ParticleSentryᴬᴵ

You need a large collection of images, the more images the better. If you have a 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.

  Hypothesis/Goodness-of-fit test result, distribution curve, P-value for the test statistic, fingerprint (probability density function) and other visualization tools to diagnose when process upset occurs.   

    Definitely. As new information is gained, the new image condition can be added and a new fingerprint (probability density function) can be generated containing the now known class. This allows for easy root-cause analysis and issue detection in the future.  

 It 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. Conceptually, our technology will work with any modality that generates an image (e.g. BMI, MFI, fluorescence, raman, 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, the compendial method for lot release) have been proven to be inaccurate in protein-based drugs. LO cannot accurately resolve the translucent aggregate particles found in protein drugs and thus 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 particle size and count data. Using these images, ParticleSentryᴬᴵ leverages the the valuable textural and morphological detail of the subvisible particles and aggregates. These data allow you to move beyond particle size and count alone and characterize the profile of your drug product - as you saw in the fingerprint (probability density function) images. This quantification allows easy detection of process results that are outside of the intended/accepted parameters. A robust fingerprint includes possible 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 our key use cases is monitoring at-line or on-line at various points in the product lifecycle and places within 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 that development work as well by processing images of the various combinations of ingredients used in formulation testing and developing fingerprints for each. 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.