SEED Cell seeding can be automated on a liquid handler. This may involve seeding of cell suspension for 2D cultures or handling of organoids mixed in Matrigel.
MAINTAIN Cells are maintained in an incubator, and media changes can be scheduled and carried out on the liquid handling deck.
iPSC culture workflow Automate processes such as seeding, feeding, imaging, and analysis, with AI monitoring cell morphology and confluence.
PASSAGE Passaging is often carried out when iPSC are confluent. In this case, a decision-making protocol can be set up to trigger the passaging step.
Experience the full cell culture journey—seed, maintain, monitor, and passage—through our interactive visual workflow.
MONITOR Cells are monitored with an imager. This is followed by on-the-fly, AI-enabled image analysis, which can be configured to trigger downstream steps based on the results.
Spheroid culture workflow Automate formation, culture, and analysis, assessing spheroid size, viability, and morphology through integrated imaging and AI tools.
CRC organoid workflow Automate medium exchange, passaging, and imaging, with real-time AI-driven decision-making ensuring optimal growth conditions.
2D/3D example workflows
The CellXpress.ai™ system orchestrates each phase of cell culture using a modular platform that combines liquid handling, incubation, imaging, and AI-powered analysis. With automated decision-making and real-time feedback, users can design flexible protocols, monitor progress across timepoints, and trigger next steps—all within a single, integrated software environment.
View in full screen
Protocol seeding Cells handled manually are usually grown in cell culture flasks. However, the footprint of flasks is not amenable to robotics due to the need for additional components such as decappers and non-standard grippers. In automation, cell culture is typically done in SBS standard 6-well plates or up to 384-well plates (the seeding step involves dispensing cells onto a tissue culture plate with the growth media). This step can be automated with a liquid handler.
Automated cell seeding
The CellXpress.ai Automated Cell Culture System transforms the cell seeding process through precision liquid handling and standardized protocols. Automated cell handling: The system utilizes an 8-channel pipette head (Span 8) to precisely transfer cell suspensions with minimal variability. Programmed mixing: Automated mixing ensures consistent cell suspension before and during the seeding process. Precise dispensing: Controlled dispensing rates minimize cell stress while ensuring even distribution across culture vessels. Protocol-driven process: Turnkey, validated protocols guide the entire seeding process, eliminating variation between operators. Environmental stability: Integrated environmental controls maintain optimal conditions during the sensitive seeding phase. The CellXpress.ai system's liquid handling capabilities eliminate the variability inherent in manual pipetting techniques, resulting in consistent seeding density across multiple vessels and experiments.
Automated iPSC culture: Human iPSC cells adapted to feeder-free conditions (SC102A-1, System Biosciences) were thawed and cultured in Complete mTeSRTM Plus culture medium (STEMCELL Technologies) in Matrigel coated 6-well plates (cat. #354277, Corning). Once the cells are established in culture, the plates were transferred to the CellXpress.ai for maintenance. The “Feeding” phase in the software was setup to do daily media change. mTeSR media was added to the media container and stored on deck (at 4°C) for the duration of the experiment. Automated colorectal cancer organoid culture: Colorectal cancer (CRC) organoids (Line ISO68, Cellesce) were handled according manufacturer’s instructions. Briefly, organoids were thawed quickly at 37°C, gently resuspended and washed in media. Pellet containing organoids were resuspended in 80% Matrigel and manually dispensed into a deep well plate. The CellXpress.ai system was used to pipette 40μl of organoid suspension into a 24well plate. The plate kept at 37°C for 15 mins to allow the Matrigel to set, before the addition of complete media.
Cell culture material and methods Featured poster: Using the power of AI in automated cell culture
Matrigel domes are automatically positioned and the ECM suspencion is combined with organoids (cells). The seeded domes are configured in 24 well plates, incubated before being transferred to the incubator and moved back to the deck to introduce other media.
