Predicting Antibody Developability Profiles Through Early Stage Discovery Screening

Developability considerations for bispecific and multispecific antibodies

Bispecific antibodies (bsAb) and multispecific antibodies (msAb) encompass a diverse variety of formats that can concurrently bind multiple epitopes, unlocking mechanisms to address previously difficult-to-treat or incurable diseases. Early assessment of candidate developability enables demotion of antibodies with low potential and promotion of the most promising candidates for further development. Protein-based therapies have a stringent set of developability requirements in order to be competitive (e.g. high-concentration formulation, and long half-life) and their assessment requires a robust toolkit of methods, few of which are validated for interrogating bsAbs/msAbs. Important considerations when assessing the developability of bsAbs/msAbs include their molecular format, likelihood for immunogenicity, specificity, stability, and potential for high-volume production. Here, we summarize the critical aspects of developability assessment, and provide guidance on how to develop a comprehensive plan tailored to a given bsAb/msAb.

Comprehensive characterization of higher order structure changes in methionine oxidized monoclonal antibodies via NMR chemometric analysis and biophysical approaches

The higher order structure (HOS) of monoclonal antibodies (mAbs) is an important quality attribute with strong contribution to clinically relevant biological functions and drug safety. Due to the multi-faceted nature of HOS, the synergy of multiple complementary analytical approaches can substantially improve the understanding, accuracy, and resolution of HOS characterization. In this study, we applied one- and two-dimensional (1D and 2D) nuclear magnetic resonance (NMR) spectroscopy coupled with chemometric analysis, as well as circular dichroism (CD), differential scanning calorimetry (DSC), and fluorescence spectroscopy as orthogonal methods, to characterize the impact of methionine (Met) oxidation on the HOS of an IgG1 mAb. We used a forced degradation method involving concentration-dependent oxidation by peracetic acid, in which Met oxidation is site-specifically quantified by liquid chromatography-mass spectrometry. Conventional biophysical techniques report nuanced results, in which CD detects no change to the secondary structure and little change in the tertiary structure. Yet, DSC measurements show the destabilization of Fab and Fc domains due to Met oxidation. More importantly, our study demonstrates that 1D and 2D NMR and chemometric analysis can provide semi-quantitative analysis of chemical modifications and resolve localized conformational changes with high sensitivity. Furthermore, we leveraged a novel 15N-Met labeling technique of the antibody to directly observe structural perturbations at the oxidation sites. The NMR methods described here to probe HOS changes are highly reliable and practical in biopharmaceutical characterization.

Matrixed CDR grafting: A neoclassical framework for antibody humanization and developability

Discovery and optimization of a biotherapeutic monoclonal antibody requires a careful balance of target engagement and physicochemical developability properties. To take full advantage of the sequence diversity provided by different antibody discovery platforms, a rapid and reliable process for humanization of antibodies from nonhuman sources is required. Canonically, maximizing homology of the human variable region (V-region) to the original germline was believed to result in preservation of binding, often without much consideration for inherent molecular properties. We expand on this approach by grafting the complementary determining regions (CDRs) of a mouse anti-LAG3 antibody into an extensive matrix of human variable heavy chain (VH) and variable light chain (VL) framework regions with substantially broader sequence homology to assess the impact on complementary determining region-framework compatibility through progressive evaluation of expression, affinity, biophysical developability, and function. Specific VH and VL framework sequences were associated with major expression and purification phenotypes. Greater VL sequence conservation was correlated with retained or improved affinity. Analysis of grafts that bound the target demonstrated that initial developability criteria were significantly impacted by VH, but not VL. In contrast, cell binding and functional characteristics were significantly impacted by VL, but not VH. Principal component analysis of all factors identified multiple grafts that exhibited more favorable antibody properties, notably with nonoptimal sequence conservation. Overall, this study demonstrates that modern throughput systems enable a more thorough, customizable, and systematic analysis of graft-framework combinations, resulting in humanized antibodies with improved global properties that may progress through development more quickly and with a greater probability of success.

Facilitating high throughput bispecific antibody production and potential applications within biopharmaceutical discovery workflows

A major driver for the recent investment surge in bispecific antibody (bsAb) platforms and products is the multitude of distinct mechanisms of action that bsAbs offer compared to a combination of two monoclonal antibodies. Four bsAb products were granted first regulatory approvals in the US or EU during 2023 and the biopharmaceutical industry pipeline is brimming with bsAb candidates across a broad range of therapeutic applications. In previously reported bsAb discovery campaigns, following a hypothesis-based choice of two specific target proteins, selections and screening activities have often been performed in mono-specific formats. The conversion to bispecific modalities has usually been positioned toward the end of the discovery process and has involved small numbers of lead molecules, largely due to challenges in expressing, purifying, and analyzing large numbers of bsAbs. In this review, we discuss emerging strategies to facilitate the production of expanded bsAb panels, focusing particularly upon combinatorial methods to generate bsAb matrices. Such technologies will enable screening in. bispecific formats at earlier stages of discovery campaigns, not only widening the accessible protein space to maximize chances of success, but also advancing empirical bi-target validation activities to assess initial target selection hypotheses.

Next generation of multispecific antibody engineering

Multispecific antibodies recognize two or more epitopes located on the same or distinct targets. This added capability through protein design allows these man-made molecules to address unmet medical needs that are no longer possible with single targeting such as with monoclonal antibodies or cytokines alone. However, the approach to the development of these multispecific molecules has been met with numerous road bumps, which suggests that a new workflow for multispecific molecules is required. The investigation of the molecular basis that mediates the successful assembly of the building blocks into non-native quaternary structures will lead to the writing of a playbook for multispecifics. This is a must do if we are to design workflows that we can control and in turn predict success. Here, we reflect on the current state-of-the-art of therapeutic biologics and look at the building blocks, in terms of proteins, and tools that can be used to build the foundations of such a next-generation workflow.

Optimization of therapeutic antibodies for reduced self-association and non-specific binding via interpretable machine learning

Antibody development, delivery, and efficacy are influenced by antibody-antigen affinity interactions, off-target interactions that reduce antibody bioavailability and pharmacokinetics, and repulsive self-interactions that increase the stability of concentrated antibody formulations and reduce their corresponding viscosity. Yet identifying antibody variants with optimal combinations of these three types of interactions is challenging. Here we show that interpretable machine-learning classifiers, leveraging antibody structural features descriptive of their variable regions and trained on experimental data for a panel of 80 clinical-stage monoclonal antibodies, can identify antibodies with optimal combinations of low off-target binding in a common physiological-solution condition and low self-association in a common antibody-formulation condition. For three clinical-stage antibodies with suboptimal combinations of off-target binding and self-association, the classifiers predicted variable-region mutations that optimized non-affinity interactions while maintaining high-affinity antibody-antigen interactions. Interpretable machine-learning models may facilitate the optimization of antibody candidates for therapeutic applications.

