The present bottleneck in biosimilar bioprocess development has become evaluation of analytical results due to recent advances in analytics, such as automated sample preparation and development of high-throughput methods. Currently automated chromatogram integration and annotation is only efficient for simple chromatograms. In an ever more competitive field of biosimilars this represents a serious drawback since chromatographic analytical methods that provide some of the most valuable physicochemical quality attributes of the product also require careful chromatogram integration and annotation. This work focuses on the glycan mapping analytical method as utilized in the development of monoclonal antibody biosimilars, evaluating more than 2000 chromatograms from various biosimilar projects. It proposes a modified workflow by implementing automatic machine learning algorithms to determine the proportion of specific relevant glycan species in a sample directly from the chromatogram. Data preparation and analysis is performed using a pipeline approach in a way that modules can be independently improved and exchanged. Required module functions are spline interpolation, asymmetric least squares, parametric time warping, and partial least squares regression. The workflow enables transparent, faster, and less subjective evaluation of analytic raw data while maintaining an accuracy comparable to manual integration. Improved method robustness and accuracy provide additional insight on the glycan dynamics, while also helping us obtain a clearer understanding of how the differences in glycan structures effect protein functionality and help guide bioprocess development more efficiently. The presented methodology reduces the costs and time of biosimilar development and should be applicable for any chromatogram based analytical method.
|