CellXpress.ai software combines four software packages - liquid handling, image acquisition, AI-analysis, robot scheduling - into a single, unified platform
Liquid handler enables media exchange, feeding, passaging, other functions
Protocol maintenance Following seeding, vessels containing cells are placed in an incubator where temperature, CO2, and humidity are regulated. This transfer step is carried out with a robotic plate handler and an automation-compatible incubator. As cells get established and grow in culture, they deplete the culture medium of its nutrients. Over time, this medium must be replaced with fresh medium to ensure a healthy culture. A liquid handler is used to automate this step, and depending on available deck positions, multiple plates can be handled in parallel to increase throughput significantly.
Automated maintenance
The CellXpress.ai system delivers consistent maintenance through scheduled interventions and precise environmental control. Automated media exchanges: The system performs media changes according to programmed schedules without human intervention. Media temperature management: Dedicated heating and cooling positions ensure media is at optimal temperature before introduction to cells. Environmental regulation: Integrated CO₂, temperature, and humidity control maintain stable conditions throughout the culture period. Contamination prevention: Automated hydrogen peroxide decontamination and on-deck UV decontamination features maintain sterility. Smart media handling: Software-controlled heating, cooling, stirring, and volume tracking support various workflow environments with different media vessel types. This comprehensive approach to maintenance eliminates the variability and potential for human error associated with manual culture techniques, while the automated decontamination features significantly reduce contamination risks.
Monitoring of iPSC was carried with the CellXpress.ai built-in imager. The “monitoring” phase was set up in the protocol to image the wells every 12 hours. To quantify confluency, an image analysis protocol that utilizes a pre-trained, deep learning model was used to segment iPSC colonies. Decision making component was also added to the protocol such that when iPSC confluency reaches > 80%, the user is informed via email. Passaging may also automatically be triggered in this way. The protocol used to monitor of CRC organoids is similar to that for iPSC. Daily imaging of the plate was scheduled. Media exchange was carried out every three days. Passaging occurred every 7 days.
Remove media and introduce fresh media. Set the process protocol to repeat the routine every “X” hours.
Monitoring and maintenance Featured poster: Using the power of AI in automated cell culture
Automated incubator 44 or 154 plates
HEPA filter and UV lamp for sterilization inside
Protocol monitoring Cells are routinely monitored using a microscope to ensure that the culture is thriving as expected. Some of the characteristics to note are cell morphology and confluency. Detection of contamination in cell cultures is part of the routine monitoring step. Early detection can help prevent widespread contamination and allow countermeasures to be implemented; a robotic plate handler transfers plates to an automated high-content imager for image acquisition. More advanced automation solutions may include on-the-fly analysis of the image data to extract key measurements such as confluency, cell size, and more.
Automated monitoring
The CellXpress.ai system revolutionizes culture monitoring through advanced imaging capabilities and AI-powered analysis. Integrated imaging system: The platform features a 24-megapixel camera system with objectives ranging from 2X to 40X for detailed cell visualization. Multiple imaging modalities: Supports time-lapse, Z-stack, and optional Digital Confocal imaging across multiple channels (up to 6 fluorescence channels). Automated imaging schedule: Performs regular imaging according to programmed intervals without user intervention. AI-powered image analysis: Machine learning algorithms analyze cellular morphology, confluence, and health status in real-time. Data-driven decisions: AI-based classification and segmentation enable automated decision-making regarding maintenance and passaging needs. This integrated monitoring approach provides comprehensive documentation of the entire cell culture process while enabling real-time assessment of culture status without human subjectivity.
AI-based image analysis Featured poster: Using the power of AI in automated cell culture
In addition to maintaining cells in culture with regular media changes, it is also important to carry out routine monitoring of cells to ensure that the cells are growing as expected and detect anomalies (such as contamination). In most small-scale settings, monitoring usually involves visual inspection of cells. This is rarely feasible in high throughput environment. Thus, we have automated cell culture monitoring using an image-base, quantitative approach.
Spheroids
iPSC culture
Airway organoidsin Matrigel
Bright field transmitted light imaging is commonly used to image cells in culture. However, segmentation of transmitted light images is challenging due to the meniscus effects and shading or edge artifacts. The example of artifacts above (Well edge effects, heterogenous background, and debris in media) are observed in transmitted light images.