Improved Diffusion Interaction Parameter Measurement to Predict the Viscosity of Concentrated mAb Solutions

During the developability assessment of therapeutic monoclonal antibody (mAb) candidates, utilization of robust high-throughput predictive assays enables rapid selection of top candidates with low risks for late-stage development. Predicting the viscosities of highly concentrated mAbs using limited materials is an important aspect of developability assessment because high viscosity can complicate manufacturability, stability, and administration. Here, we report a high-throughput assay measuring protein-protein interactions to predict mAb viscosity. The diffusion interaction parameter (kD) measures colloidal self-association in dilute solutions and has been reported to be predictive of the mAb viscosity at high concentrations. However, kD of Amgen early stage IgG1 mAb candidates measured in 10 mM acetate at pH 5.2 containing sucrose and polysorbate (denoted A52SuT) shows only weak correlation to their viscosities at 140 mg/mL in A52SuT. We hypothesize that kD measured in A52SuT reflects primarily long-range electrostatic repulsions because most of these mAb candidates carry strong net positive charges in this low ionic strength formulation with pH (5.2) well below pI values of mAb candidates. However, the viscosities of high concentration mAbs depend heavily on short-range molecular interactions. We propose an improved kD method in which salt is added to suppress charge repulsions and to allow for detection of key short-range interactions in dilute solutions. Salt types and salt concentrations were screened, and an optimal salt condition was identified. This optimized method was further validated using two test mAb sets. Overall, the method improves the Pearson R2 between kD and viscosity (6-230 cP) from 0.24 to 0.80 for a data set consisting of 37 mAbs.

Prediction of Antibody Viscosity from Dilute Solution Measurements

The high antibody doses required to achieve a therapeutic effect often necessitate high-concentration products that can lead to challenging viscosity issues in production and delivery. Predicting antibody viscosity in early development can play a pivotal role in reducing late-stage development costs. In recent years, numerous efforts have been made to predict antibody viscosity through dilute solution measurements. A key finding is that the entanglement of long, flexible complexes contributes to the sharp rise in antibody viscosity at the required dosing. This entanglement model establishes a connection between the two-body binding affinity and the many-body viscosity. Exploiting this insight, this study connects dilute solution measurements of self-association to high-concentration viscosity profiles to quantify the relationship between these regimes. The resulting model has exhibited success in predicting viscosity at high concentrations (around 150 mg/mL) from dilute solution measurements, with only a few outliers remaining. Our physics-based approach provides an understanding of fundamental physics, interpretable connections to experimental data, the potential to extrapolate beyond training conditions, and the capacity to effectively explain the physical mechanics behind these outliers. Conducting hypothesis-driven experiments that specifically target the viscosity and relaxation mechanisms of outlier molecules may allow us to unravel the intricacies of their behavior and, in turn, enhance the performance of our model.

Antibody sequence-based prediction of pH gradient elution in multimodal chromatography

Multimodal chromatography has emerged as a promising technique for antibody purification, owing to its capacity to selectively capture and separate target molecules. However, the optimization of chromatography parameters remains a challenge due to the intricate nature of protein-ligand interactions. To tackle this issue, efficient predictive tools are essential for the development and optimization of multimodal chromatography processes. In this study, we introduce a methodology that predicts the elution behavior of antibodies in multimodal chromatography based on their amino acid sequences. We analyzed a total of 64 full-length antibodies, including IgG1, IgG4, and IgG-like multispecific formats, which were eluted using linear pH gradients from pH 9.0 to 4.0 on the anionic mixed-mode resin Capto adhere. Homology models were constructed, and 1312 antibody-specific physicochemical descriptors were calculated for each molecule. Our analysis identified six key structural features of the multimodal antibody interaction, which were correlated with the elution behavior, emphasizing the antibody variable region. The results show that our methodology can predict pH gradient elution for a diverse range of antibodies and antibody formats, with a test set R² of 0.898. The developed model can inform process development by predicting initial conditions for multimodal elution, thereby reducing trial and error during process optimization. Furthermore, the model holds the potential to enable an in silico manufacturability assessment by screening target antibodies that adhere to standardized purification conditions. In conclusion, this study highlights the feasibility of using structure-based prediction to enhance antibody purification in the biopharmaceutical industry. This approach can lead to more efficient and cost-effective process development while increasing process understanding.

Exploring a role for flow-induced aggregation assays in platform formulation optimisation for antibody-based proteins

The development time of therapeutic monoclonal antibodies (mAbs) has been shortened by formulation platforms and the assessment of 'protein stability' using 'developability' assays. A range of assays are used to measure stability to a variety of stresses, including forces induced by hydrodynamic flow. We have previously developed a low-volume Extensional Flow Device (EFD) which subjects proteins to defined fluid flow fields in the presence of glass interfaces and used it to identify robust candidate sequences. Here, we study the aggregation of mAbs and Fc-fusion proteins using the EFD and orbital shaking under different formulations, investigating the relationship between these assays and evaluating their potential in formulation optimisation. EFD experiments identified the least aggregation-prone molecule using a fraction of the material and time involved in traditional screening. We also show that the EFD can differentiate between different formulations and that protective formulations containing polysorbate 80 stabilised poorly developable Fc-fusion proteins against EFD-induced aggregation up to two-fold. Our work highlights common platform formulation additives that affect the extent of aggregation under EFD-stress, as well as identifying factors that modulate the underlying aggregation mechanism. Together, our data could aid the choice of platform formulations early in development for next-generation therapeutics including fusion proteins.

