The scalability of all this is certainly going to be a challenge. Data generation remains a real bottleneck for organ-on-chip development. Meeting automation and high-throughput requirements is essential – not only to produce the volume of data needed, but to do so in a way that is compatible with downstream analysis and capable of gaining meaningful insight into fundamental cancer mechanisms. Closing the loop between biological interrogation, downstream analysis, and computational modelling – and back to the biology – is where the real power of these platforms lies, and where the field has the most work to do. These are pressing questions bioengineering faces, and exciting ones: meeting them will feed the broader field in return, enabling better, more accessible microphysiological systems across a wider range of models, organs, and biomedical applications.
The expanding use of AI
AI sits as the integrating layer across all of it as an active experimental co-pilot. AI-driven inference, hypothesis generation, foundation models trained on large-scale spatial and single-cell datasets will become important, with experimental platforms serving as high-quality inputs to that pipeline. The boundary between computational prediction and experimental validation is already blurring, this is an opportunity to shape these tools into one of the most powerful collaborative instruments cancer research – and science more broadly – will ever have.
Building that integrated infrastructure – standardised, regulatorily credible, and spanning in vitro platforms, spatial omics, and AI pipelines – is a defining challenge for the next decade. It will broaden the scope of discovery and substantially reduce the time and failure rate between bench and clinic, with the ambitious goal of turning scientific innovation into faster, better targeted, more equitable treatment.
On talent and expertise, a productive cooperation is emerging between deep specialists and genuinely multidisciplinary profiles – particularly in technical areas – sustaining the interdisciplinary expertise that drives discovery. Equally important is increasing permeability between research, technology, and clinical application. Models like Cancer Grand Challenges – uniting world-leading teams across disciplines and borders to tackle cancer’s hardest problems – represent the kind of coordinated, large-scale collaboration that will become ever more central to how the field operates.
I see these changes as truly positive, and they give me real hope and confidence in the discoveries to come.
Source link
