Application Number: AU 2026201883
Configurable Handheld Biological Analyzers for Identification of Biological Products Based on Raman Spectroscopy Portable Raman Identity Testing for Drug Substances
The patent describes a configurable handheld biological analyzer with a processor, scanner and memory into which a biological classification model configuration is loaded. The model configuration includes a biological classification model that receives a Raman-based spectra dataset for a sample scanned by the device. A spectral preprocessing algorithm reduces variance in the Raman spectra before
View the Configurable Handheld Biological Analyzers for Identification of Biological Products Based on Raman Spectroscopy PDF
Download the PDF version of this Application Open to Public Inspection
This patent describes a handheld Raman spectroscopy analyzer for identifying biological products, together with the classification model architecture and spectral preprocessing methods that make it work. The model configuration is transferable across multiple handheld units, supporting consistent identity testing across a biopharmaceutical supply chain.
The Problem
Identity testing is a routine but high-stakes step in biological drug manufacturing and distribution. Operators need to confirm that a vial, bag or container holds the product its label claims before that product is administered to a patient or moved further down the chain. Modern Raman spectroscopy is well suited to the task because it gives a molecular fingerprint from the surface or through the container, without destroying the sample. Translating that into a deployable handheld instrument is harder than it sounds: the spectra carry meaningful biological signal but also a great deal of noise and instrument-to-instrument variance, and any classification model has to be both accurate and portable across the fleet of analyzers in use.
What This Invention Does
The patent describes a configurable handheld biological analyzer with a processor, scanner and memory into which a biological classification model configuration is loaded. The model configuration includes a biological classification model that receives a Raman-based spectra dataset for a sample scanned by the device. A spectral preprocessing algorithm reduces variance in the Raman spectra before classification. The model then identifies a biological product type based on the spectra and on a classification component selected to minimise either Q-residual error or summary-of-fit error.
The disclosure covers both the analyzer and the methods, and explicitly contemplates transferring the same model configuration to other configurable handheld analyzers so that an identification calibrated on one device behaves consistently on the rest of the fleet.
Key Features
- Handheld form factor. Raman identity testing brought to a portable, deployable device rather than a benchtop instrument.
- Configurable model loading. The biological classification model is loaded as a configuration into the device, so the same hardware can be repurposed across products and use cases.
- Spectral preprocessing for variance reduction. A preprocessing stage reduces noise and instrument-to-instrument variance, giving the classifier cleaner input.
- Error-aware classifier selection. The classification component is chosen to minimise Q-residual error or summary-of-fit value, both standard chemometric quality metrics.
- Model portability across the fleet. A model trained or tuned on one analyzer can be transferred to and loaded on other analyzers, supporting consistent identification across an organisation.
Who Is Behind It
The applicant is Amgen Inc., one of the largest biotechnology companies in the world and a long-standing developer of process analytical technology for biologics manufacturing. The named inventors are Robert Soto and David Meriage. The Australian patent attorney of record is listed on the title page.
Why It Matters
Identity testing of biologics is regulated under strict frameworks from agencies such as the TGA in Australia and equivalents worldwide. A handheld, model-portable Raman platform that integrates with a biologics manufacturer’s quality systems can reduce sampling delays, lower laboratory load and tighten the loop between production and dispatch. With biologics manufacturing expanding in Australia under government industry-development programs, protection on this analyzer architecture matters both for Amgen’s own operations and for any partner manufacturing or distributing their products in the region.
Related Concepts
- Raman spectroscopy – the spectroscopic technique behind the identification.
- Chemometrics – the data-analysis discipline behind the model and metrics used.
- Process analytical technology – the regulatory and operational context for in-line and at-line analyzers.
- Biopharmaceutical – the broader product category being tested.
- Quality control in pharmaceutical manufacturing – the function the analyzer plugs into.
AU 2026201883 was published in the Australian Official Journal of Patents on 2 April 2026 and is open for public inspection. Patent applications represent inventions that are sought to be protected and do not necessarily reflect commercially available products.
Related Patents Open to Public Inspections
See related Patents open to public inspection.
Smarter Biosensors
Medical Device Innovation
Smart Medical Devices Talk to Each Other
Neural Networks Enable Intelligent Entity Matching in Database Systems
Disclaimer
The information presented in this article is provided for general informational and illustrative purposes only.
Content on this page may be derived from publicly available intellectual property records, including patent documentation and related materials. While reasonable care is taken in compiling and summarising this information, ATMOSS does not guarantee the accuracy, completeness, currency, or reliability of any content presented.
This article is not a substitute for reviewing the original source documents. Patent applications, specifications, claims, and related records may contain detailed technical, legal, and contextual information that is not fully represented in this summary.
ATMOSS does not provide legal, technical, or commercial advice. Users should not rely on this content for decision-making purposes.
For authoritative and up-to-date information, users should refer directly to the official records available via IP Australia and other relevant intellectual property databases. Links to these official sources are provided where applicable.
ATMOSS accepts no liability for any loss, damage, or consequences arising from the use of, or reliance on, the information contained in this article.