Search for: All records

Abstract Therapeutic antibody development requires selection and engineering of molecules with high affinity and other drug-like biophysical properties. Co-optimization of multiple antibody properties remains a difficult and time-consuming process that impedes drug development. Here we evaluate the use of machine learning to simplify antibody co-optimization for a clinical-stage antibody (emibetuzumab) that displays high levels of both on-target (antigen) and off-target (non-specific) binding. We mutate sites in the antibody complementarity-determining regions, sort the antibody libraries for high and low levels of affinity and non-specific binding, and deep sequence the enriched libraries. Interestingly, machine learning models trained on datasets with binary labels enable predictions of continuous metrics that are strongly correlated with antibody affinity and non-specific binding. These models illustrate strong tradeoffs between these two properties, as increases in affinity along the co-optimal (Pareto) frontier require progressive reductions in specificity. Notably, models trained with deep learning features enable prediction of novel antibody mutations that co-optimize affinity and specificity beyond what is possible for the original antibody library. These findings demonstrate the power of machine learning models to greatly expand the exploration of novel antibody sequence space and accelerate the development of highly potent, drug-like antibodies. 

Abstract Chinese hamster ovary (CHO) cells, predominant hosts for recombinant biotherapeutics production, generate lactate as a major glycolysis by‐product. High lactate levels adversely impact cell growth and productivity. The goal of this study was to reduce lactate in CHO cell cultures by adding chemical inhibitors to hexokinase‐2 (HK2), the enzyme catalyzing the conversion of glucose to glucose 6‐phosphate, and examine their impact on lactate accumulation, cell growth, protein titers, andN‐glycosylation. Five inhibitors of HK2 enzyme at different concentrations were evaluated, of which 2‐deoxy‐d‐glucose (2DG) and 5‐thio‐d‐glucose (5TG) successfully reduced lactate accumulation with only limited impacts on CHO cell growth. Individual 2DG and 5TG supplementation led to a 35%–45% decrease in peak lactate, while their combined supplementation resulted in a 60% decrease in peak lactate. Inhibitor supplementation led to at least 50% decrease in moles of lactate produced per mol of glucose consumed. Recombinant EPO‐Fc titers peaked earlier relative to the end of culture duration in supplemented cultures leading to at least 11% and as high as 32% increase in final EPO‐Fc titers. Asparagine, pyruvate, and serine consumption rates also increased in the exponential growth phase in 2DG and 5TG treated cultures, thus, rewiring central carbon metabolism due to low glycolytic fluxes.N‐glycan analysis of EPO‐Fc revealed an increase in high mannose glycans from 5% in control cultures to 25% and 37% in 2DG and 5TG‐supplemented cultures, respectively. Inhibitor supplementation also led to a decrease in bi‐, tri‐, and tetra‐antennary structures and up to 50% lower EPO‐Fc sialylation. Interestingly, addition of 2DG led to the incorporation of 2‐deoxy‐hexose (2DH) on EPO‐FcN‐glycans and addition of 5TG resulted in the first‐ever observedN‐glycan incorporation of 5‐thio‐hexose (5TH). Six percent to 23% ofN‐glycans included 5TH moieties, most likely 5‐thio‐mannose and/or 5‐thio‐galactose and/or possibly 5‐thio‐N‐acetylglucosamine, and 14%–33% ofN‐glycans included 2DH moieties, most likely 2‐deoxy‐mannose and/or 2‐deoxy‐galactose, for cultures treated with different concentrations of 5TG and 2DG, respectively. Our study is the first to evaluate the impact of these glucose analogs on CHO cell growth, protein production, cell metabolism,N‐glycosylation processing, and formation of alternative glycoforms.