Making Adherent Cell Assays AI-Ready for Next Generation Drug Discovery
Traditional adherent cell assays remain a major bottleneck in early drug discovery.
As drug discovery organizations accelerate toward automated, data‑driven, and AI‑enabled workflows, one foundational bottleneck continues to slow progress: adherent cell assays. Despite underpinning a significant proportion of early discovery and profiling experiments, traditional adherent cell workflows remain labor‑intensive, difficult to automate, and prone to variability.
Few leaders have examined these challenges as closely as Jeroen Verheyen, co‑founder and CEO of Semarion, whose work focuses on transforming adherent cells into standardized, assay‑ready reagents compatible with modern automation infrastructure.
In this article, Verheyen explains why traditional adherent cell assays restrict decision‑making in early drug discovery, how Semarion’s platform supports automation and AI‑driven experimentation, and what role standardized cell models may play as the industry moves toward self‑driving laboratories and new approach methodologies.
Why traditional adherent cell assays remain a bottleneck
What are the less discussed but most limiting challenges of traditional adherent cell assays?
Adherent cell assays account for a surprisingly large share of drug discovery spending. “Our market analysis shows that 25–45% of drug discovery R&D costs are associated with adherent cell assays,” Verheyen said.
Much of that cost stems from manual cell preparation. Cells must be continuously cultured, passaged, trypsinized, seeded, and allowed to attach before experiments can begin. This process introduces substantial batch‑to‑batch variability, even within the same lab.
“Cell preparation can take days, but the actual assaying might just take a couple of hours,” Verheyen explained. “That creates a very narrow assaying window and makes smart planning and timing extremely difficult.”
Automation has improved downstream assaying steps, but cell preparation itself remains challenging to scale. Existing automation solutions are often prohibitively expensive and still limited in throughput, leaving many organizations reliant on manual workflows.
Miniaturization presents another constraint. While drug discovery has largely plateaued at 384‑well formats, pushing adherent assays beyond that scale is difficult for many adherent, imaging-based, or biologically complex cell assays. At the same time, discovery teams must constantly compromise between throughput and data richness, often opting for simpler models to preserve robustness and scalability.
Why limitations in adherent cell assays matter for early discovery decisions:
- Manual cell preparation drives cost, labor burden, and batch variability.
- Narrow assaying windows complicate automation scheduling and throughput.
- Limited miniaturization and variability force compromises between data complexity and robustness.
Decoupling cell preparation from assaying to enable automation and AI
How does Semarion’s platform make adherent assays more compatible with modern drug discovery workflows?
Verheyen described automation and AI as part of a “golden triangle” alongside high‑quality data generation. While AI has reshaped experimental design and hypothesis generation, it still depends on robust, reproducible biological data.
“Our focus is on making cell assays more automation‑friendly and dramatically increasing both data throughput and data richness,” he said.
Semarion’s approach centers on converting adherent cells into assay‑ready, barcoded reagents using microchip-style microfabrication. The result is a platform of microscopic carriers, called SemaCytes®.
“These can be viewed as microscopic, barcoded petri dishes that can be handled in suspension while the cells remain in an adherent 2D morphology,” Verheyen explained. “Once cells are attached, you can freeze them down, store them in biobanks, and deploy them on demand directly into automation systems.”
By decoupling cell preparation from assaying, researchers can retrieve pre‑prepared cells, multiplex them using barcode identifiers, and immediately execute experiments using liquid‑handling robots.
“You could generate an AI‑driven hypothesis in the morning, execute the experiment in the afternoon, and feed the data back into the AI model the same day,” Verheyen said.
Accelerate your PROTACs drug discovery and development
This eBook shows how an integrated, end-to-end analytical approach helps labs generate reliable, regulatory-ready PROTAC data at every stage of development.View eBook
Perhaps most transformative is the ability to multiplex multiple cell models within a single well. Instead of one drug–one cell interaction, researchers can observe responses across many cell types simultaneously.
What standardized, assay‑ready cells unlock:
- On‑demand deployment of adherent cells without manual preparation.
- Seamless integration with robotic liquid handling and imaging systems.
- Multiplexed experiments that dramatically increase data density per assay.
Real‑world adoption across screening and profiling applications
Where has this approach already made a tangible impact in drug discovery?
Verheyen emphasized that Semarion’s platform is intentionally plug‑and‑play, compatible with existing microscopes, assays, and microplate formats. This has led to adoption across several high‑value application areas.
