Coupling of Trastuzumab chromatographic profiling with machine learning tools: A complementary approach for biosimilarity and stability assessment.

Biosimilar products present a growing opportunity to improve the global healthcare systems. The amount of accepted variability during the comparative assessments of biosimilar products introduces a significant challenge for both the biosimilar developers and the regulatory authorities. The aim of this study was to explore unsupervised machine learning tools as a mathematical aid for the interpretation and visualization of such comparability under control and stress conditions using data extracted from high throughput analytical techniques. For this purpose, a head-to-head analysis of the physicochemical characteristics of three Trastuzumab (TTZ) approved biosimilars and the originator product (Herceptin®) was performed. The studied quality attributes included the primary structure and identity by peptide mapping (PM) with reversed-phase chromatography-UV detection, size and charge profiles by stability-indicating size exclusion and cation exchange chromatography. Stress conditions involved pH and thermal stress. Principal component analysis (PCA) and two of the widely used cluster analysis tools, namely, K-means and Density-based Spatial Clustering of Applications with Noise (DBSCAN), were explored for clustering and feature representation of varied analytical datasets. It has been shown that the clustering patterns delineated by the used algorithms changed based on the included chromatographic profiles. The applied data analysis tools were found effective in revealing patterns of similarity and variability between i) intact and stressed as well as ii) originator and biosimilar samples.

Coupling of on-column trypsin digestion-peptide mapping and principal component analysis for stability and biosimilarity assessment of recombinant human growth hormone.

Peptide mapping (PM) is a vital technique in biopharmaceutical industry. The fingerprint obtained helps to qualitatively confirm host stability as well as verify primary structure, purity and integrity of the target protein. Yet, in-solution digestion followed by tandem mass spectrometry is not suitable as a routine quality control test. It is time consuming and requires sophisticated, expensive instruments and highly skilled operators. In an attempt to enhance the fuctionality of PM and extract multi-dimentional data about various critical quality attributes and comparability of biosimilars, coupling of PM generated using immobilized trypsin followed by HPLC-UV to principal component analysis (PCA) is proposed. Recombinant human growth hormone (rhGH); was selected as a model biopharmaceutical since it is available in the market from different manufacturers and its PM is a well-established pharmacopoeial test. Samples of different rhGH biosimilars as well as degraded samples: deamidated and oxidized were subjected to trypsin digestion followed by RP-HPLC-UV analysis. PCA of the entire chromatograms of test and reference samples was then conducted. Comparison of the scores of samples and investigation of the loadings plots clearly indicated the applicability of PM-PCA for: i) identity testing, ii) biosimilarity assessment and iii) stability evaluation. Hotelling's T2 and Q statistics were employed at 95% confidence level to measure the variation and to test the conformance of each sample to the PCA model, respectively. Coupling of PM to PCA provided a novel tool to identify peptide fragments responsible for variation between the test and reference samples as well as evaluation of the extent and relative significance of this variability. Transformation of conventional PM that is largely based on subjective visual comparison into an objective statiscally-guided analysis framework should provide a simple and economic tool to help both manufacturers and regulatory authorities in quality and biosimilarity assessment of biopharmaceuticals.