A Research Journey: Over a Decade of Denaturing and Native-MS Analyses of Hydrophobic and Membrane Proteins in Amgen Therapeutic Discovery

Membrane proteins and associated complexes currently comprise the majority of therapeutic targets and remain among the most challenging classes of proteins for analytical characterization. Through long-term strategic collaborations forged between industrial and academic research groups, there has been tremendous progress in advancing membrane protein mass spectrometry (MS) analytical methods and their concomitant application to Amgen therapeutic project progression. Herein, I will describe a detailed and personal account of how electrospray ionization (ESI) native mass spectrometry (nMS), ion mobility-MS (IM-MS), reversed phase liquid chromatographic mass spectrometry (RPLC-MS), high-throughput solid phase extraction mass spectrometry, and matrix-assisted laser desorption ionization mass spectrometry methods were developed, optimized, and validated within Amgen Research, and importantly, how these analytical methods were applied for membrane and hydrophobic protein analyses and ultimately therapeutic project support and progression. Additionally, I will discuss all the highly important and productive collaborative efforts, both internal Amgen and external academic, which were key in generating the samples, methods, and associated data described herein. I will also describe some early and previously unpublished nano-ESI (nESI) native-MS data from Amgen Research and the highly productive University of California Los Angeles (UCLA) collaboration. I will also present previously unpublished examples of real-life Amgen biotherapeutic membrane protein projects that were supported by all the MS (and IM) analytical techniques described herein. I will start by describing the initial nESI nMS experiments performed at Amgen in 2011 on empty nanodisc molecules, using a quadrupole time-of-flight MS, and how these experiments progressed on to the 15 Tesla Fourier transform ion cyclotron resonance MS at UCLA. Then described are monomeric and multimeric membrane protein data acquired in both nESI nMS and tandem-MS modes, using multiple methods of ion activation, resulting in dramatic spectral simplification. Also described is how we investigated the far less established and less published subject, that is denaturing RPLC-MS analysis of membrane proteins, and how we developed a highly robust and reproducible RPLC-MS method capable of effective separation of membrane proteins differing in only the presence or absence of an N-terminal post translational modification. Also described is the evolution of the aforementioned RPLC-MS method into a high-throughput solid phase extraction MS method. Finally, I will give my opinion on key developments and how the area of nMS of membrane proteins needs to evolve to a state where it can be applied within the biopharmaceutical research environment for routine therapeutic project support.

Deep learning in preclinical antibody drug discovery and development

Antibody drugs have become a key part of biotherapeutics. Patients suffering from various diseases have benefited from antibody therapies. However, its development process is rather long, expensive and risky. To speed up the process, reduce cost and improve success rate, artificial intelligence, especially deep learning methods, have been widely used in all aspects of preclinical antibody drug development, from library generation to hit identification, developability screening, lead selection and optimization. In this review, we systematically summarize antibody encodings, deep learning architectures and models used in preclinical antibody drug discovery and development. We also critically discuss challenges and opportunities, problems and possible solutions, current applications and future directions of deep learning in antibody drug development.

Integration of a perfusion reactor and continuous precipitation in an entirely membrane-based process for antibody capture

Continuous precipitation coupled with continuous tangential flow filtration is a cost-effective alternative for the capture of recombinant antibodies from crude cell culture supernatant. The removal of surge tanks between unit operations, by the adoption of tubular reactors, maintains a continuous harvest and mass flow of product with the advantage of a narrow residence time distribution (RTD). We developed a continuous process implementing two orthogonal precipitation methods, CaCl2 precipitation for removal of host-cell DNA and polyethylene glycol (PEG) for capturing the recombinant antibody, with no influence on the glycosylation profile. Our lab-scale prototype consisting of two tubular reactors and two stages of tangential flow microfiltration was continuously operated for up to 8 days in a truly continuous fashion and without any product flow interruption, both as a stand-alone capture and as an integrated perfusion-capture. Furthermore, we explored the use of a negatively charged membrane adsorber for flow-through anion exchange as first polishing step. We obtained a product recovery of approximately 80% and constant product quality, with more than two logarithmic reduction values (LRVs) for both host-cell proteins and host-cell DNA by the combination of the precipitation-based capture and the first polishing step.

Predicting and Interpreting Protein Developability Via Transfer of Convolutional Sequence Representation

Engineered proteins have emerged as novel diagnostics, therapeutics, and catalysts. Often, poor protein developability─quantified by expression, solubility, and stability─hinders utility. The ability to predict protein developability from amino acid sequence would reduce the experimental burden when selecting candidates. Recent advances in screening technologies enabled a high-throughput (HT) developability dataset for 105 of 1020 possible variants of protein ligand scaffold Gp2. In this work, we evaluate the ability of neural networks to learn a developability representation from a HT dataset and transfer this knowledge to predict recombinant expression beyond observed sequences. The model convolves learned amino acid properties to predict expression levels 44% closer to the experimental variance compared to a non-embedded control. Analysis of learned amino acid embeddings highlights the uniqueness of cysteine, the importance of hydrophobicity and charge, and the unimportance of aromaticity, when aiming to improve the developability of small proteins. We identify clusters of similar sequences with increased recombinant expression through nonlinear dimensionality reduction and we explore the inferred expression landscape via nested sampling. The analysis enables the first direct visualization of the fitness landscape and highlights the existence of evolutionary bottlenecks in sequence space giving rise to competing subpopulations of sequences with different developability. The work advances applied protein engineering efforts by predicting and interpreting protein scaffold expression from a limited dataset. Furthermore, our statistical mechanical treatment of the problem advances foundational efforts to characterize the structure of the protein fitness landscape and the amino acid characteristics that influence protein developability.

Discovery of ABBV-154, an anti-TNF Glucocorticoid Receptor Modulator Immunology Antibody-Drug Conjugate (iADC)

Stable attachment of drug-linkers to the antibody is a critical requirement, and for maleimide conjugation to cysteine, it is achieved by ring hydrolysis of the succinimide ring. During ADC profiling in our in-house property screening funnel, we discovered that the succinimide ring open form is in equilibrium with the ring closed succinimide. Bromoacetamide (BrAc) was identified as the optimal replacement, as it affords stable attachment of the drug-linker to the antibody while completely removing the undesired ring open-closed equilibrium. Additionally, BrAc also offers multiple benefits over maleimide, especially with respect to homogeneity of the ADC structure. In combination with a short, hydrophilic linker and phosphate prodrug on the payload, this afforded a stable ADC (ABBV-154) with the desired properties to enable long-term stability to facilitate subcutaneous self-administration.

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.

Co-crystallisation and humanisation of an anti-HER2 single-domain antibody as a theranostic tool

Human epidermal growth factor receptor-2 (HER2) is a well-recognised biomarker associated with 25% of breast cancers. In most cases, early detection and/or treatment correlates with an increased chance of survival. This study, has identified and characterised a highly specific anti-HER2 single-domain antibody (sdAb), NM-02, as a potential theranostic tool. Complete structural description by X-ray crystallography has revealed a non-overlapping epitope with current anti-HER2 antibodies. To reduce the immunogenicity risk, NM-02 underwent a humanisation process and retained wild type-like binding properties. To further de-risk the progression towards chemistry, manufacturing and control (CMC) we performed full developability profiling revealing favourable thermal and physical biochemical 'drug-like' properties. Finally, the application of the lead humanised NM-02 candidate (variant K) for HER2-specific imaging purposes was demonstrated using breast cancer HER2+/BT474 xenograft mice.

