Labman, a specialist in bespoke laboratory automation, has demonstrated an integrated platform that automates the sample journey from the bioreactor and connects laboratory analysis with AI-driven process optimisation. Developed in collaboration with CPI, Basetwo AI and Nicoya through an Innovate UK-funded international project, the platform marks an important step towards more autonomous upstream bioprocess development.
The system brings together automated sample collection and preparation with Nicoya’s Alto Digital SPR platform for label-free antibody titre quantitation, alongside Basetwo’s AI predictive modelling and control software. This enables data from bioreactor samples to inform process adjustments, helping optimise conditions during cell cultivation.
Labman developed the automation hardware and software architecture to connect these stages into a coordinated workflow. The project showcased closed-loop control of fed-batch mammalian cell culture for trastuzumab production (a biosimilar used in the treatment of breast cancer). Runs were demonstrated across bioreactor scales from 0.2 litre using an Ambr 250 system and a 10 litre Sartorius bioreactor, both at CPI.
Automating the sample journey
Bioprocess development often relies on manual sampling, sample preparation and analysis, requiring significant staff time and making continuous monitoring challenging, particularly outside normal working hours. As part of the integrated workflow, Labman’s robotic system automatically collected and prepared bioreactor samples for analysis on Nicoya’s Alto Digital SPR platform, enabling unattended antibody titer quantitation directly from crude culture supernatant during the bioreactor run.
By automating these steps and connecting analytical results with AI-driven control, the platform demonstrates how laboratories can reduce manual intervention and enable more responsive process optimisation. During the project, the system used predictive control to adjust nutrient feeding, maintaining glucose levels within a target range and supporting improvements in cell viability and product titre compared with manual control.
A key outcome for Labman is a flexible approach that can be adapted to different workflows, bioreactors, analytical instruments and AI platforms. Rather than being tied to a single instrument or process, the system provides a template for integrating the technologies needed to automate upstream process development.
This is a really exciting development for Labman. We’ve demonstrated how we can automate the sample journey from the bioreactor, bringing together sample collection, preparation and analytical equipment with AI-driven process optimisation. These steps have traditionally involved a lot of manual work, so connecting them in a single workflow opens up new possibilities for upstream process development.
Our approach is flexible, allowing us to build around the workflow and technologies a customer needs. It provides a foundation for laboratories to make better use of automation and AI, bringing us a step closer to the self-driving lab.
Tom Smith - Head of Bioprocess Automation | Labman
The real opportunity here isn’t simply automating laboratory activities, but using the data we generate to make better decisions as a bioprocess develops. By bringing together automated sampling, analytics and AI-driven control, this collaboration has demonstrated how processes can respond to information in real time, reducing reliance on manual intervention.
Demonstrating this approach across different bioreactor scales is an important step towards more autonomous bioprocess development. It highlights the potential to accelerate process understanding, make better use of experimental data and ultimately develop more efficient and robust manufacturing processes. This is a great example of how collaboration between technology developers and bioprocessing experts can help translate emerging technologies into practical solutions for industry.
Philip Probert - Director of Biologics, RNA Centre of Excellence and Medicines Manufacturing Innovation Centre | CPI
Biopharma manufacturers have invested heavily in bioreactor infrastructure, but critical process decisions still depend on measurements taken hours apart.
At Basetwo, this means using soft sensing combined with model-predictive control (MPC) to use existing bioreactor data to predict what’s happening inside it, automatically adjust the process, and ultimately produce higher performance outcomes. This approach makes autonomous process control more accessible without requiring manufacturers to install additional spectroscopic instrumentation.
Thouheed Abdul Gaffoor - CEO | Basetwo
The challenge of integrating an analytical instrument into an automated workflow is getting the handoffs right – what the robot delivers, what the instrument expects, and how the results are communicated. Labman solved that challenge.
Their system draws samples from the bioreactor, prepares them, and loads them onto Alto Digital SPR through its automation interface. From there, Alto automatically runs calibration standards and quantifies antibody titer directly from crude culture supernatant, without operator intervention. That kind of unattended, repeatable measurement is exactly what Digital SPR was designed for.
Jamie McQuay, VP of Engineering | Nicoya