Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Color Flow Imaging Microscopy Improves Identification of Stress Sources of Protein Aggregates in Biopharmaceuticals

Michaela Cohrs, Shiwoo Koak, Yejin Lee, Yu Jin Sung, Wesley De Neve, Hristo L. Svilenov, Utku Ozbulak

TL;DR

It is demonstrated that deep learning with color FIM images consistently outperforms monochrome images, thus highlighting the potential of color FIM in stress source classification compared to its monochrome counterparts.

Abstract

Protein-based therapeutics play a pivotal role in modern medicine targeting various diseases. Despite their therapeutic importance, these products can aggregate and form subvisible particles (SvPs), which can compromise their efficacy and trigger immunological responses, emphasizing the critical need for robust monitoring techniques. Flow Imaging Microscopy (FIM) has been a significant advancement in detecting SvPs, evolving from monochrome to more recently incorporating color imaging. Complementing SvP images obtained via FIM, deep learning techniques have recently been employed successfully for stress source identification of monochrome SvPs. In this study, we explore the potential of color FIM to enhance the characterization of stress sources in SvPs. To achieve this, we curate a new dataset comprising 16,000 SvPs from eight commercial monoclonal antibodies subjected to heat and mechanical stress. Using both supervised and self-supervised convolutional neural networks, as well as vision transformers in large-scale experiments, we demonstrate that deep learning with color FIM images consistently outperforms monochrome images, thus highlighting the potential of color FIM in stress source classification compared to its monochrome counterparts.

Color Flow Imaging Microscopy Improves Identification of Stress Sources of Protein Aggregates in Biopharmaceuticals

TL;DR

It is demonstrated that deep learning with color FIM images consistently outperforms monochrome images, thus highlighting the potential of color FIM in stress source classification compared to its monochrome counterparts.

Abstract

Protein-based therapeutics play a pivotal role in modern medicine targeting various diseases. Despite their therapeutic importance, these products can aggregate and form subvisible particles (SvPs), which can compromise their efficacy and trigger immunological responses, emphasizing the critical need for robust monitoring techniques. Flow Imaging Microscopy (FIM) has been a significant advancement in detecting SvPs, evolving from monochrome to more recently incorporating color imaging. Complementing SvP images obtained via FIM, deep learning techniques have recently been employed successfully for stress source identification of monochrome SvPs. In this study, we explore the potential of color FIM to enhance the characterization of stress sources in SvPs. To achieve this, we curate a new dataset comprising 16,000 SvPs from eight commercial monoclonal antibodies subjected to heat and mechanical stress. Using both supervised and self-supervised convolutional neural networks, as well as vision transformers in large-scale experiments, we demonstrate that deep learning with color FIM images consistently outperforms monochrome images, thus highlighting the potential of color FIM in stress source classification compared to its monochrome counterparts.
Paper Structure (10 sections, 1 equation, 2 figures, 3 tables)

This paper contains 10 sections, 1 equation, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Materials
  4. Dataset
  5. Models
  6. Color Conversion
  7. Training
  8. Experimental Results
  9. Conclusions and Future Perspectives
  10. Acknowledgements

Figures (2)

  • Figure 1: Distribution of the height and width of the SvP images used in this study for (left) heat stress and (right) mechanical stress. The red line in both figures highlights 1:1 aspect ratio.
  • Figure 2: An example set of subvisible protein aggregate images is shown in (a) RGB format, followed by (b) grayscale, and (c, d, e) individual red, green, and blue channels, respectively. Protein aggregates on the left side are formed due to heat stress, whereas those on the right are formed due to mechanical stress.