Embedding Dynamics in Intrinsic Physicochemical Profiles of Market-Stage Antibody-Based Biotherapeutics

Deep learning-based design and experimental validation of a medicine-like human antibody library

Antibody generation requires the use of one or more time-consuming methods, namely animal immunization, and in vitro display technologies. However, the recent availability of large amounts of antibody sequence and structural data in the public domain along with the advent of generative deep learning algorithms raises the possibility of computationally generating novel antibody sequences with desirable developability attributes. Here, we describe a deep learning model for computationally generating libraries of highly human antibody variable regions whose intrinsic physicochemical properties resemble those of the variable regions of the marketed antibody-based biotherapeutics (medicine-likeness). We generated 100000 variable region sequences of antigen-agnostic human antibodies belonging to the IGHV3-IGKV1 germline pair using a training dataset of 31416 human antibodies that satisfied our computational developability criteria. The in-silico generated antibodies recapitulate intrinsic sequence, structural, and physicochemical properties of the training antibodies, and compare favorably with the experimentally measured biophysical attributes of 100 variable regions of marketed and clinical stage antibody-based biotherapeutics. A sample of 51 highly diverse in-silico generated antibodies with >90th percentile medicine-likeness and > 90% humanness was evaluated by two independent experimental laboratories. Our data show the in-silico generated sequences exhibit high expression, monomer content, and thermal stability along with low hydrophobicity, self-association, and non-specific binding when produced as full-length monoclonal antibodies. The ability to computationally generate developable human antibody libraries is a first step towards enabling in-silico discovery of antibody-based biotherapeutics. These findings are expected to accelerate in-silico discovery of antibody-based biotherapeutics and expand the druggable antigen space to include targets refractory to conventional antibody discovery methods requiring in vitro antigen production.

Biophysical cartography of the native and human-engineered antibody landscapes quantifies the plasticity of antibody developability

Designing effective monoclonal antibody (mAb) therapeutics faces a multi-parameter optimization challenge known as "developability", which reflects an antibody's ability to progress through development stages based on its physicochemical properties. While natural antibodies may provide valuable guidance for mAb selection, we lack a comprehensive understanding of natural developability parameter (DP) plasticity (redundancy, predictability, sensitivity) and how the DP landscapes of human-engineered and natural antibodies relate to one another. These gaps hinder fundamental developability profile cartography. To chart natural and engineered DP landscapes, we computed 40 sequence- and 46 structure-based DPs of over two million native and human-engineered single-chain antibody sequences. We find lower redundancy among structure-based compared to sequence-based DPs. Sequence DP sensitivity to single amino acid substitutions varied by antibody region and DP, and structure DP values varied across the conformational ensemble of antibody structures. We show that sequence DPs are more predictable than structure-based ones across different machine-learning tasks and embeddings, indicating a constrained sequence-based design space. Human-engineered antibodies localize within the developability and sequence landscapes of natural antibodies, suggesting that human-engineered antibodies explore mere subspaces of the natural one. Our work quantifies the plasticity of antibody developability, providing a fundamental resource for multi-parameter therapeutic mAb design.

Contextualising the developability risk of antibodies with lambda light chains using enhanced therapeutic antibody profiling

Antibodies with lambda light chains (λ-antibodies) are generally considered to be less developable than those with kappa light chains (κ-antibodies). Though this hypothesis has not been formally established, it has led to substantial systematic biases in drug discovery pipelines and thus contributed to kappa dominance amongst clinical-stage therapeutics. However, the identification of increasing numbers of epitopes preferentially engaged by λ-antibodies shows there is a functional cost to neglecting to consider them as potential lead candidates. Here, we update our Therapeutic Antibody Profiler (TAP) tool to use the latest data and machine learning-based structure prediction, and apply it to evaluate developability risk profiles for κ-antibodies and λ-antibodies based on their surface physicochemical properties. We find that while human λ-antibodies on average have a higher risk of developability issues than κ-antibodies, a sizeable proportion are assigned lower-risk profiles by TAP and should represent more tractable candidates for therapeutic development. Through a comparative analysis of the low- and high-risk populations, we highlight opportunities for strategic design that TAP suggests would enrich for more developable λ-antibodies. Overall, we provide context to the differing developability of κ- and λ-antibodies, enabling a rational approach to incorporate more diversity into the initial pool of immunotherapeutic candidates.

