are often asked if it necessary to replace lab spreadsheets with a LIMS or ELN before using AI/ML and the answer is “no” – it may require more effort to normalize your data sets to make them comparable and consistent, but there are no absolutes when it comes to your data.  

Over recent years, Digital Transformation (DT) has become an area of increasing focus for businesses. DT dictates a much wider scope to laboratory systems with greater depth of functionality, increased benefits, and consequently a longer delivery time frame associated with the implementation of a programme of changes. It feels like many lab-based companies and their lab informatics teams are just starting to understand the challenges associated with DT.   

Given that AI/ML works best with more data, you may want to include digital transition as a part of your AI/ML program. An incremental/parallel delivery of DT and AI/ML coverage is often a pragmatic approach, allowing your AI/ML model scope to increase as your DT program delivers more data dimensions. 

Is My Data Consistent and Interoperable? 

For most organisations this is a difficult question to answer without analysing the state of your informatics landscape. Unless you are a green-field facility with an unlimited budget, the chances are pretty low that your scientific informatics platforms were carefully and consistently implemented from day zero:  systems evolve; get upgraded, replaced and migrated; systems from multiple vendors are used; applications have been developed in house; workflows are modified – all leading to inconsistencies in terminology and gaps in data elements. Mapping out data flows and manual transitions between systems is a great way to identify these gaps, and identify the work needed to consolidate your reference data sets. A good question to ask repeatedly during this process is ‘Which is the source of truth for this data element…?’ 

Is data perfection necessary before I develop my central data repository? 

In short, no it isn’t.  The central data repository (CDR) relies on being able to access data from each of the producing systems that will be included in the AI/ML modelling. Data is going to be transported to the data layer using either a native application tool, or an external interface such as ETL, and usually after a particular workflow has completed in the source application – for example data review and authorization. This means you are going to need a range of approaches to get the data you need in the CDR according to capabilities, data types and underlying technology of each source application. It therefore makes sense to start the CDR connectivity for each of your producing systems when the data is ready to be used, i.e. consistent, interoperable, comprehensive enough to contribute to the model. 

Need more information? 

If you’d like to read a more in-depth discussion of the issues highlighted in this blog, we have published a white paper on the subject “Machine Learning and Lab Informatics – Where to Start?” 

Send us an email at info@scimcon.com if you’d like us to help you navigating the AI/ML journey, we’d be happy to discuss your individual needs.  

Scimcon sponsors SmartLab Exchange EU and USA and identifies key themes at Europe event for 2023 lab informatics?

The SmartLab Exchange Europe 2023, whichtook place from 22-23 February in Amsterdam, Netherlands, is one of the global meetings for lab informatics leaders. Scimcon continues its proud sponsorship of this event, as well as this month’s North American event in San Diego on 22-23 March, facilitating one-to-one meetings with a number of informatics customers from all major lab-centric sectors. The continued sponsorship of the event provides access to the community of senior R&D, Quality Assurance and Quality Control decision-makers from industry in both North America and Europe.

Feedback and voice of the Industry

Attending from Scimcon was co-founder and lead consultant, Geoff Parker, who took the opportunity to poll attendees and delegates of the attending organisations, to identify the current 2023 trends in the lab informatics industry. This includes R&D executives, Quality Assurance and Control leaders, and Regulatory specialists from organisations such as GSK, P&G, AstraZeneca, BioNTech, and more.

Summary of trends in lab informatics for the modern lab

In the informal poll of attendees at SmartLab Exchange, Scimcon has been able to identify key trends and themes that are important to the modern lab in 2023.

Of the total 73 delegates polled, 68 delegates – with budgets ranging between 500k to millions in GBP – volunteered which technologies they are interested in investing in within the coming 12 months.

Some of the key investment priorities included:

    • 30.8% flagged digitalisation as a priority in 2023 (21 delegates)
    • 20.6% noted automation as a priority investment area (14 delegates)
    • 13% cited LIMS as 2023 priority (9 delegates)

    Scimcon sponsors SmartLab Exchange for another year, and reports on the delegate priorities in 2023.

    When asked about additional investment priorities, 7 delegates stated that the following areas were also of interest this coming year:

    • Digitalisation, Agile process, AI
    • Automated Analytics/Analysis
    • Harmonisation
    • People/Talent
    • Risk assessment, based methodologies, toxicology, product expertise
    • Reducing QC Testing
    • Infrastructure

    Attendees also ranked their interests and what topics they wanted to address at SmartLab. As illustrated, lab automation, and AI/ML in particular, are high priorities for lab leaders in 2023, with other high priority areas including data quality and integrity, instrument connectivity and IoT, and data integration.

    This year’s event also saw the Scimcon team hosting the opening panel discussion, ‘What is the future for human scientists as AI and ML deliver the promised step change in laboratory practice?’, where key opinion leaders were invited to participate in the discussion to kick off the event. Panellists at the European conference were Edith Gardenier from Genmab, and Andy Phillips and Robin Brouwer from AstraZeneca.

    Geoff summarises “As lab informatics consultants with a global customer base in leading lab centric organisations, it is important to us to check in frequently with influential decision-makers from the lab. SmartLab Exchange offers us a useful ability to poll the attendees and see trends that will impact the modern lab decision-maker, and will help us at Scimcon to hone the way we partner with our customers. The attendees we spoke to were split between R&D and QA/QC – with 43% in R&D, 24% in Quality, and 16% in both. We very much look forward to catching up with delegates at the US event in March, and it will be interesting to see how trends and priorities differ or align between the US and Europe.”

    SmartLab Exchange is attended by invite-only decision-makers. The unique invite-only format of the event means that both sponsors, speakers and delegates can access a closed community that meets their individual needs. 

    Scimcon is proud to continue its sponsorship of the SmartLab Exchange Europe and US events in 2023, and the team is excited to connect with delegates at the US event on 22-23rd March 2023.

    To learn more about how Scimcon supports science centric organisations with data solutions and lab digitalisation, or to organise a meeting at the US event, contact us today.

    To catch up on the themes discussed in our EU panel discussion, you can read our blog here.

    In order to work as intended, this site stores cookies on your device. Accepting improves our site and provides you with personalized service.
    Click here to learn more