Predictive Nature of High-Throughput Assays in ADC Formulation Screening

Utilization of high-throughput biophysical screening techniques during early screening studies is warranted due to the limited amount of material and large number of samples. But the predictability of the data to longer-term storage stability is critical as the high-throughput methods assist in defining the design space for the longer-term studies. In this study, the biophysical properties of two ADCs in 16 formulation conditions were evaluated using high-throughput techniques. Conformational stability and colloidal stability were evaluated by determining Tm values, kD, B22, and Tagg. In addition, the samples were placed on stability and the extent of aggregate formation over the 8-week interval was determined. The rank order of the 16 different formulations in the high-throughput assays was compared to the rank order observed during the stability studies to assess the predictive capabilities of the screening methods. It was demonstrated that similar rank orders can be expected between high-throughput physical stability indicating assays such as Tagg and B22 and traditional aggregation by SEC data, whereas conformational stability read-outs (Tm) are less predictive. In addition, the high-throughput assays appropriately identified the poor performing formulation conditions, which is ultimately what is desired of screening assays.

Optimization of Drug-Linker to Enable Long-term Storage of Antibody-Drug Conjugate for Subcutaneous Dosing

To facilitate subcutaneous dosing, biotherapeutics need to exhibit properties that enable high-concentration formulation and long-term stability in the formulation buffer. For antibody-drug conjugates (ADCs), the introduction of drug-linkers can lead to increased hydrophobicity and higher levels of aggregation, which are both detrimental to the properties required for subcutaneous dosing. Herein we show how the physicochemical properties of ADCs could be controlled through the drug-linker chemistry in combination with prodrug chemistry of the payload, and how optimization of these combinations could afford ADCs with significantly improved solution stability. Key to achieving this optimization is the use of an accelerated stress test performed in a minimal formulation buffer.

Subclass Effects on Self-Association and Viscosity of Monoclonal Antibodies at High Concentrations

The effects of a subclass of monoclonal antibodies (mAbs) on protein-protein interactions, formation of reversible oligomers (clusters), and viscosity (η) are not well understood at high concentrations. Herein, we quantify a short-range anisotropic attraction between the complementarity-determining region (CDR) and CH3 domains (KCDR-CH3) for vedolizumab IgG1, IgG2, or IgG4 subclasses by fitting small-angle X-ray scattering (SAXS) structure factor Seff(q) data with an extensive library of 12-bead coarse-grained (CG) molecular dynamics simulations. The KCDR-CH3 bead attraction strength was isolated from the strength of long-range electrostatic repulsion for the full mAb, which was determined from the theoretical net charge and a scaling parameter ψ to account for solvent accessibility and ion pairing. At low ionic strength (IS), the strongest short-range attraction (KCDR-CH3) and consequently the largest clusters and highest η were observed with IgG1, the subclass with the most positively charged CH3 domain. Furthermore, the trend in KCDR-CH3 with the subclass followed the electrostatic interaction energy between the CDR and CH3 regions calculated with the BioLuminate software using the 3D mAb structure and molecular interaction potentials. Whereas the equilibrium cluster size distributions and fractal dimensions were determined from fits of SAXS with the MD simulations, the degree of cluster rigidity under flow was estimated from the experimental η with a phenomenological model. For the systems with the largest clusters, especially IgG1, the inefficient packing of mAbs in the clusters played the largest role in increasing η, whereas for other systems, the relative contribution from stress produced by the clusters was more significant. The ability to relate η to short-range attraction from SAXS measurements at high concentrations and to theoretical characterization of electrostatic patches on the 3D surface is not only of fundamental interest but also of practical value for mAb discovery, processing, formulation, and subcutaneous delivery.

Accelerating therapeutic protein design with computational approaches toward the clinical stage

Therapeutic protein, represented by antibodies, is of increasing interest in human medicine. However, clinical translation of therapeutic protein is still largely hindered by different aspects of developability, including affinity and selectivity, stability and aggregation prevention, solubility and viscosity reduction, and deimmunization. Conventional optimization of the developability with widely used methods, like display technologies and library screening approaches, is a time and cost-intensive endeavor, and the efficiency in finding suitable solutions is still not enough to meet clinical needs. In recent years, the accelerated advancement of computational methodologies has ushered in a transformative era in the field of therapeutic protein design. Owing to their remarkable capabilities in feature extraction and modeling, the integration of cutting-edge computational strategies with conventional techniques presents a promising avenue to accelerate the progression of therapeutic protein design and optimization toward clinical implementation. Here, we compared the differences between therapeutic protein and small molecules in developability and provided an overview of the computational approaches applicable to the design or optimization of therapeutic protein in several developability issues.

Application of germline antibody features to vaccine development, antibody discovery, antibody optimization and disease diagnosis

Although the efficacy and commercial success of vaccines and therapeutic antibodies have been tremendous, designing and discovering new drug candidates remains a labor-, time- and cost-intensive endeavor with high risks. The main challenges of vaccine development are inducing a strong immune response in broad populations and providing effective prevention against a group of highly variable pathogens. Meanwhile, antibody discovery faces several great obstacles, especially the blindness in antibody screening and the unpredictability of the developability and druggability of antibody drugs. These challenges are largely due to poorly understanding of germline antibodies and the antibody responses to pathogen invasions. Thanks to the recent developments in high-throughput sequencing and structural biology, we have gained insight into the germline immunoglobulin (Ig) genes and germline antibodies and then the germline antibody features associated with antigens and disease manifestation. In this review, we firstly outline the broad associations between germline antibodies and antigens. Moreover, we comprehensively review the recent applications of antigen-specific germline antibody features, physicochemical properties-associated germline antibody features, and disease manifestation-associated germline antibody features on vaccine development, antibody discovery, antibody optimization, and disease diagnosis. Lastly, we discuss the bottlenecks and perspectives of current and potential applications of germline antibody features in the biotechnology field.

