Statistical modeling of the drug load distribution on trastuzumab emtansine (Kadcyla), a lysine-linked antibody drug conjugate

Abstract

Trastuzumab emtansine (Kadcyla) is a recently approved antibody-drug conjugate produced by attachment of the anti-tubulin drug, DM1, to lysine amines via the SMCC linker. The resulting product exhibits a drug load distribution from 0 to 8 drugs per antibody that can be quantified using mass spectrometry. Different statistical models were tested against the experimental data derived from samples produced during process characterization studies to determine best fit. The Poisson distribution gives the best correlation for samples manufactured using the target process conditions (yielding the target average drug to antibody ratio (DAR) of 3.5) as well as those produced under conditions that exceed the allowed manufacturing ranges and yield products with average DAR values that are significantly different from the target (i.e., ≤3.0 or ≥4.0). The Poisson distribution establishes a link between average DAR values and drug load distributions, implying that measurement and control of the former (i.e., via a simple UV spectrophotometric method) could be used to indirectly control the latter in trastuzumab emtansine.