Deeplearning can be used for segmentation of challenging images. The workflow starts with data annotation followed by model training and validation. This process continues iteratively until the model is satisfactory.
The image analysis software, IN Carta, includes a deep-learning based segmentation tool (SINAP). Shown here is the SINAP interface for image annotation to create training data. Images are loaded in the main panel while the annotation tools (red box) are on the right.
Models to segment differentiated and undifferentiated cells may be trained using SINAP. Arrows point to areas of differentiation. Right: Overlay of segmentation mask shown.
Segmentation mask distinguishes between iPSC colonies differentiated cells.
IN Carta Image Analysis Software Advanced AI-analysis, machine-learning classification, and deep-learning segmentation
Robotics Elevator moves plates to liquid handler or imager
High-content Imaging System Monitors cells and organoids culture with decision-making based image analysis
Protocol passage Most cells in culture proliferate over time. Cells that have proliferated will eventually cover most of the surface of the culture vessel (known as confluent). Usually, when cells reach about 70 to 80% confluency, they need to be “passaged”. This refers to the act of transferring some or all cells from a previous culture to a fresh growth medium. To automate cell passaging, a liquid handler may be programmed to remove media, add enzymatic reagents to detach cells from the labware surface, and dispense the cell suspension into new plates. In some instances, such as with organoids, a centrifuge is required to pellet the tissues. An automation-compatible centrifuge may be integrated in the workflow to support this step.
Automated passaging
The CellXpress.ai system transforms cell passaging from a manual, time-sensitive task into a standardized, automated process. AI-guided timing: Machine learning algorithms analyze cell density and morphology to determine optimal passaging timing. Automated protocol execution: The system handles the complete passaging workflow, from media removal to cell detachment and collection. Standardized parameters: Consistent application of dissociation agents and incubation times eliminates process variability. Cell counting and viability assessment: Integrated analysis determines cell concentration and viability for appropriate reseeding. Controlled reseeding: Precise dispensing ensures consistent seeding density in new vessels. By automating the passaging process, the system eliminates the subjectivity of determining when to passage and standardizes the procedure across all samples and experiments.
Image-based AI for automated decision-making Featured poster: Using the power of AI in automated cell culture
Confluency, is a common metric used to determine whether cells are ready for passaging. I non-automated workflows, confluency is usually a subjective measure based on the user’s cell culture experience. Similarly, in the culture of adult stem cell derived organoids (such as intestinal), factors such as size and morphology is used to determined when passaging should be carried out. Here, we have integrated an AI-based image analysis approach in the CellXpress.ai system to make “decisions” in cell culture.
Monitoring of cell cultures such as iPSC culture starts with image acquisition followed by analysis using IN Carta’s SINAP. Measurement output is then used to trigger future actions such as “inform user” via email or to start passaging.
iPSC cultures are imaged daily with Confluency used in the decision-making setup. Graph shows iPSC confluency over time.
Example of cell culture protocol with decision making rules set up.
For quality control, the CellXpress.ai software includes a“widget” setup for custom dashboard view over time (A). Samples from each well is tracked in the software. For example, at time point8, well A1 was passaged and seeded into well A3 of the new plate.
CRC organoids were seeded and maintained in culture in the CellXpress. Plate was imaged daily, media change was carried out every 3 days. Shown here is the same well imaged over time. B) HCT116 cells seeded into 96 well plates. Shown here are spheroids on day two post seeding. Note the uniformity of the spheroids.
Automated 3D cell culture (organoids, spheroids)
Passaging protocol Full workflow protocol set in “phases” and defined by user including automated, image analysis decision making for feeding/monitoring, seeding, and passaging
Liquid handler enables media exchange, feeding, and passaging
Automated centrifuge Expansion ports for integrated solutions
Application Note Give researchers their time back with automated decision-making for cell culture and expansion Tissue culture remains the most routine, hands-on, and time-consuming part of biological studies. In addition, due to protocol complexity, sensitivity to errors, and substantial training requirements, these processes are difficult to automate with assured reproducibility and quality. Here, we share results from a fully automated standard cell culture process with protocols that provide automated maintenance and expansion — controlled by image-based automated decision making – of HCT116 cell lines.
