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.
The corona that forms as protein adsorbs to gold nanospheres (AuNSs) is directly influenced by the surface chemistry of the AuNS. Tools to predict adsorption outcomes are needed for intelligent design of nanomaterials for biological applications. We hypothesized that the denaturation behavior of a protein might be a useful predictor of adsorption behavior to AuNSs, and used this idea to study protein adsorption to anionic citrate-capped AuNSs and to cationic poly(allylamine hydrochloride) (PAH) wrapped AuNSs. Three proteins (α-amylase (A-Amy), β-lactoglobulin (BLG), and bovine serum albumin (BSA)), representing three different classes of acid denaturation behavior, were selected with BLG being the least deformable and BSA being the most deformable. Protein adsorption to AuNSs was monitored via UV-vis spectrophotometry and dynamic light scattering. Changes to the protein structure upon AuNS interaction were monitored via circular dichroism spectroscopy. Binding constants were determined using the Langmuir adsorption isotherm, resulting in BSA > BLG ≫ A-Amy affinities for citrate-capped gold nanospheres. PAH-coated AuNSs displayed little affinity for these proteins at similar concentrations as citrate-coated AuNSs and became agglomerated at high protein concentrations. The enzymatic activity of A-Amy/citrate AuNS conjugates was measured via colorimetric assay, and found to be 11% of free A-Amy, suggesting that binding restricts access to the active site. Across both citrate AuNSs and PAH AuNSs, the changes in secondary structure were greatest for BSA > A-Amy > BLG, which does follow the trends predicted by acid denaturation characteristics.
Highlights d Directed evolution of nanobodies that potently neutralize SARS-CoV-2 d CDR-swapping mutagenesis facilitates large affinity and activity improvements d Nanobody binding to RBD competes with ACE2 and two classes of neutralizing mAbs d Neutralizing nanobodies display drug-like biophysical properties
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.