ParticleSentryᴬᴵ is a software product that brings artificial intelligence and flow imaging microscopy technologies together in biopharmaceutical production. We identify protein aggregation, batch variation and anomalies during the biologic development and manufacturing processes, enabling better control of drug product quality. Our technology develops ‘fingerprints’ that quantitatively characterize protein drug production and protein aggregates under different stressors. These fingerprints are used to identify and resolve issues at every stage of product development and manufacture.
Combining Machine Learning and BMI: A Case Study 06/2022 (pdf)Download
Testing Precision Limits of Neural Net-Based Quality Control Metrics in Digital Microscopy 02/2022 (pdf)Download
Machine Learning and Accelerated Stress Approaches to Differentiate Causes of Aggregation 03/2021 (pdf)Download
Machine Learning & Statistical Analyses for Extr. & Char. Fingerprints of Antibody Aggregation 04/20 (pdf)Download
Shifting Paradigms Revisited: Biotechnology and the Pharmaceutical Sciences 08/2019 (pdf)Download
Deep CNN Analysis of FIM Data to Classify Subvisible Particles in Protein Formulations 12/2017 (pdf)Download
Compendial methods for particle analysis encounter difficulties when applied to proteinaceous drugs. This presentation covers how to combine AI, computational statistics, and high-throughput microscopy to characterize particles and protein aggregates in biologics. Analyzing morphological and textural particle features, the method delivers quantitative, actionable information for formulation development, container qualification, and fill-finish quality control. Four case studies are reviewed. .
This video demonstrates the "Create Fingerprint" functionality provided in ParticleSentryᴬᴵ software.
This video demonstrates the process steps to compare new sample images to an existing Fingerprint in ParticleSentryᴬᴵ software. The video also briefly demonstrates the process to view the particle images contained in your test.
Normal Process Fingerprint vs. Process Shift Fingerprint
You need a large collection of images, the more images the better. If you have known reference condition images and images from related accelerated stability studies, they can be incorporated into the fingerprint as well. More images enhance the overall analysis.
Fingerprint (probability density function), hypothesis/goodness-of-fit test result, distribution curve, P-value for the test statistic, and other visualization tools to diagnose when process upset occurs.
Definitely. As new data is captured and understood, new image conditions can be added, and a new fingerprint (probability density function) can be generated containing the new class(es). This allows for easy root-cause analysis and issue detection in the future.
ParticleSentryᴬᴵ is biologic specific. In our experience, mAbs differ and are significantly influenced by factors like excipients, surfactants, etc. While most of our work has focused on mAbs, we are not constrained to look only at mAbs.
We do have experience with other modalities. Our technology will work with any modality that generates an image (e.g., BMI, MFI, fluorescence, Raman, imaging flow cytometry, etc.).
Yes. While the bulk of our work has been with flow imaging microscopy, we do have experience with other modalities. We have worked with MFI images in the past. MFI’s settings are locked down, making extraction of images for convolutional neural network analysis more difficult. That said, we'd love to work with you to see what can be done with your MFI images.
Particle size and count data from light obscuration (LO) have been proven to be inaccurate in protein-based drugs. LO cannot accurately resolve the translucent aggregate particles found in protein drugs and undercounts or under-sizes these particles. Protein drugs are inherently aggregation-prone and manufacturing stressors increase the likelihood of aggregate formation throughout the manufacturing process. Many drug manufacturers already use flow imaging microscopy as an orthogonal measurement to LO particle size and count data. Using these images, ParticleSentryᴬᴵ leverages the textural and morphological detail of the subvisible particles and aggregates. These data allow you to move beyond particle size and count alone and characterize your drug product - as you saw in the fingerprint (probability density function) images. This quantification allows easy detection of outlier conditions. A robust fingerprint includes many process issues (pH shock, pump failure, etc.) and allows you to identify the root cause quickly and easily. Finally, part of the regulatory burden placed on biologic manufacturers involves demonstrating an aggregate control strategy throughout the development and manufacturing processes, and ParticleSentryᴬᴵ, in addition to providing actionable data, delivers on the requirement to demonstrate an aggregate control strategy.
One of the key use cases for ParticleSentryᴬᴵ is monitoring at-line or on-line at various points in the manufacturing process. If it is possible to obtain images, we can create a fingerprint. Excipients, surfactants, and other additives can change the morphology and composition of subvisible particles and are typically studied during candidate selection and formulation. ParticleSentryᴬᴵ can support formulation development work by processing images of the various combinations of ingredients used in formulation testing and development. These fingerprints can be compared to images from long-term stability and other testing protocols to quantitatively determine the stability of the formulation over time.