Quantifying drug tissue biodistribution by integrating high content screening with deep-learning analysis.

Quantitatively determining in vivo achievable drug concentrations in targeted organs of animal models and subsequent target engagement confirmation is a challenge to drug discovery and translation due to lack of bioassay technologies that can discriminate drug binding with different mechanisms. We have developed a multiplexed and high-throughput method to quantify drug distribution in tissues by integrating high content screening (HCS) with U-Net based deep learning (DL) image analysis models. This technology combination allowed direct visualization and quantification of biologics drug binding in targeted tissues with cellular resolution, thus enabling biologists to objectively determine drug binding kinetics.

Leveraging the IncuCyte Technology for Higher-Throughput and Automated Chemotaxis Assays for Target Validation and Compound Characterization.

Chemotaxis is the directional movement of cells in response to a chemical stimulus and is vital for many physiological processes, including immune responses, tumor metastasis, wound healing, and blood vessel formation. Therefore, modulation of chemotaxis is likely to be of therapeutic benefit. Hence, a high-throughput means to conduct chemotaxis assays is advantageous for lead evaluation and optimization in drug discovery. In this study, we have validated a novel approach for a higher-throughput, label-free, image-based IncuCyte chemotaxis assay encompassing various cell types, including T cells, B cells, mouse Th17, immature and mature dendritic cells, monocyte THP-1, CCRF-CEM, monocytes, neutrophils, macrophages, and MDA-MB-231. These assays enable us to visualize chemotactic cell migration in real time and perform kinetic cell motility studies on an automated platform, thereby allowing us to incorporate the quantitative studies of cell migration behavior into a routine drug discovery screening cascade.

Establishing a high-throughput and automated cancer cell proliferation panel for oncology lead optimization.

Tumor cell proliferation assays are widely used for oncology drug discovery, including target validation, lead compound identification, and optimization, as well as determination of compound off-target activities. Taking advantage of robotic systems to maintain cell culture and perform cell proliferation assays would greatly increase productivity and efficiency. Here we describe the establishment of automated systems for high-throughput cell proliferation assays in a panel of 13 human tumor cell lines. These cell lines were selected from various types of human tumors containing a broad range of well-characterized mutations in multiple cellular signaling pathways. Standard procedures for cell culture and assay performance were developed and optimized in each cell line. Moreover, in-house developed software (i.e., Toolset, Curvemaster, and Biobars) was applied to analyze the data and generate data reports. Using tool compounds, we have shown that results obtained through this panel exhibit high reproducibility over a long period. Furthermore, we have demonstrated that this panel can be used to identify sensitive and insensitive cell lines for specific cancer targets, to drive cellular structure-activity relationships, and to profile compound off-target activities. All those efforts are important for cancer drug discovery lead optimization.