Optical density (OD) is a critical process parameter during fermentation, this being directly related to cell density, which provides valuable information regarding the state of the process. However, to measure OD, sampling of the fermentation broth is required. This is particularly challenging for high-throughput-microbioreactor (HT-MBR) systems, which require robotic liquid-handling (LiHa) systems for process control tasks, such as pH regulation or carbon feed additions. Bioreactor volume is limited and automated at-line sampling occupies the resources of LiHa systems; this affects their ability to carry out the aforementioned pipetting operations. Minimizing the number of physical OD measurements is therefore of significant interest. However, fewer measurements also result in less process information. This resource conflict has previously represented a challenge. We present an artificial neural-network-based soft sensor developed for the real-time estimation of the OD in an MBR system. This sensor was able to estimate the OD to a high degree of accuracy (>95%), even without informative process variables stemming from, e.g., off-gas analysis only available at larger scales. Furthermore, we investigated and demonstrated scaling of the soft sensor’s generalization capabilities with the data from different antibody fragments expressing Escherichia coli strains. This study contributes to accelerated biopharmaceutical process development.

Market segmentation partitions multivariate data using some clustering algorithm, resulting in some number of homogeneousclusters of consumers for marketing purposes. Often this type of data has no clear cluster structure, that is, no separations or gapsbetween clusters of points exist, which is why this is considered partitioning rather than clustering. Understanding the differencesbetween the clusters is typically done by examining single features. However, this can be inconclusive as multiple clusters might share similar characteristics on individual features and the market segmentation partition actually defines the clusters based on different linear constraints on the features. To understand what uniquely characterizes a cluster of customers, examining linear combinations of features may be helpful. This article introduces the R package lionfish that provides interactive and dynamic tools to facilitate the exploration and refining of market segmentations. The package integrates tour algorithms that use linear combinations of features to view high-dimensional data, from the tourr package, with Python-powered interactivity, allowing manual control, interactive selection, and multiple linked windows, to support revising the cluster memberships based on visual feedback. The focus is on the widely used k-means clustering algorithm, but the tools also support other algorithms. The utility of the software is demonstrated through three example analyses from the domain of market segmentation. The flexible, user-driven approach provided by package lionfish offers deeper insights into complex market behaviors, enabling more effective segmentation and enhancing strategic decision-making.