Increasing the binding affinity of an antibody to its target antigen is a crucial task in antibody therapeutics development. This paper presents a pretrainable geometric graph neural network, GearBind, and explores its potential in in silico affinity maturation. Leveraging multi-relational graph construction, multi-level geometric message passing and contrastive pretraining on mass-scale, unlabeled protein structural data, GearBind outperforms previous state-of-the-art approaches on SKEMPI and an independent test set. A powerful ensemble model based on GearBind is then derived and used to successfully enhance the binding of two antibodies with distinct formats and target antigens. ELISA EC₅₀ values of the designed antibody mutants are decreased by up to 17 fold, and K_D values by up to 6.1 fold. These promising results underscore the utility of geometric deep learning and effective pretraining in macromolecule interaction modeling tasks.

Single-domain antibodies (sdAbs), initially identified in camelids or sharks and commonly referred to as nanobodies or VNARs, have emerged as a promising alternative to conventional therapeutic antibodies. These sdAbs have many superior physicochemical and pharmacological properties, including small size, good solubility and thermostability, easier accessible epitopes, and strong tissue penetration. However, the inherent challenges associated with the animal origin of sdAbs limit their clinical use. In recent years, various innovative humanization technologies, including complementarity-determining region (CDR) grafting or complete engineering of fully human sdAbs, have been developed to mitigate potential immunogenicity issues and enhance their compatibility. This review provides a comprehensive exploration of sdAbs, emphasizing their distinctive features and the progress in humanization methodologies. In addition, we provide an overview of the recent progress in developing drugs and therapeutic strategies based on sdAbs and their potential in solid tumor treatment, such as sdAb–drug conjugates, multispecific sdAbs, sdAb-based delivery systems, and sdAb-based cell therapy.

In recent years, substantial therapeutic efficacy of antibody-drug conjugates (ADCs) has been validated through approvals of 16 ADCs for the treatment of malignant tumors. However, realization of the maximum clinical use of ADCs requires surmounting extant challenges, mainly the limitations in tumor penetration capabilities when targeting solid tumors. To resolve the hurdle of suboptimal tumor penetration, miniaturized antibody fragments with engineered formats have been harnessed for ADC assembly. By virtue of their reduced molecular sizes, antibody fragment-drug conjugates hold considerable promise for efficacious delivery of cytotoxic agents, thus conferring superior therapeutic outcomes. This review will focus on current advancements in novel ADC development utilizing smaller antibody formats from ~6 to 80 kDa, with particular emphasis on single-domain antibodies, which have been widely applied in novel ADC design. Additionally, strategies to optimize clinical translation are discussed, including half-life extension, acceleration of internalization, and reduction of immunogenic potential.

Monoclonal antibodies (mAbs) are widely used in cancer therapy but often show limited efficacy for solid tumors. Enhancing anti-tumor activity by fusing cytokines to tumor-targeting mAbs, which specifically activate immune cells within the tumor microenvironment, represents a promising strategy. However, the optimal design and therapeutic efficacy of antibody–cytokine fusion formats remain unclear. The epithelial cell adhesion molecule (EpCAM), frequently overexpressed in a variety of carcinomas, serves as the target for immunotherapies. In this study, we identified a fully human mAb targeting EpCAM, designated as m801, from a previously constructed phage-displayed fully human antibody library. By fusing m801 with an IL-2 variant (IL-2v) in two configurations, m801.2 (2 anti-EpCAM Fab + 1 IL-2v) and m801.3 (1 anti-EpCAM Fab + 1 IL-2v), we identified m801.2 as the lead candidate due to its superior biophysical properties, including high thermal stability, homogeneity, and low aggregation. Furthermore, m801.2 showed strong binding affinity to EpCAM, with KD values of 0.6 nM, and an EpCAM-expressing tumor cell line, comparable to the original IgG m801. Additionally, m801.2 exhibited IL-2 receptor β subunit (IL-2Rβ)-biased binding activity, with a KD of 27.3 nM, resulting in superior effective T cell activation. In an SW480 xenograft mice model, m801.2 significantly inhibited tumor growth and demonstrated high tolerability. These findings suggest a valuable framework for the future design of immunocytokine therapies.

Background: As one of the most promising classes of next-generation antibody therapeutics, bispecific antibodies (bsAbs) have gained increasing attention owing to their unique dual-targeting mechanisms. However, current bsAb formats often face challenges such as low expression levels, poor homogeneity, and unstable therapeutic efficacy due to their complex structures. Therefore, it is urgent to overcome the current technical limitations and develop novel formats of bsAbs with more stable structures and improved expression efficiency. Methods: Through rational design and phage display-based screening, we engineered a novel light-chain single-domain antibody (VHHL). Using modular assembly and replacement strategies, the VHHL was reconstituted into conventional immunoglobulin G (IgG)s and the resulting bsAbs were comprehensively characterized by size-exclusion high-performance liquid chromatography, biolayer interferometry binding assay, enzyme-linked immunosorbent assay, and flow cytometry. Results: A light chain engineering strategy combining complementarity-determining region 3 (CDR3)-grafting with site-directed mutagenesis of CDR1/CDR2 was developed to generate VHHLs. Through phage screening, two mouse CD16-specific VHHL candidates with favorable binding affinities and biophysical properties were identified, and one of which was structurally resolved via X-ray crystallography (3.05 Å resolution). When incorporated into full-length IgGs, the resulting bsAbs retained high structural similarity to natural monoclonal antibodies and maintained dual antigen-binding capabilities through their respective light and heavy chains. Conclusions: Consequently, this study presents a novel IgG-format bsAb platform enabled by the integration of a rationally designed antigen-binding VHHL, providing a streamlined and versatile strategy for the development of multifunctional antibodies. Statement of Significance We developed a novel class of light-chain single-domain antibody (VHHL). By incorporating VHHL into full-length IgG, the resulting bispecific antibody (bsAb) retained the structural integrity of native IgG while preserving the independent antigen-binding activities of both the heavy and light chains, offering a simplified and flexible approach for bsAb generation.

Increasing the binding affinity of an antibody to its target antigen is a crucial task in antibody therapeutics development. This paper presents a pretrainable geometric graph neural network, GearBind, and explores its potential in in silico affinity maturation. Leveraging multi-relational graph construction, multi-level geometric message passing and contrastive pretraining on mass-scale, unlabeled protein structural data, GearBind outperforms previous state-of-the-art approaches on SKEMPI and an independent test set. A powerful ensemble model based on GearBind is then derived and used to successfully enhance the binding of two antibodies with distinct formats and target antigens. ELISA EC ₅₀ values of the designed antibody mutants are decreased by up to 17 fold, and K _D values by up to 6.1 fold. These promising results underscore the utility of geometric deep learning and effective pretraining in macromolecule interaction modeling tasks.