The in vitro micronucleus (MN) assay is a well-established assay for quantification of DNA damage, and is required by regulatory bodies worldwide to screen chemicals for genetic toxicity. The MN assay is performed in two variations: scoring MN in cytokinesis-blocked binucleated cells or directly in unblocked mononucleated cells. Several methods have been developed to score the MN assay, including manual and automated microscopy, and conventional flow cytometry, each with advantages and limitations. Previously, we applied imaging flow cytometry (IFC) using the ImageStream® to develop a rapid and automated MN assay based on high throughput image capture and feature-based image analysis in the IDEAS® software. However, the analysis strategy required rigorous optimization across chemicals and cell lines. To overcome the complexity and rigidity of feature-based image analysis, in this study we used the Amnis® AI software to develop a deep-learning method based on convolutional neural networks to score IFC data in both the cytokinesis-blocked and unblocked versions of the MN assay. We show that the use of the Amnis AI software to score imagery acquired using the ImageStream® compares well to manual microscopy and outperforms IDEAS® feature-based analysis, facilitating full automation of the MN assay.

Monitoring protein particles is increasingly emphasized in the development of biopharmaceuticals due to potential immunogenicity. Accurate quantitation of protein particles is complicated by silicone oil droplets, a common pharmaceutical component in pre-filled syringes. Though silicone oil is typically regarded as harmless, numerous reports have indicated protein adsorption may render these particles with immunostimulatory properties. Imaging flow cytometry (IFC) is an emerging pharmaceutical method capable of capturing high-resolution brightfield and fluorescence imagery from samples in suspension. In this study, we created a data analysis strategy using artificial intelligence (AI) software to classify brightfield images collected with IFC as protein or silicone oil. The AI software performs image classification using deep learning with a convolutional neural network architecture, for identification of subtle morphological phenotypes. The AI model yielded robust classification of particles >2 mm across various sources of protein and silicone oil particles and over the instrument life cycle. Next, the AI model was combined with IFC fluorescence images to differentiate potentially immunogenic protein-adsorbed silicone and innocuous native silicone. The methods reported herein provide added analytical capability for characterization of particulate matter in therapeutic formulations, and may be applied for optimization of protein formulations and evaluation of product consistency.

No abstract

No abstract