Multidimensional Protein Solubility Optimization with an Ultrahigh-Throughput Microfluidic Platform

Protein-based biologics are highly suitable for drug development as they exhibit low toxicity and high specificity for their targets. However, for therapeutic applications, biologics must often be formulated to elevated concentrations, making insufficient solubility a critical bottleneck in the drug development pipeline. Here, we report an ultrahigh-throughput microfluidic platform for protein solubility screening. In comparison with previous methods, this microfluidic platform can make, incubate, and measure samples in a few minutes, uses just 20 μg of protein (>10-fold improvement), and yields 10,000 data points (1000-fold improvement). This allows quantitative comparison of formulation excipients, such as sodium chloride, polysorbate, histidine, arginine, and sucrose. Additionally, we can measure how solubility is affected by the combinatorial effect of multiple additives, find a suitable pH for the formulation, and measure the impact of mutations on solubility, thus enabling the screening of large libraries. By reducing material and time costs, this approach makes detailed multidimensional solubility optimization experiments possible, streamlining drug development and increasing our understanding of biotherapeutic solubility and the effects of excipients.

Computational and artificial intelligence-based methods for antibody development

Due to their high target specificity and binding affinity, therapeutic antibodies are currently the largest class of biotherapeutics. The traditional largely empirical antibody development process is, while mature and robust, cumbersome and has significant limitations. Substantial recent advances in computational and artificial intelligence (AI) technologies are now starting to overcome many of these limitations and are increasingly integrated into development pipelines. Here, we provide an overview of AI methods relevant for antibody development, including databases, computational predictors of antibody properties and structure, and computational antibody design methods with an emphasis on machine learning (ML) models, and the design of complementarity-determining region (CDR) loops, antibody structural components critical for binding.

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

Adequate stability, manufacturability, and safety are crucial to bringing an antibody-based biotherapeutic to the market. Following the concept of holistic in silico developability, we introduce a physicochemical description of 91 market-stage antibody-based biotherapeutics based on orthogonal molecular properties of variable regions (Fvs) embedded in different simulation environments, mimicking conditions experienced by antibodies during manufacturing, formulation, and in vivo. In this work, the evaluation of molecular properties includes conformational flexibility of the Fvs using molecular dynamics (MD) simulations. The comparison between static homology models and simulations shows that MD significantly affects certain molecular descriptors like surface molecular patches. Moreover, the structural stability of a subset of Fv regions is linked to changes in their specific molecular interactions with ions in different experimental conditions. This is supported by the observation of differences in protein melting temperatures upon addition of NaCl. A DEvelopability Navigator In Silico (DENIS) is proposed to compare mAb candidates for their similarity with market-stage biotherapeutics in terms of physicochemical properties and conformational stability. Expanding on our previous developability guidelines (Ahmed et al. Proc. Natl. Acad. Sci. 2021, 118 (37), e2020577118), the hydrodynamic radius and the protein strand ratio are introduced as two additional descriptors that enable a more comprehensive in silico characterization of biotherapeutic drug candidates. Test cases show how this approach can facilitate identification and optimization of intrinsically developable lead candidates. DENIS represents an advanced computational tool to progress biotherapeutic drug candidates from discovery into early development by predicting drug properties in different aqueous environments.

Protein Stability After Administration: A Physiologic Consideration

Regulatory authorities and the scientific community have identified the need to monitor the in vivo stability of therapeutic proteins (TPs). Due to the unique physiologic conditions in patients, the stability of TPs after administration can deviate largely from their stability under drug product (DP) conditions. TPs can degrade at substantial rates once immersed in the in vivo milieu. Changes in protein stability upon administration to patients are critical as they can have implications on patient safety and clinical effectiveness of DPs. Physiologic conditions are challenging to simulate and require dedicated in vitro models for specific routes of administration. Advancements of in vitro models enable to simulate the exposure to physiologic conditions prior to resource demanding pre-clinical and clinical studies. This enables to evaluate the in vivo stability and thus may allow to improve the safety/efficacy profile of DPs. While in vitro-in vivo correlations are challenging, benchmarking DP candidates enables to identify liabilities and optimize molecules. The in vivo stability should be an integral part of holistic stability assessments during early development. Such assessments can accelerate development timelines and lead to more stable DPs for patients.

Toward real-world automated antibody design with combinatorial Bayesian optimization

Antibodies are multimeric proteins capable of highly specific molecular recognition. The complementarity determining region 3 of the antibody variable heavy chain (CDRH3) often dominates antigen-binding specificity. Hence, it is a priority to design optimal antigen-specific CDRH3 to develop therapeutic antibodies. The combinatorial structure of CDRH3 sequences makes it impossible to query binding-affinity oracles exhaustively. Moreover, antibodies are expected to have high target specificity and developability. Here, we present AntBO, a combinatorial Bayesian optimization framework utilizing a CDRH3 trust region for an in silico design of antibodies with favorable developability scores. The in silico experiments on 159 antigens demonstrate that AntBO is a step toward practically viable in vitro antibody design. In under 200 calls to the oracle, AntBO suggests antibodies outperforming the best binding sequence from 6.9 million experimentally obtained CDRH3s. Additionally, AntBO finds very-high-affinity CDRH3 in only 38 protein designs while requiring no domain knowledge.

Identifying developability risks for clinical progression of antibodies using high-throughput in vitro and in silico approaches

With the growing significance of antibodies as a therapeutic class, identifying developability risks early during development is of paramount importance. Several high-throughput in vitro assays and in silico approaches have been proposed to de-risk antibodies during early stages of the discovery process. In this review, we have compiled and collectively analyzed published experimental assessments and computational metrics for clinical antibodies. We show that flags assigned based on in vitro measurements of polyspecificity and hydrophobicity are more predictive of clinical progression than their in silico counterparts. Additionally, we assessed the performance of published models for developability predictions on molecules not used during model training. We find that generalization to data outside of those used for training remains a challenge for models. Finally, we highlight the challenges of reproducibility in computed metrics arising from differences in homology modeling, in vitro assessments relying on complex reagents, as well as curation of experimental data often used to assess the utility of high-throughput approaches. We end with a recommendation to enable assay reproducibility by inclusion of controls with disclosed sequences, as well as sharing of structural models to enable the critical assessment and improvement of in silico predictions.

SUMO: In Silico Sequence Assessment Using Multiple Optimization Parameters

To select the most promising screening hits from antibody and VHH display campaigns for subsequent in-depth profiling and optimization, it is highly desirable to assess and select sequences on properties beyond only their binding signals from the sorting process. In addition, developability risk criteria, sequence diversity, and the anticipated complexity for sequence optimization are relevant attributes for hit selection and optimization. Here, we describe an approach for the in silico developability assessment of antibody and VHH sequences. This method not only allows for ranking and filtering multiple sequences with regard to their predicted developability properties and diversity, but also visualizes relevant sequence and structural features of potentially problematic regions and thereby provides rationales and starting points for multi-parameter sequence optimization.