In phenotypic screening, including cell painting assays, companies have traditionally relied on a single cell model. Semarion has helped pharmaceutical companies and contract research organizations screen 4–8 cell models concurrently in fully automated workflows, generating richer phenotypic datasets with improved predictive power.
Another area of traction is antibody discovery, where flow‑based screening systems can be limited by throughput and operational complexity. By enabling high‑content imaging–based antibody screening, Semarion supports multiplexed evaluation of engineered cell lines expressing different protein variants, including orthologs relevant to antibody–drug conjugate programs.
Finally, in compound profiling, later‑stage functional assays often rely on cyclical testing during lead optimization. Here, the ability to miniaturize assays, multiplex patient-derived cells, and standardize preparations enables faster iteration without sacrificing biological relevance.
Where standardized adherent assays deliver immediate value:
- Multiplexed phenotypic screening across diverse cell models.
- High‑content antibody screening with improved throughput and reliability.
- Faster, more informative compound profiling using complex or patient‑derived cells.
Supporting the shift toward more physiologically relevant models
How do regulatory and industry trends toward new approach methodologies change discovery workflows?
Tech Spotlight: High-Throughput Screening 2026
Explore reliable high-throughput screening workflows for vaccine and antibody discovery, covering assay design, validation and data analysis to improve reproducibility, data quality and candidate prioritization.View Webinar
Regulatory agencies, including the US Food and Drug Administration, are gradually encouraging alternatives to animal testing during preclinical development. While this shift is most pronounced in regulated safety studies, it also influences earlier discovery stages. As advanced in vitro tools become standard in preclinical testing, they naturally migrate upstream into discovery.
Patient‑derived models, induced pluripotent stem cell‑based systems, organoids, spheroids, and organ‑on-a‑chip platforms are all gaining traction. However, these models introduce new challenges around throughput, reproducibility, and variability.
By standardizing 2D patient‑derived cells as assay‑ready units, Semarion enables large‑batch differentiation, freezing, and reuse across entire screening campaigns. This approach reduces batch effects while preserving biological relevance.
Looking ahead, similar principles could be extended to 3D systems using the same microcarrier‑based strategy.
How standardization helps balance complexity and reliability:
- Batch‑frozen, differentiated cells reduce variability in patient‑derived studies.
- Assay‑ready formats make advanced models operationally feasible at scale.
- Extending standardization to 3D systems may bridge complexity and throughput.
Adherent cell assays in the era of self‑driving labs
As automation and AI become embedded across drug discovery, how will adherent cell assays evolve over the next five years?
Verheyen expects continued consolidation around modular automation systems and deeper hardware–software integration.
Cell and Gene Therapies: The Evolution of Advanced Biologics
This eBook takes a look at the challenges shaping advanced biologics, alongside practical strategies to improve consistency, scalability, and compliance across development and manufacturing.View eBook
Another emerging need is simplified programming. “What people really want are AI‑driven interfaces, almost conversational, to design and run experiments without complex coding.”
Emphasis is also shifting from brute‑force screening to intelligent, iterative experimental design. Rather than screening millions of compounds indiscriminately, AI systems increasingly prioritize smaller, data‑guided sets, refining hypotheses in real time.
These trends culminate in the concept of self‑driving labs, autonomous environments where AI models generate hypotheses, execute experiments, analyze results, and iterate continuously.
“Our goal is to make adherent cells a standardized, automation‑ready unit,” Verheyen concluded. “That removes a bottleneck that has constrained discovery for more than 30 years.”
What will define next‑generation assay evolution:
- Modular, interoperable automation infrastructure.
- AI‑guided experimental design driving smarter, faster iteration.
- Standardized cell reagents enabling autonomous discovery workflows.
As drug discovery moves toward autonomous, data‑driven experimentation, the ability to standardize and automate biological inputs becomes just as critical as advances in AI or robotics.
Key takeaways:
- Traditional adherent cell assays remain a major bottleneck due to manual preparation, variability, and poor automation compatibility.
- Assay‑ready, barcoded cell formats enable multiplexing, higher data density, and seamless integration with AI‑driven workflows.
- Standardization of complex and patient‑derived models is key to balancing biological relevance with reliability, throughput, and future self‑driving lab systems.
This content includes text that has been created with the assistance of generative AI and has undergone editorial review before publishing. Technology Networks' AI policy can be found here.
Add Technology Networks as a preferred Google source to see more of our trusted coverage.
