Organoids

Three-dimensional cell model systems such as tumour organoids allow for in vitro modelling of self-organized tissue with functional and histologic similarity to in vivo tissue. However, there is a need for standard protocols and techniques to confirm the presence of cancer within organoids derived from tumour tissue. The aim of this study was to assess the utility of a Nanostring gene expression-based machine learning classifier to determine the presence of cancer or normal organoids in cultures developed from both benign and cancerous stomach biopsies. A prospective cohort of normal and cancer stomach biopsies were collected from 2019 to 2022. Tissue specimens were processed for formalin-fixed paraffin-embedding (FFPE) and a subset of specimens were established in organoid cultures. Specimens were labelled as normal or cancer according to analysis of the FFPE tissue by two pathologists. The gene expression in FFPE and organoid tissue was measured using a 107 gene Nanostring codeset and normalized using the Removal of Unwanted Variation III algorithm. Our machine learning model was developed using five-fold nested cross-validation to classify normal or cancer gastric tissue from publicly available Asian Cancer Research Group (ACRG) gene expression data. The models were externally validated using the Cancer Genome Atlas (TCGA), as well as our own FFPE and organoid gene expression data. A total of 60 samples were collected, including 38 cancer FFPE specimens, 5 normal FFPE specimens, 12 cancer organoids, and 5 normal organoids. The optimal model design used a Least Absolute Shrinkage and Selection Operator model for feature selection and an ElasticNet model for classification, yielding area under the curve (AUC) values of 0.99 [95% CI: 0.99–1], 0.90 [95% CI: 0.87–0.93], and 0.79 [95% CI: 0.74–0.84] for ACRG (internal test), FFPE, and organoid (external test) data, respectively. The performance of our final model on external data achieved AUC values of 0.99 [95% CI: 0.98–1], 0.94 [95% CI: 0.86–1], and 0.85 [95% CI: 0.63–1] for TCGA, FFPE, and organoid specimens, respectively. Using a public database to create a machine learning model in combination with a Nanostring gene expression assay allows us to allocate organoids and their paired whole tissue samples. This platform yielded reasonable accuracy for FFPE and organoid specimens, with the former being more accurate. This study re-affirms that although organoids are a high-fidelity model, there are still limitations in validating the recapitulation of cancer in vitro.

Ensuring access to safe drinking water is a fundamental public health priority, yet the growing diversity of contaminants demands more human-relevant toxicity assessment frameworks. Conventional models based on immortalized cell lines or sentinel species, while informative, lack the tissue complexity and inter-individual variability required to capture realistic human responses. Organoids, three-dimensional epithelial structures derived from adult or pluripotent stem cells, retain the genomic, histological, and functional characteristics of their original tissue, enabling assessment of contaminant-induced toxicity, short-term peak exposures, and inter-donor variability within a single system. This study examined whether current international drinking water guidelines remain protective or if recent organoid-based findings reveal toxicity at differing concentrations. Comparative synthesis indicates that per- and polyfluoroalkyl substances (PFAS) often display organoid toxicity at concentrations above current thresholds, suggesting conservative guidelines, whereas most metals are properly regulated. However, some metals exhibit toxicity at concentrations that include levels below guideline values, highlighting the need for further investigation. Emerging contaminants, including pesticides, nanoparticles, microplastics, and endocrine disruptors, induce adverse effects at environmentally relevant concentrations, despite limited or absent regulatory limits. Integrating organoid-based toxicology with high-frequency monitoring and dynamic exposure modeling could refine water quality guidelines and support adaptive regulatory frameworks that better reflect real-world exposure patterns and human diversity.

Cancer remains a leading cause of mortality worldwide. Patient-derived organoids (PDOs) are three-dimensional (3D) cultures that recapitulate tumor histology, genetics, and cellular heterogeneity, providing physiologically relevant preclinical models. Integrating PDOs with artificial intelligence (AI) and machine learning (ML) enables scalable analysis of high-dimensional datasets, including imaging, transcriptomics, proteomics, and pharmacological readouts. These approaches support prediction of drug sensitivity, biomarker discovery, and patient stratification. Recent advances—such as deep learning (DL), transfer learning, federated learning, and self-supervised learning—enhance phenotypic profiling, cross-institutional model training, and translational prediction. In this review, we summarize the current state of AI-driven PDO research, highlighting methodological approaches, preclinical and clinical applications, challenges, and emerging trends. We also propose strategies for standardization, validation, and multi-modal integration to accelerate patient-specific therapeutic strategies.