Approaches to expand the conventional toolbox for discovery and selection of antibodies with drug-like physicochemical properties

Antibody drugs should exhibit not only high-binding affinity for their target antigens but also favorable physicochemical drug-like properties. Such drug-like biophysical properties are essential for the successful development of antibody drug products. The traditional approaches used in antibody drug development require significant experimentation to produce, optimize, and characterize many candidates. Therefore, it is attractive to integrate new methods that can optimize the process of selecting antibodies with both desired target-binding and drug-like biophysical properties. Here, we summarize a selection of techniques that can complement the conventional toolbox used to de-risk antibody drug development. These techniques can be integrated at different stages of the antibody development process to reduce the frequency of physicochemical liabilities in antibody libraries during initial discovery and to co-optimize multiple antibody features during early-stage antibody engineering and affinity maturation. Moreover, we highlight biophysical and computational approaches that can be used to predict physical degradation pathways relevant for long-term storage and in-use stability to reduce the need for extensive experimentation.

Assessing developability early in the discovery process for novel biologics

Beyond potency, a good developability profile is a key attribute of a biological drug. Selecting and screening for such attributes early in the drug development process can save resources and avoid costly late-stage failures. Here, we review some of the most important developability properties that can be assessed early on for biologics. These include the influence of the source of the biologic, its biophysical and pharmacokinetic properties, and how well it can be expressed recombinantly. We furthermore present in silico, in vitro, and in vivo methods and techniques that can be exploited at different stages of the discovery process to identify molecules with liabilities and thereby facilitate the selection of the most optimal drug leads. Finally, we reflect on the most relevant developability parameters for injectable versus orally delivered biologics and provide an outlook toward what general trends are expected to rise in the development of biologics.

Analytical Workflows to Unlock Predictive Power in Biotherapeutic Developability

PURPOSE

Forming accurate data models that assist the design of developability assays is one area that requires a deep and practical understanding of the problem domain. We aim to incorporate expert knowledge into the model building process by creating new metrics from instrument data and by guiding the choice of input parameters and Machine Learning (ML) techniques.

METHODS

We generated datasets from the biophysical characterisation of 5 monoclonal antibodies (mAbs). We explored combinations of techniques and parameters to uncover the ones that better describe specific molecular liabilities, such as conformational and colloidal instability. We also employed ML algorithms to predict metrics from the dataset.

RESULTS

We found that the combination of Differential Scanning Calorimetry (DSC) and Light Scattering thermal ramps enabled us to identify domain-specific aggregation in mAbs that would be otherwise overlooked by common developability workflows. We also found that the response to different salt concentrations provided information about colloidal stability in agreement with charge distribution models. Finally, we predicted DSC transition temperatures from the dataset, and used the order of importance of different metrics to increase the explainability of the model.

CONCLUSIONS

The new analytical workflows enabled a better description of molecular behaviour and uncovered links between structural properties and molecular liabilities. In the future this new understanding will be coupled with ML algorithms to unlock their predictive power during developability assessment.

Structure-Based Optimization of Antibody-Based Biotherapeutics for Improved Developability: A Practical Guide for Molecular Modelers

A great effort to avoid known developability risks is now more often being made earlier during the lead candidate discovery and optimization phase of biotherapeutic drug development. Predictive computational strategies, used in the early stages of antibody discovery and development, to mitigate the risk of late-stage failure of antibody candidates, are highly valuable. Various structure-based methods exist for accurately predicting properties critical to developability, and, in this chapter, we discuss the history of their development and demonstrate how they can be used to filter large sets of candidates arising from target affinity screening and to optimize lead candidates for developability. Methods for modeling antibody structures from sequence and detecting post-translational modifications and chemical degradation liabilities are also discussed.

Development of in silico models to predict viscosity and mouse clearance using a comprehensive analytical data set collected on 83 scaffold-consistent monoclonal antibodies

Biologic drug discovery pipelines are designed to deliver protein therapeutics that have exquisite functional potency and selectivity while also manifesting biophysical characteristics suitable for manufacturing, storage, and convenient administration to patients. The ability to use computational methods to predict biophysical properties from protein sequence, potentially in combination with high throughput assays, could decrease timelines and increase the success rates for therapeutic developability engineering by eliminating lengthy and expensive cycles of recombinant protein production and testing. To support development of high-quality predictive models for antibody developability, we designed a sequence-diverse panel of 83 effector functionless IgG1 antibodies displaying a range of biophysical properties, produced and formulated each protein under standard platform conditions, and collected a comprehensive package of analytical data, including in vitro assays and in vivo mouse pharmacokinetics. We used this robust training data set to build machine learning classifier models that can predict complex protein behavior from these data and features derived from predicted and/or experimental structures. Our models predict with 87% accuracy whether viscosity at 150 mg/mL is above or below a threshold of 15 centipoise (cP) and with 75% accuracy whether the area under the plasma drug concentration-time curve (AUC0-672 h) in normal mouse is above or below a threshold of 3.9 × 106 h x ng/mL.

Developability profiling of a panel of Fc engineered SARS-CoV-2 neutralizing antibodies

To combat the COVID-19 pandemic, potential therapies have been developed and moved into clinical trials at an unprecedented pace. Some of the most promising therapies are neutralizing antibodies against SARS-CoV-2. In order to maximize the therapeutic effectiveness of such neutralizing antibodies, Fc engineering to modulate effector functions and to extend half-life is desirable. However, it is critical that Fc engineering does not negatively impact the developability properties of the antibodies, as these properties play a key role in ensuring rapid development, successful manufacturing, and improved overall chances of clinical success. In this study, we describe the biophysical characterization of a panel of Fc engineered ("TM-YTE") SARS-CoV-2 neutralizing antibodies, the same Fc modifications as those found in AstraZeneca's Evusheld (AZD7442; tixagevimab and cilgavimab), in which the TM modification (L234F/L235E/P331S) reduce binding to FcγR and C1q and the YTE modification (M252Y/S254T/T256E) extends serum half-life. We have previously shown that combining both the TM and YTE Fc modifications can reduce the thermal stability of the CH2 domain and possibly lead to developability challenges. Here we show, using a diverse panel of TM-YTE SARS-CoV-2 neutralizing antibodies, that despite lowering the thermal stability of the Fc CH2 domain, the TM-YTE platform does not have any inherent developability liabilities and shows an in vivo pharmacokinetic profile in human FcRn transgenic mice similar to the well-characterized YTE platform. The TM-YTE is therefore a developable, effector function reduced, half-life extended antibody platform.