Exploring molecular determinants and pharmacokinetic properties of IgG1-scFv bispecific antibodies

Bispecific antibodies (BsAbs) capable of recognizing two distinct epitopes or antigens offer promising therapeutic options for various diseases by targeting multiple pathways. The favorable pharmacokinetic (PK) properties of monoclonal antibodies (mAbs) are crucial, as they directly influence patient safety and therapeutic efficacy. For numerous mAb therapeutics, optimization of neonatal Fc receptor (FcRn) interactions and elimination of unfavorable molecular properties have led to improved PK properties. However, many BsAbs exhibit unfavorable PK, which has precluded their development as drugs. In this report, we present studies on the molecular determinants underlying the distinct PK profiles of three IgG1-scFv BsAbs. Our study indicated that high levels of nonspecific interactions, elevated isoelectric point (pI), and increased number of positively charged patches contributed to the fast clearance of IgG1-scFv. FcRn chromatography results revealed specific scFv-FcRn interactions that are unique to the IgG1-scFv, which was further supported by molecular dynamics (MD) simulation. These interactions likely stabilize the BsAb FcRn interaction at physiological pH, which in turn could disrupt FcRn-mediated BsAb recycling. In addition to the empirical observations, we also evaluated the impact of in silico properties, including pI differential between the Fab and scFv and the ratio of dipole moment to hydrophobic moment (RM) and their correlation with the observed clearance. These findings highlight that the PK properties of BsAbs may be governed by novel determinants, owing to their increased structural complexity compared to immunoglobulin G (IgG) 1 antibodies.

Predicting deamidation and isomerization sites in therapeutic antibodies using structure-based in silico approaches

Asparagine (Asn) deamidation and aspartic acid (Asp) isomerization are common degradation pathways that affect the stability of therapeutic antibodies. These modifications can pose a significant challenge in the development of biopharmaceuticals. As such, the early engineering and selection of chemically stable monoclonal antibodies (mAbs) can substantially mitigate the risk of subsequent failure. In this study, we introduce a novel in silico approach for predicting deamidation and isomerization sites in therapeutic antibodies by analyzing the structural environment surrounding asparagine and aspartate residues. The resulting quantitative structure-activity relationship (QSAR) model was trained using previously published forced degradation data from 57 clinical-stage mAbs. The predictive accuracy of the model was evaluated for four different states of the protein structure: (1) static homology models, (2) enhancing low-frequency vibrational modes during short molecular dynamics (MD) runs, (3) a combination of (2) with a protonation state reassignment, and (4) conventional full-atomistic MD simulations. The most effective QSAR model considered the accessible surface area (ASA) of the residue, the pKa value of the backbone amide, and the root mean square deviations of both the alpha carbon and the side chain. The accuracy was further enhanced by incorporating the QSAR model into a decision tree, which also includes empirical information about the sequential successor and the position in the protein. The resulting model has been implemented as a plugin named "Forecasting Reactivity of Isomerization and Deamidation in Antibodies" in MOE software, completed with a user-friendly graphical interface to facilitate its use.

How can we discover developable antibody-based biotherapeutics?

Antibody-based biotherapeutics have emerged as a successful class of pharmaceuticals despite significant challenges and risks to their discovery and development. This review discusses the most frequently encountered hurdles in the research and development (R&D) of antibody-based biotherapeutics and proposes a conceptual framework called biopharmaceutical informatics. Our vision advocates for the syncretic use of computation and experimentation at every stage of biologic drug discovery, considering developability (manufacturability, safety, efficacy, and pharmacology) of potential drug candidates from the earliest stages of the drug discovery phase. The computational advances in recent years allow for more precise formulation of disease concepts, rapid identification, and validation of targets suitable for therapeutic intervention and discovery of potential biotherapeutics that can agonize or antagonize them. Furthermore, computational methods for de novo and epitope-specific antibody design are increasingly being developed, opening novel computationally driven opportunities for biologic drug discovery. Here, we review the opportunities and limitations of emerging computational approaches for optimizing antigens to generate robust immune responses, in silico generation of antibody sequences, discovery of potential antibody binders through virtual screening, assessment of hits, identification of lead drug candidates and their affinity maturation, and optimization for developability. The adoption of biopharmaceutical informatics across all aspects of drug discovery and development cycles should help bring affordable and effective biotherapeutics to patients more quickly.