Sub-Visible Particle Classification and Label Consistency Analysis for Flow-Imaging Microscopy Via Machine Learning Methods

Sub-visible particles can be a quality concern in pharmaceutical products, especially parenteral preparations. To quantify and characterize these particles, liquid samples may be passed through a flow-imaging microscopy instrument that also generates images of each detected particle. Machine learning techniques have increasingly been applied to this kind of data to detect changes in experimental conditions or classify specific types of particles, primarily focusing on silicone oil. That technique generally requires manual labeling of particle images by subject matter experts, a time-consuming and complex task. In this study, we created artificial datasets of silicone oil, protein particles, and glass particles that mimicked complex datasets of particles found in biopharmaceutical products. We used unsupervised learning techniques to effectively describe particle composition by sample. We then trained independent one-class classifiers to detect specific particle populations: silicone oil and glass particles. We also studied the consistency of the particle labels used to evaluate these models. Our results show that one-class classifiers are a reasonable choice for handling heterogeneous flow-imaging microscopy data and that unsupervised learning can aid in the labeling process. However, we found agreement among experts to be rather low, especially for smaller particles (< 8 µm for our Micro-Flow Imaging data). Given the fact that particle label confidence is not usually reported in the literature, we recommend more careful assessment of this topic in the future.

Evaluation of a Self-Supervised Machine Learning Method for Screening of Particulate Samples: A Case Study in Liquid Formulations

Imaging is commonly used as a characterization method in the pharmaceuticals industry, including for quantifying subvisible particles in solid and liquid formulations. Extracting information beyond particle size, such as classifying morphological subpopulations, requires some type of image analysis method. Suggested methods to classify particles have been based on pre-determined morphological features or use supervised training of convolutional neural networks to learn image representations in relation to ground truth labels. Complications arising from highly complex morphologies, unforeseen classes, and time-consuming preparation of ground truth labels, are some of the challenges faced by these methods. In this work, we evaluate the application of a self-supervised contrastive learning method in studying particle images from therapeutic solutions. Unlike with supervised training, this approach does not require ground truth labels and representations are learned by comparing particle images and their augmentations. This method provides a fast and easily implementable tool of coarse screening for morphological attribute assessment. Furthermore, our analysis shows that in cases with relatively balanced datasets, a small subset of an image dataset is sufficient to train a convolutional neural network encoder capable of extracting useful image representations. It is also demonstrated that particle classes typically observed in protein solutions administered by pre-filled syringes emerge as separated clusters in the encoder's embedding space, facilitating performing tasks such as training weakly-supervised classifiers or identifying the presence of new subpopulations.

Targeting the Wnt Signaling Pathway in Liver Fibrosis for Drug Options: An Update

Liver fibrosis is a life-threatening disease, with challenging morbidity and mortality for healthcare systems worldwide. It imparts an enormous economic burden to societies, making continuous research and informational updates about its pathogenesis and treatment crucial. This review's focus is on the current knowledge about the Wnt signaling pathway, serving as an important pathway in liver fibrosis development and activation of hepatic stellate cells (HSCs). Two types of Wnt pathways are distinguished, namely the ß-catenin-dependent canonical and non-canonical Ca²⁺ or planar cell polarity (PCP)-dependent pathway. The dynamic balance of physiologically healthy liver and hepatocytes is disturbed by repeated liver injuries. Activation of the ß-catenin Wnt pathway prevents the regeneration of hepatocytes by the replacement of extracellular matrix (ECM), leading to the appearance of scar tissue and the formation of regenerated nodular hepatocytes, lacking the original function of healthy hepatocytes. Therefore, liver function is reduced due to the severely advanced disease. Selective inhibition of ß-catenin inhibits inflammatory processes (since chemokines and pro-inflammatory cytokines are produced during Wnt activation), reduces growth of activated HSCs and reduces collagen synthesis and angiogenesis, thereby reducing the progression of liver fibrosis in vivo. While the canonical Wnt pathway is usually inactive in a physiologically healthy liver, it shows activity during cell regeneration or renewal and in certain pathophysiological conditions, such as liver diseases and cancer. Targeted blocking of some of the basic components of the Wnt pathway is a therapeutic approach. These include the frizzled transmembrane receptor (Fz) receptors using the secreted frizzled-related protein family (sFRP), Fz-coreceptors low-density LRP 5/6 through dickkopf-related protein 1 (DKK1) or niclosamide, glycogen kinase-3 beta (GSK-3β) using SB-216763, cyclic-AMP response element-binding protein (CBP) using PRI-724 and ICG-001, the lymphoid enhancer binding factor (LEF)/T cell-specific transcription factor (TCF) system as well as Wnt inhibitory factor 1 (WIF1) and miR-17-5p using pinostilbene hydrate (PSH). Significant progress has been made in inhibiting Wnt and thus stopping the progression of liver fibrosis by diminishing key components for its action. Comprehending the role of the Wnt signaling pathway in liver fibrosis may lead to discovery of novel targets in liver fibrosis therapeutic strategies' development.