A machine learning strategy for the identification of key in silico descriptors and prediction models for IgG monoclonal antibody developability properties

Identification of favorable biophysical properties for protein therapeutics as part of developability assessment is a crucial part of the preclinical development process. Successful prediction of such properties and bioassay results from calculated in silico features has potential to reduce the time and cost of delivering clinical-grade material to patients, but nevertheless has remained an ongoing challenge to the field. Here, we demonstrate an automated and flexible machine learning workflow designed to compare and identify the most powerful features from computationally derived physiochemical feature sets, generated from popular commercial software packages. We implement this workflow with medium-sized datasets of human and humanized IgG molecules to generate predictive regression models for two key developability endpoints, hydrophobicity and poly-specificity. The most important features discovered through the automated workflow corroborate several previous literature reports, and newly discovered features suggest directions for further research and potential model improvement.

Blueprint for antibody biologics developability

Large-molecule antibody biologics have revolutionized medicine owing to their superior target specificity, pharmacokinetic and pharmacodynamic properties, safety and toxicity profiles, and amenability to versatile engineering. In this review, we focus on preclinical antibody developability, including its definition, scope, and key activities from hit to lead optimization and selection. This includes generation, computational and in silico approaches, molecular engineering, production, analytical and biophysical characterization, stability and forced degradation studies, and process and formulation assessments. More recently, it is apparent these activities not only affect lead selection and manufacturability, but ultimately correlate with clinical progression and success. Emerging developability workflows and strategies are explored as part of a blueprint for developability success that includes an overview of the four major molecular properties that affect all developability outcomes: 1) conformational, 2) chemical, 3) colloidal, and 4) other interactions. We also examine risk assessment and mitigation strategies that increase the likelihood of success for moving the right candidate into the clinic.

Conformation specific antagonistic high affinity antibodies to the RON receptor kinase for imaging and therapy

The RON receptor tyrosine kinase is an exceptionally interesting target in oncology and immunology. It is not only overexpressed in a wide variety of tumors but also has been shown to be expressed on myeloid cells associated with tumor infiltration, where it serves to dampen tumour immune responses and reduce the efficacy of anti-CTLA4 therapy. Potent and selective inhibitory antibodies to RON might therefore both inhibit tumor cell growth and stimulate immune rejection of tumors. We derived cloned and sequenced a new panel of exceptionally avid anti-RON antibodies with picomolar binding affinities that inhibit MSP-induced RON signaling and show remarkable potency in antibody dependent cellular cytotoxicity. Antibody specificity was validated by cloning the antibody genes and creating recombinant antibodies and by the use of RON knock out cell lines. When radiolabeled with 89-Zirconium, the new antibodies 3F8 and 10G1 allow effective immuno-positron emission tomography (immunoPET) imaging of RON-expressing tumors and recognize universally exposed RON epitopes at the cell surface. The 10G1 was further developed into a novel bispecific T cell engager with a 15 pM EC50 in cytotoxic T cell killing assays.

Accelerated CMC workflows to enable speed to clinic in the COVID-19 era: A multi-company view from the biopharmaceutical industry

The COVID-19 pandemic has placed unprecedented pressure on biopharmaceutical companies to develop efficacious preventative and therapeutic treatments, which is unlikely to abate in the coming years. The importance of fast progress to clinical evaluation for treatments, which tackle unmet medical needs puts strain on traditional product development timelines, which can take years from start to finish. Although previous work has been successful in reducing phase 1 timelines for recombinant antibodies, through utilization of the latest technological advances and acceptance of greater business risk or costs, substantially faster development is likely achievable without increased risk to patients during initial clinical evaluation. To optimize lessons learned from the pandemic and maximize multi-stakeholder (i.e., patients, clinicians, companies, regulatory agencies) benefit, we conducted an industry wide benchmarking survey in September/October 2021. The aims of this survey were to: (i) benchmark current technical practices of key process and product development activities related to manufacturing of therapeutic proteins, (ii) understand the impact of changes implemented in COVID-19 accelerated Ab programs, and whether any such changes can be retained as part of sustainable long-term business practices and (iii) understand whether any accelerative action(s) taken have (negatively) impacted the wider development process. This article provides an in-depth analysis of this data, ultimately highlighting an industry perspective of how biopharmaceutical companies can sustainably adopt new approaches to therapeutic protein development and production.

Advancing humanized monoclonal antibody for counteracting fentanyl toxicity towards clinical development

Innovative therapies to complement current treatments are needed to curb the growing incidence of fatal overdoses related to synthetic opioids. Murine and chimeric monoclonal antibodies (mAb) specific for fentanyl and its analogs have demonstrated pre-clinical efficacy in preventing and reversing drug-induced toxicity in rodent models. However, mAb-based therapeutics require extensive engineering as well as in vitro and in vivo characterization to advance to first-in-human clinical trials. Here, novel murine anti-fentanyl mAbs were selected for development based on affinity for fentanyl, and efficacy in counteracting the pharmacological effects of fentanyl in mice. Humanization and evaluation of mutations designed to eliminate predicted post-translational modifications resulted in two humanized mAbs that were effective at preventing fentanyl-induced pharmacological effects in rats. These humanized mAbs showed favorable biophysical properties with respect to aggregation and hydrophobicity by chromatography-based assays, and thermostability by dynamic scanning fluorimetry. These results collectively support that the humanized anti-fentanyl mAbs developed herein warrant further clinical development for treatment of fentanyl toxicity.

Risk-Based Control Strategies of Recombinant Monoclonal Antibody Charge Variants

Since the first approval of the anti-CD3 recombinant monoclonal antibody (mAb), muromonab-CD3, a mouse antibody for the prevention of transplant rejection, by the US Food and Drug Administration (FDA) in 1986, mAb therapeutics have become increasingly important to medical care. A wealth of information about mAbs regarding their structure, stability, post-translation modifications, and the relationship between modification and function has been reported. Yet, substantial resources are still required throughout development and commercialization to have appropriate control strategies to maintain consistent product quality, safety, and efficacy. A typical feature of mAbs is charge heterogeneity, which stems from a variety of modifications, including modifications that are common to many mAbs or unique to a specific molecule or process. Charge heterogeneity is highly sensitive to process changes and thus a good indicator of a robust process. It is a high-risk quality attribute that could potentially fail the specification and comparability required for batch disposition. Failure to meet product specifications or comparability can substantially affect clinical development timelines. To mitigate these risks, the general rule is to maintain a comparable charge profile when process changes are inevitably introduced during development and even after commercialization. Otherwise, new peaks or varied levels of acidic and basic species must be justified based on scientific knowledge and clinical experience for a specific molecule. Here, we summarize the current understanding of mAb charge variants and outline risk-based control strategies to support process development and ultimately commercialization.