Cell culture is a labor-intensive task that require constant attention to details and pose substantial demands on scientists’ time during all hours of the week—including weekends. Automation can not only alleviate these time-sensitive and highly routine tasks from the scientist, but can also reduce human error and inconsistencies associated with manual processes. While automated liquid handling has previously been developed for complex processes with liquid handler devices, automating the entire process is far more challenging. Decision making based on cell density or growth rates is notoriously hard to automate and to ensure the process quality. Monitoring cell culture development using imaging and image-based decision making presents a unique opportunity to fully automate the entire cell culture process—not just the liquid handling steps. Automated decision making enables not only media exchange and passaging, but also enables cell culture control in the absence of scientists in the lab. Here, we describe the methods to enable consistent and reliable cell culture passaging and maintenance with minimal user interaction.
Continue your journey by learning how we've fully automated cell culture passaging and expansion using decision making-based image analysis
Download application note
iPSC Culture The workflows for assays involving stem cells are similar to other cell-based assays, but there are critical differences. Differentiation is often involved in stem cell assays because of the need to start with undifferentiated cells, or because the assay is studying the differentiation process.
Featured asset Automation of iPSC culture, passaging, and expansion with the CellXpress.ai Automated Cell Culture System In this application note, we present an automated iPSC culture and passaging protocol that was developed to alleviate the limitations that come with labor-intensive workflows. Developed on the new CellXpress.ai™ Automated Cell Culture System, this method provides hands-free management of demanding feeding and passaging schedules by monitoring the development of cell cultures with periodic imaging and analysis. Machine learning was used to initiate passaging and to detect cell differentiation.
Automated iPSC cell culture workflow
The CellXpress.ai cell culture system enables the maintenance and expansion of iPSC cell lines with media exchange and automated passaging triggered by imaging/ morphology-based criteria, thus ensuring the consistent treatment of your iPSC cell culture.
Tumor Spheroid Culture One of the most significant objectives in cancer research is to understand tumor cell formation. Compared to 2D cell cultures, spheroids mimic solid tumors much more accurately. They help display the physiological changes that differentiate tumor cells from healthy cells. Multicellular tumor spheroid models give deeper insights into the tumor microenvironment, allowing researchers to visualize cell-to-cell interactions, how tumor cells absorb nutrients, and how they proliferate.
Featured asset Cell culture automation of the 3D cancer spheroid assay with the CellXpress.ai cell culture system To expedite and standardize the spheroid assay, we developed 3D cell culture automation methods using the CellXpress.ai™ Automated Cell Culture System to provide automated plating, passaging, media exchange, and organoid monitoring in response to compound treatment, and endpoint assays. In this app note, we describe the automation of a colorectal cell culture workflow where we automated the culture and imaging of colorectal cancer 3D spheroids formed from HCT116 cell lines in U-shape low attachment plates.
Automated spheroid cell culture workflow
The CellXpress.ai cell culture system offers a non-Matrigel 3D protocol for cancer spheroids. Here we show an automated workflow that includes plating, media exchange, staining, and imaging.
Intestinal Organoid Culture Attrition in the therapeutic pipeline can often be attributed to the lack of translational efficacy from the pre-clinical phase to the clinic. Organoids show great promise as a game-changer in disease modeling and drug screening since they better resemble tissue structure and functionality and show more predictive responses to drugs. However, challenges associated with the practical adoption of organoids, such as assay complexity, reproducibility, and the ability to scale up have limited their widespread adoption as a primary screening method in drug discovery.
Featured asset Automation of 3D intestinal organoids culture with CellXpress.ai Automated Cell Culture System The CellXpress.ai system offers AI-driven, end-to-end cell culture management – from liquid handling to endpoint assay execution to complex image analysis. In this app note, we present results from an automated intestinal workflow that can be used as the basis for other commonly used 3D organoid protocols in matrix domes.
Automated organoid cell culture workflow
The cell composition and arrangement of the epithelium make intestinal organoids useful for studying intestinal cell biology, regeneration, and differentiation, as well as disease phenotypes, including effects of specific mutations, microbiome, or inflammation process.