Non-specificity as the sticky problem in therapeutic antibody development

Antibodies are highly potent therapeutic scaffolds with more than a hundred different products approved on the market. Successful development of antibody-based drugs requires a trade-off between high target specificity and target binding affinity. In order to better understand this problem, we here review non-specific interactions and explore their fundamental physicochemical origins. We discuss the role of surface patches - clusters of surface-exposed amino acid residues with similar physicochemical properties - as inducers of non-specific interactions. These patches collectively drive interactions including dipole-dipole, π-stacking and hydrophobic interactions to complementary moieties. We elucidate links between these supramolecular assembly processes and macroscopic development issues, such as decreased physical stability and poor in vivo half-life. Finally, we highlight challenges and opportunities for optimizing protein binding specificity and minimizing non-specificity for future generations of therapeutics.

Developability assessment at early-stage discovery to enable development of antibody-derived therapeutics

Developability refers to the likelihood that an antibody candidate will become a manufacturable, safe and efficacious drug. Although the safety and efficacy of a drug candidate will be well considered by sponsors and regulatory agencies, developability in the narrow sense can be defined as the likelihood that an antibody candidate will go smoothly through the chemistry, manufacturing and control (CMC) process at a reasonable cost and within a reasonable timeline. Developability in this sense is the focus of this review. To lower the risk that an antibody candidate with poor developability will move to the CMC stage, the candidate's developability-related properties should be screened, assessed and optimized as early as possible. Assessment of developability at the early discovery stage should be performed in a rapid and high-throughput manner while consuming small amounts of testing materials. In addition to monoclonal antibodies, bispecific antibodies, multispecific antibodies and antibody-drug conjugates, as the derivatives of monoclonal antibodies, should also be assessed for developability. Moreover, we propose that the criterion of developability is relative: expected clinical indication, and the dosage and administration route of the antibody could affect this criterion. We also recommend a general screening process during the early discovery stage of antibody-derived therapeutics. With the advance of artificial intelligence-aided prediction of protein structures and features, computational tools can be used to predict, screen and optimize the developability of antibody candidates and greatly reduce the risk of moving a suboptimal candidate to the development stage.

High-Throughput Mass Spectrometry for Biopharma: A Universal Modality and Target Independent Analytical Method for Accurate Biomolecule Characterization

Reversed-phase liquid chromatographic mass spectrometry (rpLC-MS) is a universal, platformed, and essential analytical technique within pharmaceutical and biopharmaceutical research. Typical rpLC method gradient times can range from 5 to 20 min. As monoclonal antibody (mAb) therapies continue to evolve and bispecific antibodies (BsAbs) become more established, research stage engineering panels will clearly evolve in size. Therefore, high-throughput (HT) MS and automated deconvolution methods are key for success. Additionally, newer therapeutics such as bispecific T-cell engagers and nucleic acid-based modalities will also require MS characterization. Herein, we present a modality and target agnostic HT solid-phase extraction (SPE) MS method that affords the analysis of a 96-well plate in 41.4 min, compared to the traditional rpLC-MS method that would typically take 14.4 h. The described method can accurately determine the molecular weights for monodispersed and highly polydispersed biotherapeutic species and membrane proteins; determine levels of glycosylation, glycation, and formylation; detect levels of chain mispairing; and determine accurate drug-to-antibody ratio values.

Antibody apparent solubility prediction from sequence by transfer learning

Developing therapeutic monoclonal antibodies (mAbs) for the subcutaneous administration requires identifying mAbs with superior solubility that are amenable for high-concentration formulation. However, experimental screening is often material and labor intensive. Here, we present a strategy (named solPredict) that employs the embeddings from pretrained protein language modeling to predict the apparent solubility of mAbs in histidine (pH 6.0) buffer. A dataset of 220 diverse, in-house mAbs were used for model training and hyperparameter tuning through 5-fold cross validation. solPredict achieves high correlation with experimental solubility on an independent test set of 40 mAbs. Importantly, solPredict performs well for both IgG1 and IgG4 subclasses despite the distinct solubility behaviors. This approach eliminates the need of 3D structure modeling of mAbs, descriptor computation, and expert-crafted input features. The minimal computational expense of solPredict enables rapid, large-scale, and high-throughput screening of mAbs using sequence information alone during early antibody discovery.

Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space

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.

Hexamerization of Anti-SARS CoV IgG1 Antibodies Improves Neutralization Capacity

The SARS-CoV-2 pandemic and particularly the emerging variants have deepened the need for widely available therapeutic options. We have demonstrated that hexamer-enhancing mutations in the Fc region of anti-SARS-CoV IgG antibodies lead to a noticeable improvement in IC50 in both pseudo and live virus neutralization assay compared to parental molecules. We also show that hexamer-enhancing mutants improve C1q binding to target surface. To our knowledge, this is the first time this format has been explored for application in viral neutralization and the studies provide proof-of-concept for the use of hexamer-enhanced IgG1 molecules as potential anti-viral therapeutics.

Healthy humans can be a source of antibodies countering COVID-19

Here, we describe the isolation of 18 unique anti SARS-CoV-2 human single-chain antibodies from an antibody library derived from healthy donors. The selection used a combination of phage and yeast display technologies and included counter-selection strategies meant to direct the selection of the receptor-binding motif (RBM) of SARS-CoV-2 spike protein's receptor binding domain (RBD2). Selected antibodies were characterized in various formats including IgG, using flow cytometry, ELISA, high throughput SPR, and fluorescence microscopy. We report antibodies' RBD2 recognition specificity, binding affinity, and epitope diversity, as well as ability to block RBD2 binding to the human receptor angiotensin-converting enzyme 2 (ACE2) and to neutralize authentic SARS-CoV-2 virus infection in vitro. We present evidence supporting that: 1) most of our antibodies (16 out of 18) selectively recognize RBD2; 2) the best performing 8 antibodies target eight different epitopes of RBD2; 3) one of the pairs tested in sandwich assays detects RBD2 with sub-picomolar sensitivity; and 4) two antibody pairs inhibit SARS-CoV-2 infection at low nanomolar half neutralization titers. Based on these results, we conclude that our antibodies have high potential for therapeutic and diagnostic applications. Importantly, our results indicate that readily available non immune (naïve) antibody libraries obtained from healthy donors can be used to select high-quality monoclonal antibodies, bypassing the need for blood of infected patients, and offering a widely accessible and low-cost alternative to more sophisticated and expensive antibody selection approaches (e.g. single B cell analysis and natural evolution in humanized mice).